| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.8745, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019979028262377118, | |
| "loss": 0.8093, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019893981312363562, | |
| "loss": 0.7357, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019744105246469263, | |
| "loss": 0.7535, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.4003306031227112, | |
| "eval_runtime": 1.7839, | |
| "eval_samples_per_second": 2.242, | |
| "eval_steps_per_second": 0.561, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001953038210948861, | |
| "loss": 0.7249, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019254212296427044, | |
| "loss": 0.7118, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018917405376582145, | |
| "loss": 0.7467, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018522168236559695, | |
| "loss": 0.6714, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.3684937059879303, | |
| "eval_runtime": 1.7853, | |
| "eval_samples_per_second": 2.24, | |
| "eval_steps_per_second": 0.56, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00018071090619916093, | |
| "loss": 0.654, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00017567128158176953, | |
| "loss": 0.6392, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00017013583004418993, | |
| "loss": 0.5745, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.000164140821963114, | |
| "loss": 0.5364, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.3665352761745453, | |
| "eval_runtime": 1.7852, | |
| "eval_samples_per_second": 2.241, | |
| "eval_steps_per_second": 0.56, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00015772553890390197, | |
| "loss": 0.5693, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00015093201623287631, | |
| "loss": 0.563, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00014380476768566824, | |
| "loss": 0.5478, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00013639049369634876, | |
| "loss": 0.5763, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.3363753855228424, | |
| "eval_runtime": 1.7851, | |
| "eval_samples_per_second": 2.241, | |
| "eval_steps_per_second": 0.56, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012873777539848283, | |
| "loss": 0.4891, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00012089675630312754, | |
| "loss": 0.5331, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011291881373954065, | |
| "loss": 0.5679, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010485622221144484, | |
| "loss": 0.5982, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.3186224400997162, | |
| "eval_runtime": 1.7828, | |
| "eval_samples_per_second": 2.244, | |
| "eval_steps_per_second": 0.561, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.676181087466444e-05, | |
| "loss": 0.5467, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.868861738047158e-05, | |
| "loss": 0.5706, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.068954035279121e-05, | |
| "loss": 0.504, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.281699277636572e-05, | |
| "loss": 0.5267, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.32175499200820923, | |
| "eval_runtime": 1.7846, | |
| "eval_samples_per_second": 2.241, | |
| "eval_steps_per_second": 0.56, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.512255856701177e-05, | |
| "loss": 0.5414, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.765665457425102e-05, | |
| "loss": 0.5412, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.0468200231001286e-05, | |
| "loss": 0.4611, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.360429701490934e-05, | |
| "loss": 0.5073, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.31275978684425354, | |
| "eval_runtime": 1.7833, | |
| "eval_samples_per_second": 2.243, | |
| "eval_steps_per_second": 0.561, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.710991982161555e-05, | |
| "loss": 0.4778, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.102762227218957e-05, | |
| "loss": 0.5454, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.5397257885675397e-05, | |
| "loss": 0.5612, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.025571894372794e-05, | |
| "loss": 0.4983, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.31457942724227905, | |
| "eval_runtime": 1.7821, | |
| "eval_samples_per_second": 2.245, | |
| "eval_steps_per_second": 0.561, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.563669475839956e-05, | |
| "loss": 0.4941, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1570450926997655e-05, | |
| "loss": 0.4926, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.083631020418791e-06, | |
| "loss": 0.5094, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.199082004372957e-06, | |
| "loss": 0.5116, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.31357938051223755, | |
| "eval_runtime": 1.7811, | |
| "eval_samples_per_second": 2.246, | |
| "eval_steps_per_second": 0.561, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.9357045374040825e-06, | |
| "loss": 0.4244, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.30832912661093e-06, | |
| "loss": 0.4511, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.2761895254306287e-07, | |
| "loss": 0.4179, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4662, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.3136279284954071, | |
| "eval_runtime": 1.7836, | |
| "eval_samples_per_second": 2.243, | |
| "eval_steps_per_second": 0.561, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 100, | |
| "total_flos": 1.493507298557952e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |