hwm21's picture
Training in progress, step 4200, checkpoint
50f2f84 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 51.851851851851855,
"eval_steps": 500,
"global_step": 4200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.6172839506172839,
"grad_norm": 62.88630294799805,
"learning_rate": 9.916000000000001e-06,
"loss": 6.6856,
"step": 50
},
{
"epoch": 1.2345679012345678,
"grad_norm": 387.6339111328125,
"learning_rate": 9.818000000000002e-06,
"loss": 5.5869,
"step": 100
},
{
"epoch": 1.8518518518518519,
"grad_norm": 245.18975830078125,
"learning_rate": 9.718e-06,
"loss": 5.159,
"step": 150
},
{
"epoch": 2.4691358024691357,
"grad_norm": 330.3158264160156,
"learning_rate": 9.618e-06,
"loss": 4.0494,
"step": 200
},
{
"epoch": 3.0864197530864197,
"grad_norm": 138.14215087890625,
"learning_rate": 9.518000000000001e-06,
"loss": 3.6313,
"step": 250
},
{
"epoch": 3.7037037037037037,
"grad_norm": 166.69479370117188,
"learning_rate": 9.418e-06,
"loss": 3.3391,
"step": 300
},
{
"epoch": 4.320987654320987,
"grad_norm": 107.54407501220703,
"learning_rate": 9.318e-06,
"loss": 3.3295,
"step": 350
},
{
"epoch": 4.938271604938271,
"grad_norm": 293.8923034667969,
"learning_rate": 9.218e-06,
"loss": 3.0956,
"step": 400
},
{
"epoch": 5.555555555555555,
"grad_norm": 226.05360412597656,
"learning_rate": 9.118000000000001e-06,
"loss": 3.0271,
"step": 450
},
{
"epoch": 6.172839506172839,
"grad_norm": 352.8487854003906,
"learning_rate": 9.018e-06,
"loss": 3.0627,
"step": 500
},
{
"epoch": 6.790123456790123,
"grad_norm": 97.6641616821289,
"learning_rate": 8.918000000000002e-06,
"loss": 3.0312,
"step": 550
},
{
"epoch": 7.407407407407407,
"grad_norm": 90.92312622070312,
"learning_rate": 8.818000000000001e-06,
"loss": 3.0228,
"step": 600
},
{
"epoch": 8.024691358024691,
"grad_norm": 241.7625732421875,
"learning_rate": 8.718e-06,
"loss": 3.0873,
"step": 650
},
{
"epoch": 8.641975308641975,
"grad_norm": 162.14071655273438,
"learning_rate": 8.618000000000001e-06,
"loss": 2.9582,
"step": 700
},
{
"epoch": 9.25925925925926,
"grad_norm": 128.74766540527344,
"learning_rate": 8.518e-06,
"loss": 2.9787,
"step": 750
},
{
"epoch": 9.876543209876543,
"grad_norm": 164.0232391357422,
"learning_rate": 8.418000000000001e-06,
"loss": 2.969,
"step": 800
},
{
"epoch": 10.493827160493828,
"grad_norm": 110.58142852783203,
"learning_rate": 8.318e-06,
"loss": 2.884,
"step": 850
},
{
"epoch": 11.11111111111111,
"grad_norm": 111.70948791503906,
"learning_rate": 8.218e-06,
"loss": 2.8216,
"step": 900
},
{
"epoch": 11.728395061728396,
"grad_norm": 111.31181335449219,
"learning_rate": 8.118000000000001e-06,
"loss": 2.8621,
"step": 950
},
{
"epoch": 12.345679012345679,
"grad_norm": 84.1104507446289,
"learning_rate": 8.018e-06,
"loss": 2.7653,
"step": 1000
},
{
"epoch": 12.962962962962964,
"grad_norm": 85.67730712890625,
"learning_rate": 7.918e-06,
"loss": 2.8418,
"step": 1050
},
{
"epoch": 13.580246913580247,
"grad_norm": 567.8911743164062,
"learning_rate": 7.818e-06,
"loss": 2.789,
"step": 1100
},
{
"epoch": 14.197530864197532,
"grad_norm": 98.47197723388672,
"learning_rate": 7.718000000000001e-06,
"loss": 2.7996,
"step": 1150
},
{
"epoch": 14.814814814814815,
"grad_norm": 86.87311553955078,
"learning_rate": 7.618000000000001e-06,
"loss": 2.7087,
"step": 1200
},
{
"epoch": 15.432098765432098,
"grad_norm": 115.806640625,
"learning_rate": 7.518000000000001e-06,
"loss": 2.6898,
"step": 1250
},
{
"epoch": 16.049382716049383,
"grad_norm": 108.76448059082031,
"learning_rate": 7.418000000000001e-06,
"loss": 2.7533,
"step": 1300
},
{
"epoch": 16.666666666666668,
"grad_norm": 137.66285705566406,
"learning_rate": 7.318000000000001e-06,
"loss": 2.6817,
"step": 1350
},
{
"epoch": 17.28395061728395,
"grad_norm": 167.23983764648438,
"learning_rate": 7.218e-06,
"loss": 2.6612,
"step": 1400
},
{
"epoch": 17.901234567901234,
"grad_norm": 80.27250671386719,
"learning_rate": 7.118e-06,
"loss": 2.7053,
"step": 1450
},
{
"epoch": 18.51851851851852,
"grad_norm": 87.89417266845703,
"learning_rate": 7.018e-06,
"loss": 2.6016,
"step": 1500
},
{
"epoch": 19.135802469135804,
"grad_norm": 244.07081604003906,
"learning_rate": 6.9180000000000005e-06,
"loss": 2.6377,
"step": 1550
},
{
"epoch": 19.753086419753085,
"grad_norm": 66.56304931640625,
"learning_rate": 6.818e-06,
"loss": 2.5969,
"step": 1600
},
{
"epoch": 20.37037037037037,
"grad_norm": 146.2065887451172,
"learning_rate": 6.718e-06,
"loss": 2.5849,
"step": 1650
},
{
"epoch": 20.987654320987655,
"grad_norm": 105.38662719726562,
"learning_rate": 6.618000000000001e-06,
"loss": 2.588,
"step": 1700
},
{
"epoch": 21.604938271604937,
"grad_norm": 172.37232971191406,
"learning_rate": 6.518000000000001e-06,
"loss": 2.5201,
"step": 1750
},
{
"epoch": 22.22222222222222,
"grad_norm": 1186.192626953125,
"learning_rate": 6.418000000000001e-06,
"loss": 2.5618,
"step": 1800
},
{
"epoch": 22.839506172839506,
"grad_norm": 181.00384521484375,
"learning_rate": 6.318000000000001e-06,
"loss": 2.496,
"step": 1850
},
{
"epoch": 23.45679012345679,
"grad_norm": 90.32185363769531,
"learning_rate": 6.2180000000000004e-06,
"loss": 2.5254,
"step": 1900
},
{
"epoch": 24.074074074074073,
"grad_norm": 117.39266967773438,
"learning_rate": 6.1180000000000005e-06,
"loss": 2.4665,
"step": 1950
},
{
"epoch": 24.691358024691358,
"grad_norm": 117.4901123046875,
"learning_rate": 6.018000000000001e-06,
"loss": 2.4541,
"step": 2000
},
{
"epoch": 25.308641975308642,
"grad_norm": 112.75492095947266,
"learning_rate": 5.918000000000001e-06,
"loss": 2.4716,
"step": 2050
},
{
"epoch": 25.925925925925927,
"grad_norm": 75.71508026123047,
"learning_rate": 5.818e-06,
"loss": 2.4643,
"step": 2100
},
{
"epoch": 26.54320987654321,
"grad_norm": 87.87818145751953,
"learning_rate": 5.718e-06,
"loss": 2.452,
"step": 2150
},
{
"epoch": 27.160493827160494,
"grad_norm": 119.02462005615234,
"learning_rate": 5.618e-06,
"loss": 2.4431,
"step": 2200
},
{
"epoch": 27.77777777777778,
"grad_norm": 95.6996841430664,
"learning_rate": 5.518e-06,
"loss": 2.396,
"step": 2250
},
{
"epoch": 28.395061728395063,
"grad_norm": 82.37759399414062,
"learning_rate": 5.420000000000001e-06,
"loss": 2.4554,
"step": 2300
},
{
"epoch": 29.012345679012345,
"grad_norm": 63.04928207397461,
"learning_rate": 5.320000000000001e-06,
"loss": 2.3868,
"step": 2350
},
{
"epoch": 29.62962962962963,
"grad_norm": 85.531494140625,
"learning_rate": 5.220000000000001e-06,
"loss": 2.4088,
"step": 2400
},
{
"epoch": 30.246913580246915,
"grad_norm": 148.06163024902344,
"learning_rate": 5.12e-06,
"loss": 2.4479,
"step": 2450
},
{
"epoch": 30.864197530864196,
"grad_norm": 120.42308807373047,
"learning_rate": 5.02e-06,
"loss": 2.4293,
"step": 2500
},
{
"epoch": 31.48148148148148,
"grad_norm": 47.70389938354492,
"learning_rate": 4.92e-06,
"loss": 2.3727,
"step": 2550
},
{
"epoch": 32.098765432098766,
"grad_norm": 67.6549301147461,
"learning_rate": 4.8200000000000004e-06,
"loss": 2.3938,
"step": 2600
},
{
"epoch": 32.71604938271605,
"grad_norm": 71.10252380371094,
"learning_rate": 4.7200000000000005e-06,
"loss": 2.3758,
"step": 2650
},
{
"epoch": 33.333333333333336,
"grad_norm": 69.4305419921875,
"learning_rate": 4.620000000000001e-06,
"loss": 2.3855,
"step": 2700
},
{
"epoch": 33.95061728395062,
"grad_norm": 58.54874038696289,
"learning_rate": 4.520000000000001e-06,
"loss": 2.3638,
"step": 2750
},
{
"epoch": 34.5679012345679,
"grad_norm": 135.54541015625,
"learning_rate": 4.42e-06,
"loss": 2.3785,
"step": 2800
},
{
"epoch": 35.18518518518518,
"grad_norm": 191.87705993652344,
