| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.998499249624812, | |
| "global_step": 4990, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.991983967935872e-05, | |
| "loss": 6.0598, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 7.983967935871744e-05, | |
| "loss": 3.2882, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.9581081867218018, | |
| "eval_runtime": 30.7575, | |
| "eval_samples_per_second": 7.218, | |
| "eval_steps_per_second": 1.821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.975951903807616e-05, | |
| "loss": 2.8014, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.967935871743487e-05, | |
| "loss": 2.5059, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.384403944015503, | |
| "eval_runtime": 30.8572, | |
| "eval_samples_per_second": 7.194, | |
| "eval_steps_per_second": 1.815, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.95991983967936e-05, | |
| "loss": 2.404, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 7.951903807615231e-05, | |
| "loss": 2.3368, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.3643715381622314, | |
| "eval_runtime": 30.9262, | |
| "eval_samples_per_second": 7.178, | |
| "eval_steps_per_second": 1.811, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.943887775551104e-05, | |
| "loss": 2.2994, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.935871743486974e-05, | |
| "loss": 2.3476, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.349405288696289, | |
| "eval_runtime": 30.9436, | |
| "eval_samples_per_second": 7.174, | |
| "eval_steps_per_second": 1.81, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 7.927855711422847e-05, | |
| "loss": 2.3623, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 7.919839679358717e-05, | |
| "loss": 2.3185, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 2.369673252105713, | |
| "eval_runtime": 30.9718, | |
| "eval_samples_per_second": 7.168, | |
| "eval_steps_per_second": 1.808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 7.91182364729459e-05, | |
| "loss": 2.433, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 7.903807615230462e-05, | |
| "loss": 2.3468, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 2.32550048828125, | |
| "eval_runtime": 31.009, | |
| "eval_samples_per_second": 7.159, | |
| "eval_steps_per_second": 1.806, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 7.895791583166334e-05, | |
| "loss": 2.2554, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 7.887775551102205e-05, | |
| "loss": 2.262, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 2.2511556148529053, | |
| "eval_runtime": 31.035, | |
| "eval_samples_per_second": 7.153, | |
| "eval_steps_per_second": 1.804, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.879759519038077e-05, | |
| "loss": 2.2116, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.871743486973949e-05, | |
| "loss": 2.1646, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 2.194511651992798, | |
| "eval_runtime": 31.0667, | |
| "eval_samples_per_second": 7.146, | |
| "eval_steps_per_second": 1.803, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.86372745490982e-05, | |
| "loss": 2.1732, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 7.855711422845692e-05, | |
| "loss": 2.1558, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 2.188542366027832, | |
| "eval_runtime": 31.077, | |
| "eval_samples_per_second": 7.144, | |
| "eval_steps_per_second": 1.802, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 7.847695390781564e-05, | |
| "loss": 2.2353, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 7.839679358717435e-05, | |
| "loss": 2.1934, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.148287057876587, | |
| "eval_runtime": 31.1071, | |
| "eval_samples_per_second": 7.137, | |
| "eval_steps_per_second": 1.8, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.831663326653307e-05, | |
| "loss": 2.0947, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.823647294589179e-05, | |
| "loss": 2.0855, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.115215301513672, | |
| "eval_runtime": 31.1349, | |
| "eval_samples_per_second": 7.13, | |
| "eval_steps_per_second": 1.799, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.81563126252505e-05, | |
| "loss": 2.1728, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.807615230460922e-05, | |
| "loss": 2.0844, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 2.0839340686798096, | |
| "eval_runtime": 31.1371, | |
| "eval_samples_per_second": 7.13, | |
| "eval_steps_per_second": 1.798, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.799599198396795e-05, | |
| "loss": 2.0497, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.791583166332665e-05, | |
| "loss": 2.0647, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 2.0615038871765137, | |
| "eval_runtime": 31.1492, | |
| "eval_samples_per_second": 7.127, | |
| "eval_steps_per_second": 1.798, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.783567134268538e-05, | |
| "loss": 2.0643, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.775551102204409e-05, | |
| "loss": 1.9665, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 2.0329749584198, | |
| "eval_runtime": 31.1654, | |
| "eval_samples_per_second": 7.123, | |
| "eval_steps_per_second": 1.797, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.767535070140282e-05, | |
| "loss": 1.9736, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.759519038076152e-05, | |
| "loss": 1.9761, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 2.0067899227142334, | |
| "eval_runtime": 31.1584, | |
| "eval_samples_per_second": 7.125, | |
| "eval_steps_per_second": 1.797, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.751503006012025e-05, | |
| "loss": 1.9611, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.743486973947897e-05, | |
| "loss": 1.9428, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.9913756847381592, | |
| "eval_runtime": 31.1769, | |
| "eval_samples_per_second": 7.121, | |
| "eval_steps_per_second": 1.796, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.735470941883769e-05, | |
| "loss": 1.9547, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.72745490981964e-05, | |
| "loss": 1.9351, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.9368627071380615, | |
| "eval_runtime": 31.1785, | |
| "eval_samples_per_second": 7.12, | |
| "eval_steps_per_second": 1.796, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.719438877755512e-05, | |
| "loss": 1.9509, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.711422845691384e-05, | |
| "loss": 1.9366, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.9138563871383667, | |
| "eval_runtime": 31.1927, | |
| "eval_samples_per_second": 7.117, | |
| "eval_steps_per_second": 1.795, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.703406813627255e-05, | |
| "loss": 1.9439, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.695390781563127e-05, | |
| "loss": 1.9548, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.8788814544677734, | |
| "eval_runtime": 31.199, | |
| "eval_samples_per_second": 7.116, | |
| "eval_steps_per_second": 1.795, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.687374749498999e-05, | |
| "loss": 1.9061, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.67935871743487e-05, | |
| "loss": 1.9625, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.848646640777588, | |
| "eval_runtime": 31.2024, | |
| "eval_samples_per_second": 7.115, | |
| "eval_steps_per_second": 1.795, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.671342685370742e-05, | |
| "loss": 1.9024, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.663326653306614e-05, | |
| "loss": 1.8584, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.8197656869888306, | |
| "eval_runtime": 31.2023, | |
| "eval_samples_per_second": 7.115, | |
| "eval_steps_per_second": 1.795, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.655310621242485e-05, | |
| "loss": 1.7843, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.647294589178357e-05, | |
| "loss": 1.8857, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.8118294477462769, | |
| "eval_runtime": 31.1985, | |
| "eval_samples_per_second": 7.116, | |
| "eval_steps_per_second": 1.795, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.639278557114229e-05, | |
| "loss": 1.7888, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 7.6312625250501e-05, | |
| "loss": 1.7574, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.760263442993164, | |
| "eval_runtime": 31.1988, | |
| "eval_samples_per_second": 7.116, | |
| "eval_steps_per_second": 1.795, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.623246492985973e-05, | |
| "loss": 1.7695, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.615230460921844e-05, | |
| "loss": 1.8114, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.7369911670684814, | |
| "eval_runtime": 31.2207, | |
| "eval_samples_per_second": 7.111, | |
| "eval_steps_per_second": 1.794, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.607214428857717e-05, | |
| "loss": 1.7307, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 7.599198396793587e-05, | |
| "loss": 1.7303, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.720489263534546, | |
| "eval_runtime": 31.2198, | |
| "eval_samples_per_second": 7.111, | |
| "eval_steps_per_second": 1.794, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 7.59118236472946e-05, | |
| "loss": 1.6382, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.58316633266533e-05, | |
| "loss": 1.7535, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.7123703956604004, | |
| "eval_runtime": 31.1991, | |
| "eval_samples_per_second": 7.116, | |
| "eval_steps_per_second": 1.795, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.575150300601203e-05, | |
| "loss": 1.6792, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 7.567134268537075e-05, | |
| "loss": 1.7775, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.7013072967529297, | |
| "eval_runtime": 31.2171, | |
| "eval_samples_per_second": 7.111, | |
| "eval_steps_per_second": 1.794, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.559118236472947e-05, | |
| "loss": 1.7402, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 7.551102204408818e-05, | |
| "loss": 1.685, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6611982583999634, | |
| "eval_runtime": 31.2154, | |
| "eval_samples_per_second": 7.112, | |
| "eval_steps_per_second": 1.794, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 7.54308617234469e-05, | |
| "loss": 1.7125, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.535070140280562e-05, | |
| "loss": 1.5898, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.6577653884887695, | |
| "eval_runtime": 31.217, | |
| "eval_samples_per_second": 7.112, | |
| "eval_steps_per_second": 1.794, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.527054108216433e-05, | |
| "loss": 1.6172, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.519038076152305e-05, | |
| "loss": 1.7875, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.645772933959961, | |
| "eval_runtime": 31.2182, | |
| "eval_samples_per_second": 7.111, | |
| "eval_steps_per_second": 1.794, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.511022044088177e-05, | |
| "loss": 1.5817, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.50300601202405e-05, | |
| "loss": 1.628, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.6252926588058472, | |
| "eval_runtime": 31.2223, | |
| "eval_samples_per_second": 7.11, | |
| "eval_steps_per_second": 1.794, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.49498997995992e-05, | |
| "loss": 1.6397, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.486973947895793e-05, | |
| "loss": 1.6186, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6194863319396973, | |
| "eval_runtime": 31.2314, | |
| "eval_samples_per_second": 7.108, | |
| "eval_steps_per_second": 1.793, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.478957915831663e-05, | |
| "loss": 1.6546, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.470941883767536e-05, | |
| "loss": 1.6899, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.6101500988006592, | |
| "eval_runtime": 31.2273, | |
| "eval_samples_per_second": 7.109, | |
| "eval_steps_per_second": 1.793, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.462925851703407e-05, | |
| "loss": 1.6294, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 7.45490981963928e-05, | |
| "loss": 1.5908, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.5906888246536255, | |
| "eval_runtime": 31.2321, | |
| "eval_samples_per_second": 7.108, | |
| "eval_steps_per_second": 1.793, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 7.446893787575151e-05, | |
| "loss": 1.6827, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 7.438877755511023e-05, | |
| "loss": 1.6514, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.6103746891021729, | |
| "eval_runtime": 31.239, | |
| "eval_samples_per_second": 7.107, | |
| "eval_steps_per_second": 1.793, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 7.430861723446895e-05, | |
| "loss": 1.73, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 7.422845691382766e-05, | |
| "loss": 1.6027, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.576550841331482, | |
| "eval_runtime": 31.2402, | |
| "eval_samples_per_second": 7.106, | |
| "eval_steps_per_second": 1.793, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 7.414829659318638e-05, | |
| "loss": 1.5685, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.40681362725451e-05, | |
| "loss": 1.6319, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.562269926071167, | |
| "eval_runtime": 31.2342, | |
| "eval_samples_per_second": 7.108, | |
| "eval_steps_per_second": 1.793, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.398797595190381e-05, | |
| "loss": 1.5724, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.390781563126253e-05, | |
| "loss": 1.6103, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5764440298080444, | |
| "eval_runtime": 31.2479, | |
| "eval_samples_per_second": 7.104, | |
| "eval_steps_per_second": 1.792, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.382765531062125e-05, | |
| "loss": 1.6548, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 7.374749498997996e-05, | |
| "loss": 1.4518, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.544908881187439, | |
| "eval_runtime": 31.2325, | |
| "eval_samples_per_second": 7.108, | |
| "eval_steps_per_second": 1.793, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 7.366733466933868e-05, | |
| "loss": 1.5493, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.35871743486974e-05, | |
| "loss": 1.498, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.5345020294189453, | |
| "eval_runtime": 31.2401, | |
| "eval_samples_per_second": 7.106, | |
| "eval_steps_per_second": 1.793, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 7.350701402805611e-05, | |
| "loss": 1.5031, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.342685370741484e-05, | |
| "loss": 1.5266, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.541326642036438, | |
| "eval_runtime": 31.2476, | |
| "eval_samples_per_second": 7.105, | |
| "eval_steps_per_second": 1.792, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 7.334669338677355e-05, | |
| "loss": 1.4406, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.326653306613228e-05, | |
| "loss": 1.5622, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.5228804349899292, | |
| "eval_runtime": 31.2404, | |
| "eval_samples_per_second": 7.106, | |
| "eval_steps_per_second": 1.793, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.318637274549098e-05, | |
| "loss": 1.5308, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.310621242484971e-05, | |
| "loss": 1.4863, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.5208450555801392, | |
| "eval_runtime": 31.2453, | |
| "eval_samples_per_second": 7.105, | |
| "eval_steps_per_second": 1.792, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.302605210420841e-05, | |
| "loss": 1.5183, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.294589178356714e-05, | |
| "loss": 1.5492, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.4996235370635986, | |
| "eval_runtime": 31.241, | |
| "eval_samples_per_second": 7.106, | |
| "eval_steps_per_second": 1.793, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 7.286573146292586e-05, | |
| "loss": 1.4304, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.278557114228458e-05, | |
| "loss": 1.5515, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.4857271909713745, | |
| "eval_runtime": 31.2521, | |
| "eval_samples_per_second": 7.104, | |
| "eval_steps_per_second": 1.792, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.27054108216433e-05, | |
| "loss": 1.506, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.262525050100201e-05, | |
| "loss": 1.4799, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.493463158607483, | |
| "eval_runtime": 31.2544, | |
| "eval_samples_per_second": 7.103, | |
| "eval_steps_per_second": 1.792, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.254509018036073e-05, | |
| "loss": 1.5673, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.246492985971944e-05, | |
| "loss": 1.4514, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.4745410680770874, | |
| "eval_runtime": 31.2458, | |
| "eval_samples_per_second": 7.105, | |
| "eval_steps_per_second": 1.792, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.238476953907816e-05, | |
| "loss": 1.6031, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.230460921843688e-05, | |
| "loss": 1.5462, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.4784045219421387, | |
| "eval_runtime": 31.2514, | |
| "eval_samples_per_second": 7.104, | |
| "eval_steps_per_second": 1.792, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.22244488977956e-05, | |
| "loss": 1.4849, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.214428857715431e-05, | |
| "loss": 1.6032, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.4910966157913208, | |
| "eval_runtime": 31.2331, | |
| "eval_samples_per_second": 7.108, | |
| "eval_steps_per_second": 1.793, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.206412825651303e-05, | |
| "loss": 1.5241, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.198396793587175e-05, | |
| "loss": 1.7418, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.473315954208374, | |
| "eval_runtime": 31.2557, | |
| "eval_samples_per_second": 7.103, | |
| "eval_steps_per_second": 1.792, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.190380761523046e-05, | |
| "loss": 1.4456, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.182364729458918e-05, | |
| "loss": 1.4983, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.4645960330963135, | |
| "eval_runtime": 31.1687, | |
| "eval_samples_per_second": 7.123, | |
| "eval_steps_per_second": 1.797, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.17434869739479e-05, | |
| "loss": 1.4675, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.166332665330663e-05, | |
| "loss": 1.5383, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 1.4441555738449097, | |
| "eval_runtime": 31.242, | |
| "eval_samples_per_second": 7.106, | |
| "eval_steps_per_second": 1.792, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.158316633266533e-05, | |
| "loss": 1.4809, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.150300601202406e-05, | |
| "loss": 1.3454, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.4332164525985718, | |
| "eval_runtime": 31.2551, | |
| "eval_samples_per_second": 7.103, | |
| "eval_steps_per_second": 1.792, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.142284569138276e-05, | |
| "loss": 1.2579, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.134268537074149e-05, | |
| "loss": 1.3128, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.4260525703430176, | |
| "eval_runtime": 31.259, | |
| "eval_samples_per_second": 7.102, | |
| "eval_steps_per_second": 1.791, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.12625250501002e-05, | |
| "loss": 1.4444, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.118236472945893e-05, | |
| "loss": 1.5472, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 1.4231517314910889, | |
| "eval_runtime": 31.2585, | |
| "eval_samples_per_second": 7.102, | |
| "eval_steps_per_second": 1.792, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.110220440881764e-05, | |
