winddude's picture
upload checkpoints
be373c1
{
"best_metric": 0.7434859871864319,
"best_model_checkpoint": "/loras/wizardLM-lama-lora/checkpoint-2600",
"epoch": 2.447058823529412,
"global_step": 2600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.8867,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 4.000000000000001e-06,
"loss": 1.1368,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 6e-06,
"loss": 1.295,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 8.000000000000001e-06,
"loss": 1.5052,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 2.4325,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 1.2e-05,
"loss": 0.8676,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 1.4e-05,
"loss": 1.1109,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.2301,
"step": 80
},
{
"epoch": 0.08,
"learning_rate": 1.8e-05,
"loss": 1.3888,
"step": 90
},
{
"epoch": 0.09,
"learning_rate": 1.98e-05,
"loss": 1.8821,
"step": 100
},
{
"epoch": 0.1,
"learning_rate": 1.994167206740117e-05,
"loss": 0.7725,
"step": 110
},
{
"epoch": 0.11,
"learning_rate": 1.9876863253402464e-05,
"loss": 0.9668,
"step": 120
},
{
"epoch": 0.12,
"learning_rate": 1.981205443940376e-05,
"loss": 1.0496,
"step": 130
},
{
"epoch": 0.13,
"learning_rate": 1.9747245625405055e-05,
"loss": 1.1681,
"step": 140
},
{
"epoch": 0.14,
"learning_rate": 1.9682436811406353e-05,
"loss": 1.5396,
"step": 150
},
{
"epoch": 0.15,
"learning_rate": 1.961762799740765e-05,
"loss": 0.7308,
"step": 160
},
{
"epoch": 0.16,
"learning_rate": 1.9552819183408944e-05,
"loss": 0.8913,
"step": 170
},
{
"epoch": 0.17,
"learning_rate": 1.9488010369410243e-05,
"loss": 0.9641,
"step": 180
},
{
"epoch": 0.18,
"learning_rate": 1.9423201555411538e-05,
"loss": 1.0816,
"step": 190
},
{
"epoch": 0.19,
"learning_rate": 1.9358392741412834e-05,
"loss": 1.3788,
"step": 200
},
{
"epoch": 0.19,
"eval_loss": 0.8617203235626221,
"eval_runtime": 300.2687,
"eval_samples_per_second": 6.661,
"eval_steps_per_second": 0.833,
"step": 200
},
{
"epoch": 0.2,
"learning_rate": 1.929358392741413e-05,
"loss": 0.7194,
"step": 210
},
{
"epoch": 0.21,
"learning_rate": 1.9228775113415424e-05,
"loss": 0.8622,
"step": 220
},
{
"epoch": 0.22,
"learning_rate": 1.9163966299416723e-05,
"loss": 0.9538,
"step": 230
},
{
"epoch": 0.23,
"learning_rate": 1.9099157485418018e-05,
"loss": 1.042,
"step": 240
},
{
"epoch": 0.24,
"learning_rate": 1.9034348671419314e-05,
"loss": 1.3558,
"step": 250
},
{
"epoch": 0.24,
"learning_rate": 1.8969539857420612e-05,
"loss": 0.6768,
"step": 260
},
{
"epoch": 0.25,
"learning_rate": 1.8904731043421908e-05,
"loss": 0.8537,
"step": 270
},
{
"epoch": 0.26,
"learning_rate": 1.8839922229423203e-05,
"loss": 0.9221,
"step": 280
},
{
"epoch": 0.27,
"learning_rate": 1.8775113415424498e-05,
"loss": 1.0197,
"step": 290
},
{
"epoch": 0.28,
"learning_rate": 1.8710304601425794e-05,
"loss": 1.3147,
"step": 300
},
{
"epoch": 0.29,
"learning_rate": 1.8645495787427092e-05,
"loss": 0.6808,
"step": 310
},
{
"epoch": 0.3,
"learning_rate": 1.8580686973428388e-05,
"loss": 0.8355,
"step": 320
},
{
"epoch": 0.31,
"learning_rate": 1.8515878159429683e-05,
"loss": 0.8984,
"step": 330
},
{
"epoch": 0.32,
"learning_rate": 1.8451069345430982e-05,
"loss": 0.9932,
"step": 340
},
{
"epoch": 0.33,
"learning_rate": 1.8386260531432277e-05,
"loss": 1.2925,
"step": 350
},
{
"epoch": 0.34,
"learning_rate": 1.8321451717433572e-05,
"loss": 0.6815,
"step": 360
},
{
"epoch": 0.35,
"learning_rate": 1.8256642903434868e-05,
"loss": 0.8236,
"step": 370
},
{
"epoch": 0.36,
"learning_rate": 1.8191834089436163e-05,
"loss": 0.9039,
"step": 380
},
{
"epoch": 0.37,
"learning_rate": 1.8127025275437462e-05,
"loss": 1.0104,
"step": 390
},
{
"epoch": 0.38,
"learning_rate": 1.8062216461438757e-05,
"loss": 1.3078,
"step": 400
},
{
"epoch": 0.38,
"eval_loss": 0.8122736811637878,
"eval_runtime": 299.8615,
"eval_samples_per_second": 6.67,
"eval_steps_per_second": 0.834,
"step": 400
},
{
"epoch": 0.39,
"learning_rate": 1.7997407647440052e-05,
"loss": 0.6648,
"step": 410
},
{
"epoch": 0.4,
"learning_rate": 1.793259883344135e-05,
"loss": 0.8128,
"step": 420
},
{
"epoch": 0.4,
"learning_rate": 1.7867790019442646e-05,
"loss": 0.8792,
"step": 430
},
{
"epoch": 0.41,
"learning_rate": 1.7802981205443942e-05,
"loss": 0.9825,
"step": 440
},
{
"epoch": 0.42,
"learning_rate": 1.7738172391445237e-05,
"loss": 1.2814,
"step": 450
},
{
"epoch": 0.43,
"learning_rate": 1.7673363577446532e-05,
"loss": 0.6499,
"step": 460
},
{
"epoch": 0.44,
"learning_rate": 1.7608554763447828e-05,
"loss": 0.8126,
"step": 470
},
{
"epoch": 0.45,
"learning_rate": 1.7543745949449126e-05,
"loss": 0.8822,
"step": 480
},
{
"epoch": 0.46,
"learning_rate": 1.7478937135450422e-05,
"loss": 0.9976,
"step": 490
},
{
"epoch": 0.47,
"learning_rate": 1.741412832145172e-05,
"loss": 1.281,
"step": 500
},
{
"epoch": 0.48,
"learning_rate": 1.7349319507453016e-05,
"loss": 0.6655,
"step": 510
},
{
"epoch": 0.49,
"learning_rate": 1.728451069345431e-05,
"loss": 0.7992,
"step": 520
},
{
"epoch": 0.5,
"learning_rate": 1.7219701879455607e-05,
"loss": 0.8835,
"step": 530
},
{
"epoch": 0.51,
"learning_rate": 1.7154893065456902e-05,
"loss": 0.9881,
"step": 540
},
{
"epoch": 0.52,
"learning_rate": 1.7090084251458197e-05,
"loss": 1.2499,
"step": 550
},
{
"epoch": 0.53,
"learning_rate": 1.7025275437459496e-05,
"loss": 0.6659,
"step": 560
},
{
"epoch": 0.54,
"learning_rate": 1.696046662346079e-05,
"loss": 0.7963,
"step": 570
},
{
"epoch": 0.55,
"learning_rate": 1.689565780946209e-05,
"loss": 0.8647,
"step": 580
},
{
"epoch": 0.56,
"learning_rate": 1.6830848995463385e-05,
"loss": 0.9665,
"step": 590
},
{
"epoch": 0.56,
"learning_rate": 1.676604018146468e-05,
"loss": 1.2426,
"step": 600
},
{
"epoch": 0.56,
"eval_loss": 0.7926119565963745,
"eval_runtime": 299.7623,
"eval_samples_per_second": 6.672,
"eval_steps_per_second": 0.834,
"step": 600
},
{
"epoch": 0.57,
"learning_rate": 1.6701231367465976e-05,
"loss": 0.6608,
"step": 610
},
{
"epoch": 0.58,
"learning_rate": 1.6636422553467275e-05,
"loss": 0.7964,
"step": 620
},
{
"epoch": 0.59,
"learning_rate": 1.657161373946857e-05,
"loss": 0.8514,
"step": 630
},
{
"epoch": 0.6,
"learning_rate": 1.6506804925469865e-05,
"loss": 0.9737,
"step": 640
},
{
"epoch": 0.61,
"learning_rate": 1.644199611147116e-05,
"loss": 1.2815,
"step": 650
},
{
"epoch": 0.62,
"learning_rate": 1.6377187297472456e-05,
"loss": 0.6379,
"step": 660
},
{
"epoch": 0.63,
"learning_rate": 1.6312378483473755e-05,
"loss": 0.7866,
"step": 670
},
{
"epoch": 0.64,
"learning_rate": 1.624756966947505e-05,
"loss": 0.8569,
"step": 680
},
{
"epoch": 0.65,
"learning_rate": 1.618276085547635e-05,
"loss": 0.9911,
"step": 690
},
{
"epoch": 0.66,
"learning_rate": 1.6117952041477644e-05,
"loss": 1.2482,
"step": 700
},
{
"epoch": 0.67,
"learning_rate": 1.605314322747894e-05,
"loss": 0.648,
"step": 710
},
{
"epoch": 0.68,
"learning_rate": 1.5988334413480235e-05,
"loss": 0.7883,
"step": 720
},
{
"epoch": 0.69,
"learning_rate": 1.592352559948153e-05,
"loss": 0.8677,
"step": 730
},
{
"epoch": 0.7,
"learning_rate": 1.5858716785482825e-05,
"loss": 0.9587,
"step": 740
},
{
"epoch": 0.71,
"learning_rate": 1.5793907971484124e-05,
"loss": 1.2299,
"step": 750
},
{
"epoch": 0.72,
"learning_rate": 1.572909915748542e-05,
"loss": 0.6436,
"step": 760
},
{
"epoch": 0.72,
"learning_rate": 1.5664290343486715e-05,
"loss": 0.8006,
"step": 770
},
{
"epoch": 0.73,
"learning_rate": 1.5599481529488013e-05,
"loss": 0.8623,
"step": 780
},
{
"epoch": 0.74,
"learning_rate": 1.553467271548931e-05,
"loss": 0.9719,
"step": 790
},
{
"epoch": 0.75,
"learning_rate": 1.5469863901490604e-05,
"loss": 1.2219,
"step": 800
},
{
"epoch": 0.75,
"eval_loss": 0.7824305295944214,
"eval_runtime": 299.6393,
"eval_samples_per_second": 6.675,
"eval_steps_per_second": 0.834,
"step": 800
},
{
"epoch": 0.76,
"learning_rate": 1.54050550874919e-05,
"loss": 0.6453,
"step": 810
},
{
"epoch": 0.77,
"learning_rate": 1.5340246273493195e-05,
"loss": 0.7844,
"step": 820
},
{
"epoch": 0.78,
"learning_rate": 1.5275437459494494e-05,
"loss": 0.8451,
"step": 830
},
{
"epoch": 0.79,
"learning_rate": 1.5210628645495789e-05,
"loss": 0.9621,
"step": 840
},
{
"epoch": 0.8,
"learning_rate": 1.5145819831497084e-05,
"loss": 1.2478,
"step": 850
},
{
"epoch": 0.81,
"learning_rate": 1.5081011017498381e-05,
"loss": 0.6479,
"step": 860
},
{
"epoch": 0.82,
"learning_rate": 1.5016202203499677e-05,
"loss": 0.7962,
"step": 870
},
{
"epoch": 0.83,
"learning_rate": 1.4951393389500974e-05,
"loss": 0.8617,
"step": 880
},
{
"epoch": 0.84,
"learning_rate": 1.488658457550227e-05,
"loss": 0.9766,
"step": 890
},
{
"epoch": 0.85,
"learning_rate": 1.4821775761503566e-05,
"loss": 1.2458,
"step": 900
},
{
"epoch": 0.86,
"learning_rate": 1.4756966947504863e-05,
"loss": 0.6426,
"step": 910
},
{
"epoch": 0.87,
"learning_rate": 1.4692158133506158e-05,
"loss": 0.7907,
"step": 920
},
{
"epoch": 0.88,
"learning_rate": 1.4627349319507454e-05,
"loss": 0.858,
"step": 930
},
{
"epoch": 0.88,
"learning_rate": 1.456254050550875e-05,
"loss": 0.9703,
"step": 940
},
{
"epoch": 0.89,
"learning_rate": 1.4497731691510046e-05,
"loss": 1.2434,
"step": 950
},
{
"epoch": 0.9,
"learning_rate": 1.4432922877511341e-05,
"loss": 0.6524,
"step": 960
},
{
"epoch": 0.91,
"learning_rate": 1.436811406351264e-05,
"loss": 0.7836,
"step": 970
},
{
"epoch": 0.92,
"learning_rate": 1.4303305249513935e-05,
"loss": 0.8631,
"step": 980
},
{
"epoch": 0.93,
"learning_rate": 1.4238496435515232e-05,
"loss": 0.9614,
"step": 990
},
{
"epoch": 0.94,
"learning_rate": 1.4173687621516528e-05,