"learning_rate": 4.32e-06,
"loss": 2.3247,
"step": 2850
},
{
"epoch": 35.80246913580247,
"grad_norm": 101.19218444824219,
"learning_rate": 4.22e-06,
"loss": 2.3322,
"step": 2900
},
{
"epoch": 36.41975308641975,
"grad_norm": 97.59493255615234,
"learning_rate": 4.12e-06,
"loss": 2.3189,
"step": 2950
},
{
"epoch": 37.03703703703704,
"grad_norm": 50.98225784301758,
"learning_rate": 4.0200000000000005e-06,
"loss": 2.3337,
"step": 3000
},
{
"epoch": 37.65432098765432,
"grad_norm": 78.88179016113281,
"learning_rate": 3.920000000000001e-06,
"loss": 2.3707,
"step": 3050
},
{
"epoch": 38.27160493827161,
"grad_norm": 136.63319396972656,
"learning_rate": 3.820000000000001e-06,
"loss": 2.2602,
"step": 3100
},
{
"epoch": 38.888888888888886,
"grad_norm": 87.68150329589844,
"learning_rate": 3.7200000000000004e-06,
"loss": 2.3111,
"step": 3150
},
{
"epoch": 39.50617283950617,
"grad_norm": 179.4459686279297,
"learning_rate": 3.62e-06,
"loss": 2.3092,
"step": 3200
},
{
"epoch": 40.123456790123456,
"grad_norm": 76.10836791992188,
"learning_rate": 3.52e-06,
"loss": 2.3029,
"step": 3250
},
{
"epoch": 40.74074074074074,
"grad_norm": 85.23873901367188,
"learning_rate": 3.4200000000000007e-06,
"loss": 2.2699,
"step": 3300
},
{
"epoch": 41.358024691358025,
"grad_norm": 156.77699279785156,
"learning_rate": 3.3200000000000004e-06,
"loss": 2.2795,
"step": 3350
},
{
"epoch": 41.97530864197531,
"grad_norm": 87.01202392578125,
"learning_rate": 3.2200000000000005e-06,
"loss": 2.2961,
"step": 3400
},
{
"epoch": 42.592592592592595,
"grad_norm": 208.42947387695312,
"learning_rate": 3.12e-06,
"loss": 2.2692,
"step": 3450
},
{
"epoch": 43.20987654320987,
"grad_norm": 82.78223419189453,
"learning_rate": 3.0200000000000003e-06,
"loss": 2.2482,
"step": 3500
},
{
"epoch": 43.82716049382716,
"grad_norm": 110.6844482421875,
"learning_rate": 2.92e-06,
"loss": 2.2755,
"step": 3550
},
{
"epoch": 44.44444444444444,
"grad_norm": 57.944942474365234,
"learning_rate": 2.82e-06,
"loss": 2.302,
"step": 3600
},
{
"epoch": 45.06172839506173,
"grad_norm": 72.0767593383789,
"learning_rate": 2.7200000000000002e-06,
"loss": 2.2305,
"step": 3650
},
{
"epoch": 45.67901234567901,
"grad_norm": 154.40426635742188,
"learning_rate": 2.6200000000000003e-06,
"loss": 2.2532,
"step": 3700
},
{
"epoch": 46.2962962962963,
"grad_norm": 112.4802017211914,
"learning_rate": 2.52e-06,
"loss": 2.2596,
"step": 3750
},
{
"epoch": 46.91358024691358,
"grad_norm": 97.9261245727539,
"learning_rate": 2.42e-06,
"loss": 2.2296,
"step": 3800
},
{
"epoch": 47.53086419753087,
"grad_norm": 86.22404479980469,
"learning_rate": 2.3200000000000002e-06,
"loss": 2.2086,
"step": 3850
},
{
"epoch": 48.148148148148145,
"grad_norm": 118.13029479980469,
"learning_rate": 2.2200000000000003e-06,
"loss": 2.2208,
"step": 3900
},
{
"epoch": 48.76543209876543,
"grad_norm": 83.22029113769531,
"learning_rate": 2.12e-06,
"loss": 2.2228,
"step": 3950
},
{
"epoch": 49.382716049382715,
"grad_norm": 46.90211868286133,
"learning_rate": 2.02e-06,
"loss": 2.2279,
"step": 4000
},
{
"epoch": 50.0,
"grad_norm": 666.5877685546875,
"learning_rate": 1.9200000000000003e-06,
"loss": 2.2356,
"step": 4050
},
{
"epoch": 50.617283950617285,
"grad_norm": 73.89546966552734,
"learning_rate": 1.8200000000000002e-06,
"loss": 2.2332,
"step": 4100
},
{
"epoch": 51.23456790123457,
"grad_norm": 205.4402313232422,
"learning_rate": 1.72e-06,
"loss": 2.1635,
"step": 4150
},
{
"epoch": 51.851851851851855,
"grad_norm": 46.229618072509766,
"learning_rate": 1.6200000000000002e-06,
"loss": 2.1759,
"step": 4200
}
],
"logging_steps": 50,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 62,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.6054212980736e+19,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}