| "loss": 1.5043, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.102204408817636e-05, | |
| "loss": 1.252, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.3924123048782349, | |
| "eval_runtime": 31.2631, | |
| "eval_samples_per_second": 7.101, | |
| "eval_steps_per_second": 1.791, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 7.094188376753508e-05, | |
| "loss": 1.4416, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 7.086172344689379e-05, | |
| "loss": 1.3538, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.3975321054458618, | |
| "eval_runtime": 31.264, | |
| "eval_samples_per_second": 7.101, | |
| "eval_steps_per_second": 1.791, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.078156312625251e-05, | |
| "loss": 1.4595, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 7.070140280561123e-05, | |
| "loss": 1.5448, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 1.391546368598938, | |
| "eval_runtime": 31.2681, | |
| "eval_samples_per_second": 7.1, | |
| "eval_steps_per_second": 1.791, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 7.062124248496996e-05, | |
| "loss": 1.5233, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 7.054108216432866e-05, | |
| "loss": 1.4016, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 1.4025028944015503, | |
| "eval_runtime": 31.2695, | |
| "eval_samples_per_second": 7.1, | |
| "eval_steps_per_second": 1.791, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 7.046092184368739e-05, | |
| "loss": 1.3933, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 7.038076152304609e-05, | |
| "loss": 1.3041, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.383679747581482, | |
| "eval_runtime": 31.2652, | |
| "eval_samples_per_second": 7.101, | |
| "eval_steps_per_second": 1.791, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 7.030060120240482e-05, | |
| "loss": 1.1945, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 7.022044088176353e-05, | |
| "loss": 1.3857, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 1.3890188932418823, | |
| "eval_runtime": 31.2731, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 7.014028056112226e-05, | |
| "loss": 1.3095, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 7.006012024048097e-05, | |
| "loss": 1.2923, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 1.3452343940734863, | |
| "eval_runtime": 31.2652, | |
| "eval_samples_per_second": 7.101, | |
| "eval_steps_per_second": 1.791, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.997995991983969e-05, | |
| "loss": 1.3602, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.98997995991984e-05, | |
| "loss": 1.28, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 1.349170446395874, | |
| "eval_runtime": 31.2663, | |
| "eval_samples_per_second": 7.1, | |
| "eval_steps_per_second": 1.791, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.981963927855712e-05, | |
| "loss": 1.3712, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.973947895791584e-05, | |
| "loss": 1.4052, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 1.3253566026687622, | |
| "eval_runtime": 31.2668, | |
| "eval_samples_per_second": 7.1, | |
| "eval_steps_per_second": 1.791, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.965931863727456e-05, | |
| "loss": 1.2965, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.957915831663327e-05, | |
| "loss": 1.3992, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 1.367018461227417, | |
| "eval_runtime": 31.2605, | |
| "eval_samples_per_second": 7.102, | |
| "eval_steps_per_second": 1.791, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 6.949899799599199e-05, | |
| "loss": 1.3044, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 6.941883767535071e-05, | |
| "loss": 1.5044, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.3153263330459595, | |
| "eval_runtime": 31.2645, | |
| "eval_samples_per_second": 7.101, | |
| "eval_steps_per_second": 1.791, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 6.933867735470942e-05, | |
| "loss": 1.3481, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.925851703406814e-05, | |
| "loss": 1.2274, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 1.314244270324707, | |
| "eval_runtime": 31.2738, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 6.917835671342686e-05, | |
| "loss": 1.3536, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 6.909819639278557e-05, | |
| "loss": 1.2392, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.3149820566177368, | |
| "eval_runtime": 31.2585, | |
| "eval_samples_per_second": 7.102, | |
| "eval_steps_per_second": 1.792, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 6.901803607214429e-05, | |
| "loss": 1.2368, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 6.893787575150301e-05, | |
| "loss": 1.365, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 1.296552300453186, | |
| "eval_runtime": 31.2732, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 6.885771543086174e-05, | |
| "loss": 1.1902, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 6.877755511022044e-05, | |
| "loss": 1.3024, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 1.2687900066375732, | |
| "eval_runtime": 31.2617, | |
| "eval_samples_per_second": 7.101, | |
| "eval_steps_per_second": 1.791, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 6.869739478957917e-05, | |
| "loss": 1.2785, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 6.861723446893787e-05, | |
| "loss": 1.347, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 1.2873570919036865, | |
| "eval_runtime": 31.2708, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 6.85370741482966e-05, | |
| "loss": 1.4252, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 6.845691382765531e-05, | |
| "loss": 1.3898, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 1.2543420791625977, | |
| "eval_runtime": 31.2712, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 6.837675350701404e-05, | |
| "loss": 1.1915, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 6.829659318637275e-05, | |
| "loss": 1.4256, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 1.2396987676620483, | |
| "eval_runtime": 31.2721, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 6.821643286573147e-05, | |
| "loss": 1.1646, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 6.813627254509019e-05, | |
| "loss": 1.2566, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.2429862022399902, | |
| "eval_runtime": 31.2712, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 6.80561122244489e-05, | |
| "loss": 1.209, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 6.797595190380762e-05, | |
| "loss": 1.2473, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.2135179042816162, | |
| "eval_runtime": 31.2749, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.791, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 6.789579158316634e-05, | |
| "loss": 1.1848, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 6.781563126252505e-05, | |
| "loss": 1.1466, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.2170690298080444, | |
| "eval_runtime": 31.2836, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.773547094188377e-05, | |
| "loss": 1.2543, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.765531062124249e-05, | |
| "loss": 1.3065, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 1.1896520853042603, | |
| "eval_runtime": 31.2763, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.79, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.75751503006012e-05, | |
| "loss": 1.1649, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.749498997995992e-05, | |
| "loss": 1.3033, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 1.1646301746368408, | |
| "eval_runtime": 31.2767, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.79, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.741482965931864e-05, | |
| "loss": 1.0613, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 6.733466933867735e-05, | |
| "loss": 1.1166, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.1722773313522339, | |
| "eval_runtime": 31.2753, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.791, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.725450901803607e-05, | |
| "loss": 1.1091, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.717434869739479e-05, | |
| "loss": 1.0874, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.1511393785476685, | |
| "eval_runtime": 31.2755, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.791, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.709418837675352e-05, | |
| "loss": 1.2602, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 6.701402805611222e-05, | |
| "loss": 1.017, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 1.1395540237426758, | |
| "eval_runtime": 31.2767, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.79, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 6.693386773547095e-05, | |
| "loss": 1.153, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 6.685370741482966e-05, | |
| "loss": 1.0437, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.1016473770141602, | |
| "eval_runtime": 31.2746, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.791, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 6.677354709418839e-05, | |
| "loss": 1.0316, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 6.669338677354709e-05, | |
| "loss": 1.2206, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 1.0841138362884521, | |
| "eval_runtime": 31.2759, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.791, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 6.661322645290582e-05, | |
| "loss": 0.9704, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 6.653306613226454e-05, | |
| "loss": 0.9738, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 1.0759927034378052, | |
| "eval_runtime": 31.2775, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.79, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 6.645290581162325e-05, | |
| "loss": 1.1332, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 6.637274549098197e-05, | |
| "loss": 1.1351, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 1.0561842918395996, | |
| "eval_runtime": 31.2727, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 6.629258517034069e-05, | |
| "loss": 1.0462, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 6.62124248496994e-05, | |
| "loss": 1.0697, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 1.05562424659729, | |
| "eval_runtime": 31.2794, | |
| "eval_samples_per_second": 7.097, | |
| "eval_steps_per_second": 1.79, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 6.613226452905812e-05, | |
| "loss": 1.1096, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 6.605210420841685e-05, | |
| "loss": 1.0296, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 1.034234881401062, | |
| "eval_runtime": 31.2794, | |
| "eval_samples_per_second": 7.097, | |
| "eval_steps_per_second": 1.79, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 6.597194388777555e-05, | |
| "loss": 1.0413, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 6.589178356713428e-05, | |
| "loss": 1.0904, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 1.0046826601028442, | |
| "eval_runtime": 31.283, | |
| "eval_samples_per_second": 7.097, | |
| "eval_steps_per_second": 1.79, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 6.581162324649299e-05, | |
| "loss": 1.0728, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 6.573146292585172e-05, | |
| "loss": 1.01, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 1.018371820449829, | |
| "eval_runtime": 31.2848, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 6.565130260521042e-05, | |
| "loss": 1.047, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 6.557114228456915e-05, | |
| "loss": 0.951, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.9845412969589233, | |
| "eval_runtime": 31.2866, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 6.549098196392787e-05, | |
| "loss": 0.9055, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 6.541082164328658e-05, | |
| "loss": 1.0111, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 0.9674527049064636, | |
| "eval_runtime": 31.2872, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 6.53306613226453e-05, | |
| "loss": 0.9433, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 6.525050100200402e-05, | |
| "loss": 1.0824, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.9758660793304443, | |
| "eval_runtime": 31.2867, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 6.517034068136273e-05, | |
| "loss": 0.9381, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.509018036072145e-05, | |
| "loss": 0.9745, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.9335694909095764, | |
| "eval_runtime": 31.2906, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 6.501002004008017e-05, | |
| "loss": 0.8404, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.492985971943888e-05, | |
| "loss": 0.8632, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.934661865234375, | |
| "eval_runtime": 31.2917, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 6.48496993987976e-05, | |
| "loss": 0.9011, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 6.476953907815632e-05, | |
| "loss": 0.9959, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 0.9394508600234985, | |
| "eval_runtime": 31.2847, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 6.468937875751503e-05, | |
| "loss": 0.967, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.460921843687375e-05, | |
| "loss": 0.8906, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.8965132236480713, | |
| "eval_runtime": 31.292, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 6.452905811623247e-05, | |
| "loss": 0.9108, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 6.444889779559118e-05, | |
| "loss": 1.0552, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.8891679048538208, | |
| "eval_runtime": 31.2905, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.43687374749499e-05, | |
| "loss": 0.8783, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.428857715430863e-05, | |
| "loss": 0.8387, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.8821650147438049, | |
| "eval_runtime": 31.2928, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.420841683366733e-05, | |
| "loss": 0.9528, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.412825651302606e-05, | |
| "loss": 1.0068, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.8804778456687927, | |
| "eval_runtime": 31.2971, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.404809619238477e-05, | |
| "loss": 0.9084, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.39679358717435e-05, | |
| "loss": 1.083, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8489722013473511, | |
| "eval_runtime": 31.2897, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 6.38877755511022e-05, | |
| "loss": 0.9829, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.380761523046093e-05, | |
| "loss": 0.8407, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 0.8456799387931824, | |
| "eval_runtime": 31.202, | |
| "eval_samples_per_second": 7.115, | |
| "eval_steps_per_second": 1.795, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 6.372745490981965e-05, | |
| "loss": 0.7473, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.364729458917836e-05, | |
| "loss": 0.7468, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.8285406827926636, | |
| "eval_runtime": 31.2693, | |
| "eval_samples_per_second": 7.1, | |
| "eval_steps_per_second": 1.791, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 6.356713426853708e-05, | |
| "loss": 0.892, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 6.34869739478958e-05, | |
| "loss": 0.8421, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.8055410385131836, | |
| "eval_runtime": 31.2828, | |
| "eval_samples_per_second": 7.097, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.340681362725451e-05, | |
| "loss": 0.7795, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.332665330661323e-05, | |
| "loss": 0.8407, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.8160460591316223, | |
| "eval_runtime": 31.2892, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.324649298597195e-05, | |
| "loss": 0.7307, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.316633266533066e-05, | |
| "loss": 0.8126, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 0.8266436457633972, | |
| "eval_runtime": 31.2933, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 6.308617234468938e-05, | |
| "loss": 0.7997, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.30060120240481e-05, | |
| "loss": 0.7318, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.815096914768219, | |
| "eval_runtime": 31.3047, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 6.292585170340681e-05, | |
| "loss": 0.7908, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 6.284569138276553e-05, | |
| "loss": 0.9142, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 0.7875866889953613, | |
| "eval_runtime": 31.2805, | |
| "eval_samples_per_second": 7.097, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 6.276553106212425e-05, | |
| "loss": 0.7489, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 6.268537074148298e-05, | |
| "loss": 0.6483, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.7866150736808777, | |
| "eval_runtime": 31.2895, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 6.260521042084168e-05, | |
| "loss": 0.7886, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 6.252505010020041e-05, | |
| "loss": 0.8092, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.7817696332931519, | |
| "eval_runtime": 31.2844, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 6.244488977955911e-05, | |
| "loss": 0.6213, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 6.236472945891785e-05, | |
| "loss": 0.8235, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.7707763910293579, | |
| "eval_runtime": 31.2903, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 6.228456913827655e-05, | |
| "loss": 0.8963, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 6.220440881763528e-05, | |
| "loss": 0.7062, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.7692943811416626, | |
| "eval_runtime": 31.2891, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 6.2124248496994e-05, | |
| "loss": 0.7988, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 6.204408817635271e-05, | |
| "loss": 0.7348, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.7874757647514343, | |
| "eval_runtime": 31.2928, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 6.196392785571143e-05, | |
| "loss": 0.6604, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 6.188376753507015e-05, | |
| "loss": 0.7507, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.7566913962364197, | |
| "eval_runtime": 31.2871, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 6.180360721442886e-05, | |
| "loss": 0.7219, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 6.172344689378758e-05, | |
| "loss": 0.7588, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.7564798593521118, | |
| "eval_runtime": 31.2861, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 6.16432865731463e-05, | |
| "loss": 0.7573, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 6.156312625250501e-05, | |
| "loss": 0.605, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 0.7298113703727722, | |
| "eval_runtime": 31.2916, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.148296593186374e-05, | |
| "loss": 0.7134, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.140280561122245e-05, | |
| "loss": 0.8721, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.7254282236099243, | |
| "eval_runtime": 31.2918, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.132264529058118e-05, | |
| "loss": 0.8905, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.124248496993988e-05, | |
| "loss": 0.6988, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.7072407007217407, | |
| "eval_runtime": 31.2946, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.116232464929861e-05, | |
| "loss": 0.6772, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.108216432865731e-05, | |
| "loss": 0.6294, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.7082269787788391, | |
| "eval_runtime": 31.303, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.100200400801604e-05, | |
| "loss": 0.5605, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.092184368737475e-05, | |
| "loss": 0.7117, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 0.7112658619880676, | |
| "eval_runtime": 31.295, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.0841683366733476e-05, | |
| "loss": 0.7873, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.0761523046092186e-05, | |
| "loss": 0.8558, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.6991309523582458, | |
| "eval_runtime": 31.3002, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 6.068136272545091e-05, | |
| "loss": 0.8755, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 6.060120240480962e-05, | |
| "loss": 0.6187, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.690467119216919, | |
| "eval_runtime": 31.2955, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 6.052104208416834e-05, | |
| "loss": 0.7238, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 6.044088176352706e-05, | |
| "loss": 0.6791, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 0.687512993812561, | |
| "eval_runtime": 31.3006, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 6.0360721442885776e-05, | |
| "loss": 0.7325, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 6.028056112224449e-05, | |
| "loss": 0.5447, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 0.6869089007377625, | |
| "eval_runtime": 31.296, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 6.0200400801603217e-05, | |
| "loss": 0.7392, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 6.0120240480961926e-05, | |
| "loss": 0.7299, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 0.6777493357658386, | |
| "eval_runtime": 31.2976, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 6.004008016032065e-05, | |
| "loss": 0.7736, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.995991983967936e-05, | |
| "loss": 0.5829, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.6657550930976868, | |
| "eval_runtime": 31.2961, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 5.987975951903808e-05, | |
| "loss": 0.7086, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 5.979959919839679e-05, | |
| "loss": 0.6435, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.6603330969810486, | |
| "eval_runtime": 31.2999, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 5.971943887775552e-05, | |
| "loss": 0.6293, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.9639278557114233e-05, | |
| "loss": 0.7303, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.6578312516212463, | |
| "eval_runtime": 31.305, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.955911823647295e-05, | |
| "loss": 0.6796, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.947895791583167e-05, | |
| "loss": 0.7244, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 0.6594119668006897, | |
| "eval_runtime": 31.3007, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.939879759519039e-05, | |
| "loss": 0.6601, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 5.93186372745491e-05, | |
| "loss": 0.6463, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 0.640873372554779, | |
| "eval_runtime": 31.295, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 5.9238476953907824e-05, | |
| "loss": 0.6722, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 5.9158316633266534e-05, | |
| "loss": 0.7766, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.6417058706283569, | |
| "eval_runtime": 31.3016, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 5.907815631262526e-05, | |
| "loss": 0.5843, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 5.899799599198397e-05, | |
| "loss": 0.6012, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 0.646079957485199, | |
| "eval_runtime": 31.2989, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 5.891783567134269e-05, | |
| "loss": 0.7435, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.883767535070141e-05, | |
| "loss": 0.5974, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.6364943981170654, | |
| "eval_runtime": 31.305, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 5.8757515030060124e-05, | |
| "loss": 0.6149, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.867735470941884e-05, | |
| "loss": 0.556, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 0.6301265358924866, | |
| "eval_runtime": 31.3004, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.859719438877756e-05, | |
| "loss": 0.5322, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.8517034068136274e-05, | |
| "loss": 0.6369, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.6247262358665466, | |
| "eval_runtime": 31.298, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.8436873747495e-05, | |
| "loss": 0.6517, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.835671342685371e-05, | |
| "loss": 0.5699, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.6162915229797363, | |
| "eval_runtime": 31.2973, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.827655310621243e-05, | |
| "loss": 0.6318, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 5.819639278557114e-05, | |
| "loss": 0.624, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 0.6137639880180359, | |
| "eval_runtime": 31.3062, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 5.8116232464929865e-05, | |
| "loss": 0.695, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 5.8036072144288574e-05, | |
| "loss": 0.6774, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 0.6134688854217529, | |
| "eval_runtime": 31.2931, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 5.79559118236473e-05, | |
| "loss": 0.5395, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 5.7875751503006015e-05, | |
| "loss": 0.5553, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.6075760126113892, | |
| "eval_runtime": 31.3038, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 5.779559118236473e-05, | |
| "loss": 0.8059, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 5.7715430861723455e-05, | |
| "loss": 0.604, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 0.5937612652778625, | |
| "eval_runtime": 31.3124, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 5.763527054108217e-05, | |
| "loss": 0.6524, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 5.755511022044089e-05, | |
| "loss": 0.6087, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.5955749750137329, | |
| "eval_runtime": 31.3138, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.7474949899799605e-05, | |
| "loss": 0.6067, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 5.739478957915833e-05, | |
| "loss": 0.5935, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 0.5933490991592407, | |
| "eval_runtime": 31.3036, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 5.731462925851704e-05, | |
| "loss": 0.6652, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 5.723446893787576e-05, | |
| "loss": 0.6042, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 0.5911222100257874, | |
| "eval_runtime": 31.2993, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.715430861723447e-05, | |
| "loss": 0.6957, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.7074148296593195e-05, | |
| "loss": 0.6425, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 0.5844302773475647, | |
| "eval_runtime": 31.2967, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.6993987975951905e-05, | |
| "loss": 0.4406, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 5.691382765531063e-05, | |
| "loss": 0.6316, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.5744926929473877, | |
| "eval_runtime": 31.3029, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 5.6833667334669345e-05, | |
| "loss": 0.5697, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 5.675350701402806e-05, | |
| "loss": 0.597, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 0.5694547891616821, | |
| "eval_runtime": 31.311, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.667334669338678e-05, | |
| "loss": 0.5544, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.6593186372745496e-05, | |
| "loss": 0.5754, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 0.5703684091567993, | |
| "eval_runtime": 31.3157, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.651302605210421e-05, | |
| "loss": 0.465, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.6432865731462936e-05, | |
| "loss": 0.5197, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 0.5696949362754822, | |
| "eval_runtime": 31.3085, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.6352705410821646e-05, | |
| "loss": 0.6936, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.627254509018037e-05, | |
| "loss": 0.6256, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.5596420764923096, | |
| "eval_runtime": 31.3048, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.619238476953908e-05, | |
| "loss": 0.6175, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 5.61122244488978e-05, | |
| "loss": 0.5818, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.5599228739738464, | |
| "eval_runtime": 31.3107, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.603206412825652e-05, | |
| "loss": 0.5264, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 5.5951903807615236e-05, | |
| "loss": 0.5464, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_loss": 0.5564998388290405, | |
| "eval_runtime": 31.303, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 5.587174348697395e-05, | |
| "loss": 0.3897, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 5.579158316633267e-05, | |
| "loss": 0.4616, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 0.5629072189331055, | |
| "eval_runtime": 31.0222, | |
| "eval_samples_per_second": 7.156, | |
| "eval_steps_per_second": 1.805, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 5.5711422845691386e-05, | |
| "loss": 0.6419, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 5.563126252505011e-05, | |
| "loss": 0.6482, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.5529131889343262, | |
| "eval_runtime": 31.2128, | |
| "eval_samples_per_second": 7.112, | |
| "eval_steps_per_second": 1.794, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 5.555110220440882e-05, | |
| "loss": 0.5377, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 5.547094188376754e-05, | |
| "loss": 0.5356, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_loss": 0.5526372790336609, | |
| "eval_runtime": 31.2759, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.791, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 5.539078156312625e-05, | |
| "loss": 0.589, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 5.5310621242484976e-05, | |
| "loss": 0.5688, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 0.5528168678283691, | |
| "eval_runtime": 31.2986, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 5.5230460921843686e-05, | |
| "loss": 0.4732, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 5.515030060120241e-05, | |
| "loss": 0.6018, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 0.5408484935760498, | |
| "eval_runtime": 31.3037, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 5.5070140280561127e-05, | |
| "loss": 0.505, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 5.498997995991984e-05, | |
| "loss": 0.5794, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_loss": 0.5370539426803589, | |
| "eval_runtime": 31.3017, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 5.490981963927856e-05, | |
| "loss": 0.5621, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 5.4829659318637283e-05, | |
| "loss": 0.5443, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_loss": 0.537534236907959, | |
| "eval_runtime": 31.2972, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 5.474949899799599e-05, | |
| "loss": 0.449, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 5.466933867735472e-05, | |
| "loss": 0.4435, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 0.5345003604888916, | |
| "eval_runtime": 31.2985, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 5.458917835671343e-05, | |
| "loss": 0.4819, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 5.450901803607215e-05, | |
| "loss": 0.5087, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.5292515754699707, | |
| "eval_runtime": 31.3021, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 5.442885771543086e-05, | |
| "loss": 0.453, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 5.4348697394789584e-05, | |
| "loss": 0.518, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_loss": 0.5336319804191589, | |
| "eval_runtime": 31.2945, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 5.42685370741483e-05, | |
| "loss": 0.5508, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 5.418837675350702e-05, | |
| "loss": 0.5914, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 0.5315628051757812, | |
| "eval_runtime": 31.3062, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 5.4108216432865734e-05, | |
| "loss": 0.5609, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 5.402805611222446e-05, | |
| "loss": 0.5667, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_loss": 0.5254489183425903, | |
| "eval_runtime": 31.2915, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 5.394789579158317e-05, | |
| "loss": 0.5349, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 5.386773547094189e-05, | |
| "loss": 0.5218, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 0.5206549167633057, | |
| "eval_runtime": 31.2983, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 5.37875751503006e-05, | |
| "loss": 0.5036, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 5.3707414829659324e-05, | |
| "loss": 0.4267, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_loss": 0.5270143151283264, | |
| "eval_runtime": 31.2985, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 5.3627254509018034e-05, | |
| "loss": 0.5262, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 5.354709418837676e-05, | |
| "loss": 0.5839, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "eval_loss": 0.5198652148246765, | |
| "eval_runtime": 31.2991, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 5.3466933867735474e-05, | |
| "loss": 0.4521, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 5.338677354709419e-05, | |
| "loss": 0.5095, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 0.5267544984817505, | |
| "eval_runtime": 31.299, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 5.3306613226452914e-05, | |
| "loss": 0.5022, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 5.3226452905811624e-05, | |
| "loss": 0.4616, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_loss": 0.5191987752914429, | |
| "eval_runtime": 31.2917, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 5.314629258517035e-05, | |
| "loss": 0.5251, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 5.3066132264529065e-05, | |
| "loss": 0.5027, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_loss": 0.5106366872787476, | |
| "eval_runtime": 31.2948, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 5.298597194388778e-05, | |
| "loss": 0.5192, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 5.29058116232465e-05, | |
| "loss": 0.441, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_loss": 0.5149854421615601, | |
| "eval_runtime": 31.2974, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 5.282565130260522e-05, | |
| "loss": 0.5155, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 5.274549098196393e-05, | |
| "loss": 0.4416, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 0.5155748724937439, | |
| "eval_runtime": 31.2962, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 5.2665330661322655e-05, | |
| "loss": 0.5154, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 5.2585170340681365e-05, | |
| "loss": 0.4411, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "eval_loss": 0.5102916955947876, | |
| "eval_runtime": 31.2896, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 5.250501002004009e-05, | |
| "loss": 0.5015, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 5.24248496993988e-05, | |
| "loss": 0.47, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 0.5037886500358582, | |
| "eval_runtime": 31.2923, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 5.234468937875752e-05, | |
| "loss": 0.403, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 5.226452905811624e-05, | |
| "loss": 0.5079, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.5047650337219238, | |
| "eval_runtime": 31.2924, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 5.2184368737474955e-05, | |
| "loss": 0.4939, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 5.210420841683367e-05, | |
| "loss": 0.3913, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_loss": 0.508187472820282, | |
| "eval_runtime": 31.2958, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 5.2024048096192395e-05, | |
| "loss": 0.3983, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 5.1943887775551105e-05, | |
| "loss": 0.4977, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_loss": 0.49760758876800537, | |
| "eval_runtime": 31.3045, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 5.186372745490983e-05, | |
| "loss": 0.5879, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 5.178356713426854e-05, | |
| "loss": 0.5905, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "eval_loss": 0.4974704384803772, | |
| "eval_runtime": 31.2985, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 5.170340681362726e-05, | |
| "loss": 0.5392, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 5.162324649298597e-05, | |
| "loss": 0.4362, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 0.4961581230163574, | |
| "eval_runtime": 31.306, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 5.1543086172344696e-05, | |
| "loss": 0.522, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.146292585170341e-05, | |
| "loss": 0.4309, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 0.500778317451477, | |
| "eval_runtime": 31.3034, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 5.138276553106213e-05, | |
| "loss": 0.5687, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 5.1302605210420846e-05, | |
| "loss": 0.4477, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_loss": 0.49876537919044495, | |
| "eval_runtime": 31.2939, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 5.122244488977956e-05, | |
| "loss": 0.4987, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 5.114228456913828e-05, | |
| "loss": 0.4826, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 0.488558828830719, | |
| "eval_runtime": 31.2964, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 5.1062124248497e-05, | |
| "loss": 0.597, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 5.098196392785571e-05, | |
| "loss": 0.6181, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "eval_loss": 0.48853781819343567, | |
| "eval_runtime": 31.2965, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 5.0901803607214436e-05, | |
| "loss": 0.5415, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 5.0821643286573146e-05, | |
| "loss": 0.4738, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_loss": 0.48789137601852417, | |
| "eval_runtime": 31.2967, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.074148296593187e-05, | |
| "loss": 0.5222, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 5.066132264529058e-05, | |
| "loss": 0.4932, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_loss": 0.4817972481250763, | |
| "eval_runtime": 31.2976, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 5.05811623246493e-05, | |
| "loss": 0.4425, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 5.050100200400802e-05, | |
| "loss": 0.4684, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_loss": 0.4812251031398773, | |
| "eval_runtime": 31.2943, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 5.0420841683366736e-05, | |
| "loss": 0.5561, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 5.034068136272545e-05, | |
| "loss": 0.5484, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "eval_loss": 0.47668221592903137, | |
| "eval_runtime": 31.2926, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 5.0260521042084176e-05, | |
| "loss": 0.5458, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 5.0180360721442886e-05, | |
| "loss": 0.5086, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "eval_loss": 0.4790602922439575, | |
| "eval_runtime": 31.298, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 5.010020040080161e-05, | |
| "loss": 0.4593, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 5.002004008016032e-05, | |
| "loss": 0.3548, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 0.4792560935020447, | |
| "eval_runtime": 31.2988, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 4.993987975951904e-05, | |
| "loss": 0.4227, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 4.985971943887775e-05, | |
| "loss": 0.5229, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 0.47653260827064514, | |
| "eval_runtime": 31.3054, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 4.977955911823648e-05, | |
| "loss": 0.3925, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 4.9699398797595193e-05, | |
| "loss": 0.4578, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_loss": 0.4703618884086609, | |
| "eval_runtime": 31.3015, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 4.961923847695391e-05, | |
| "loss": 0.4669, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 4.953907815631263e-05, | |
| "loss": 0.5277, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_loss": 0.4690556526184082, | |
| "eval_runtime": 31.3076, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 4.945891783567135e-05, | |
| "loss": 0.3436, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 4.937875751503006e-05, | |
| "loss": 0.4683, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_loss": 0.4648754894733429, | |
| "eval_runtime": 31.2941, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.9298597194388784e-05, | |
| "loss": 0.4551, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 4.9218436873747494e-05, | |
| "loss": 0.448, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "eval_loss": 0.46837684512138367, | |
| "eval_runtime": 31.2979, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 4.913827655310622e-05, | |
| "loss": 0.5228, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 4.905811623246493e-05, | |
| "loss": 0.3752, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_loss": 0.4696580469608307, | |
| "eval_runtime": 31.3122, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 4.897795591182365e-05, | |
| "loss": 0.5608, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 4.889779559118237e-05, | |
| "loss": 0.4631, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_loss": 0.467781126499176, | |
| "eval_runtime": 31.3015, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 4.8817635270541084e-05, | |
| "loss": 0.4402, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.873747494989981e-05, | |
| "loss": 0.4277, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_loss": 0.4608190953731537, | |
| "eval_runtime": 31.3027, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.865731462925852e-05, | |
| "loss": 0.3894, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 4.857715430861724e-05, | |
| "loss": 0.3646, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_loss": 0.460921972990036, | |
| "eval_runtime": 31.2992, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 4.849699398797596e-05, | |
| "loss": 0.3929, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 4.8416833667334674e-05, | |
| "loss": 0.5276, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_loss": 0.45434585213661194, | |
| "eval_runtime": 31.2975, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 4.833667334669339e-05, | |
| "loss": 0.4141, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 4.8256513026052115e-05, | |
| "loss": 0.431, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 0.4538600444793701, | |
| "eval_runtime": 31.2976, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 4.8176352705410824e-05, | |
| "loss": 0.6326, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.809619238476955e-05, | |
| "loss": 0.5465, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 0.4550160765647888, | |
| "eval_runtime": 31.3034, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.801603206412826e-05, | |
| "loss": 0.5185, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.793587174348698e-05, | |
| "loss": 0.4954, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 0.4522875249385834, | |
| "eval_runtime": 31.2925, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.785571142284569e-05, | |
| "loss": 0.4591, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.7775551102204415e-05, | |
| "loss": 0.4886, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_loss": 0.4499128758907318, | |
| "eval_runtime": 31.1861, | |
| "eval_samples_per_second": 7.119, | |
| "eval_steps_per_second": 1.796, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.769539078156313e-05, | |
| "loss": 0.3942, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 4.761523046092185e-05, | |
| "loss": 0.4898, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 0.4461597204208374, | |
| "eval_runtime": 31.2639, | |
| "eval_samples_per_second": 7.101, | |
| "eval_steps_per_second": 1.791, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 4.7535070140280565e-05, | |
| "loss": 0.3444, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 4.745490981963929e-05, | |
| "loss": 0.4072, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "eval_loss": 0.4478509724140167, | |
| "eval_runtime": 31.292, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 4.7374749498998e-05, | |
| "loss": 0.4066, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 4.729458917835672e-05, | |
| "loss": 0.4565, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 0.4457860291004181, | |
| "eval_runtime": 31.3, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 4.721442885771543e-05, | |
| "loss": 0.419, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 4.7134268537074155e-05, | |
| "loss": 0.3739, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 0.4474635720252991, | |
| "eval_runtime": 31.3042, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 4.7054108216432865e-05, | |
| "loss": 0.5401, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 4.697394789579159e-05, | |
| "loss": 0.4211, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_loss": 0.44858118891716003, | |
| "eval_runtime": 31.3113, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 4.6893787575150305e-05, | |
| "loss": 0.4913, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 4.681362725450902e-05, | |
| "loss": 0.4048, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_loss": 0.4393081068992615, | |
| "eval_runtime": 31.3163, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.673346693386774e-05, | |
| "loss": 0.3935, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 4.665330661322646e-05, | |
| "loss": 0.5064, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "eval_loss": 0.4351194500923157, | |
| "eval_runtime": 31.3041, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 4.657314629258517e-05, | |
| "loss": 0.3017, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 4.6492985971943896e-05, | |
| "loss": 0.4652, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_loss": 0.43793508410453796, | |
| "eval_runtime": 31.3085, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 4.6412825651302606e-05, | |
| "loss": 0.4423, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 4.633266533066133e-05, | |
| "loss": 0.4061, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "eval_loss": 0.43406903743743896, | |
| "eval_runtime": 31.3118, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.625250501002004e-05, | |
| "loss": 0.3877, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 4.617234468937876e-05, | |
| "loss": 0.3784, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "eval_loss": 0.4390106499195099, | |
| "eval_runtime": 31.3101, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 4.609218436873748e-05, | |
| "loss": 0.415, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.6012024048096196e-05, | |
| "loss": 0.4142, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "eval_loss": 0.43537265062332153, | |
| "eval_runtime": 31.3175, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.593186372745491e-05, | |
| "loss": 0.4459, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 4.585170340681363e-05, | |
| "loss": 0.3625, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "eval_loss": 0.4415459930896759, | |
| "eval_runtime": 31.299, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 4.5771543086172346e-05, | |
| "loss": 0.4102, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.569138276553107e-05, | |
| "loss": 0.3807, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_loss": 0.4403214752674103, | |
| "eval_runtime": 31.3171, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 4.561122244488978e-05, | |
| "loss": 0.544, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 4.55310621242485e-05, | |
| "loss": 0.4154, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_loss": 0.4307992458343506, | |
| "eval_runtime": 31.3169, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.545090180360721e-05, | |
| "loss": 0.405, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 4.5370741482965936e-05, | |
| "loss": 0.4509, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 0.429840087890625, | |
| "eval_runtime": 31.316, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 4.5290581162324646e-05, | |
| "loss": 0.3593, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 4.521042084168337e-05, | |
| "loss": 0.4254, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 0.42388150095939636, | |
| "eval_runtime": 31.3164, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 4.5130260521042086e-05, | |
| "loss": 0.4071, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 4.50501002004008e-05, | |
| "loss": 0.4323, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_loss": 0.42136842012405396, | |
| "eval_runtime": 31.3202, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 4.496993987975952e-05, | |
| "loss": 0.3243, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 4.4889779559118243e-05, | |
| "loss": 0.4359, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_loss": 0.4290623068809509, | |
| "eval_runtime": 31.3259, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 4.480961923847695e-05, | |
| "loss": 0.4209, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 4.472945891783568e-05, | |
| "loss": 0.3759, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "eval_loss": 0.4223538935184479, | |
| "eval_runtime": 31.3287, | |
| "eval_samples_per_second": 7.086, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 4.464929859719439e-05, | |
| "loss": 0.4106, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 4.456913827655311e-05, | |
| "loss": 0.4534, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 0.42248478531837463, | |
| "eval_runtime": 31.3216, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 4.448897795591182e-05, | |
| "loss": 0.3862, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 4.4408817635270544e-05, | |
| "loss": 0.4013, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "eval_loss": 0.42617106437683105, | |
| "eval_runtime": 31.3246, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 4.432865731462927e-05, | |
| "loss": 0.3103, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 4.424849699398798e-05, | |
| "loss": 0.4331, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_loss": 0.4213978052139282, | |
| "eval_runtime": 31.3244, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.41683366733467e-05, | |
| "loss": 0.381, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 4.408817635270542e-05, | |
| "loss": 0.4373, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "eval_loss": 0.4198138117790222, | |
| "eval_runtime": 31.3271, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 4.4008016032064134e-05, | |
| "loss": 0.3603, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 4.392785571142285e-05, | |
| "loss": 0.4975, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 0.42358022928237915, | |
| "eval_runtime": 31.3249, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 4.384769539078157e-05, | |
| "loss": 0.342, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 4.3767535070140284e-05, | |
| "loss": 0.423, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_loss": 0.4189080595970154, | |
| "eval_runtime": 31.3275, | |
| "eval_samples_per_second": 7.086, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 4.368737474949901e-05, | |
| "loss": 0.4149, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 4.360721442885772e-05, | |
| "loss": 0.4503, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 0.4171365201473236, | |
| "eval_runtime": 31.3168, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 4.352705410821644e-05, | |
| "loss": 0.415, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.344689378757515e-05, | |
| "loss": 0.3796, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_loss": 0.41718369722366333, | |
| "eval_runtime": 31.3195, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 4.3366733466933874e-05, | |
| "loss": 0.3788, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 4.3286573146292584e-05, | |
| "loss": 0.4063, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "eval_loss": 0.41249218583106995, | |
| "eval_runtime": 31.3221, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.320641282565131e-05, | |
| "loss": 0.4379, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 4.3126252505010025e-05, | |
| "loss": 0.3841, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "eval_loss": 0.41186362504959106, | |
| "eval_runtime": 31.3313, | |
| "eval_samples_per_second": 7.086, | |
| "eval_steps_per_second": 1.787, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.304609218436874e-05, | |
| "loss": 0.3669, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 4.296593186372746e-05, | |
| "loss": 0.2956, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 0.4147048890590668, | |
| "eval_runtime": 31.3349, | |
| "eval_samples_per_second": 7.085, | |
| "eval_steps_per_second": 1.787, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.288577154308618e-05, | |
| "loss": 0.5446, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 4.280561122244489e-05, | |
| "loss": 0.3486, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_loss": 0.42460867762565613, | |
| "eval_runtime": 31.3167, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 4.2725450901803615e-05, | |
| "loss": 0.3405, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 4.2645290581162325e-05, | |
| "loss": 0.3585, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_loss": 0.4116860330104828, | |
| "eval_runtime": 31.3378, | |
| "eval_samples_per_second": 7.084, | |
| "eval_steps_per_second": 1.787, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 4.256513026052105e-05, | |
| "loss": 0.3642, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 4.248496993987976e-05, | |
| "loss": 0.4496, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 0.40906357765197754, | |
| "eval_runtime": 31.3315, | |
| "eval_samples_per_second": 7.086, | |
| "eval_steps_per_second": 1.787, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 4.240480961923848e-05, | |
| "loss": 0.4845, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 4.23246492985972e-05, | |
| "loss": 0.399, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "eval_loss": 0.40488967299461365, | |
| "eval_runtime": 31.3211, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 4.2244488977955915e-05, | |
| "loss": 0.4057, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 4.216432865731463e-05, | |
| "loss": 0.3885, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "eval_loss": 0.4003817141056061, | |
| "eval_runtime": 31.3245, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 4.2084168336673355e-05, | |
| "loss": 0.3819, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 4.2004008016032065e-05, | |
| "loss": 0.3728, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 0.4003088176250458, | |
| "eval_runtime": 31.3239, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 4.192384769539079e-05, | |
| "loss": 0.3902, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 4.18436873747495e-05, | |
| "loss": 0.2698, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "eval_loss": 0.40085363388061523, | |
| "eval_runtime": 31.3226, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 4.176352705410822e-05, | |
| "loss": 0.3917, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 4.168336673346693e-05, | |
| "loss": 0.3799, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "eval_loss": 0.40029290318489075, | |
| "eval_runtime": 31.329, | |
| "eval_samples_per_second": 7.086, | |
| "eval_steps_per_second": 1.787, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.1603206412825656e-05, | |
| "loss": 0.3973, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 4.152304609218437e-05, | |
| "loss": 0.4888, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "eval_loss": 0.3974343240261078, | |
| "eval_runtime": 31.3235, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 4.144288577154309e-05, | |
| "loss": 0.2457, | |
| "step": 2405 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 4.1362725450901806e-05, | |
| "loss": 0.3795, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 0.3994871973991394, | |
| "eval_runtime": 31.3159, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 4.128256513026052e-05, | |
| "loss": 0.3535, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 4.120240480961924e-05, | |
| "loss": 0.4249, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 0.3967938721179962, | |
| "eval_runtime": 31.3239, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 4.112224448897796e-05, | |
| "loss": 0.4219, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 4.104208416833667e-05, | |
| "loss": 0.4635, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_loss": 0.4001442790031433, | |
| "eval_runtime": 31.3171, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 4.0961923847695396e-05, | |
| "loss": 0.3439, | |
| "step": 2435 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 4.0881763527054106e-05, | |
| "loss": 0.4965, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_loss": 0.39344674348831177, | |
| "eval_runtime": 31.3149, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 4.080160320641283e-05, | |
| "loss": 0.3569, | |
| "step": 2445 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 4.072144288577154e-05, | |
| "loss": 0.3745, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "eval_loss": 0.3987390697002411, | |
| "eval_runtime": 31.318, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 4.064128256513026e-05, | |
| "loss": 0.4011, | |
| "step": 2455 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 4.056112224448898e-05, | |
| "loss": 0.3601, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "eval_loss": 0.3985511064529419, | |
| "eval_runtime": 31.3089, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 4.0480961923847696e-05, | |
| "loss": 0.4154, | |
| "step": 2465 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 4.040080160320641e-05, | |
| "loss": 0.2878, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_loss": 0.39409133791923523, | |
| "eval_runtime": 31.3205, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.0320641282565136e-05, | |
| "loss": 0.3433, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 4.0240480961923846e-05, | |
| "loss": 0.4297, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_loss": 0.3889669179916382, | |
| "eval_runtime": 31.3109, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 4.016032064128257e-05, | |
| "loss": 0.3173, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 4.008016032064128e-05, | |
| "loss": 0.278, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 0.3974519968032837, | |
| "eval_runtime": 31.3206, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3572, | |
| "step": 2495 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 3.991983967935872e-05, | |
| "loss": 0.4509, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "eval_loss": 0.39074984192848206, | |
| "eval_runtime": 31.3198, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 3.983967935871744e-05, | |
| "loss": 0.2818, | |
| "step": 2505 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 3.9759519038076153e-05, | |
| "loss": 0.3202, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 0.3872080147266388, | |
| "eval_runtime": 31.1989, | |