"loss": 1.1941,
"step": 1000
},
{
"epoch": 0.94,
"eval_loss": 0.7744362950325012,
"eval_runtime": 299.861,
"eval_samples_per_second": 6.67,
"eval_steps_per_second": 0.834,
"step": 1000
},
{
"epoch": 0.95,
"learning_rate": 1.4108878807517823e-05,
"loss": 0.6435,
"step": 1010
},
{
"epoch": 0.96,
"learning_rate": 1.404406999351912e-05,
"loss": 0.7933,
"step": 1020
},
{
"epoch": 0.97,
"learning_rate": 1.3979261179520415e-05,
"loss": 0.8488,
"step": 1030
},
{
"epoch": 0.98,
"learning_rate": 1.391445236552171e-05,
"loss": 0.9462,
"step": 1040
},
{
"epoch": 0.99,
"learning_rate": 1.384964355152301e-05,
"loss": 1.2181,
"step": 1050
},
{
"epoch": 1.0,
"learning_rate": 1.3784834737524305e-05,
"loss": 0.8102,
"step": 1060
},
{
"epoch": 1.01,
"learning_rate": 1.3720025923525602e-05,
"loss": 0.7588,
"step": 1070
},
{
"epoch": 1.02,
"learning_rate": 1.3655217109526897e-05,
"loss": 0.7429,
"step": 1080
},
{
"epoch": 1.03,
"learning_rate": 1.3590408295528192e-05,
"loss": 0.8237,
"step": 1090
},
{
"epoch": 1.04,
"learning_rate": 1.352559948152949e-05,
"loss": 0.9022,
"step": 1100
},
{
"epoch": 1.04,
"learning_rate": 1.3460790667530785e-05,
"loss": 1.1454,
"step": 1110
},
{
"epoch": 1.05,
"learning_rate": 1.339598185353208e-05,
"loss": 0.7898,
"step": 1120
},
{
"epoch": 1.06,
"learning_rate": 1.3331173039533379e-05,
"loss": 0.7567,
"step": 1130
},
{
"epoch": 1.07,
"learning_rate": 1.3266364225534674e-05,
"loss": 0.8251,
"step": 1140
},
{
"epoch": 1.08,
"learning_rate": 1.320155541153597e-05,
"loss": 0.9032,
"step": 1150
},
{
"epoch": 1.09,
"learning_rate": 1.3136746597537267e-05,
"loss": 1.1508,
"step": 1160
},
{
"epoch": 1.1,
"learning_rate": 1.3071937783538562e-05,
"loss": 0.7785,
"step": 1170
},
{
"epoch": 1.11,
"learning_rate": 1.3007128969539859e-05,
"loss": 0.7428,
"step": 1180
},
{
"epoch": 1.12,
"learning_rate": 1.2942320155541154e-05,
"loss": 0.817,
"step": 1190
},
{
"epoch": 1.13,
"learning_rate": 1.287751134154245e-05,
"loss": 0.9169,
"step": 1200
},
{
"epoch": 1.13,
"eval_loss": 0.7671642899513245,
"eval_runtime": 299.7006,
"eval_samples_per_second": 6.673,
"eval_steps_per_second": 0.834,
"step": 1200
},
{
"epoch": 1.14,
"learning_rate": 1.2812702527543748e-05,
"loss": 1.1475,
"step": 1210
},
{
"epoch": 1.15,
"learning_rate": 1.2747893713545044e-05,
"loss": 0.7852,
"step": 1220
},
{
"epoch": 1.16,
"learning_rate": 1.2683084899546339e-05,
"loss": 0.7535,
"step": 1230
},
{
"epoch": 1.17,
"learning_rate": 1.2618276085547636e-05,
"loss": 0.8209,
"step": 1240
},
{
"epoch": 1.18,
"learning_rate": 1.2553467271548931e-05,
"loss": 0.8976,
"step": 1250
},
{
"epoch": 1.19,
"learning_rate": 1.2488658457550227e-05,
"loss": 1.1478,
"step": 1260
},
{
"epoch": 1.2,
"learning_rate": 1.2423849643551524e-05,
"loss": 0.7667,
"step": 1270
},
{
"epoch": 1.2,
"learning_rate": 1.2359040829552819e-05,
"loss": 0.7423,
"step": 1280
},
{
"epoch": 1.21,
"learning_rate": 1.2294232015554118e-05,
"loss": 0.8198,
"step": 1290
},
{
"epoch": 1.22,
"learning_rate": 1.2229423201555413e-05,
"loss": 0.9104,
"step": 1300
},
{
"epoch": 1.23,
"learning_rate": 1.2164614387556708e-05,
"loss": 1.1482,
"step": 1310
},
{
"epoch": 1.24,
"learning_rate": 1.2099805573558005e-05,
"loss": 0.7704,
"step": 1320
},
{
"epoch": 1.25,
"learning_rate": 1.20349967595593e-05,
"loss": 0.7337,
"step": 1330
},
{
"epoch": 1.26,
"learning_rate": 1.1970187945560596e-05,
"loss": 0.8179,
"step": 1340
},
{
"epoch": 1.27,
"learning_rate": 1.1905379131561893e-05,
"loss": 0.8862,
"step": 1350
},
{
"epoch": 1.28,
"learning_rate": 1.1840570317563188e-05,
"loss": 1.1095,
"step": 1360
},
{
"epoch": 1.29,
"learning_rate": 1.1775761503564487e-05,
"loss": 0.7373,
"step": 1370
},
{
"epoch": 1.3,
"learning_rate": 1.1710952689565782e-05,
"loss": 0.7339,
"step": 1380
},
{
"epoch": 1.31,
"learning_rate": 1.1646143875567078e-05,
"loss": 0.8043,
"step": 1390
},
{
"epoch": 1.32,
"learning_rate": 1.1581335061568375e-05,
"loss": 0.9076,
"step": 1400
},
{
"epoch": 1.32,
"eval_loss": 0.7581225633621216,
"eval_runtime": 299.5432,
"eval_samples_per_second": 6.677,
"eval_steps_per_second": 0.835,
"step": 1400
},
{
"epoch": 1.33,
"learning_rate": 1.151652624756967e-05,
"loss": 1.1136,
"step": 1410
},
{
"epoch": 1.34,
"learning_rate": 1.1451717433570965e-05,
"loss": 0.7379,
"step": 1420
},
{
"epoch": 1.35,
"learning_rate": 1.1386908619572264e-05,
"loss": 0.7476,
"step": 1430
},
{
"epoch": 1.36,
"learning_rate": 1.132209980557356e-05,
"loss": 0.8104,
"step": 1440
},
{
"epoch": 1.36,
"learning_rate": 1.1257290991574855e-05,
"loss": 0.9083,
"step": 1450
},
{
"epoch": 1.37,
"learning_rate": 1.1192482177576152e-05,
"loss": 1.088,
"step": 1460
},
{
"epoch": 1.38,
"learning_rate": 1.1127673363577447e-05,
"loss": 0.7491,
"step": 1470
},
{
"epoch": 1.39,
"learning_rate": 1.1062864549578744e-05,
"loss": 0.7275,
"step": 1480
},
{
"epoch": 1.4,
"learning_rate": 1.099805573558004e-05,
"loss": 0.7944,
"step": 1490
},
{
"epoch": 1.41,
"learning_rate": 1.0933246921581335e-05,
"loss": 0.8868,
"step": 1500
},
{
"epoch": 1.42,
"learning_rate": 1.0868438107582634e-05,
"loss": 1.1016,
"step": 1510
},
{
"epoch": 1.43,
"learning_rate": 1.0803629293583929e-05,
"loss": 0.7377,
"step": 1520
},
{
"epoch": 1.44,
"learning_rate": 1.0738820479585224e-05,
"loss": 0.7386,
"step": 1530
},
{
"epoch": 1.45,
"learning_rate": 1.0674011665586521e-05,
"loss": 0.8005,
"step": 1540
},
{
"epoch": 1.46,
"learning_rate": 1.0609202851587817e-05,
"loss": 0.8879,
"step": 1550
},
{
"epoch": 1.47,
"learning_rate": 1.0544394037589114e-05,
"loss": 1.1047,
"step": 1560
},
{
"epoch": 1.48,
"learning_rate": 1.0479585223590409e-05,
"loss": 0.735,
"step": 1570
},
{
"epoch": 1.49,
"learning_rate": 1.0414776409591704e-05,
"loss": 0.7362,
"step": 1580
},
{
"epoch": 1.5,
"learning_rate": 1.0349967595593003e-05,
"loss": 0.8034,
"step": 1590
},
{
"epoch": 1.51,
"learning_rate": 1.0285158781594298e-05,
"loss": 0.8826,
"step": 1600
},
{
"epoch": 1.51,
"eval_loss": 0.7535994648933411,
"eval_runtime": 299.5957,
"eval_samples_per_second": 6.676,
"eval_steps_per_second": 0.834,
"step": 1600
},
{
"epoch": 1.52,
"learning_rate": 1.0220349967595594e-05,
"loss": 1.0577,
"step": 1610
},
{
"epoch": 1.52,
"learning_rate": 1.015554115359689e-05,
"loss": 0.7438,
"step": 1620
},
{
"epoch": 1.53,
"learning_rate": 1.0090732339598186e-05,
"loss": 0.7374,
"step": 1630
},
{
"epoch": 1.54,