| "eval_samples_per_second": 7.116, | |
| "eval_steps_per_second": 1.795, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 3.967935871743487e-05, | |
| "loss": 0.3529, | |
| "step": 2515 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.959919839679359e-05, | |
| "loss": 0.3047, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 0.3956039547920227, | |
| "eval_runtime": 31.2729, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 1.791, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 3.951903807615231e-05, | |
| "loss": 0.3407, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 3.943887775551103e-05, | |
| "loss": 0.2931, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "eval_loss": 0.39254140853881836, | |
| "eval_runtime": 31.2872, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 3.9358717434869744e-05, | |
| "loss": 0.3376, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 3.927855711422846e-05, | |
| "loss": 0.3487, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "eval_loss": 0.3909657597541809, | |
| "eval_runtime": 31.2934, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 3.919839679358718e-05, | |
| "loss": 0.4409, | |
| "step": 2545 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 3.9118236472945894e-05, | |
| "loss": 0.2792, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_loss": 0.3901335895061493, | |
| "eval_runtime": 31.3009, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 3.903807615230461e-05, | |
| "loss": 0.2794, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 3.895791583166333e-05, | |
| "loss": 0.3446, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_loss": 0.38729164004325867, | |
| "eval_runtime": 31.2913, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 3.8877755511022044e-05, | |
| "loss": 0.3807, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 3.879759519038076e-05, | |
| "loss": 0.3482, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "eval_loss": 0.3839856684207916, | |
| "eval_runtime": 31.2918, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 3.8717434869739484e-05, | |
| "loss": 0.333, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 3.86372745490982e-05, | |
| "loss": 0.3464, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_loss": 0.38349151611328125, | |
| "eval_runtime": 31.2954, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 3.855711422845692e-05, | |
| "loss": 0.446, | |
| "step": 2585 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 3.8476953907815634e-05, | |
| "loss": 0.3212, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "eval_loss": 0.3845639228820801, | |
| "eval_runtime": 31.3009, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 3.839679358717435e-05, | |
| "loss": 0.2797, | |
| "step": 2595 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 3.831663326653307e-05, | |
| "loss": 0.3847, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "eval_loss": 0.3818623721599579, | |
| "eval_runtime": 31.298, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 3.8236472945891784e-05, | |
| "loss": 0.4431, | |
| "step": 2605 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 3.81563126252505e-05, | |
| "loss": 0.3212, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "eval_loss": 0.38965049386024475, | |
| "eval_runtime": 31.2995, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 3.807615230460922e-05, | |
| "loss": 0.3441, | |
| "step": 2615 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 3.7995991983967935e-05, | |
| "loss": 0.358, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "eval_loss": 0.381111204624176, | |
| "eval_runtime": 31.2872, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 3.791583166332665e-05, | |
| "loss": 0.287, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 3.7835671342685375e-05, | |
| "loss": 0.3471, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_loss": 0.38052383065223694, | |
| "eval_runtime": 31.2873, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 3.775551102204409e-05, | |
| "loss": 0.2928, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 3.767535070140281e-05, | |
| "loss": 0.3348, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "eval_loss": 0.38677719235420227, | |
| "eval_runtime": 31.2908, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 3.7595190380761525e-05, | |
| "loss": 0.3454, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 3.751503006012025e-05, | |
| "loss": 0.342, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "eval_loss": 0.3768896162509918, | |
| "eval_runtime": 31.29, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 3.7434869739478965e-05, | |
| "loss": 0.2887, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 3.735470941883768e-05, | |
| "loss": 0.4504, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "eval_loss": 0.3774382770061493, | |
| "eval_runtime": 31.2944, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 3.72745490981964e-05, | |
| "loss": 0.3159, | |
| "step": 2665 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 3.7194388777555115e-05, | |
| "loss": 0.2713, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "eval_loss": 0.3802602291107178, | |
| "eval_runtime": 31.2859, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 3.711422845691383e-05, | |
| "loss": 0.3543, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 3.703406813627255e-05, | |
| "loss": 0.3848, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "eval_loss": 0.3776351511478424, | |
| "eval_runtime": 31.2876, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 3.6953907815631265e-05, | |
| "loss": 0.3891, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 3.687374749498998e-05, | |
| "loss": 0.354, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "eval_loss": 0.3758071959018707, | |
| "eval_runtime": 31.2908, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 3.67935871743487e-05, | |
| "loss": 0.3596, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 3.671342685370742e-05, | |
| "loss": 0.3796, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 0.37596631050109863, | |
| "eval_runtime": 31.2928, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 3.663326653306614e-05, | |
| "loss": 0.2658, | |
| "step": 2705 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 3.6553106212424856e-05, | |
| "loss": 0.3654, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "eval_loss": 0.37372830510139465, | |
| "eval_runtime": 31.2931, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 3.647294589178357e-05, | |
| "loss": 0.3026, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 3.639278557114229e-05, | |
| "loss": 0.3448, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_loss": 0.38118383288383484, | |
| "eval_runtime": 31.2914, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 3.6312625250501006e-05, | |
| "loss": 0.2915, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 3.623246492985972e-05, | |
| "loss": 0.355, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "eval_loss": 0.3758777379989624, | |
| "eval_runtime": 31.293, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 3.615230460921844e-05, | |
| "loss": 0.3554, | |
| "step": 2735 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 3.6072144288577156e-05, | |
| "loss": 0.288, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "eval_loss": 0.3711189031600952, | |
| "eval_runtime": 31.2905, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 3.599198396793587e-05, | |
| "loss": 0.3532, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 3.591182364729459e-05, | |
| "loss": 0.2991, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "eval_loss": 0.3690561354160309, | |
| "eval_runtime": 31.2895, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 3.583166332665331e-05, | |
| "loss": 0.2659, | |
| "step": 2755 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 3.575150300601203e-05, | |
| "loss": 0.3443, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "eval_loss": 0.3708031177520752, | |
| "eval_runtime": 31.292, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 3.5671342685370746e-05, | |
| "loss": 0.2478, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 3.559118236472946e-05, | |
| "loss": 0.3374, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "eval_loss": 0.36587995290756226, | |
| "eval_runtime": 31.291, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 3.551102204408818e-05, | |
| "loss": 0.2512, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 3.5430861723446896e-05, | |
| "loss": 0.4078, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_loss": 0.37093624472618103, | |
| "eval_runtime": 31.2862, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 3.535070140280561e-05, | |
| "loss": 0.3944, | |
| "step": 2785 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 3.527054108216433e-05, | |
| "loss": 0.2967, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_loss": 0.3683302104473114, | |
| "eval_runtime": 31.2839, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 3.5190380761523046e-05, | |
| "loss": 0.2733, | |
| "step": 2795 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 3.511022044088176e-05, | |
| "loss": 0.3532, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "eval_loss": 0.3638099730014801, | |
| "eval_runtime": 31.2946, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 3.503006012024049e-05, | |
| "loss": 0.4112, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 3.49498997995992e-05, | |
| "loss": 0.4123, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "eval_loss": 0.36417555809020996, | |
| "eval_runtime": 31.2926, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 3.486973947895792e-05, | |
| "loss": 0.4427, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 3.478957915831664e-05, | |
| "loss": 0.3195, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "eval_loss": 0.36552584171295166, | |
| "eval_runtime": 31.2936, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 3.4709418837675353e-05, | |
| "loss": 0.2884, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 3.462925851703407e-05, | |
| "loss": 0.3161, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "eval_loss": 0.3598646819591522, | |
| "eval_runtime": 31.292, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 3.454909819639279e-05, | |
| "loss": 0.323, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 3.4468937875751504e-05, | |
| "loss": 0.4152, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "eval_loss": 0.3621058464050293, | |
| "eval_runtime": 31.2915, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 3.438877755511022e-05, | |
| "loss": 0.3332, | |
| "step": 2845 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 3.430861723446894e-05, | |
| "loss": 0.2802, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_loss": 0.36484986543655396, | |
| "eval_runtime": 31.2933, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 3.4228456913827654e-05, | |
| "loss": 0.37, | |
| "step": 2855 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 3.414829659318638e-05, | |
| "loss": 0.2909, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 0.36040765047073364, | |
| "eval_runtime": 31.2907, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 3.4068136272545094e-05, | |
| "loss": 0.3928, | |
| "step": 2865 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 3.398797595190381e-05, | |
| "loss": 0.3105, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "eval_loss": 0.3604431748390198, | |
| "eval_runtime": 31.2918, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 3.390781563126253e-05, | |
| "loss": 0.3766, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 3.3827655310621244e-05, | |
| "loss": 0.3291, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_loss": 0.355290025472641, | |
| "eval_runtime": 31.2907, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 3.374749498997996e-05, | |
| "loss": 0.3502, | |
| "step": 2885 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 3.366733466933868e-05, | |
| "loss": 0.3916, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 0.36026230454444885, | |
| "eval_runtime": 31.2896, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 3.3587174348697394e-05, | |
| "loss": 0.31, | |
| "step": 2895 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 3.350701402805611e-05, | |
| "loss": 0.3657, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "eval_loss": 0.3543720543384552, | |
| "eval_runtime": 31.2877, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 3.342685370741483e-05, | |
| "loss": 0.3137, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 3.3346693386773544e-05, | |
| "loss": 0.3745, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "eval_loss": 0.35586270689964294, | |
| "eval_runtime": 31.2748, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.791, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 3.326653306613227e-05, | |
| "loss": 0.3075, | |
| "step": 2915 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 3.3186372745490984e-05, | |
| "loss": 0.3281, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "eval_loss": 0.35174089670181274, | |
| "eval_runtime": 31.2876, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 3.31062124248497e-05, | |
| "loss": 0.2976, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 3.3026052104208425e-05, | |
| "loss": 0.2892, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "eval_loss": 0.3550553023815155, | |
| "eval_runtime": 31.2925, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 3.294589178356714e-05, | |
| "loss": 0.2826, | |
| "step": 2935 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 3.286573146292586e-05, | |
| "loss": 0.4121, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_loss": 0.34888410568237305, | |
| "eval_runtime": 31.2869, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 3.2785571142284575e-05, | |
| "loss": 0.3921, | |
| "step": 2945 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 3.270541082164329e-05, | |
| "loss": 0.2908, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_loss": 0.35319554805755615, | |
| "eval_runtime": 31.2849, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 3.262525050100201e-05, | |
| "loss": 0.2526, | |
| "step": 2955 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 3.2545090180360725e-05, | |
| "loss": 0.3677, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 0.3468542993068695, | |
| "eval_runtime": 31.2952, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 3.246492985971944e-05, | |
| "loss": 0.303, | |
| "step": 2965 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 3.238476953907816e-05, | |
| "loss": 0.341, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "eval_loss": 0.3503284752368927, | |
| "eval_runtime": 31.2896, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 3.2304609218436875e-05, | |
| "loss": 0.3035, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 3.222444889779559e-05, | |
| "loss": 0.2319, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "eval_loss": 0.3496892750263214, | |
| "eval_runtime": 31.3066, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 3.2144288577154315e-05, | |
| "loss": 0.2791, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 3.206412825651303e-05, | |
| "loss": 0.2624, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_loss": 0.34680891036987305, | |
| "eval_runtime": 31.2925, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.198396793587175e-05, | |
| "loss": 0.2614, | |
| "step": 2995 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 3.1903807615230465e-05, | |
| "loss": 0.3324, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "eval_loss": 0.3479662537574768, | |
| "eval_runtime": 31.2947, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 3.182364729458918e-05, | |
| "loss": 0.3096, | |
| "step": 3005 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 3.17434869739479e-05, | |
| "loss": 0.2114, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "eval_loss": 0.35304367542266846, | |
| "eval_runtime": 31.2007, | |
| "eval_samples_per_second": 7.115, | |
| "eval_steps_per_second": 1.795, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 3.1663326653306616e-05, | |
| "loss": 0.2836, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 3.158316633266533e-05, | |
| "loss": 0.256, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "eval_loss": 0.3500817120075226, | |
| "eval_runtime": 31.2754, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.791, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 3.150300601202405e-05, | |
| "loss": 0.2611, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 3.1422845691382766e-05, | |
| "loss": 0.2716, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "eval_loss": 0.3489656150341034, | |
| "eval_runtime": 31.2904, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 3.134268537074149e-05, | |
| "loss": 0.2764, | |
| "step": 3035 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 3.1262525050100206e-05, | |
| "loss": 0.2921, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_loss": 0.34664395451545715, | |
| "eval_runtime": 31.2969, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 3.118236472945892e-05, | |
| "loss": 0.256, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 3.110220440881764e-05, | |
| "loss": 0.2924, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "eval_loss": 0.35313141345977783, | |
| "eval_runtime": 31.2961, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 3.1022044088176356e-05, | |
| "loss": 0.3146, | |
| "step": 3055 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 3.094188376753507e-05, | |
| "loss": 0.3267, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 0.3454523980617523, | |
| "eval_runtime": 31.2999, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 3.086172344689379e-05, | |
| "loss": 0.3476, | |
| "step": 3065 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 3.0781563126252506e-05, | |
| "loss": 0.3488, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "eval_loss": 0.3427518606185913, | |
| "eval_runtime": 31.2904, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 3.070140280561122e-05, | |
| "loss": 0.3351, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 3.062124248496994e-05, | |
| "loss": 0.301, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "eval_loss": 0.3455488681793213, | |
| "eval_runtime": 31.288, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 3.0541082164328656e-05, | |
| "loss": 0.287, | |
| "step": 3085 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 3.0460921843687376e-05, | |
| "loss": 0.2656, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "eval_loss": 0.34496939182281494, | |
| "eval_runtime": 31.2947, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 3.0380761523046093e-05, | |
| "loss": 0.2814, | |
| "step": 3095 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 3.030060120240481e-05, | |
| "loss": 0.2377, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "eval_loss": 0.3474458158016205, | |
| "eval_runtime": 31.2977, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 3.022044088176353e-05, | |
| "loss": 0.2179, | |
| "step": 3105 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 3.0140280561122247e-05, | |
| "loss": 0.2344, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "eval_loss": 0.34611740708351135, | |
| "eval_runtime": 31.2932, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 3.0060120240480963e-05, | |
| "loss": 0.3124, | |
| "step": 3115 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 2.997995991983968e-05, | |
| "loss": 0.2816, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_loss": 0.3488862216472626, | |
| "eval_runtime": 31.3005, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 2.9899799599198397e-05, | |
| "loss": 0.3506, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 2.9819639278557117e-05, | |
| "loss": 0.2675, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "eval_loss": 0.34268468618392944, | |
| "eval_runtime": 31.3, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 2.9739478957915833e-05, | |
| "loss": 0.375, | |
| "step": 3135 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 2.965931863727455e-05, | |
| "loss": 0.3315, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "eval_loss": 0.3393230736255646, | |
| "eval_runtime": 31.3008, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 2.9579158316633267e-05, | |
| "loss": 0.2561, | |