"learning_rate": 1.0025923525599481e-05,
"loss": 0.8051,
"step": 1640
},
{
"epoch": 1.55,
"learning_rate": 9.961114711600778e-06,
"loss": 0.8904,
"step": 1650
},
{
"epoch": 1.56,
"learning_rate": 9.896305897602074e-06,
"loss": 1.0818,
"step": 1660
},
{
"epoch": 1.57,
"learning_rate": 9.83149708360337e-06,
"loss": 0.7392,
"step": 1670
},
{
"epoch": 1.58,
"learning_rate": 9.766688269604668e-06,
"loss": 0.7311,
"step": 1680
},
{
"epoch": 1.59,
"learning_rate": 9.701879455605963e-06,
"loss": 0.8017,
"step": 1690
},
{
"epoch": 1.6,
"learning_rate": 9.637070641607258e-06,
"loss": 0.9037,
"step": 1700
},
{
"epoch": 1.61,
"learning_rate": 9.572261827608555e-06,
"loss": 1.0718,
"step": 1710
},
{
"epoch": 1.62,
"learning_rate": 9.507453013609852e-06,
"loss": 0.73,
"step": 1720
},
{
"epoch": 1.63,
"learning_rate": 9.442644199611148e-06,
"loss": 0.734,
"step": 1730
},
{
"epoch": 1.64,
"learning_rate": 9.377835385612443e-06,
"loss": 0.8022,
"step": 1740
},
{
"epoch": 1.65,
"learning_rate": 9.31302657161374e-06,
"loss": 0.8691,
"step": 1750
},
{
"epoch": 1.66,
"learning_rate": 9.248217757615037e-06,
"loss": 1.0903,
"step": 1760
},
{
"epoch": 1.67,
"learning_rate": 9.183408943616332e-06,
"loss": 0.7463,
"step": 1770
},
{
"epoch": 1.68,
"learning_rate": 9.118600129617628e-06,
"loss": 0.7366,
"step": 1780
},
{
"epoch": 1.68,
"learning_rate": 9.053791315618925e-06,
"loss": 0.8132,
"step": 1790
},
{
"epoch": 1.69,
"learning_rate": 8.988982501620222e-06,
"loss": 0.8853,
"step": 1800
},
{
"epoch": 1.69,
"eval_loss": 0.7502772808074951,
"eval_runtime": 299.2776,
"eval_samples_per_second": 6.683,
"eval_steps_per_second": 0.835,
"step": 1800
},
{
"epoch": 1.7,
"learning_rate": 8.924173687621517e-06,
"loss": 1.0866,
"step": 1810
},
{
"epoch": 1.71,
"learning_rate": 8.859364873622813e-06,
"loss": 0.7208,
"step": 1820
},
{
"epoch": 1.72,
"learning_rate": 8.79455605962411e-06,
"loss": 0.7377,
"step": 1830
},
{
"epoch": 1.73,
"learning_rate": 8.729747245625407e-06,
"loss": 0.799,
"step": 1840
},
{
"epoch": 1.74,
"learning_rate": 8.664938431626702e-06,
"loss": 0.8706,
"step": 1850
},
{
"epoch": 1.75,
"learning_rate": 8.600129617627997e-06,
"loss": 1.0855,
"step": 1860
},
{
"epoch": 1.76,
"learning_rate": 8.535320803629294e-06,
"loss": 0.7377,
"step": 1870
},
{
"epoch": 1.77,
"learning_rate": 8.470511989630591e-06,
"loss": 0.7311,
"step": 1880
},
{
"epoch": 1.78,
"learning_rate": 8.405703175631887e-06,
"loss": 0.8087,
"step": 1890
},
{
"epoch": 1.79,
"learning_rate": 8.340894361633182e-06,
"loss": 0.8853,
"step": 1900
},
{
"epoch": 1.8,
"learning_rate": 8.276085547634479e-06,
"loss": 1.0839,
"step": 1910
},
{
"epoch": 1.81,
"learning_rate": 8.211276733635774e-06,
"loss": 0.7329,
"step": 1920
},
{
"epoch": 1.82,
"learning_rate": 8.146467919637071e-06,
"loss": 0.7274,
"step": 1930
},
{
"epoch": 1.83,
"learning_rate": 8.081659105638368e-06,
"loss": 0.7952,
"step": 1940
},
{
"epoch": 1.84,
"learning_rate": 8.016850291639664e-06,
"loss": 0.8648,
"step": 1950
},
{
"epoch": 1.84,
"learning_rate": 7.952041477640959e-06,
"loss": 1.0634,
"step": 1960
},
{
"epoch": 1.85,
"learning_rate": 7.887232663642256e-06,
"loss": 0.7349,
"step": 1970
},
{
"epoch": 1.86,