| "step": 3145 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 2.9498997995991984e-05, | |
| "loss": 0.335, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "eval_loss": 0.3406154215335846, | |
| "eval_runtime": 31.3005, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 2.9418837675350704e-05, | |
| "loss": 0.3748, | |
| "step": 3155 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 2.933867735470942e-05, | |
| "loss": 0.2418, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "eval_loss": 0.3384529948234558, | |
| "eval_runtime": 31.2977, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 2.9258517034068137e-05, | |
| "loss": 0.3214, | |
| "step": 3165 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 2.9178356713426854e-05, | |
| "loss": 0.215, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "eval_loss": 0.33930283784866333, | |
| "eval_runtime": 31.3001, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 2.909819639278557e-05, | |
| "loss": 0.2009, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 2.9018036072144287e-05, | |
| "loss": 0.2279, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "eval_loss": 0.342680424451828, | |
| "eval_runtime": 31.3037, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 2.8937875751503007e-05, | |
| "loss": 0.2684, | |
| "step": 3185 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 2.8857715430861727e-05, | |
| "loss": 0.2907, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_loss": 0.33792585134506226, | |
| "eval_runtime": 31.3001, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 2.8777555110220444e-05, | |
| "loss": 0.284, | |
| "step": 3195 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 2.8697394789579164e-05, | |
| "loss": 0.2184, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "eval_loss": 0.34375742077827454, | |
| "eval_runtime": 31.3016, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 2.861723446893788e-05, | |
| "loss": 0.3549, | |
| "step": 3205 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 2.8537074148296598e-05, | |
| "loss": 0.3484, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "eval_loss": 0.33638885617256165, | |
| "eval_runtime": 31.3083, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 2.8456913827655314e-05, | |
| "loss": 0.2836, | |
| "step": 3215 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 2.837675350701403e-05, | |
| "loss": 0.2327, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "eval_loss": 0.3405826687812805, | |
| "eval_runtime": 31.3055, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 2.8296593186372748e-05, | |
| "loss": 0.2421, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 2.8216432865731468e-05, | |
| "loss": 0.2571, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 0.3399759531021118, | |
| "eval_runtime": 31.3102, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 2.8136272545090185e-05, | |
| "loss": 0.2913, | |
| "step": 3235 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 2.80561122244489e-05, | |
| "loss": 0.2864, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "eval_loss": 0.3367003798484802, | |
| "eval_runtime": 31.3053, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 2.7975951903807618e-05, | |
| "loss": 0.2917, | |
| "step": 3245 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 2.7895791583166335e-05, | |
| "loss": 0.2383, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "eval_loss": 0.3376709818840027, | |
| "eval_runtime": 31.3097, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 2.7815631262525055e-05, | |
| "loss": 0.2364, | |
| "step": 3255 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 2.773547094188377e-05, | |
| "loss": 0.187, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_loss": 0.334637314081192, | |
| "eval_runtime": 31.3083, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 2.7655310621242488e-05, | |
| "loss": 0.2886, | |
| "step": 3265 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 2.7575150300601205e-05, | |
| "loss": 0.2453, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "eval_loss": 0.33486467599868774, | |
| "eval_runtime": 31.3013, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 2.749498997995992e-05, | |
| "loss": 0.3396, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 2.7414829659318642e-05, | |
| "loss": 0.296, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "eval_loss": 0.33391273021698, | |
| "eval_runtime": 31.3077, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 2.733466933867736e-05, | |
| "loss": 0.2475, | |
| "step": 3285 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 2.7254509018036075e-05, | |
| "loss": 0.2601, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "eval_loss": 0.3335227370262146, | |
| "eval_runtime": 31.2966, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 2.7174348697394792e-05, | |
| "loss": 0.2877, | |
| "step": 3295 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 2.709418837675351e-05, | |
| "loss": 0.2927, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "eval_loss": 0.33400464057922363, | |
| "eval_runtime": 31.2901, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 2.701402805611223e-05, | |
| "loss": 0.246, | |
| "step": 3305 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 2.6933867735470945e-05, | |
| "loss": 0.2796, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "eval_loss": 0.33034074306488037, | |
| "eval_runtime": 31.2965, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 2.6853707414829662e-05, | |
| "loss": 0.307, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 2.677354709418838e-05, | |
| "loss": 0.2393, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "eval_loss": 0.3351325988769531, | |
| "eval_runtime": 31.3032, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 2.6693386773547095e-05, | |
| "loss": 0.3415, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 2.6613226452905812e-05, | |
| "loss": 0.2764, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_loss": 0.3287622332572937, | |
| "eval_runtime": 31.3032, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 2.6533066132264532e-05, | |
| "loss": 0.3419, | |
| "step": 3335 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 2.645290581162325e-05, | |
| "loss": 0.2547, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "eval_loss": 0.3326658010482788, | |
| "eval_runtime": 31.3149, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 2.6372745490981966e-05, | |
| "loss": 0.2263, | |
| "step": 3345 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 2.6292585170340682e-05, | |
| "loss": 0.3247, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "eval_loss": 0.3279091715812683, | |
| "eval_runtime": 31.3129, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 2.62124248496994e-05, | |
| "loss": 0.2162, | |
| "step": 3355 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 2.613226452905812e-05, | |
| "loss": 0.3217, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "eval_loss": 0.32833293080329895, | |
| "eval_runtime": 31.3104, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 2.6052104208416836e-05, | |
| "loss": 0.3017, | |
| "step": 3365 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 2.5971943887775553e-05, | |
| "loss": 0.2881, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "eval_loss": 0.33072584867477417, | |
| "eval_runtime": 31.3091, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 2.589178356713427e-05, | |
| "loss": 0.2871, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 2.5811623246492986e-05, | |
| "loss": 0.2897, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "eval_loss": 0.3281080722808838, | |
| "eval_runtime": 31.3013, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 2.5731462925851706e-05, | |
| "loss": 0.2671, | |
| "step": 3385 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 2.5651302605210423e-05, | |
| "loss": 0.3096, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "eval_loss": 0.3256888687610626, | |
| "eval_runtime": 31.3048, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 2.557114228456914e-05, | |
| "loss": 0.3105, | |
| "step": 3395 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 2.5490981963927856e-05, | |
| "loss": 0.2463, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "eval_loss": 0.3243662714958191, | |
| "eval_runtime": 31.3033, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 2.5410821643286573e-05, | |
| "loss": 0.3127, | |
| "step": 3405 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 2.533066132264529e-05, | |
| "loss": 0.2404, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "eval_loss": 0.32544904947280884, | |
| "eval_runtime": 31.3022, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 2.525050100200401e-05, | |
| "loss": 0.2506, | |
| "step": 3415 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 2.5170340681362726e-05, | |
| "loss": 0.2907, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "eval_loss": 0.32269883155822754, | |
| "eval_runtime": 31.2987, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 2.5090180360721443e-05, | |
| "loss": 0.2479, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 2.501002004008016e-05, | |
| "loss": 0.2749, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "eval_loss": 0.3225778043270111, | |
| "eval_runtime": 31.3034, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 2.4929859719438877e-05, | |
| "loss": 0.2815, | |
| "step": 3435 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 2.4849699398797597e-05, | |
| "loss": 0.2262, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "eval_loss": 0.32259687781333923, | |
| "eval_runtime": 31.3032, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 2.4769539078156313e-05, | |
| "loss": 0.3338, | |
| "step": 3445 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 2.468937875751503e-05, | |
| "loss": 0.2799, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "eval_loss": 0.3232540488243103, | |
| "eval_runtime": 31.2972, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 2.4609218436873747e-05, | |
| "loss": 0.2203, | |
| "step": 3455 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 2.4529058116232464e-05, | |
| "loss": 0.2764, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "eval_loss": 0.31978297233581543, | |
| "eval_runtime": 31.3045, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 2.4448897795591184e-05, | |
| "loss": 0.3449, | |
| "step": 3465 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 2.4368737474949904e-05, | |
| "loss": 0.2644, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "eval_loss": 0.3230922222137451, | |
| "eval_runtime": 31.3046, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 2.428857715430862e-05, | |
| "loss": 0.2169, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 2.4208416833667337e-05, | |
| "loss": 0.2733, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_loss": 0.3187558650970459, | |
| "eval_runtime": 31.3014, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 2.4128256513026057e-05, | |
| "loss": 0.2509, | |
| "step": 3485 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 2.4048096192384774e-05, | |
| "loss": 0.2861, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_loss": 0.3191593587398529, | |
| "eval_runtime": 31.3055, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 2.396793587174349e-05, | |
| "loss": 0.3167, | |
| "step": 3495 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 2.3887775551102207e-05, | |
| "loss": 0.1757, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 0.3242829144001007, | |
| "eval_runtime": 31.3027, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 2.3807615230460924e-05, | |
| "loss": 0.2188, | |
| "step": 3505 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 2.3727454909819644e-05, | |
| "loss": 0.2588, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "eval_loss": 0.3237724304199219, | |
| "eval_runtime": 31.201, | |
| "eval_samples_per_second": 7.115, | |
| "eval_steps_per_second": 1.795, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 2.364729458917836e-05, | |
| "loss": 0.2842, | |
| "step": 3515 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 2.3567134268537078e-05, | |
| "loss": 0.2132, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "eval_loss": 0.3207135498523712, | |
| "eval_runtime": 31.2833, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 2.3486973947895794e-05, | |
| "loss": 0.2001, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 2.340681362725451e-05, | |
| "loss": 0.2787, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 0.32723355293273926, | |
| "eval_runtime": 31.2924, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 2.332665330661323e-05, | |
| "loss": 0.1942, | |
| "step": 3535 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 2.3246492985971948e-05, | |
| "loss": 0.2786, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "eval_loss": 0.32288235425949097, | |
| "eval_runtime": 31.2971, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 2.3166332665330665e-05, | |
| "loss": 0.1944, | |
| "step": 3545 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 2.308617234468938e-05, | |
| "loss": 0.2854, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_loss": 0.32317566871643066, | |
| "eval_runtime": 31.2981, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 2.3006012024048098e-05, | |
| "loss": 0.224, | |
| "step": 3555 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 2.2925851703406815e-05, | |
| "loss": 0.1982, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "eval_loss": 0.3237103521823883, | |
| "eval_runtime": 31.3037, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2.2845691382765535e-05, | |
| "loss": 0.2057, | |
| "step": 3565 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 2.276553106212425e-05, | |
| "loss": 0.2022, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "eval_loss": 0.3253968060016632, | |
| "eval_runtime": 31.3005, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 2.2685370741482968e-05, | |
| "loss": 0.1863, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 2.2605210420841685e-05, | |
| "loss": 0.2592, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "eval_loss": 0.32580825686454773, | |
| "eval_runtime": 31.2975, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 2.25250501002004e-05, | |
| "loss": 0.2837, | |
| "step": 3585 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 2.2444889779559122e-05, | |
| "loss": 0.2299, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "eval_loss": 0.32067885994911194, | |
| "eval_runtime": 31.2956, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 2.236472945891784e-05, | |
| "loss": 0.1787, | |
| "step": 3595 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 2.2284569138276555e-05, | |
| "loss": 0.2054, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_loss": 0.31973427534103394, | |
| "eval_runtime": 31.2985, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 2.2204408817635272e-05, | |
| "loss": 0.2326, | |
| "step": 3605 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 2.212424849699399e-05, | |
| "loss": 0.208, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "eval_loss": 0.32161736488342285, | |
| "eval_runtime": 31.2934, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 2.204408817635271e-05, | |
| "loss": 0.283, | |
| "step": 3615 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 2.1963927855711425e-05, | |
| "loss": 0.2432, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "eval_loss": 0.3228018283843994, | |
| "eval_runtime": 31.2953, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 2.1883767535070142e-05, | |
| "loss": 0.2692, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 2.180360721442886e-05, | |
| "loss": 0.2452, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "eval_loss": 0.3180503249168396, | |
| "eval_runtime": 31.2954, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 2.1723446893787575e-05, | |
| "loss": 0.284, | |
| "step": 3635 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 2.1643286573146292e-05, | |
| "loss": 0.264, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "eval_loss": 0.3237510919570923, | |
| "eval_runtime": 31.3062, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 2.1563126252505012e-05, | |
| "loss": 0.1818, | |
| "step": 3645 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 2.148296593186373e-05, | |
| "loss": 0.2019, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "eval_loss": 0.3177684545516968, | |
| "eval_runtime": 31.3017, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 2.1402805611222446e-05, | |
| "loss": 0.2007, | |
| "step": 3655 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 2.1322645290581162e-05, | |
| "loss": 0.2299, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "eval_loss": 0.32181212306022644, | |
| "eval_runtime": 31.3118, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 2.124248496993988e-05, | |
| "loss": 0.242, | |
| "step": 3665 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 2.11623246492986e-05, | |
| "loss": 0.2465, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "eval_loss": 0.3172205090522766, | |
| "eval_runtime": 31.3041, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 2.1082164328657316e-05, | |
| "loss": 0.2447, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 2.1002004008016033e-05, | |
| "loss": 0.2466, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "eval_loss": 0.3167315125465393, | |
| "eval_runtime": 31.3046, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 2.092184368737475e-05, | |
| "loss": 0.3394, | |
| "step": 3685 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 2.0841683366733466e-05, | |
| "loss": 0.2824, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "eval_loss": 0.3142654299736023, | |
| "eval_runtime": 31.3029, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 2.0761523046092186e-05, | |
| "loss": 0.2809, | |
| "step": 3695 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 2.0681362725450903e-05, | |
| "loss": 0.2314, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "eval_loss": 0.3143279254436493, | |
| "eval_runtime": 31.3083, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 2.060120240480962e-05, | |
| "loss": 0.2344, | |
| "step": 3705 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 2.0521042084168336e-05, | |
| "loss": 0.2822, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "eval_loss": 0.31426194310188293, | |
| "eval_runtime": 31.3051, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 2.0440881763527053e-05, | |
| "loss": 0.2441, | |
| "step": 3715 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 2.036072144288577e-05, | |
| "loss": 0.2254, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "eval_loss": 0.3139478862285614, | |
| "eval_runtime": 31.3076, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 2.028056112224449e-05, | |
| "loss": 0.3121, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 2.0200400801603206e-05, | |
| "loss": 0.2454, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "eval_loss": 0.32176563143730164, | |
| "eval_runtime": 31.3037, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 2.0120240480961923e-05, | |
| "loss": 0.178, | |
| "step": 3735 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 2.004008016032064e-05, | |
| "loss": 0.2656, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_loss": 0.3115682899951935, | |
| "eval_runtime": 31.3043, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1.995991983967936e-05, | |
| "loss": 0.2158, | |
| "step": 3745 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 1.9879759519038077e-05, | |
| "loss": 0.2172, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_loss": 0.3154009282588959, | |
| "eval_runtime": 31.3017, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 1.9799599198396793e-05, | |
| "loss": 0.1828, | |
| "step": 3755 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 1.9719438877755514e-05, | |
| "loss": 0.2408, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "eval_loss": 0.3127301037311554, | |
| "eval_runtime": 31.2971, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 1.963927855711423e-05, | |
| "loss": 0.262, | |
| "step": 3765 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 1.9559118236472947e-05, | |
| "loss": 0.1761, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "eval_loss": 0.3148895502090454, | |
| "eval_runtime": 31.2992, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 1.9478957915831664e-05, | |
| "loss": 0.2206, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1.939879759519038e-05, | |
| "loss": 0.2232, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "eval_loss": 0.3114352226257324, | |
| "eval_runtime": 31.2962, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.93186372745491e-05, | |
| "loss": 0.2738, | |
| "step": 3785 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.9238476953907817e-05, | |
| "loss": 0.2902, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "eval_loss": 0.3135593831539154, | |
| "eval_runtime": 31.304, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 1.9158316633266534e-05, | |
| "loss": 0.1814, | |
| "step": 3795 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 1.907815631262525e-05, | |
| "loss": 0.2485, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_loss": 0.31458309292793274, | |
| "eval_runtime": 31.3021, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 1.8997995991983967e-05, | |
| "loss": 0.2788, | |
| "step": 3805 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1.8917835671342687e-05, | |
| "loss": 0.1901, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_loss": 0.30936095118522644, | |
| "eval_runtime": 31.3065, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 1.8837675350701404e-05, | |
| "loss": 0.2153, | |
| "step": 3815 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 1.8757515030060124e-05, | |
| "loss": 0.2962, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "eval_loss": 0.3120403587818146, | |
| "eval_runtime": 31.3087, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 1.867735470941884e-05, | |
| "loss": 0.253, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 1.8597194388777558e-05, | |
| "loss": 0.2093, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "eval_loss": 0.31331053376197815, | |
| "eval_runtime": 31.2958, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.8517034068136274e-05, | |
| "loss": 0.2398, | |
| "step": 3835 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 1.843687374749499e-05, | |
| "loss": 0.368, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "eval_loss": 0.3063763976097107, | |
| "eval_runtime": 31.3038, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 1.835671342685371e-05, | |
| "loss": 0.2372, | |
| "step": 3845 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.8276553106212428e-05, | |
| "loss": 0.2849, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_loss": 0.3091437518596649, | |
| "eval_runtime": 31.2956, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 1.8196392785571145e-05, | |
| "loss": 0.2551, | |
| "step": 3855 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 1.811623246492986e-05, | |
| "loss": 0.1948, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "eval_loss": 0.3075093924999237, | |
| "eval_runtime": 31.2948, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 1.8036072144288578e-05, | |
| "loss": 0.2395, | |
| "step": 3865 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1.7955911823647295e-05, | |
| "loss": 0.2241, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "eval_loss": 0.30777955055236816, | |
| "eval_runtime": 31.2961, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 1.7875751503006015e-05, | |
| "loss": 0.2796, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 1.779559118236473e-05, | |
| "loss": 0.1935, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "eval_loss": 0.30446866154670715, | |
| "eval_runtime": 31.2946, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 1.7715430861723448e-05, | |
| "loss": 0.2199, | |
| "step": 3885 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 1.7635270541082165e-05, | |
| "loss": 0.2045, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "eval_loss": 0.3065406084060669, | |
| "eval_runtime": 31.2936, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 1.755511022044088e-05, | |
| "loss": 0.1856, | |
| "step": 3895 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 1.74749498997996e-05, | |
| "loss": 0.159, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_loss": 0.30820584297180176, | |
| "eval_runtime": 31.2972, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 1.739478957915832e-05, | |
| "loss": 0.3111, | |
| "step": 3905 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.7314629258517035e-05, | |
| "loss": 0.1714, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "eval_loss": 0.3057255148887634, | |
| "eval_runtime": 31.2961, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.7234468937875752e-05, | |
| "loss": 0.1983, | |
| "step": 3915 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 1.715430861723447e-05, | |
| "loss": 0.1984, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "eval_loss": 0.3059474527835846, | |
| "eval_runtime": 31.3004, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 1.707414829659319e-05, | |
| "loss": 0.2186, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 1.6993987975951905e-05, | |
| "loss": 0.2397, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "eval_loss": 0.30371129512786865, | |
| "eval_runtime": 31.2982, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1.6913827655310622e-05, | |
| "loss": 0.2559, | |
| "step": 3935 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 1.683366733466934e-05, | |
| "loss": 0.1884, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "eval_loss": 0.3053794205188751, | |
| "eval_runtime": 31.2925, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 1.6753507014028055e-05, | |
| "loss": 0.2414, | |
| "step": 3945 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 1.6673346693386772e-05, | |
| "loss": 0.2585, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "eval_loss": 0.30300775170326233, | |
| "eval_runtime": 31.3, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1.6593186372745492e-05, | |
| "loss": 0.2049, | |
| "step": 3955 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 1.6513026052104212e-05, | |
| "loss": 0.2476, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "eval_loss": 0.30583810806274414, | |
| "eval_runtime": 31.2909, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 1.643286573146293e-05, | |
| "loss": 0.2572, | |
| "step": 3965 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.6352705410821646e-05, | |
| "loss": 0.2525, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_loss": 0.3032612204551697, | |
| "eval_runtime": 31.2935, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1.6272545090180362e-05, | |
| "loss": 0.2901, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 1.619238476953908e-05, | |
| "loss": 0.2001, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "eval_loss": 0.30624955892562866, | |
| "eval_runtime": 31.2914, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 1.6112224448897796e-05, | |
| "loss": 0.1784, | |
| "step": 3985 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 1.6032064128256516e-05, | |
| "loss": 0.1985, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_loss": 0.3039126992225647, | |
| "eval_runtime": 31.2929, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 1.5951903807615233e-05, | |
| "loss": 0.247, | |
| "step": 3995 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 1.587174348697395e-05, | |
| "loss": 0.1984, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_loss": 0.3139249384403229, | |
| "eval_runtime": 31.2927, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 1.5791583166332666e-05, | |
| "loss": 0.1848, | |
| "step": 4005 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 1.5711422845691383e-05, | |
| "loss": 0.2008, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_loss": 0.3099471926689148, | |
| "eval_runtime": 31.2217, | |
| "eval_samples_per_second": 7.11, | |
| "eval_steps_per_second": 1.794, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 1.5631262525050103e-05, | |
| "loss": 0.1658, | |
| "step": 4015 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 1.555110220440882e-05, | |
| "loss": 0.2159, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "eval_loss": 0.3085058629512787, | |
| "eval_runtime": 31.2776, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 1.5470941883767536e-05, | |
| "loss": 0.2254, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 1.5390781563126253e-05, | |
| "loss": 0.2305, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "eval_loss": 0.3107781410217285, | |
| "eval_runtime": 31.2779, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 1.531062124248497e-05, | |
| "loss": 0.1916, | |
| "step": 4035 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 1.5230460921843688e-05, | |
| "loss": 0.2007, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_loss": 0.30502209067344666, | |
| "eval_runtime": 31.29, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 1.5150300601202405e-05, | |
| "loss": 0.2161, | |
| "step": 4045 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 1.5070140280561123e-05, | |
| "loss": 0.2124, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "eval_loss": 0.31148508191108704, | |
| "eval_runtime": 31.2984, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 1.498997995991984e-05, | |
| "loss": 0.2602, | |
| "step": 4055 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 1.4909819639278558e-05, | |
| "loss": 0.1435, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "eval_loss": 0.3084125816822052, | |
| "eval_runtime": 31.2938, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 1.4829659318637275e-05, | |
| "loss": 0.192, | |
| "step": 4065 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 1.4749498997995992e-05, | |
| "loss": 0.1968, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "eval_loss": 0.3087104856967926, | |
| "eval_runtime": 31.2947, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 1.466933867735471e-05, | |
| "loss": 0.167, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 1.4589178356713427e-05, | |
| "loss": 0.2507, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "eval_loss": 0.3084275722503662, | |
| "eval_runtime": 31.2993, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 1.4509018036072144e-05, | |
| "loss": 0.164, | |
| "step": 4085 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 1.4428857715430864e-05, | |
| "loss": 0.1703, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "eval_loss": 0.3060537874698639, | |
| "eval_runtime": 31.2962, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 1.4348697394789582e-05, | |
| "loss": 0.2239, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 1.4268537074148299e-05, | |
| "loss": 0.2511, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_loss": 0.310585081577301, | |
| "eval_runtime": 31.2934, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 1.4188376753507016e-05, | |
| "loss": 0.1675, | |
| "step": 4105 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 1.4108216432865734e-05, | |
| "loss": 0.1698, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "eval_loss": 0.3134320378303528, | |
| "eval_runtime": 31.2953, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 1.402805611222445e-05, | |
| "loss": 0.1757, | |
| "step": 4115 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 1.3947895791583167e-05, | |
| "loss": 0.2518, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "eval_loss": 0.3101155757904053, | |
| "eval_runtime": 31.2883, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 1.3867735470941886e-05, | |
| "loss": 0.1248, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 1.3787575150300602e-05, | |
| "loss": 0.1489, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "eval_loss": 0.3090272843837738, | |
| "eval_runtime": 31.2934, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 1.3707414829659321e-05, | |
| "loss": 0.1893, | |
| "step": 4135 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 1.3627254509018038e-05, | |
| "loss": 0.1759, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "eval_loss": 0.3098497688770294, | |
| "eval_runtime": 31.2929, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 1.3547094188376754e-05, | |
| "loss": 0.2406, | |
| "step": 4145 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 1.3466933867735473e-05, | |
| "loss": 0.1939, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_loss": 0.305558979511261, | |
| "eval_runtime": 31.2912, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 1.338677354709419e-05, | |
| "loss": 0.211, | |
| "step": 4155 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 1.3306613226452906e-05, | |
| "loss": 0.2168, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "eval_loss": 0.31060683727264404, | |
| "eval_runtime": 31.2852, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 1.3226452905811624e-05, | |
| "loss": 0.2253, | |
| "step": 4165 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 1.3146292585170341e-05, | |
| "loss": 0.2119, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "eval_loss": 0.3051324188709259, | |
| "eval_runtime": 31.2925, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 1.306613226452906e-05, | |
| "loss": 0.1942, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 1.2985971943887776e-05, | |
| "loss": 0.1793, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "eval_loss": 0.30557873845100403, | |
| "eval_runtime": 31.3033, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 1.2905811623246493e-05, | |
| "loss": 0.1906, | |
| "step": 4185 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 1.2825651302605211e-05, | |
| "loss": 0.2434, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "eval_loss": 0.30504488945007324, | |
| "eval_runtime": 31.2924, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 1.2745490981963928e-05, | |
| "loss": 0.1886, | |
| "step": 4195 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 1.2665330661322645e-05, | |
| "loss": 0.2601, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "eval_loss": 0.30650991201400757, | |
| "eval_runtime": 31.2933, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 1.2585170340681363e-05, | |
| "loss": 0.1338, | |
| "step": 4205 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 1.250501002004008e-05, | |
| "loss": 0.1791, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "eval_loss": 0.3051263391971588, | |
| "eval_runtime": 31.3026, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 1.2424849699398798e-05, | |
| "loss": 0.2534, | |
| "step": 4215 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 1.2344689378757515e-05, | |
| "loss": 0.1404, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_loss": 0.3057839870452881, | |
| "eval_runtime": 31.8248, | |
| "eval_samples_per_second": 6.976, | |
| "eval_steps_per_second": 1.76, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 1.2264529058116232e-05, | |
| "loss": 0.2097, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 1.2184368737474952e-05, | |
| "loss": 0.222, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "eval_loss": 0.3059149384498596, | |
| "eval_runtime": 31.2917, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 1.2104208416833669e-05, | |
| "loss": 0.1822, | |
| "step": 4235 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 1.2024048096192387e-05, | |
| "loss": 0.1809, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "eval_loss": 0.30699098110198975, | |
| "eval_runtime": 31.297, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 1.1943887775551104e-05, | |
| "loss": 0.1847, | |
| "step": 4245 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 1.1863727454909822e-05, | |
| "loss": 0.1745, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "eval_loss": 0.30655932426452637, | |
| "eval_runtime": 31.8903, | |
| "eval_samples_per_second": 6.961, | |
| "eval_steps_per_second": 1.756, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 1.1783567134268539e-05, | |
| "loss": 0.2631, | |
| "step": 4255 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 1.1703406813627256e-05, | |
| "loss": 0.2236, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "eval_loss": 0.30122604966163635, | |
| "eval_runtime": 31.2919, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 1.1623246492985974e-05, | |
| "loss": 0.1922, | |
| "step": 4265 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 1.154308617234469e-05, | |
| "loss": 0.1965, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "eval_loss": 0.30368027091026306, | |
| "eval_runtime": 31.3086, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 1.1462925851703407e-05, | |
| "loss": 0.1554, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 1.1382765531062126e-05, | |
| "loss": 0.1836, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "eval_loss": 0.3051268458366394, | |
| "eval_runtime": 31.6028, | |
| "eval_samples_per_second": 7.025, | |
| "eval_steps_per_second": 1.772, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 1.1302605210420842e-05, | |
| "loss": 0.1924, | |
| "step": 4285 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 1.1222444889779561e-05, | |
| "loss": 0.1912, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "eval_loss": 0.30165210366249084, | |
| "eval_runtime": 31.2902, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 1.1142284569138278e-05, | |
| "loss": 0.1751, | |
| "step": 4295 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 1.1062124248496994e-05, | |
| "loss": 0.2207, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "eval_loss": 0.30252379179000854, | |
| "eval_runtime": 31.3027, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 1.0981963927855713e-05, | |
| "loss": 0.1475, | |
| "step": 4305 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 1.090180360721443e-05, | |
| "loss": 0.2481, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "eval_loss": 0.29974907636642456, | |
| "eval_runtime": 31.3079, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 1.0821643286573146e-05, | |
| "loss": 0.124, | |
| "step": 4315 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 1.0741482965931864e-05, | |
| "loss": 0.1506, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "eval_loss": 0.30026939511299133, | |
| "eval_runtime": 31.4042, | |
| "eval_samples_per_second": 7.069, | |
| "eval_steps_per_second": 1.783, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 1.0661322645290581e-05, | |
| "loss": 0.1864, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 1.05811623246493e-05, | |
| "loss": 0.2216, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "eval_loss": 0.30346396565437317, | |
| "eval_runtime": 31.3544, | |
| "eval_samples_per_second": 7.08, | |
| "eval_steps_per_second": 1.786, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 1.0501002004008016e-05, | |
| "loss": 0.1759, | |
| "step": 4335 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 1.0420841683366733e-05, | |
| "loss": 0.1866, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "eval_loss": 0.301408588886261, | |
| "eval_runtime": 31.3231, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 1.0340681362725451e-05, | |
| "loss": 0.1588, | |
| "step": 4345 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 1.0260521042084168e-05, | |
| "loss": 0.2025, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "eval_loss": 0.30352672934532166, | |
| "eval_runtime": 31.2959, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 1.0180360721442885e-05, | |
| "loss": 0.1465, | |
| "step": 4355 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 1.0100200400801603e-05, | |
| "loss": 0.1521, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "eval_loss": 0.2992115318775177, | |
| "eval_runtime": 31.3056, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 1.002004008016032e-05, | |
| "loss": 0.2296, | |
| "step": 4365 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 9.939879759519038e-06, | |
| "loss": 0.1598, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_loss": 0.30343157052993774, | |
| "eval_runtime": 31.304, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 9.859719438877757e-06, | |
| "loss": 0.2342, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 9.779559118236473e-06, | |
| "loss": 0.185, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "eval_loss": 0.3016977906227112, | |
| "eval_runtime": 31.3084, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 9.69939879759519e-06, | |
| "loss": 0.1527, | |
| "step": 4385 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 9.619238476953909e-06, | |