"learning_rate": 7.822423849643553e-06,
"loss": 0.7271,
"step": 1980
},
{
"epoch": 1.87,
"learning_rate": 7.757615035644848e-06,
"loss": 0.8063,
"step": 1990
},
{
"epoch": 1.88,
"learning_rate": 7.692806221646144e-06,
"loss": 0.8607,
"step": 2000
},
{
"epoch": 1.88,
"eval_loss": 0.7480069994926453,
"eval_runtime": 299.2706,
"eval_samples_per_second": 6.683,
"eval_steps_per_second": 0.835,
"step": 2000
},
{
"epoch": 1.89,
"learning_rate": 7.627997407647441e-06,
"loss": 1.0588,
"step": 2010
},
{
"epoch": 1.9,
"learning_rate": 7.563188593648737e-06,
"loss": 0.735,
"step": 2020
},
{
"epoch": 1.91,
"learning_rate": 7.498379779650033e-06,
"loss": 0.7207,
"step": 2030
},
{
"epoch": 1.92,
"learning_rate": 7.433570965651329e-06,
"loss": 0.8006,
"step": 2040
},
{
"epoch": 1.93,
"learning_rate": 7.3687621516526254e-06,
"loss": 0.8723,
"step": 2050
},
{
"epoch": 1.94,
"learning_rate": 7.303953337653922e-06,
"loss": 1.0789,
"step": 2060
},
{
"epoch": 1.95,
"learning_rate": 7.239144523655219e-06,
"loss": 0.7357,
"step": 2070
},
{
"epoch": 1.96,
"learning_rate": 7.174335709656514e-06,
"loss": 0.7231,
"step": 2080
},
{
"epoch": 1.97,
"learning_rate": 7.10952689565781e-06,
"loss": 0.8069,
"step": 2090
},
{
"epoch": 1.98,
"learning_rate": 7.044718081659106e-06,
"loss": 0.8683,
"step": 2100
},
{
"epoch": 1.99,
"learning_rate": 6.979909267660402e-06,
"loss": 1.0976,
"step": 2110
},
{
"epoch": 2.0,
"learning_rate": 6.915100453661699e-06,
"loss": 0.828,
"step": 2120
},
{
"epoch": 2.0,
"learning_rate": 6.850291639662995e-06,
"loss": 0.7945,
"step": 2130
},
{
"epoch": 2.01,
"learning_rate": 6.785482825664291e-06,
"loss": 0.6952,
"step": 2140
},
{
"epoch": 2.02,
"learning_rate": 6.720674011665586e-06,
"loss": 0.7797,
"step": 2150
},
{
"epoch": 2.03,
"learning_rate": 6.655865197666883e-06,
"loss": 0.8416,
"step": 2160
},
{
"epoch": 2.04,
"learning_rate": 6.5910563836681796e-06,
"loss": 0.9752,
"step": 2170
},
{
"epoch": 2.05,
"learning_rate": 6.526247569669476e-06,
"loss": 0.8453,
"step": 2180
},
{
"epoch": 2.06,
"learning_rate": 6.461438755670771e-06,
"loss": 0.6891,
"step": 2190
},
{
"epoch": 2.07,
"learning_rate": 6.396629941672068e-06,
"loss": 0.7682,
"step": 2200
},
{
"epoch": 2.07,
"eval_loss": 0.7461003661155701,
"eval_runtime": 299.2127,
"eval_samples_per_second": 6.684,
"eval_steps_per_second": 0.836,
"step": 2200
},
{
"epoch": 2.08,
"learning_rate": 6.331821127673364e-06,
"loss": 0.8392,
"step": 2210
},
{
"epoch": 2.09,
"learning_rate": 6.2670123136746604e-06,
"loss": 1.0085,
"step": 2220
},
{
"epoch": 2.1,
"learning_rate": 6.202203499675956e-06,
"loss": 0.8442,
"step": 2230
},
{
"epoch": 2.11,
"learning_rate": 6.137394685677253e-06,
"loss": 0.696,
"step": 2240
},
{
"epoch": 2.12,
"learning_rate": 6.072585871678549e-06,
"loss": 0.7907,
"step": 2250
},
{
"epoch": 2.13,
"learning_rate": 6.007777057679844e-06,
"loss": 0.8585,
"step": 2260
},
{
"epoch": 2.14,
"learning_rate": 5.9429682436811405e-06,
"loss": 1.002,
"step": 2270
},
{
"epoch": 2.15,
"learning_rate": 5.8781594296824375e-06,
"loss": 0.8646,
"step": 2280
},
{
"epoch": 2.16,
"learning_rate": 5.813350615683734e-06,
"loss": 0.712,
"step": 2290
},
{
"epoch": 2.16,
"learning_rate": 5.748541801685029e-06,
"loss": 0.7795,
"step": 2300
},
{
"epoch": 2.17,
"learning_rate": 5.683732987686326e-06,
"loss": 0.8444,
"step": 2310
},
{
"epoch": 2.18,
"learning_rate": 5.618924173687622e-06,
"loss": 1.0058,
"step": 2320
},
{
"epoch": 2.19,
"learning_rate": 5.554115359688918e-06,
"loss": 0.8736,
"step": 2330
},
{
"epoch": 2.2,
"learning_rate": 5.489306545690214e-06,
"loss": 0.6925,
"step": 2340
},
{
"epoch": 2.21,
"learning_rate": 5.424497731691511e-06,
"loss": 0.7789,
"step": 2350
},
{
"epoch": 2.22,
"learning_rate": 5.359688917692807e-06,
"loss": 0.8514,
"step": 2360
},
{
"epoch": 2.23,
"learning_rate": 5.294880103694103e-06,
"loss": 1.015,
"step": 2370
},
{
"epoch": 2.24,
"learning_rate": 5.2300712896953984e-06,
"loss": 0.8451,
"step": 2380
},
{
"epoch": 2.25,
"learning_rate": 5.1652624756966955e-06,
"loss": 0.697,
"step": 2390
},
{
"epoch": 2.26,
"learning_rate": 5.100453661697992e-06,
"loss": 0.7698,
"step": 2400
},
{
"epoch": 2.26,
"eval_loss": 0.7449027299880981,
"eval_runtime": 299.205,
"eval_samples_per_second": 6.684,
"eval_steps_per_second": 0.836,
"step": 2400
},
{
"epoch": 2.27,
"learning_rate": 5.035644847699287e-06,
"loss": 0.855,
"step": 2410
},
{
"epoch": 2.28,
"learning_rate": 4.970836033700583e-06,
"loss": 1.019,
"step": 2420
},
{
"epoch": 2.29,
"learning_rate": 4.90602721970188e-06,
"loss": 0.8669,
"step": 2430
},
{
"epoch": 2.3,
"learning_rate": 4.8412184057031755e-06,
"loss": 0.6836,
"step": 2440
},
{
"epoch": 2.31,
"learning_rate": 4.7764095917044725e-06,
"loss": 0.7765,
"step": 2450
},
{
"epoch": 2.32,
"learning_rate": 4.711600777705768e-06,
"loss": 0.8514,
"step": 2460
},
{
"epoch": 2.32,
"learning_rate": 4.646791963707065e-06,
"loss": 1.003,
"step": 2470
},
{
"epoch": 2.33,
"learning_rate": 4.58198314970836e-06,
"loss": 0.8447,
"step": 2480
},
{
"epoch": 2.34,
"learning_rate": 4.517174335709657e-06,
"loss": 0.7001,
"step": 2490
},
{
"epoch": 2.35,
"learning_rate": 4.4523655217109526e-06,
"loss": 0.7817,
"step": 2500
},
{
"epoch": 2.36,
"learning_rate": 4.38755670771225e-06,
"loss": 0.8452,
"step": 2510
},
{
"epoch": 2.37,
"learning_rate": 4.322747893713545e-06,
"loss": 0.9991,
"step": 2520
},
{
"epoch": 2.38,
"learning_rate": 4.257939079714842e-06,
"loss": 0.857,
"step": 2530
},
{
"epoch": 2.39,
"learning_rate": 4.193130265716137e-06,
"loss": 0.689,
"step": 2540
},
{
"epoch": 2.4,
"learning_rate": 4.128321451717434e-06,
"loss": 0.7796,
"step": 2550
},
{
"epoch": 2.41,
"learning_rate": 4.0635126377187305e-06,
"loss": 0.8431,
"step": 2560
},
{
"epoch": 2.42,
"learning_rate": 3.998703823720027e-06,
"loss": 1.0061,
"step": 2570
},
{
"epoch": 2.43,
"learning_rate": 3.933895009721323e-06,
"loss": 0.857,
"step": 2580
},
{
"epoch": 2.44,
"learning_rate": 3.869086195722618e-06,
"loss": 0.7073,
"step": 2590
},
{
"epoch": 2.45,
"learning_rate": 3.8042773817239147e-06,
"loss": 0.7637,
"step": 2600
},
{
"epoch": 2.45,
"eval_loss": 0.7434859871864319,
"eval_runtime": 298.8392,
"eval_samples_per_second": 6.693,
"eval_steps_per_second": 0.837,
"step": 2600
}
],
"max_steps": 3186,
"num_train_epochs": 3,
"total_flos": 3.2714347359303107e+18,
"trial_name": null,
"trial_params": null
}