| "loss": 0.2427, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "eval_loss": 0.2971956133842468, | |
| "eval_runtime": 31.2993, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 9.539078156312625e-06, | |
| "loss": 0.1416, | |
| "step": 4395 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 9.458917835671344e-06, | |
| "loss": 0.2343, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "eval_loss": 0.2979062795639038, | |
| "eval_runtime": 31.2918, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 9.378757515030062e-06, | |
| "loss": 0.2002, | |
| "step": 4405 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 9.298597194388779e-06, | |
| "loss": 0.1994, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "eval_loss": 0.2994498908519745, | |
| "eval_runtime": 31.2999, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 9.218436873747496e-06, | |
| "loss": 0.2031, | |
| "step": 4415 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 9.138276553106214e-06, | |
| "loss": 0.2671, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_loss": 0.29864001274108887, | |
| "eval_runtime": 31.9081, | |
| "eval_samples_per_second": 6.957, | |
| "eval_steps_per_second": 1.755, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 9.05811623246493e-06, | |
| "loss": 0.202, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 8.977955911823647e-06, | |
| "loss": 0.1158, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "eval_loss": 0.2991441786289215, | |
| "eval_runtime": 31.5574, | |
| "eval_samples_per_second": 7.035, | |
| "eval_steps_per_second": 1.775, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 8.897795591182366e-06, | |
| "loss": 0.2213, | |
| "step": 4435 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 8.817635270541082e-06, | |
| "loss": 0.2127, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "eval_loss": 0.3000405430793762, | |
| "eval_runtime": 31.2838, | |
| "eval_samples_per_second": 7.096, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 8.7374749498998e-06, | |
| "loss": 0.1603, | |
| "step": 4445 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 8.657314629258518e-06, | |
| "loss": 0.1691, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_loss": 0.2980547845363617, | |
| "eval_runtime": 31.2967, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 8.577154308617234e-06, | |
| "loss": 0.2523, | |
| "step": 4455 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 8.496993987975953e-06, | |
| "loss": 0.2103, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_loss": 0.2978658080101013, | |
| "eval_runtime": 31.3156, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 8.41683366733467e-06, | |
| "loss": 0.1574, | |
| "step": 4465 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 8.336673346693386e-06, | |
| "loss": 0.1392, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_loss": 0.29815390706062317, | |
| "eval_runtime": 31.3016, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 8.256513026052106e-06, | |
| "loss": 0.2192, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 8.176352705410823e-06, | |
| "loss": 0.1712, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "eval_loss": 0.2943491041660309, | |
| "eval_runtime": 31.3127, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 8.09619238476954e-06, | |
| "loss": 0.1652, | |
| "step": 4485 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 8.016032064128258e-06, | |
| "loss": 0.2435, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.2958294153213501, | |
| "eval_runtime": 31.2931, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 7.935871743486975e-06, | |
| "loss": 0.1859, | |
| "step": 4495 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 7.855711422845691e-06, | |
| "loss": 0.1715, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_loss": 0.30551087856292725, | |
| "eval_runtime": 31.309, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 7.77555110220441e-06, | |
| "loss": 0.1663, | |
| "step": 4505 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 7.695390781563127e-06, | |
| "loss": 0.1641, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "eval_loss": 0.3048071563243866, | |
| "eval_runtime": 31.2037, | |
| "eval_samples_per_second": 7.115, | |
| "eval_steps_per_second": 1.795, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 7.615230460921844e-06, | |
| "loss": 0.17, | |
| "step": 4515 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 7.535070140280562e-06, | |
| "loss": 0.1529, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "eval_loss": 0.30287060141563416, | |
| "eval_runtime": 31.2814, | |
| "eval_samples_per_second": 7.097, | |
| "eval_steps_per_second": 1.79, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 7.454909819639279e-06, | |
| "loss": 0.175, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 7.374749498997996e-06, | |
| "loss": 0.1566, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "eval_loss": 0.3046806752681732, | |
| "eval_runtime": 31.2973, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 7.2945891783567134e-06, | |
| "loss": 0.1749, | |
| "step": 4535 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 7.214428857715432e-06, | |
| "loss": 0.1382, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_loss": 0.30272936820983887, | |
| "eval_runtime": 31.302, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 7.134268537074149e-06, | |
| "loss": 0.1956, | |
| "step": 4545 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 7.054108216432867e-06, | |
| "loss": 0.1605, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "eval_loss": 0.30227676033973694, | |
| "eval_runtime": 31.3042, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 6.973947895791584e-06, | |
| "loss": 0.1675, | |
| "step": 4555 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 6.893787575150301e-06, | |
| "loss": 0.2167, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "eval_loss": 0.3055172264575958, | |
| "eval_runtime": 31.3016, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 6.813627254509019e-06, | |
| "loss": 0.1603, | |
| "step": 4565 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 6.733466933867736e-06, | |
| "loss": 0.1506, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "eval_loss": 0.303718626499176, | |
| "eval_runtime": 31.323, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 6.653306613226453e-06, | |
| "loss": 0.2345, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 6.573146292585171e-06, | |
| "loss": 0.192, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "eval_loss": 0.30387794971466064, | |
| "eval_runtime": 31.3084, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 6.492985971943888e-06, | |
| "loss": 0.1714, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 6.412825651302606e-06, | |
| "loss": 0.139, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_loss": 0.3030008375644684, | |
| "eval_runtime": 31.311, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 6.332665330661322e-06, | |
| "loss": 0.1492, | |
| "step": 4595 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 6.25250501002004e-06, | |
| "loss": 0.1974, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "eval_loss": 0.30382072925567627, | |
| "eval_runtime": 31.314, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 6.1723446893787575e-06, | |
| "loss": 0.1619, | |
| "step": 4605 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 6.092184368737476e-06, | |
| "loss": 0.167, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "eval_loss": 0.303739070892334, | |
| "eval_runtime": 31.3071, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 6.0120240480961935e-06, | |
| "loss": 0.1597, | |
| "step": 4615 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 5.931863727454911e-06, | |
| "loss": 0.2409, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "eval_loss": 0.3033643066883087, | |
| "eval_runtime": 31.3054, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 5.851703406813628e-06, | |
| "loss": 0.1673, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 5.771543086172345e-06, | |
| "loss": 0.1494, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "eval_loss": 0.30480068922042847, | |
| "eval_runtime": 31.3033, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 5.691382765531063e-06, | |
| "loss": 0.1907, | |
| "step": 4635 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 5.6112224448897804e-06, | |
| "loss": 0.1762, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_loss": 0.30366069078445435, | |
| "eval_runtime": 31.2972, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 5.531062124248497e-06, | |
| "loss": 0.1336, | |
| "step": 4645 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 5.450901803607215e-06, | |
| "loss": 0.183, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "eval_loss": 0.3042277991771698, | |
| "eval_runtime": 31.3048, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 5.370741482965932e-06, | |
| "loss": 0.2423, | |
| "step": 4655 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 5.29058116232465e-06, | |
| "loss": 0.1773, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "eval_loss": 0.3042871356010437, | |
| "eval_runtime": 31.3002, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 5.2104208416833665e-06, | |
| "loss": 0.1586, | |
| "step": 4665 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 5.130260521042084e-06, | |
| "loss": 0.1509, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "eval_loss": 0.3053213059902191, | |
| "eval_runtime": 31.3174, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 5.050100200400802e-06, | |
| "loss": 0.136, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 4.969939879759519e-06, | |
| "loss": 0.1994, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_loss": 0.30446866154670715, | |
| "eval_runtime": 31.3129, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 4.889779559118237e-06, | |
| "loss": 0.2068, | |
| "step": 4685 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 4.809619238476954e-06, | |
| "loss": 0.1928, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "eval_loss": 0.30361202359199524, | |
| "eval_runtime": 31.3048, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 4.729458917835672e-06, | |
| "loss": 0.212, | |
| "step": 4695 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 4.649298597194389e-06, | |
| "loss": 0.1158, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "eval_loss": 0.30384451150894165, | |
| "eval_runtime": 31.3031, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 4.569138276553107e-06, | |
| "loss": 0.2038, | |
| "step": 4705 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 4.488977955911824e-06, | |
| "loss": 0.1503, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "eval_loss": 0.3019496500492096, | |
| "eval_runtime": 31.3092, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 4.408817635270541e-06, | |
| "loss": 0.1511, | |
| "step": 4715 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 4.328657314629259e-06, | |
| "loss": 0.1556, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "eval_loss": 0.3029373288154602, | |
| "eval_runtime": 31.305, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 4.248496993987976e-06, | |
| "loss": 0.182, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 4.168336673346693e-06, | |
| "loss": 0.1327, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "eval_loss": 0.30504941940307617, | |
| "eval_runtime": 31.3165, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 4.0881763527054114e-06, | |
| "loss": 0.1574, | |
| "step": 4735 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 4.008016032064129e-06, | |
| "loss": 0.1772, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "eval_loss": 0.3057289719581604, | |
| "eval_runtime": 31.3047, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 3.927855711422846e-06, | |
| "loss": 0.1497, | |
| "step": 4745 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 3.847695390781563e-06, | |
| "loss": 0.1555, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "eval_loss": 0.30276989936828613, | |
| "eval_runtime": 31.3062, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 3.767535070140281e-06, | |
| "loss": 0.1281, | |
| "step": 4755 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 3.687374749498998e-06, | |
| "loss": 0.1363, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "eval_loss": 0.3013622760772705, | |
| "eval_runtime": 31.3134, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 3.607214428857716e-06, | |
| "loss": 0.1461, | |
| "step": 4765 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 3.5270541082164335e-06, | |
| "loss": 0.139, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "eval_loss": 0.3009650707244873, | |
| "eval_runtime": 31.3047, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 3.4468937875751506e-06, | |
| "loss": 0.1519, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 3.366733466933868e-06, | |
| "loss": 0.1639, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "eval_loss": 0.30125322937965393, | |
| "eval_runtime": 31.3146, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 3.2865731462925853e-06, | |
| "loss": 0.1735, | |
| "step": 4785 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.206412825651303e-06, | |
| "loss": 0.1669, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_loss": 0.30152443051338196, | |
| "eval_runtime": 31.3073, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 3.12625250501002e-06, | |
| "loss": 0.1085, | |
| "step": 4795 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 3.046092184368738e-06, | |
| "loss": 0.144, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "eval_loss": 0.30229106545448303, | |
| "eval_runtime": 31.3106, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 2.9659318637274555e-06, | |
| "loss": 0.1607, | |
| "step": 4805 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 2.8857715430861727e-06, | |
| "loss": 0.1925, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "eval_loss": 0.3034406900405884, | |
| "eval_runtime": 31.3159, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 2.8056112224448902e-06, | |
| "loss": 0.1486, | |
| "step": 4815 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 2.7254509018036073e-06, | |
| "loss": 0.1615, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_loss": 0.3025255501270294, | |
| "eval_runtime": 31.295, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 2.645290581162325e-06, | |
| "loss": 0.1677, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 2.565130260521042e-06, | |
| "loss": 0.1625, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "eval_loss": 0.3018721044063568, | |
| "eval_runtime": 31.3106, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "learning_rate": 2.4849699398797596e-06, | |
| "loss": 0.1508, | |
| "step": 4835 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 2.404809619238477e-06, | |
| "loss": 0.1355, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "eval_loss": 0.3022632300853729, | |
| "eval_runtime": 31.3118, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 2.3246492985971947e-06, | |
| "loss": 0.142, | |
| "step": 4845 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 2.244488977955912e-06, | |
| "loss": 0.1671, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "eval_loss": 0.30193448066711426, | |
| "eval_runtime": 31.3088, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 2.1643286573146294e-06, | |
| "loss": 0.1557, | |
| "step": 4855 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 2.0841683366733465e-06, | |
| "loss": 0.1447, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "eval_loss": 0.30213478207588196, | |
| "eval_runtime": 31.3072, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 2.0040080160320645e-06, | |
| "loss": 0.1617, | |
| "step": 4865 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 1.9238476953907816e-06, | |
| "loss": 0.1465, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "eval_loss": 0.3024033308029175, | |
| "eval_runtime": 31.3039, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 1.843687374749499e-06, | |
| "loss": 0.144, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 1.7635270541082167e-06, | |
| "loss": 0.1794, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "eval_loss": 0.3020671606063843, | |
| "eval_runtime": 31.3114, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.788, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 1.683366733466934e-06, | |
| "loss": 0.1762, | |
| "step": 4885 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 1.6032064128256514e-06, | |
| "loss": 0.156, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_loss": 0.30112236738204956, | |
| "eval_runtime": 31.3062, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 1.523046092184369e-06, | |
| "loss": 0.139, | |
| "step": 4895 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 1.4428857715430863e-06, | |
| "loss": 0.1018, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "eval_loss": 0.30046290159225464, | |
| "eval_runtime": 31.3036, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 1.3627254509018037e-06, | |
| "loss": 0.1524, | |
| "step": 4905 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 1.282565130260521e-06, | |
| "loss": 0.1403, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_loss": 0.3010559380054474, | |
| "eval_runtime": 31.303, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 1.2024048096192386e-06, | |
| "loss": 0.1495, | |
| "step": 4915 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 1.122244488977956e-06, | |
| "loss": 0.1126, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "eval_loss": 0.30058878660202026, | |
| "eval_runtime": 31.3099, | |
| "eval_samples_per_second": 7.09, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 1.0420841683366733e-06, | |
| "loss": 0.1365, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 9.619238476953908e-07, | |
| "loss": 0.1595, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "eval_loss": 0.3006744682788849, | |
| "eval_runtime": 31.302, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 8.817635270541084e-07, | |
| "loss": 0.1921, | |
| "step": 4935 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 8.016032064128257e-07, | |
| "loss": 0.1415, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "eval_loss": 0.3012050986289978, | |
| "eval_runtime": 31.3083, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 7.214428857715432e-07, | |
| "loss": 0.1173, | |
| "step": 4945 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 6.412825651302605e-07, | |
| "loss": 0.1651, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "eval_loss": 0.30145999789237976, | |
| "eval_runtime": 31.3009, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 5.61122244488978e-07, | |
| "loss": 0.148, | |
| "step": 4955 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 4.809619238476954e-07, | |
| "loss": 0.1558, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_loss": 0.30154505372047424, | |
| "eval_runtime": 31.3072, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 4.0080160320641286e-07, | |
| "loss": 0.191, | |
| "step": 4965 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 3.2064128256513025e-07, | |
| "loss": 0.1734, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "eval_loss": 0.301419734954834, | |
| "eval_runtime": 31.296, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 2.404809619238477e-07, | |
| "loss": 0.1638, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 1.6032064128256513e-07, | |
| "loss": 0.1909, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_loss": 0.30140334367752075, | |
| "eval_runtime": 31.2942, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 8.016032064128256e-08, | |
| "loss": 0.1475, | |
| "step": 4985 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1246, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.30139291286468506, | |
| "eval_runtime": 31.307, | |
| "eval_samples_per_second": 7.091, | |
| "eval_steps_per_second": 1.789, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 4990, | |
| "total_flos": 8.69904317939712e+16, | |
| "train_loss": 0.5887919666891347, | |
| "train_runtime": 25757.7329, | |
| "train_samples_per_second": 0.776, | |
| "train_steps_per_second": 0.194 | |
| } | |
| ], | |
| "max_steps": 4990, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.69904317939712e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |