Hugging Face's logo

souging
/
bb904e4b-d273-4a10-a7bf-c576a99770e5

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
bb904e4b-d273-4a10-a7bf-c576a99770e5 / last-checkpoint /trainer_state.json
souging's picture
souging
Training in progress, epoch 3, checkpoint
bf62b65 verified
Raw
History Blame
93.6 kB
Invalid JSON:Unexpected token 'N', ..."ad_norm": NaN, "... is not valid JSON
{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 3.287671232876712,
 "eval_steps": 500,
 "global_step": 600,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.005479452054794521,
 "grad_norm": NaN,
 "learning_rate": 2.0000000000000003e-06,
 "loss": 0.0,
 "step": 1
 },
 {
 "epoch": 0.010958904109589041,
 "grad_norm": NaN,
 "learning_rate": 4.000000000000001e-06,
 "loss": 0.0,
 "step": 2
 },
 {
 "epoch": 0.01643835616438356,
 "grad_norm": NaN,
 "learning_rate": 6e-06,
 "loss": 0.0,
 "step": 3
 },
 {
 "epoch": 0.021917808219178082,
 "grad_norm": NaN,
 "learning_rate": 8.000000000000001e-06,
 "loss": 0.0,
 "step": 4
 },
 {
 "epoch": 0.0273972602739726,
 "grad_norm": NaN,
 "learning_rate": 1e-05,
 "loss": 0.0,
 "step": 5
 },
 {
 "epoch": 0.03287671232876712,
 "grad_norm": NaN,
 "learning_rate": 1.2e-05,
 "loss": 0.0,
 "step": 6
 },
 {
 "epoch": 0.038356164383561646,
 "grad_norm": NaN,
 "learning_rate": 1.4000000000000001e-05,
 "loss": 0.0,
 "step": 7
 },
 {
 "epoch": 0.043835616438356165,
 "grad_norm": NaN,
 "learning_rate": 1.6000000000000003e-05,
 "loss": 0.0,
 "step": 8
 },
 {
 "epoch": 0.049315068493150684,
 "grad_norm": NaN,
 "learning_rate": 1.8e-05,
 "loss": 0.0,
 "step": 9
 },
 {
 "epoch": 0.0547945205479452,
 "grad_norm": NaN,
 "learning_rate": 2e-05,
 "loss": 0.0,
 "step": 10
 },
 {
 "epoch": 0.06027397260273973,
 "grad_norm": NaN,
 "learning_rate": 2.2000000000000003e-05,
 "loss": 0.0,
 "step": 11
 },
 {
 "epoch": 0.06575342465753424,
 "grad_norm": NaN,
 "learning_rate": 2.4e-05,
 "loss": 0.0,
 "step": 12
 },
 {
 "epoch": 0.07123287671232877,
 "grad_norm": NaN,
 "learning_rate": 2.6000000000000002e-05,
 "loss": 0.0,
 "step": 13
 },
 {
 "epoch": 0.07671232876712329,
 "grad_norm": NaN,
 "learning_rate": 2.8000000000000003e-05,
 "loss": 0.0,
 "step": 14
 },
 {
 "epoch": 0.0821917808219178,
 "grad_norm": NaN,
 "learning_rate": 3e-05,
 "loss": 0.0,
 "step": 15
 },
 {
 "epoch": 0.08767123287671233,
 "grad_norm": NaN,
 "learning_rate": 3.2000000000000005e-05,
 "loss": 0.0,
 "step": 16
 },
 {
 "epoch": 0.09315068493150686,
 "grad_norm": NaN,
 "learning_rate": 3.4000000000000007e-05,
 "loss": 0.0,
 "step": 17
 },
 {
 "epoch": 0.09863013698630137,
 "grad_norm": NaN,
 "learning_rate": 3.6e-05,
 "loss": 0.0,
 "step": 18
 },
 {
 "epoch": 0.10410958904109589,
 "grad_norm": NaN,
 "learning_rate": 3.8e-05,
 "loss": 0.0,
 "step": 19
 },
 {
 "epoch": 0.1095890410958904,
 "grad_norm": NaN,
 "learning_rate": 4e-05,
 "loss": 0.0,
 "step": 20
 },
 {
 "epoch": 0.11506849315068493,
 "grad_norm": NaN,
 "learning_rate": 4.2e-05,
 "loss": 0.0,
 "step": 21
 },
 {
 "epoch": 0.12054794520547946,
 "grad_norm": NaN,
 "learning_rate": 4.4000000000000006e-05,
 "loss": 0.0,
 "step": 22
 },
 {
 "epoch": 0.12602739726027398,
 "grad_norm": NaN,
 "learning_rate": 4.600000000000001e-05,
 "loss": 0.0,
 "step": 23
 },
 {
 "epoch": 0.13150684931506848,
 "grad_norm": NaN,
 "learning_rate": 4.8e-05,
 "loss": 0.0,
 "step": 24
 },
 {
 "epoch": 0.136986301369863,
 "grad_norm": NaN,
 "learning_rate": 5e-05,
 "loss": 0.0,
 "step": 25
 },
 {
 "epoch": 0.14246575342465753,
 "grad_norm": NaN,
 "learning_rate": 5.2000000000000004e-05,
 "loss": 0.0,
 "step": 26
 },
 {
 "epoch": 0.14794520547945206,
 "grad_norm": NaN,
 "learning_rate": 5.4000000000000005e-05,
 "loss": 0.0,
 "step": 27
 },
 {
 "epoch": 0.15342465753424658,
 "grad_norm": NaN,
 "learning_rate": 5.6000000000000006e-05,
 "loss": 0.0,
 "step": 28
 },
 {
 "epoch": 0.1589041095890411,
 "grad_norm": NaN,
 "learning_rate": 5.8e-05,
 "loss": 0.0,
 "step": 29
 },
 {
 "epoch": 0.1643835616438356,
 "grad_norm": NaN,
 "learning_rate": 6e-05,
 "loss": 0.0,
 "step": 30
 },
 {
 "epoch": 0.16986301369863013,
 "grad_norm": NaN,
 "learning_rate": 6.2e-05,
 "loss": 0.0,
 "step": 31
 },
 {
 "epoch": 0.17534246575342466,
 "grad_norm": NaN,
 "learning_rate": 6.400000000000001e-05,
 "loss": 0.0,
 "step": 32
 },
 {
 "epoch": 0.18082191780821918,
 "grad_norm": NaN,
 "learning_rate": 6.6e-05,
 "loss": 0.0,
 "step": 33
 },
 {
 "epoch": 0.1863013698630137,
 "grad_norm": NaN,
 "learning_rate": 6.800000000000001e-05,
 "loss": 0.0,
 "step": 34
 },
 {
 "epoch": 0.1917808219178082,
 "grad_norm": NaN,
 "learning_rate": 7e-05,
 "loss": 0.0,
 "step": 35
 },
 {
 "epoch": 0.19726027397260273,
 "grad_norm": NaN,
 "learning_rate": 7.2e-05,
 "loss": 0.0,
 "step": 36
 },
 {
 "epoch": 0.20273972602739726,
 "grad_norm": NaN,
 "learning_rate": 7.4e-05,
 "loss": 0.0,
 "step": 37
 },
 {
 "epoch": 0.20821917808219179,
 "grad_norm": NaN,
 "learning_rate": 7.6e-05,
 "loss": 0.0,
 "step": 38
 },
 {
 "epoch": 0.2136986301369863,
 "grad_norm": NaN,
 "learning_rate": 7.800000000000001e-05,
 "loss": 0.0,
 "step": 39
 },
 {
 "epoch": 0.2191780821917808,
 "grad_norm": NaN,
 "learning_rate": 8e-05,
 "loss": 0.0,
 "step": 40
 },
 {
 "epoch": 0.22465753424657534,
 "grad_norm": NaN,
 "learning_rate": 8.2e-05,
 "loss": 0.0,
 "step": 41
 },
 {
 "epoch": 0.23013698630136986,
 "grad_norm": NaN,
 "learning_rate": 8.4e-05,
 "loss": 0.0,
 "step": 42
 },
 {
 "epoch": 0.2356164383561644,
 "grad_norm": NaN,
 "learning_rate": 8.6e-05,
 "loss": 0.0,
 "step": 43
 },
 {
 "epoch": 0.2410958904109589,
 "grad_norm": NaN,
 "learning_rate": 8.800000000000001e-05,
 "loss": 0.0,
 "step": 44
 },
 {
 "epoch": 0.2465753424657534,
 "grad_norm": NaN,
 "learning_rate": 9e-05,
 "loss": 0.0,
 "step": 45
 },
 {
 "epoch": 0.25205479452054796,
 "grad_norm": NaN,
 "learning_rate": 9.200000000000001e-05,
 "loss": 0.0,
 "step": 46
 },
 {
 "epoch": 0.25753424657534246,
 "grad_norm": NaN,
 "learning_rate": 9.4e-05,
 "loss": 0.0,
 "step": 47
 },
 {
 "epoch": 0.26301369863013696,
 "grad_norm": NaN,
 "learning_rate": 9.6e-05,
 "loss": 0.0,
 "step": 48
 },
 {
 "epoch": 0.2684931506849315,
 "grad_norm": NaN,
 "learning_rate": 9.8e-05,
 "loss": 0.0,
 "step": 49
 },
 {
 "epoch": 0.273972602739726,
 "grad_norm": NaN,
 "learning_rate": 0.0001,
 "loss": 0.0,
 "step": 50
 },
 {
 "epoch": 0.27945205479452057,
 "grad_norm": NaN,
 "learning_rate": 0.00010200000000000001,
 "loss": 0.0,
 "step": 51
 },
 {
 "epoch": 0.28493150684931506,
 "grad_norm": NaN,
 "learning_rate": 0.00010400000000000001,
 "loss": 0.0,
 "step": 52
 },
 {
 "epoch": 0.29041095890410956,
 "grad_norm": NaN,
 "learning_rate": 0.00010600000000000002,
 "loss": 0.0,
 "step": 53
 },
 {
 "epoch": 0.2958904109589041,
 "grad_norm": NaN,
 "learning_rate": 0.00010800000000000001,
 "loss": 0.0,
 "step": 54
 },
 {
 "epoch": 0.3013698630136986,
 "grad_norm": NaN,
 "learning_rate": 0.00011000000000000002,
 "loss": 0.0,
 "step": 55
 },
 {
 "epoch": 0.30684931506849317,
 "grad_norm": NaN,
 "learning_rate": 0.00011200000000000001,
 "loss": 0.0,
 "step": 56
 },
 {
 "epoch": 0.31232876712328766,
 "grad_norm": NaN,
 "learning_rate": 0.00011399999999999999,
 "loss": 0.0,
 "step": 57
 },
 {
 "epoch": 0.3178082191780822,
 "grad_norm": NaN,
 "learning_rate": 0.000116,
 "loss": 0.0,
 "step": 58
 },
 {
 "epoch": 0.3232876712328767,
 "grad_norm": NaN,
 "learning_rate": 0.000118,
 "loss": 0.0,
 "step": 59
 },
 {
 "epoch": 0.3287671232876712,
 "grad_norm": NaN,
 "learning_rate": 0.00012,
 "loss": 0.0,
 "step": 60
 },
 {
 "epoch": 0.33424657534246577,
 "grad_norm": NaN,
 "learning_rate": 0.000122,
 "loss": 0.0,
 "step": 61
 },
 {
 "epoch": 0.33972602739726027,
 "grad_norm": NaN,
 "learning_rate": 0.000124,
 "loss": 0.0,
 "step": 62
 },
 {
 "epoch": 0.3452054794520548,
 "grad_norm": NaN,
 "learning_rate": 0.000126,
 "loss": 0.0,
 "step": 63
 },
 {
 "epoch": 0.3506849315068493,
 "grad_norm": NaN,
 "learning_rate": 0.00012800000000000002,
 "loss": 0.0,
 "step": 64
 },
 {
 "epoch": 0.3561643835616438,
 "grad_norm": NaN,
 "learning_rate": 0.00013000000000000002,
 "loss": 0.0,
 "step": 65
 },
 {
 "epoch": 0.36164383561643837,
 "grad_norm": NaN,
 "learning_rate": 0.000132,
 "loss": 0.0,
 "step": 66
 },
 {
 "epoch": 0.36712328767123287,
 "grad_norm": NaN,
 "learning_rate": 0.000134,
 "loss": 0.0,
 "step": 67
 },
 {
 "epoch": 0.3726027397260274,
 "grad_norm": NaN,
 "learning_rate": 0.00013600000000000003,
 "loss": 0.0,
 "step": 68
 },
 {
 "epoch": 0.3780821917808219,
 "grad_norm": NaN,
 "learning_rate": 0.000138,
 "loss": 0.0,
 "step": 69
 },
 {
 "epoch": 0.3835616438356164,
 "grad_norm": NaN,
 "learning_rate": 0.00014,
 "loss": 0.0,
 "step": 70
 },
 {
 "epoch": 0.38904109589041097,
 "grad_norm": NaN,
 "learning_rate": 0.000142,
 "loss": 0.0,
 "step": 71
 },
 {
 "epoch": 0.39452054794520547,
 "grad_norm": NaN,
 "learning_rate": 0.000144,
 "loss": 0.0,
 "step": 72
 },
 {
 "epoch": 0.4,
 "grad_norm": NaN,
 "learning_rate": 0.000146,
 "loss": 0.0,
 "step": 73
 },
 {
 "epoch": 0.4054794520547945,
 "grad_norm": NaN,
 "learning_rate": 0.000148,
 "loss": 0.0,
 "step": 74
 },
 {
 "epoch": 0.410958904109589,
 "grad_norm": NaN,
 "learning_rate": 0.00015000000000000001,
 "loss": 0.0,
 "step": 75
 },
 {
 "epoch": 0.41643835616438357,
 "grad_norm": NaN,
 "learning_rate": 0.000152,
 "loss": 0.0,
 "step": 76
 },
 {
 "epoch": 0.42191780821917807,
 "grad_norm": NaN,
 "learning_rate": 0.000154,
 "loss": 0.0,
 "step": 77
 },
 {
 "epoch": 0.4273972602739726,
 "grad_norm": NaN,
 "learning_rate": 0.00015600000000000002,
 "loss": 0.0,
 "step": 78
 },
 {
 "epoch": 0.4328767123287671,
 "grad_norm": NaN,
 "learning_rate": 0.00015800000000000002,
 "loss": 0.0,
 "step": 79
 },
 {
 "epoch": 0.4383561643835616,
 "grad_norm": NaN,
 "learning_rate": 0.00016,
 "loss": 0.0,
 "step": 80
 },
 {
 "epoch": 0.4438356164383562,
 "grad_norm": NaN,
 "learning_rate": 0.000162,
 "loss": 0.0,
 "step": 81
 },
 {
 "epoch": 0.44931506849315067,
 "grad_norm": NaN,
 "learning_rate": 0.000164,
 "loss": 0.0,
 "step": 82
 },
 {
 "epoch": 0.4547945205479452,
 "grad_norm": NaN,
 "learning_rate": 0.000166,
 "loss": 0.0,
 "step": 83
 },
 {
 "epoch": 0.4602739726027397,
 "grad_norm": NaN,
 "learning_rate": 0.000168,
 "loss": 0.0,
 "step": 84
 },
 {
 "epoch": 0.4657534246575342,
 "grad_norm": NaN,
 "learning_rate": 0.00017,
 "loss": 0.0,
 "step": 85
 },
 {
 "epoch": 0.4712328767123288,
 "grad_norm": NaN,
 "learning_rate": 0.000172,
 "loss": 0.0,
 "step": 86
 },
 {
 "epoch": 0.4767123287671233,
 "grad_norm": NaN,
 "learning_rate": 0.000174,
 "loss": 0.0,
 "step": 87
 },
 {
 "epoch": 0.4821917808219178,
 "grad_norm": NaN,
 "learning_rate": 0.00017600000000000002,
 "loss": 0.0,
 "step": 88
 },
 {
 "epoch": 0.4876712328767123,
 "grad_norm": NaN,
 "learning_rate": 0.00017800000000000002,
 "loss": 0.0,
 "step": 89
 },
 {
 "epoch": 0.4931506849315068,
 "grad_norm": NaN,
 "learning_rate": 0.00018,
 "loss": 0.0,
 "step": 90
 },
 {
 "epoch": 0.4986301369863014,
 "grad_norm": NaN,
 "learning_rate": 0.000182,
 "loss": 0.0,
 "step": 91
 },
 {
 "epoch": 0.5041095890410959,
 "grad_norm": NaN,
 "learning_rate": 0.00018400000000000003,
 "loss": 0.0,
 "step": 92
 },
 {
 "epoch": 0.5095890410958904,
 "grad_norm": NaN,
 "learning_rate": 0.00018600000000000002,
 "loss": 0.0,
 "step": 93
 },
 {
 "epoch": 0.5150684931506849,
 "grad_norm": NaN,
 "learning_rate": 0.000188,
 "loss": 0.0,
 "step": 94
 },
 {
 "epoch": 0.5205479452054794,
 "grad_norm": NaN,
 "learning_rate": 0.00019,
 "loss": 0.0,
 "step": 95
 },
 {
 "epoch": 0.5260273972602739,
 "grad_norm": NaN,
 "learning_rate": 0.000192,
 "loss": 0.0,
 "step": 96
 },
 {
 "epoch": 0.5315068493150685,
 "grad_norm": NaN,
 "learning_rate": 0.000194,
 "loss": 0.0,
 "step": 97
 },
 {
 "epoch": 0.536986301369863,
 "grad_norm": NaN,
 "learning_rate": 0.000196,
 "loss": 0.0,
 "step": 98
 },
 {
 "epoch": 0.5424657534246575,
 "grad_norm": NaN,
 "learning_rate": 0.00019800000000000002,
 "loss": 0.0,
 "step": 99
 },
 {
 "epoch": 0.547945205479452,
 "grad_norm": NaN,
 "learning_rate": 0.0002,
 "loss": 0.0,
 "step": 100
 },
 {
 "epoch": 0.5534246575342465,
 "grad_norm": NaN,
 "learning_rate": 0.0001999980260856137,
 "loss": 0.0,
 "step": 101
 },
 {
 "epoch": 0.5589041095890411,
 "grad_norm": NaN,
 "learning_rate": 0.00019999210442038162,
 "loss": 0.0,
 "step": 102
 },
 {
 "epoch": 0.5643835616438356,
 "grad_norm": NaN,
 "learning_rate": 0.0001999822352380809,
 "loss": 0.0,
 "step": 103
 },
 {
 "epoch": 0.5698630136986301,
 "grad_norm": NaN,
 "learning_rate": 0.00019996841892833,
 "loss": 0.0,
 "step": 104
 },
 {
 "epoch": 0.5753424657534246,
 "grad_norm": NaN,
 "learning_rate": 0.00019995065603657316,
 "loss": 0.0,
 "step": 105
 },
 {
 "epoch": 0.5808219178082191,
 "grad_norm": NaN,
 "learning_rate": 0.00019992894726405893,
 "loss": 0.0,
 "step": 106
 },
 {
 "epoch": 0.5863013698630137,
 "grad_norm": NaN,
 "learning_rate": 0.0001999032934678125,
 "loss": 0.0,
 "step": 107
 },
 {
 "epoch": 0.5917808219178082,
 "grad_norm": NaN,
 "learning_rate": 0.00019987369566060176,
 "loss": 0.0,
 "step": 108
 },
 {
 "epoch": 0.5972602739726027,
 "grad_norm": NaN,
 "learning_rate": 0.00019984015501089752,
 "loss": 0.0,
 "step": 109
 },
 {
 "epoch": 0.6027397260273972,
 "grad_norm": NaN,
 "learning_rate": 0.00019980267284282717,
 "loss": 0.0,
 "step": 110
 },
 {
 "epoch": 0.6082191780821918,
 "grad_norm": NaN,
 "learning_rate": 0.00019976125063612252,
 "loss": 0.0,
 "step": 111
 },
 {
 "epoch": 0.6136986301369863,
 "grad_norm": NaN,
 "learning_rate": 0.0001997158900260614,
 "loss": 0.0,
 "step": 112
 },
 {
 "epoch": 0.6191780821917808,
 "grad_norm": NaN,
 "learning_rate": 0.00019966659280340297,
 "loss": 0.0,
 "step": 113
 },
 {
 "epoch": 0.6246575342465753,
 "grad_norm": NaN,
 "learning_rate": 0.00019961336091431727,
 "loss": 0.0,
 "step": 114
 },
 {
 "epoch": 0.6301369863013698,
 "grad_norm": NaN,
 "learning_rate": 0.00019955619646030802,
 "loss": 0.0,
 "step": 115
 },
 {
 "epoch": 0.6356164383561644,
 "grad_norm": NaN,
 "learning_rate": 0.00019949510169813003,
 "loss": 0.0,
 "step": 116
 },
 {
 "epoch": 0.6410958904109589,
 "grad_norm": NaN,
 "learning_rate": 0.0001994300790396999,
 "loss": 0.0,
 "step": 117
 },
 {
 "epoch": 0.6465753424657534,
 "grad_norm": NaN,
 "learning_rate": 0.00019936113105200085,
 "loss": 0.0,
 "step": 118
 },
 {
 "epoch": 0.6520547945205479,
 "grad_norm": NaN,
 "learning_rate": 0.00019928826045698136,
 "loss": 0.0,
 "step": 119
 },
 {
 "epoch": 0.6575342465753424,
 "grad_norm": NaN,
 "learning_rate": 0.0001992114701314478,
 "loss": 0.0,
 "step": 120
 },
 {
 "epoch": 0.663013698630137,
 "grad_norm": NaN,
 "learning_rate": 0.00019913076310695068,
 "loss": 0.0,
 "step": 121
 },
 {
 "epoch": 0.6684931506849315,
 "grad_norm": NaN,
 "learning_rate": 0.00019904614256966512,
 "loss": 0.0,
 "step": 122
 },
 {
 "epoch": 0.673972602739726,
 "grad_norm": NaN,
 "learning_rate": 0.0001989576118602651,
 "loss": 0.0,
 "step": 123
 },
 {
 "epoch": 0.6794520547945205,
 "grad_norm": NaN,
 "learning_rate": 0.0001988651744737914,
 "loss": 0.0,
 "step": 124
 },
 {
 "epoch": 0.684931506849315,
 "grad_norm": NaN,
 "learning_rate": 0.00019876883405951377,
 "loss": 0.0,
 "step": 125
 },
 {
 "epoch": 0.6904109589041096,
 "grad_norm": NaN,
 "learning_rate": 0.0001986685944207868,
 "loss": 0.0,
 "step": 126
 },
 {
 "epoch": 0.6958904109589041,
 "grad_norm": NaN,
 "learning_rate": 0.00019856445951489982,
 "loss": 0.0,
 "step": 127
 },
 {
 "epoch": 0.7013698630136986,
 "grad_norm": NaN,
 "learning_rate": 0.00019845643345292054,
 "loss": 0.0,
 "step": 128
 },
 {
 "epoch": 0.7068493150684931,
 "grad_norm": NaN,
 "learning_rate": 0.00019834452049953297,
 "loss": 0.0,
 "step": 129
 },
 {
 "epoch": 0.7123287671232876,
 "grad_norm": NaN,
 "learning_rate": 0.0001982287250728689,
 "loss": 0.0,
 "step": 130
 },
 {
 "epoch": 0.7178082191780822,
 "grad_norm": NaN,
 "learning_rate": 0.0001981090517443334,
 "loss": 0.0,
 "step": 131
 },
 {
 "epoch": 0.7232876712328767,
 "grad_norm": NaN,
 "learning_rate": 0.0001979855052384247,
 "loss": 0.0,
 "step": 132
 },
 {
 "epoch": 0.7287671232876712,
 "grad_norm": NaN,
 "learning_rate": 0.00019785809043254722,
 "loss": 0.0,
 "step": 133
 },
 {
 "epoch": 0.7342465753424657,
 "grad_norm": NaN,
 "learning_rate": 0.00019772681235681936,
 "loss": 0.0,
 "step": 134
 },
 {
 "epoch": 0.7397260273972602,
 "grad_norm": NaN,
 "learning_rate": 0.00019759167619387476,
 "loss": 0.0,
 "step": 135
 },
 {
 "epoch": 0.7452054794520548,
 "grad_norm": NaN,
 "learning_rate": 0.00019745268727865774,
 "loss": 0.0,
 "step": 136
 },
 {
 "epoch": 0.7506849315068493,
 "grad_norm": NaN,
 "learning_rate": 0.00019730985109821266,
 "loss": 0.0,
 "step": 137
 },
 {
 "epoch": 0.7561643835616438,
 "grad_norm": NaN,
 "learning_rate": 0.0001971631732914674,
 "loss": 0.0,
 "step": 138
 },
 {
 "epoch": 0.7616438356164383,
 "grad_norm": NaN,
 "learning_rate": 0.0001970126596490106,
 "loss": 0.0,
 "step": 139
 },
 {
 "epoch": 0.7671232876712328,
 "grad_norm": NaN,
 "learning_rate": 0.0001968583161128631,
 "loss": 0.0,
 "step": 140
 },
 {
 "epoch": 0.7726027397260274,
 "grad_norm": NaN,
 "learning_rate": 0.00019670014877624353,
 "loss": 0.0,
 "step": 141
 },
 {
 "epoch": 0.7780821917808219,
 "grad_norm": NaN,
 "learning_rate": 0.0001965381638833274,
 "loss": 0.0,
 "step": 142
 },
 {
 "epoch": 0.7835616438356164,
 "grad_norm": NaN,
 "learning_rate": 0.000196372367829001,
 "loss": 0.0,
 "step": 143
 },
 {
 "epoch": 0.7890410958904109,
 "grad_norm": NaN,
 "learning_rate": 0.0001962027671586086,
 "loss": 0.0,
 "step": 144
 },
 {
 "epoch": 0.7945205479452054,
 "grad_norm": NaN,
 "learning_rate": 0.0001960293685676943,
 "loss": 0.0,
 "step": 145
 },
 {
 "epoch": 0.8,
 "grad_norm": NaN,
 "learning_rate": 0.0001958521789017376,
 "loss": 0.0,
 "step": 146
 },
 {
 "epoch": 0.8054794520547945,
 "grad_norm": NaN,
 "learning_rate": 0.00019567120515588308,
 "loss": 0.0,
 "step": 147
 },
 {
 "epoch": 0.810958904109589,
 "grad_norm": NaN,
 "learning_rate": 0.00019548645447466431,
 "loss": 0.0,
 "step": 148
 },
 {
 "epoch": 0.8164383561643835,
 "grad_norm": NaN,
 "learning_rate": 0.00019529793415172192,
 "loss": 0.0,
 "step": 149
 },
 {
 "epoch": 0.821917808219178,
 "grad_norm": NaN,
 "learning_rate": 0.00019510565162951537,
 "loss": 0.0,
 "step": 150
 },
 {
 "epoch": 0.8273972602739726,
 "grad_norm": NaN,
 "learning_rate": 0.00019490961449902946,
 "loss": 0.0,
 "step": 151
 },
 {
 "epoch": 0.8328767123287671,
 "grad_norm": NaN,
 "learning_rate": 0.00019470983049947444,
 "loss": 0.0,
 "step": 152
 },
 {
 "epoch": 0.8383561643835616,
 "grad_norm": NaN,
 "learning_rate": 0.00019450630751798048,
 "loss": 0.0,
 "step": 153
 },
 {
 "epoch": 0.8438356164383561,
 "grad_norm": NaN,
 "learning_rate": 0.00019429905358928646,
 "loss": 0.0,
 "step": 154
 },
 {
 "epoch": 0.8493150684931506,
 "grad_norm": NaN,
 "learning_rate": 0.00019408807689542257,
 "loss": 0.0,
 "step": 155
 },
 {
 "epoch": 0.8547945205479452,
 "grad_norm": NaN,
 "learning_rate": 0.00019387338576538744,
 "loss": 0.0,
 "step": 156
 },
 {
 "epoch": 0.8602739726027397,
 "grad_norm": NaN,
 "learning_rate": 0.00019365498867481923,
 "loss": 0.0,
 "step": 157
 },
 {
 "epoch": 0.8657534246575342,
 "grad_norm": NaN,
 "learning_rate": 0.00019343289424566122,
 "loss": 0.0,
 "step": 158
 },
 {
 "epoch": 0.8712328767123287,
 "grad_norm": NaN,
 "learning_rate": 0.0001932071112458211,
 "loss": 0.0,
 "step": 159
 },
 {
 "epoch": 0.8767123287671232,
 "grad_norm": NaN,
 "learning_rate": 0.00019297764858882514,
 "loss": 0.0,
 "step": 160
 },
 {
 "epoch": 0.8821917808219178,
 "grad_norm": NaN,
 "learning_rate": 0.00019274451533346615,
 "loss": 0.0,
 "step": 161
 },
 {
 "epoch": 0.8876712328767123,
 "grad_norm": NaN,
 "learning_rate": 0.0001925077206834458,
 "loss": 0.0,
 "step": 162
 },
 {
 "epoch": 0.8931506849315068,
 "grad_norm": NaN,
 "learning_rate": 0.0001922672739870115,
 "loss": 0.0,
 "step": 163
 },
 {
 "epoch": 0.8986301369863013,
 "grad_norm": NaN,
 "learning_rate": 0.00019202318473658705,
 "loss": 0.0,
 "step": 164
 },
 {
 "epoch": 0.9041095890410958,
 "grad_norm": NaN,
 "learning_rate": 0.00019177546256839812,
 "loss": 0.0,
 "step": 165
 },
 {
 "epoch": 0.9095890410958904,
 "grad_norm": NaN,
 "learning_rate": 0.00019152411726209176,
 "loss": 0.0,
 "step": 166
 },
 {
 "epoch": 0.915068493150685,
 "grad_norm": NaN,
 "learning_rate": 0.0001912691587403503,
 "loss": 0.0,
 "step": 167
 },
 {
 "epoch": 0.9205479452054794,
 "grad_norm": NaN,
 "learning_rate": 0.00019101059706849957,
 "loss": 0.0,
 "step": 168
 },
 {
 "epoch": 0.9260273972602739,
 "grad_norm": NaN,
 "learning_rate": 0.0001907484424541117,
 "loss": 0.0,
 "step": 169
 },
 {
 "epoch": 0.9315068493150684,
 "grad_norm": NaN,
 "learning_rate": 0.00019048270524660196,
 "loss": 0.0,
 "step": 170
 },
 {
 "epoch": 0.936986301369863,
 "grad_norm": NaN,
 "learning_rate": 0.00019021339593682028,
 "loss": 0.0,
 "step": 171
 },
 {
 "epoch": 0.9424657534246575,
 "grad_norm": NaN,
 "learning_rate": 0.0001899405251566371,
 "loss": 0.0,
 "step": 172
 },
 {
 "epoch": 0.947945205479452,
 "grad_norm": NaN,
 "learning_rate": 0.00018966410367852362,
 "loss": 0.0,
 "step": 173
 },
 {
 "epoch": 0.9534246575342465,
 "grad_norm": NaN,
 "learning_rate": 0.0001893841424151264,
 "loss": 0.0,
 "step": 174
 },
 {
 "epoch": 0.958904109589041,
 "grad_norm": NaN,
 "learning_rate": 0.0001891006524188368,
 "loss": 0.0,
 "step": 175
 },
 {
 "epoch": 0.9643835616438357,
 "grad_norm": NaN,
 "learning_rate": 0.00018881364488135448,
 "loss": 0.0,
 "step": 176
 },
 {
 "epoch": 0.9698630136986301,
 "grad_norm": NaN,
 "learning_rate": 0.00018852313113324552,
 "loss": 0.0,
 "step": 177
 },
 {
 "epoch": 0.9753424657534246,
 "grad_norm": NaN,
 "learning_rate": 0.00018822912264349534,
 "loss": 0.0,
 "step": 178
 },
 {
 "epoch": 0.9808219178082191,
 "grad_norm": NaN,
 "learning_rate": 0.00018793163101905563,
 "loss": 0.0,
 "step": 179
 },
 {
 "epoch": 0.9863013698630136,
 "grad_norm": NaN,
 "learning_rate": 0.00018763066800438636,
 "loss": 0.0,
 "step": 180
 },
 {
 "epoch": 0.9917808219178083,
 "grad_norm": NaN,
 "learning_rate": 0.00018732624548099204,
 "loss": 0.0,
 "step": 181
 },
 {
 "epoch": 0.9972602739726028,
 "grad_norm": NaN,
 "learning_rate": 0.0001870183754669526,
 "loss": 0.0,
 "step": 182
 },
 {
 "epoch": 0.9972602739726028,
 "eval_loss": NaN,
 "eval_runtime": 23.1988,
 "eval_samples_per_second": 52.977,
 "eval_steps_per_second": 1.681,
 "step": 182
 },
 {
 "epoch": 1.0027397260273974,
 "grad_norm": NaN,
 "learning_rate": 0.000186707070116449,
 "loss": 0.0,
 "step": 183
 },
 {
 "epoch": 1.0082191780821919,
 "grad_norm": NaN,
 "learning_rate": 0.00018639234171928353,
 "loss": 0.0,
 "step": 184
 },
 {
 "epoch": 1.0136986301369864,
 "grad_norm": NaN,
 "learning_rate": 0.0001860742027003944,
 "loss": 0.0,
 "step": 185
 },
 {
 "epoch": 1.0191780821917809,
 "grad_norm": NaN,
 "learning_rate": 0.00018575266561936523,
 "loss": 0.0,
 "step": 186
 },
 {
 "epoch": 1.0246575342465754,
 "grad_norm": NaN,
 "learning_rate": 0.0001854277431699295,
 "loss": 0.0,
 "step": 187
 },
 {
 "epoch": 1.0301369863013699,
 "grad_norm": NaN,
 "learning_rate": 0.00018509944817946922,
 "loss": 0.0,
 "step": 188
 },
 {
 "epoch": 1.0356164383561643,
 "grad_norm": NaN,
 "learning_rate": 0.00018476779360850832,
 "loss": 0.0,
 "step": 189
 },
 {
 "epoch": 1.0410958904109588,
 "grad_norm": NaN,
 "learning_rate": 0.00018443279255020152,
 "loss": 0.0,
 "step": 190
 },
 {
 "epoch": 1.0465753424657533,
 "grad_norm": NaN,
 "learning_rate": 0.00018409445822981693,
 "loss": 0.0,
 "step": 191
 },
 {
 "epoch": 1.0520547945205478,
 "grad_norm": NaN,
 "learning_rate": 0.0001837528040042142,
 "loss": 0.0,
 "step": 192
 },
 {
 "epoch": 1.0575342465753426,
 "grad_norm": NaN,
 "learning_rate": 0.00018340784336131713,
 "loss": 0.0,
 "step": 193
 },
 {
 "epoch": 1.063013698630137,
 "grad_norm": NaN,
 "learning_rate": 0.00018305958991958127,
 "loss": 0.0,
 "step": 194
 },
 {
 "epoch": 1.0684931506849316,
 "grad_norm": NaN,
 "learning_rate": 0.00018270805742745617,
 "loss": 0.0,
 "step": 195
 },
 {
 "epoch": 1.073972602739726,
 "grad_norm": NaN,
 "learning_rate": 0.00018235325976284275,
 "loss": 0.0,
 "step": 196
 },
 {
 "epoch": 1.0794520547945206,
 "grad_norm": NaN,
 "learning_rate": 0.00018199521093254523,
 "loss": 0.0,
 "step": 197
 },
 {
 "epoch": 1.084931506849315,
 "grad_norm": NaN,
 "learning_rate": 0.00018163392507171842,
 "loss": 0.0,
 "step": 198
 },
 {
 "epoch": 1.0904109589041096,
 "grad_norm": NaN,
 "learning_rate": 0.0001812694164433094,
 "loss": 0.0,
 "step": 199
 },
 {
 "epoch": 1.095890410958904,
 "grad_norm": NaN,
 "learning_rate": 0.00018090169943749476,
 "loss": 0.0,
 "step": 200
 },
 {
 "epoch": 1.1013698630136985,
 "grad_norm": NaN,
 "learning_rate": 0.0001805307885711122,
 "loss": 0.0,
 "step": 201
 },
 {
 "epoch": 1.106849315068493,
 "grad_norm": NaN,
 "learning_rate": 0.00018015669848708767,
 "loss": 0.0,
 "step": 202
 },
 {
 "epoch": 1.1123287671232878,
 "grad_norm": NaN,
 "learning_rate": 0.0001797794439538571,
 "loss": 0.0,
 "step": 203
 },
 {
 "epoch": 1.1178082191780823,
 "grad_norm": NaN,
 "learning_rate": 0.00017939903986478355,
 "loss": 0.0,
 "step": 204
 },
 {
 "epoch": 1.1232876712328768,
 "grad_norm": NaN,
 "learning_rate": 0.00017901550123756906,
 "loss": 0.0,
 "step": 205
 },
 {
 "epoch": 1.1287671232876713,
 "grad_norm": NaN,
 "learning_rate": 0.00017862884321366188,
 "loss": 0.0,
 "step": 206
 },
 {
 "epoch": 1.1342465753424658,
 "grad_norm": NaN,
 "learning_rate": 0.0001782390810576588,
 "loss": 0.0,
 "step": 207
 },
 {
 "epoch": 1.1397260273972603,
 "grad_norm": NaN,
 "learning_rate": 0.00017784623015670238,
 "loss": 0.0,
 "step": 208
 },
 {
 "epoch": 1.1452054794520548,
 "grad_norm": NaN,
 "learning_rate": 0.00017745030601987337,
 "loss": 0.0,
 "step": 209
 },
 {
 "epoch": 1.1506849315068493,
 "grad_norm": NaN,
 "learning_rate": 0.00017705132427757895,
 "loss": 0.0,
 "step": 210
 },
 {
 "epoch": 1.1561643835616437,
 "grad_norm": NaN,
 "learning_rate": 0.00017664930068093498,
 "loss": 0.0,
 "step": 211
 },
 {
 "epoch": 1.1616438356164385,
 "grad_norm": NaN,
 "learning_rate": 0.0001762442511011448,
 "loss": 0.0,
 "step": 212
 },
 {
 "epoch": 1.167123287671233,
 "grad_norm": NaN,
 "learning_rate": 0.0001758361915288722,
 "loss": 0.0,
 "step": 213
 },
 {
 "epoch": 1.1726027397260275,
 "grad_norm": NaN,
 "learning_rate": 0.00017542513807361037,
 "loss": 0.0,
 "step": 214
 },
 {
 "epoch": 1.178082191780822,
 "grad_norm": NaN,
 "learning_rate": 0.00017501110696304596,
 "loss": 0.0,
 "step": 215
 },
 {
 "epoch": 1.1835616438356165,
 "grad_norm": NaN,
 "learning_rate": 0.00017459411454241822,
 "loss": 0.0,
 "step": 216
 },
 {
 "epoch": 1.189041095890411,
 "grad_norm": NaN,
 "learning_rate": 0.00017417417727387394,
 "loss": 0.0,
 "step": 217
 },
 {
 "epoch": 1.1945205479452055,
 "grad_norm": NaN,
 "learning_rate": 0.0001737513117358174,
 "loss": 0.0,
 "step": 218
 },
 {
 "epoch": 1.2,
 "grad_norm": NaN,
 "learning_rate": 0.00017332553462225602,
 "loss": 0.0,
 "step": 219
 },
 {
 "epoch": 1.2054794520547945,
 "grad_norm": NaN,
 "learning_rate": 0.00017289686274214118,
 "loss": 0.0,
 "step": 220
 },
 {
 "epoch": 1.210958904109589,
 "grad_norm": NaN,
 "learning_rate": 0.0001724653130187047,
 "loss": 0.0,
 "step": 221
 },
 {
 "epoch": 1.2164383561643834,
 "grad_norm": NaN,
 "learning_rate": 0.0001720309024887907,
 "loss": 0.0,
 "step": 222
 },
 {
 "epoch": 1.2219178082191782,
 "grad_norm": NaN,
 "learning_rate": 0.00017159364830218312,
 "loss": 0.0,
 "step": 223
 },
 {
 "epoch": 1.2273972602739727,
 "grad_norm": NaN,
 "learning_rate": 0.00017115356772092857,
 "loss": 0.0,
 "step": 224
 },
 {
 "epoch": 1.2328767123287672,
 "grad_norm": NaN,
 "learning_rate": 0.00017071067811865476,
 "loss": 0.0,
 "step": 225
 },
 {
 "epoch": 1.2383561643835617,
 "grad_norm": NaN,
 "learning_rate": 0.00017026499697988493,
 "loss": 0.0,
 "step": 226
 },
 {
 "epoch": 1.2438356164383562,
 "grad_norm": NaN,
 "learning_rate": 0.00016981654189934727,
 "loss": 0.0,
 "step": 227
 },
 {
 "epoch": 1.2493150684931507,
 "grad_norm": NaN,
 "learning_rate": 0.0001693653305812805,
 "loss": 0.0,
 "step": 228
 },
 {
 "epoch": 1.2547945205479452,
 "grad_norm": NaN,
 "learning_rate": 0.00016891138083873487,
 "loss": 0.0,
 "step": 229
 },
 {
 "epoch": 1.2602739726027397,
 "grad_norm": NaN,
 "learning_rate": 0.00016845471059286887,
 "loss": 0.0,
 "step": 230
 },
 {
 "epoch": 1.2657534246575342,
 "grad_norm": NaN,
 "learning_rate": 0.00016799533787224192,
 "loss": 0.0,
 "step": 231
 },
 {
 "epoch": 1.2712328767123289,
 "grad_norm": NaN,
 "learning_rate": 0.00016753328081210245,
 "loss": 0.0,
 "step": 232
 },
 {
 "epoch": 1.2767123287671232,
 "grad_norm": NaN,
 "learning_rate": 0.000167068557653672,
 "loss": 0.0,
 "step": 233
 },
 {
 "epoch": 1.2821917808219179,
 "grad_norm": NaN,
 "learning_rate": 0.00016660118674342517,
 "loss": 0.0,
 "step": 234
 },
 {
 "epoch": 1.2876712328767124,
 "grad_norm": NaN,
 "learning_rate": 0.00016613118653236518,
 "loss": 0.0,
 "step": 235
 },
 {
 "epoch": 1.2931506849315069,
 "grad_norm": NaN,
 "learning_rate": 0.00016565857557529566,
 "loss": 0.0,
 "step": 236
 },
 {
 "epoch": 1.2986301369863014,
 "grad_norm": NaN,
 "learning_rate": 0.0001651833725300879,
 "loss": 0.0,
 "step": 237
 },
 {
 "epoch": 1.3041095890410959,
 "grad_norm": NaN,
 "learning_rate": 0.00016470559615694446,
 "loss": 0.0,
 "step": 238
 },
 {
 "epoch": 1.3095890410958904,
 "grad_norm": NaN,
 "learning_rate": 0.00016422526531765846,
 "loss": 0.0,
 "step": 239
 },
 {
 "epoch": 1.3150684931506849,
 "grad_norm": NaN,
 "learning_rate": 0.000163742398974869,
 "loss": 0.0,
 "step": 240
 },
 {
 "epoch": 1.3205479452054796,
 "grad_norm": NaN,
 "learning_rate": 0.00016325701619131246,
 "loss": 0.0,
 "step": 241
 },
 {
 "epoch": 1.3260273972602739,
 "grad_norm": NaN,
 "learning_rate": 0.00016276913612907007,
 "loss": 0.0,
 "step": 242
 },
 {
 "epoch": 1.3315068493150686,
 "grad_norm": NaN,
 "learning_rate": 0.00016227877804881127,
 "loss": 0.0,
 "step": 243
 },
 {
 "epoch": 1.336986301369863,
 "grad_norm": NaN,
 "learning_rate": 0.00016178596130903344,
 "loss": 0.0,
 "step": 244
 },
 {
 "epoch": 1.3424657534246576,
 "grad_norm": NaN,
 "learning_rate": 0.00016129070536529766,
 "loss": 0.0,
 "step": 245
 },
 {
 "epoch": 1.347945205479452,
 "grad_norm": NaN,
 "learning_rate": 0.00016079302976946055,
 "loss": 0.0,
 "step": 246
 },
 {
 "epoch": 1.3534246575342466,
 "grad_norm": NaN,
 "learning_rate": 0.00016029295416890248,
 "loss": 0.0,
 "step": 247
 },
 {
 "epoch": 1.358904109589041,
 "grad_norm": NaN,
 "learning_rate": 0.0001597904983057519,
 "loss": 0.0,
 "step": 248
 },
 {
 "epoch": 1.3643835616438356,
 "grad_norm": NaN,
 "learning_rate": 0.00015928568201610595,
 "loss": 0.0,
 "step": 249
 },
 {
 "epoch": 1.36986301369863,
 "grad_norm": NaN,
 "learning_rate": 0.00015877852522924732,
 "loss": 0.0,
 "step": 250
 },
 {
 "epoch": 1.3753424657534246,
 "grad_norm": NaN,
 "learning_rate": 0.00015826904796685762,
 "loss": 0.0,
 "step": 251
 },
 {
 "epoch": 1.3808219178082193,
 "grad_norm": NaN,
 "learning_rate": 0.00015775727034222675,
 "loss": 0.0,
 "step": 252
 },
 {
 "epoch": 1.3863013698630138,
 "grad_norm": NaN,
 "learning_rate": 0.0001572432125594591,
 "loss": 0.0,
 "step": 253
 },
 {
 "epoch": 1.3917808219178083,
 "grad_norm": NaN,
 "learning_rate": 0.00015672689491267567,
 "loss": 0.0,
 "step": 254
 },
 {
 "epoch": 1.3972602739726028,
 "grad_norm": NaN,
 "learning_rate": 0.00015620833778521307,
 "loss": 0.0,
 "step": 255
 },
 {
 "epoch": 1.4027397260273973,
 "grad_norm": NaN,
 "learning_rate": 0.00015568756164881882,
 "loss": 0.0,
 "step": 256
 },
 {
 "epoch": 1.4082191780821918,
 "grad_norm": NaN,
 "learning_rate": 0.00015516458706284303,
 "loss": 0.0,
 "step": 257
 },
 {
 "epoch": 1.4136986301369863,
 "grad_norm": NaN,
 "learning_rate": 0.00015463943467342693,
 "loss": 0.0,
 "step": 258
 },
 {
 "epoch": 1.4191780821917808,
 "grad_norm": NaN,
 "learning_rate": 0.00015411212521268758,
 "loss": 0.0,
 "step": 259
 },
 {
 "epoch": 1.4246575342465753,
 "grad_norm": NaN,
 "learning_rate": 0.00015358267949789966,
 "loss": 0.0,
 "step": 260
 },
 {
 "epoch": 1.43013698630137,
 "grad_norm": NaN,
 "learning_rate": 0.0001530511184306734,
 "loss": 0.0,
 "step": 261
 },
 {
 "epoch": 1.4356164383561643,
 "grad_norm": NaN,
 "learning_rate": 0.0001525174629961296,
 "loss": 0.0,
 "step": 262
 },
 {
 "epoch": 1.441095890410959,
 "grad_norm": NaN,
 "learning_rate": 0.00015198173426207094,
 "loss": 0.0,
 "step": 263
 },
 {
 "epoch": 1.4465753424657535,
 "grad_norm": NaN,
 "learning_rate": 0.00015144395337815064,
 "loss": 0.0,
 "step": 264
 },
 {
 "epoch": 1.452054794520548,
 "grad_norm": NaN,
 "learning_rate": 0.00015090414157503714,
 "loss": 0.0,
 "step": 265
 },
 {
 "epoch": 1.4575342465753425,
 "grad_norm": NaN,
 "learning_rate": 0.0001503623201635761,
 "loss": 0.0,
 "step": 266
 },
 {
 "epoch": 1.463013698630137,
 "grad_norm": NaN,
 "learning_rate": 0.0001498185105339491,
 "loss": 0.0,
 "step": 267
 },
 {
 "epoch": 1.4684931506849315,
 "grad_norm": NaN,
 "learning_rate": 0.00014927273415482915,
 "loss": 0.0,
 "step": 268
 },
 {
 "epoch": 1.473972602739726,
 "grad_norm": NaN,
 "learning_rate": 0.00014872501257253323,
 "loss": 0.0,
 "step": 269
 },
 {
 "epoch": 1.4794520547945205,
 "grad_norm": NaN,
 "learning_rate": 0.00014817536741017152,
 "loss": 0.0,
 "step": 270
 },
 {
 "epoch": 1.484931506849315,
 "grad_norm": NaN,
 "learning_rate": 0.0001476238203667939,
 "loss": 0.0,
 "step": 271
 },
 {
 "epoch": 1.4904109589041097,
 "grad_norm": NaN,
 "learning_rate": 0.0001470703932165333,
 "loss": 0.0,
 "step": 272
 },
 {
 "epoch": 1.4958904109589042,
 "grad_norm": NaN,
 "learning_rate": 0.00014651510780774583,
 "loss": 0.0,
 "step": 273
 },
 {
 "epoch": 1.5013698630136987,
 "grad_norm": NaN,
 "learning_rate": 0.00014595798606214882,
 "loss": 0.0,
 "step": 274
 },
 {
 "epoch": 1.5068493150684932,
 "grad_norm": NaN,
 "learning_rate": 0.00014539904997395468,
 "loss": 0.0,
 "step": 275
 },
 {
 "epoch": 1.5123287671232877,
 "grad_norm": NaN,
 "learning_rate": 0.00014483832160900326,
 "loss": 0.0,
 "step": 276
 },
 {
 "epoch": 1.5178082191780822,
 "grad_norm": NaN,
 "learning_rate": 0.0001442758231038902,
 "loss": 0.0,
 "step": 277
 },
 {
 "epoch": 1.5232876712328767,
 "grad_norm": NaN,
 "learning_rate": 0.0001437115766650933,
 "loss": 0.0,
 "step": 278
 },
 {
 "epoch": 1.5287671232876714,
 "grad_norm": NaN,
 "learning_rate": 0.0001431456045680959,
 "loss": 0.0,
 "step": 279
 },
 {
 "epoch": 1.5342465753424657,
 "grad_norm": NaN,
 "learning_rate": 0.00014257792915650728,
 "loss": 0.0,
 "step": 280
 },
 {
 "epoch": 1.5397260273972604,
 "grad_norm": NaN,
 "learning_rate": 0.00014200857284118066,
 "loss": 0.0,
 "step": 281
 },
 {
 "epoch": 1.5452054794520547,
 "grad_norm": NaN,
 "learning_rate": 0.00014143755809932845,
 "loss": 0.0,
 "step": 282
 },
 {
 "epoch": 1.5506849315068494,
 "grad_norm": NaN,
 "learning_rate": 0.00014086490747363493,
 "loss": 0.0,
 "step": 283
 },
 {
 "epoch": 1.5561643835616439,
 "grad_norm": NaN,
 "learning_rate": 0.00014029064357136628,
 "loss": 0.0,
 "step": 284
 },
 {
 "epoch": 1.5616438356164384,
 "grad_norm": NaN,
 "learning_rate": 0.00013971478906347806,
 "loss": 0.0,
 "step": 285
 },
 {
 "epoch": 1.5671232876712329,
 "grad_norm": NaN,
 "learning_rate": 0.00013913736668372026,
 "loss": 0.0,
 "step": 286
 },
 {
 "epoch": 1.5726027397260274,
 "grad_norm": NaN,
 "learning_rate": 0.00013855839922773968,
 "loss": 0.0,
 "step": 287
 },
 {
 "epoch": 1.5780821917808219,
 "grad_norm": NaN,
 "learning_rate": 0.00013797790955218014,
 "loss": 0.0,
 "step": 288
 },
 {
 "epoch": 1.5835616438356164,
 "grad_norm": NaN,
 "learning_rate": 0.00013739592057378003,
 "loss": 0.0,
 "step": 289
 },
 {
 "epoch": 1.589041095890411,
 "grad_norm": NaN,
 "learning_rate": 0.00013681245526846783,
 "loss": 0.0,
 "step": 290
 },
 {
 "epoch": 1.5945205479452054,
 "grad_norm": NaN,
 "learning_rate": 0.00013622753667045457,
 "loss": 0.0,
 "step": 291
 },
 {
 "epoch": 1.6,
 "grad_norm": NaN,
 "learning_rate": 0.00013564118787132506,
 "loss": 0.0,
 "step": 292
 },
 {
 "epoch": 1.6054794520547944,
 "grad_norm": NaN,
 "learning_rate": 0.0001350534320191259,
 "loss": 0.0,
 "step": 293
 },
 {
 "epoch": 1.610958904109589,
 "grad_norm": NaN,
 "learning_rate": 0.0001344642923174517,
 "loss": 0.0,
 "step": 294
 },
 {
 "epoch": 1.6164383561643836,
 "grad_norm": NaN,
 "learning_rate": 0.00013387379202452917,
 "loss": 0.0,
 "step": 295
 },
 {
 "epoch": 1.621917808219178,
 "grad_norm": NaN,
 "learning_rate": 0.00013328195445229868,
 "loss": 0.0,
 "step": 296
 },
 {
 "epoch": 1.6273972602739726,
 "grad_norm": NaN,
 "learning_rate": 0.00013268880296549425,
 "loss": 0.0,
 "step": 297
 },
 {
 "epoch": 1.632876712328767,
 "grad_norm": NaN,
 "learning_rate": 0.00013209436098072095,
 "loss": 0.0,
 "step": 298
 },
 {
 "epoch": 1.6383561643835618,
 "grad_norm": NaN,
 "learning_rate": 0.0001314986519655305,
 "loss": 0.0,
 "step": 299
 },
 {
 "epoch": 1.643835616438356,
 "grad_norm": NaN,
 "learning_rate": 0.00013090169943749476,
 "loss": 0.0,
 "step": 300
 },
 {
 "epoch": 1.6493150684931508,
 "grad_norm": NaN,
 "learning_rate": 0.00013030352696327742,
 "loss": 0.0,
 "step": 301
 },
 {
 "epoch": 1.654794520547945,
 "grad_norm": NaN,
 "learning_rate": 0.0001297041581577035,
 "loss": 0.0,
 "step": 302
 },
 {
 "epoch": 1.6602739726027398,
 "grad_norm": NaN,
 "learning_rate": 0.00012910361668282719,
 "loss": 0.0,
 "step": 303
 },
 {
 "epoch": 1.6657534246575343,
 "grad_norm": NaN,
 "learning_rate": 0.0001285019262469976,
 "loss": 0.0,
 "step": 304
 },
 {
 "epoch": 1.6712328767123288,
 "grad_norm": NaN,
 "learning_rate": 0.00012789911060392294,
 "loss": 0.0,
 "step": 305
 },
 {
 "epoch": 1.6767123287671233,
 "grad_norm": NaN,
 "learning_rate": 0.00012729519355173254,
 "loss": 0.0,
 "step": 306
 },
 {
 "epoch": 1.6821917808219178,
 "grad_norm": NaN,
 "learning_rate": 0.00012669019893203759,
 "loss": 0.0,
 "step": 307
 },
 {
 "epoch": 1.6876712328767123,
 "grad_norm": NaN,
 "learning_rate": 0.00012608415062898972,
 "loss": 0.0,
 "step": 308
 },
 {
 "epoch": 1.6931506849315068,
 "grad_norm": NaN,
 "learning_rate": 0.00012547707256833823,
 "loss": 0.0,
 "step": 309
 },
 {
 "epoch": 1.6986301369863015,
 "grad_norm": NaN,
 "learning_rate": 0.0001248689887164855,
 "loss": 0.0,
 "step": 310
 },
 {
 "epoch": 1.7041095890410958,
 "grad_norm": NaN,
 "learning_rate": 0.00012425992307954075,
 "loss": 0.0,
 "step": 311
 },
 {
 "epoch": 1.7095890410958905,
 "grad_norm": NaN,
 "learning_rate": 0.00012364989970237248,
 "loss": 0.0,
 "step": 312
 },
 {
 "epoch": 1.7150684931506848,
 "grad_norm": NaN,
 "learning_rate": 0.00012303894266765908,
 "loss": 0.0,
 "step": 313
 },
 {
 "epoch": 1.7205479452054795,
 "grad_norm": NaN,
 "learning_rate": 0.00012242707609493814,
 "loss": 0.0,
 "step": 314
 },
 {
 "epoch": 1.726027397260274,
 "grad_norm": NaN,
 "learning_rate": 0.00012181432413965428,
 "loss": 0.0,
 "step": 315
 },
 {
 "epoch": 1.7315068493150685,
 "grad_norm": NaN,
 "learning_rate": 0.00012120071099220549,
 "loss": 0.0,
 "step": 316
 },
 {
 "epoch": 1.736986301369863,
 "grad_norm": NaN,
 "learning_rate": 0.00012058626087698814,
 "loss": 0.0,
 "step": 317
 },
 {
 "epoch": 1.7424657534246575,
 "grad_norm": NaN,
 "learning_rate": 0.00011997099805144069,
 "loss": 0.0,
 "step": 318
 },
 {
 "epoch": 1.7479452054794522,
 "grad_norm": NaN,
 "learning_rate": 0.00011935494680508606,
 "loss": 0.0,
 "step": 319
 },
 {
 "epoch": 1.7534246575342465,
 "grad_norm": NaN,
 "learning_rate": 0.00011873813145857249,
 "loss": 0.0,
 "step": 320
 },
 {
 "epoch": 1.7589041095890412,
 "grad_norm": NaN,
 "learning_rate": 0.00011812057636271374,
 "loss": 0.0,
 "step": 321
 },
 {
 "epoch": 1.7643835616438355,
 "grad_norm": NaN,
 "learning_rate": 0.00011750230589752762,
 "loss": 0.0,
 "step": 322
 },
 {
 "epoch": 1.7698630136986302,
 "grad_norm": NaN,
 "learning_rate": 0.00011688334447127338,
 "loss": 0.0,
 "step": 323
 },
 {
 "epoch": 1.7753424657534247,
 "grad_norm": NaN,
 "learning_rate": 0.00011626371651948838,
 "loss": 0.0,
 "step": 324
 },
 {
 "epoch": 1.7808219178082192,
 "grad_norm": NaN,
 "learning_rate": 0.0001156434465040231,
 "loss": 0.0,
 "step": 325
 },
 {
 "epoch": 1.7863013698630137,
 "grad_norm": NaN,
 "learning_rate": 0.00011502255891207572,
 "loss": 0.0,
 "step": 326
 },
 {
 "epoch": 1.7917808219178082,
 "grad_norm": NaN,
 "learning_rate": 0.00011440107825522521,
 "loss": 0.0,
 "step": 327
 },
 {
 "epoch": 1.7972602739726027,
 "grad_norm": NaN,
 "learning_rate": 0.0001137790290684638,
 "loss": 0.0,
 "step": 328
 },
 {
 "epoch": 1.8027397260273972,
 "grad_norm": NaN,
 "learning_rate": 0.00011315643590922827,
 "loss": 0.0,
 "step": 329
 },
 {
 "epoch": 1.808219178082192,
 "grad_norm": NaN,
 "learning_rate": 0.00011253332335643043,
 "loss": 0.0,
 "step": 330
 },
 {
 "epoch": 1.8136986301369862,
 "grad_norm": NaN,
 "learning_rate": 0.00011190971600948699,
 "loss": 0.0,
 "step": 331
 },
 {
 "epoch": 1.819178082191781,
 "grad_norm": NaN,
 "learning_rate": 0.00011128563848734816,
 "loss": 0.0,
 "step": 332
 },
 {
 "epoch": 1.8246575342465754,
 "grad_norm": NaN,
 "learning_rate": 0.000110661115427526,
 "loss": 0.0,
 "step": 333
 },
 {
 "epoch": 1.83013698630137,
 "grad_norm": NaN,
 "learning_rate": 0.00011003617148512149,
 "loss": 0.0,
 "step": 334
 },
 {
 "epoch": 1.8356164383561644,
 "grad_norm": NaN,
 "learning_rate": 0.00010941083133185146,
 "loss": 0.0,
 "step": 335
 },
 {
 "epoch": 1.841095890410959,
 "grad_norm": NaN,
 "learning_rate": 0.00010878511965507434,
 "loss": 0.0,
 "step": 336
 },
 {
 "epoch": 1.8465753424657534,
 "grad_norm": NaN,
 "learning_rate": 0.00010815906115681578,
 "loss": 0.0,
 "step": 337
 },
 {
 "epoch": 1.8520547945205479,
 "grad_norm": NaN,
 "learning_rate": 0.00010753268055279329,
 "loss": 0.0,
 "step": 338
 },
 {
 "epoch": 1.8575342465753426,
 "grad_norm": NaN,
 "learning_rate": 0.00010690600257144061,
 "loss": 0.0,
 "step": 339
 },
 {
 "epoch": 1.8630136986301369,
 "grad_norm": NaN,
 "learning_rate": 0.00010627905195293135,
 "loss": 0.0,
 "step": 340
 },
 {
 "epoch": 1.8684931506849316,
 "grad_norm": NaN,
 "learning_rate": 0.00010565185344820247,
 "loss": 0.0,
 "step": 341
 },
 {
 "epoch": 1.8739726027397259,
 "grad_norm": NaN,
 "learning_rate": 0.00010502443181797697,
 "loss": 0.0,
 "step": 342
 },
 {
 "epoch": 1.8794520547945206,
 "grad_norm": NaN,
 "learning_rate": 0.0001043968118317865,
 "loss": 0.0,
 "step": 343
 },
 {
 "epoch": 1.884931506849315,
 "grad_norm": NaN,
 "learning_rate": 0.00010376901826699348,
 "loss": 0.0,
 "step": 344
 },
 {
 "epoch": 1.8904109589041096,
 "grad_norm": NaN,
 "learning_rate": 0.00010314107590781284,
 "loss": 0.0,
 "step": 345
 },
 {
 "epoch": 1.895890410958904,
 "grad_norm": NaN,
 "learning_rate": 0.00010251300954433376,
 "loss": 0.0,
 "step": 346
 },
 {
 "epoch": 1.9013698630136986,
 "grad_norm": NaN,
 "learning_rate": 0.00010188484397154084,
 "loss": 0.0,
 "step": 347
 },
 {
 "epoch": 1.9068493150684933,
 "grad_norm": NaN,
 "learning_rate": 0.00010125660398833528,
 "loss": 0.0,
 "step": 348
 },
 {
 "epoch": 1.9123287671232876,
 "grad_norm": NaN,
 "learning_rate": 0.00010062831439655591,
 "loss": 0.0,
 "step": 349
 },
 {
 "epoch": 1.9178082191780823,
 "grad_norm": NaN,
 "learning_rate": 0.0001,
 "loss": 0.0,
 "step": 350
 },
 {
 "epoch": 1.9232876712328766,
 "grad_norm": NaN,
 "learning_rate": 9.937168560344412e-05,
 "loss": 0.0,
 "step": 351
 },
 {
 "epoch": 1.9287671232876713,
 "grad_norm": NaN,
 "learning_rate": 9.874339601166473e-05,
 "loss": 0.0,
 "step": 352
 },
 {
 "epoch": 1.9342465753424658,
 "grad_norm": NaN,
 "learning_rate": 9.81151560284592e-05,
 "loss": 0.0,
 "step": 353
 },
 {
 "epoch": 1.9397260273972603,
 "grad_norm": NaN,
 "learning_rate": 9.748699045566626e-05,
 "loss": 0.0,
 "step": 354
 },
 {
 "epoch": 1.9452054794520548,
 "grad_norm": NaN,
 "learning_rate": 9.685892409218717e-05,
 "loss": 0.0,
 "step": 355
 },
 {
 "epoch": 1.9506849315068493,
 "grad_norm": NaN,
 "learning_rate": 9.623098173300654e-05,
 "loss": 0.0,
 "step": 356
 },
 {
 "epoch": 1.9561643835616438,
 "grad_norm": NaN,
 "learning_rate": 9.560318816821353e-05,
 "loss": 0.0,
 "step": 357
 },
 {
 "epoch": 1.9616438356164383,
 "grad_norm": NaN,
 "learning_rate": 9.497556818202306e-05,
 "loss": 0.0,
 "step": 358
 },
 {
 "epoch": 1.967123287671233,
 "grad_norm": NaN,
 "learning_rate": 9.434814655179755e-05,
 "loss": 0.0,
 "step": 359
 },
 {
 "epoch": 1.9726027397260273,
 "grad_norm": NaN,
 "learning_rate": 9.372094804706867e-05,
 "loss": 0.0,
 "step": 360
 },
 {
 "epoch": 1.978082191780822,
 "grad_norm": NaN,
 "learning_rate": 9.309399742855942e-05,
 "loss": 0.0,
 "step": 361
 },
 {
 "epoch": 1.9835616438356163,
 "grad_norm": NaN,
 "learning_rate": 9.246731944720675e-05,
 "loss": 0.0,
 "step": 362
 },
 {
 "epoch": 1.989041095890411,
 "grad_norm": NaN,
 "learning_rate": 9.184093884318425e-05,
 "loss": 0.0,
 "step": 363
 },
 {
 "epoch": 1.9945205479452055,
 "grad_norm": NaN,
 "learning_rate": 9.121488034492569e-05,
 "loss": 0.0,
 "step": 364
 },
 {
 "epoch": 2.0,
 "grad_norm": NaN,
 "learning_rate": 9.058916866814858e-05,
 "loss": 0.0,
 "step": 365
 },
 {
 "epoch": 2.0,
 "eval_loss": NaN,
 "eval_runtime": 17.6847,
 "eval_samples_per_second": 69.495,
 "eval_steps_per_second": 2.205,
 "step": 365
 },
 {
 "epoch": 2.0054794520547947,
 "grad_norm": NaN,
 "learning_rate": 8.99638285148785e-05,
 "loss": 0.0,
 "step": 366
 },
 {
 "epoch": 2.010958904109589,
 "grad_norm": NaN,
 "learning_rate": 8.933888457247402e-05,
 "loss": 0.0,
 "step": 367
 },
 {
 "epoch": 2.0164383561643837,
 "grad_norm": NaN,
 "learning_rate": 8.871436151265184e-05,
 "loss": 0.0,
 "step": 368
 },
 {
 "epoch": 2.021917808219178,
 "grad_norm": NaN,
 "learning_rate": 8.809028399051302e-05,
 "loss": 0.0,
 "step": 369
 },
 {
 "epoch": 2.0273972602739727,
 "grad_norm": NaN,
 "learning_rate": 8.746667664356956e-05,
 "loss": 0.0,
 "step": 370
 },
 {
 "epoch": 2.032876712328767,
 "grad_norm": NaN,
 "learning_rate": 8.684356409077176e-05,
 "loss": 0.0,
 "step": 371
 },
 {
 "epoch": 2.0383561643835617,
 "grad_norm": NaN,
 "learning_rate": 8.62209709315362e-05,
 "loss": 0.0,
 "step": 372
 },
 {
 "epoch": 2.043835616438356,
 "grad_norm": NaN,
 "learning_rate": 8.559892174477479e-05,
 "loss": 0.0,
 "step": 373
 },
 {
 "epoch": 2.0493150684931507,
 "grad_norm": NaN,
 "learning_rate": 8.497744108792429e-05,
 "loss": 0.0,
 "step": 374
 },
 {
 "epoch": 2.0547945205479454,
 "grad_norm": NaN,
 "learning_rate": 8.435655349597689e-05,
 "loss": 0.0,
 "step": 375
 },
 {
 "epoch": 2.0602739726027397,
 "grad_norm": NaN,
 "learning_rate": 8.373628348051165e-05,
 "loss": 0.0,
 "step": 376
 },
 {
 "epoch": 2.0657534246575344,
 "grad_norm": NaN,
 "learning_rate": 8.311665552872662e-05,
 "loss": 0.0,
 "step": 377
 },
 {
 "epoch": 2.0712328767123287,
 "grad_norm": NaN,
 "learning_rate": 8.249769410247239e-05,
 "loss": 0.0,
 "step": 378
 },
 {
 "epoch": 2.0767123287671234,
 "grad_norm": NaN,
 "learning_rate": 8.187942363728625e-05,
 "loss": 0.0,
 "step": 379
 },
 {
 "epoch": 2.0821917808219177,
 "grad_norm": NaN,
 "learning_rate": 8.126186854142752e-05,
 "loss": 0.0,
 "step": 380
 },
 {
 "epoch": 2.0876712328767124,
 "grad_norm": NaN,
 "learning_rate": 8.064505319491398e-05,
 "loss": 0.0,
 "step": 381
 },
 {
 "epoch": 2.0931506849315067,
 "grad_norm": NaN,
 "learning_rate": 8.002900194855932e-05,
 "loss": 0.0,
 "step": 382
 },
 {
 "epoch": 2.0986301369863014,
 "grad_norm": NaN,
 "learning_rate": 7.941373912301189e-05,
 "loss": 0.0,
 "step": 383
 },
 {
 "epoch": 2.1041095890410957,
 "grad_norm": NaN,
 "learning_rate": 7.879928900779456e-05,
 "loss": 0.0,
 "step": 384
 },
 {
 "epoch": 2.1095890410958904,
 "grad_norm": NaN,
 "learning_rate": 7.818567586034577e-05,
 "loss": 0.0,
 "step": 385
 },
 {
 "epoch": 2.115068493150685,
 "grad_norm": NaN,
 "learning_rate": 7.75729239050619e-05,
 "loss": 0.0,
 "step": 386
 },
 {
 "epoch": 2.1205479452054794,
 "grad_norm": NaN,
 "learning_rate": 7.696105733234098e-05,
 "loss": 0.0,
 "step": 387
 },
 {
 "epoch": 2.126027397260274,
 "grad_norm": NaN,
 "learning_rate": 7.635010029762756e-05,
 "loss": 0.0,
 "step": 388
 },
 {
 "epoch": 2.1315068493150684,
 "grad_norm": NaN,
 "learning_rate": 7.574007692045928e-05,
 "loss": 0.0,
 "step": 389
 },
 {
 "epoch": 2.136986301369863,
 "grad_norm": NaN,
 "learning_rate": 7.513101128351454e-05,
 "loss": 0.0,
 "step": 390
 },
 {
 "epoch": 2.1424657534246574,
 "grad_norm": NaN,
 "learning_rate": 7.45229274316618e-05,
 "loss": 0.0,
 "step": 391
 },
 {
 "epoch": 2.147945205479452,
 "grad_norm": NaN,
 "learning_rate": 7.391584937101033e-05,
 "loss": 0.0,
 "step": 392
 },
 {
 "epoch": 2.1534246575342464,
 "grad_norm": NaN,
 "learning_rate": 7.330980106796246e-05,
 "loss": 0.0,
 "step": 393
 },
 {
 "epoch": 2.158904109589041,
 "grad_norm": NaN,
 "learning_rate": 7.270480644826749e-05,
 "loss": 0.0,
 "step": 394
 },
 {
 "epoch": 2.1643835616438354,
 "grad_norm": NaN,
 "learning_rate": 7.210088939607708e-05,
 "loss": 0.0,
 "step": 395
 },
 {
 "epoch": 2.16986301369863,
 "grad_norm": NaN,
 "learning_rate": 7.149807375300239e-05,
 "loss": 0.0,
 "step": 396
 },
 {
 "epoch": 2.175342465753425,
 "grad_norm": NaN,
 "learning_rate": 7.089638331717284e-05,
 "loss": 0.0,
 "step": 397
 },
 {
 "epoch": 2.180821917808219,
 "grad_norm": NaN,
 "learning_rate": 7.029584184229653e-05,
 "loss": 0.0,
 "step": 398
 },
 {
 "epoch": 2.186301369863014,
 "grad_norm": NaN,
 "learning_rate": 6.969647303672262e-05,
 "loss": 0.0,
 "step": 399
 },
 {
 "epoch": 2.191780821917808,
 "grad_norm": NaN,
 "learning_rate": 6.909830056250527e-05,
 "loss": 0.0,
 "step": 400
 },
 {
 "epoch": 2.197260273972603,
 "grad_norm": NaN,
 "learning_rate": 6.850134803446954e-05,
 "loss": 0.0,
 "step": 401
 },
 {
 "epoch": 2.202739726027397,
 "grad_norm": NaN,
 "learning_rate": 6.790563901927907e-05,
 "loss": 0.0,
 "step": 402
 },
 {
 "epoch": 2.208219178082192,
 "grad_norm": NaN,
 "learning_rate": 6.731119703450577e-05,
 "loss": 0.0,
 "step": 403
 },
 {
 "epoch": 2.213698630136986,
 "grad_norm": NaN,
 "learning_rate": 6.671804554770135e-05,
 "loss": 0.0,
 "step": 404
 },
 {
 "epoch": 2.219178082191781,
 "grad_norm": NaN,
 "learning_rate": 6.612620797547087e-05,
 "loss": 0.0,
 "step": 405
 },
 {
 "epoch": 2.2246575342465755,
 "grad_norm": NaN,
 "learning_rate": 6.55357076825483e-05,
 "loss": 0.0,
 "step": 406
 },
 {
 "epoch": 2.23013698630137,
 "grad_norm": NaN,
 "learning_rate": 6.494656798087412e-05,
 "loss": 0.0,
 "step": 407
 },
 {
 "epoch": 2.2356164383561645,
 "grad_norm": NaN,
 "learning_rate": 6.435881212867493e-05,
 "loss": 0.0,
 "step": 408
 },
 {
 "epoch": 2.241095890410959,
 "grad_norm": NaN,
 "learning_rate": 6.377246332954544e-05,
 "loss": 0.0,
 "step": 409
 },
 {
 "epoch": 2.2465753424657535,
 "grad_norm": NaN,
 "learning_rate": 6.318754473153221e-05,
 "loss": 0.0,
 "step": 410
 },
 {
 "epoch": 2.252054794520548,
 "grad_norm": NaN,
 "learning_rate": 6.260407942621998e-05,
 "loss": 0.0,
 "step": 411
 },
 {
 "epoch": 2.2575342465753425,
 "grad_norm": NaN,
 "learning_rate": 6.20220904478199e-05,
 "loss": 0.0,
 "step": 412
 },
 {
 "epoch": 2.263013698630137,
 "grad_norm": NaN,
 "learning_rate": 6.144160077226036e-05,
 "loss": 0.0,
 "step": 413
 },
 {
 "epoch": 2.2684931506849315,
 "grad_norm": NaN,
 "learning_rate": 6.086263331627976e-05,
 "loss": 0.0,
 "step": 414
 },
 {
 "epoch": 2.2739726027397262,
 "grad_norm": NaN,
 "learning_rate": 6.0285210936521955e-05,
 "loss": 0.0,
 "step": 415
 },
 {
 "epoch": 2.2794520547945205,
 "grad_norm": NaN,
 "learning_rate": 5.9709356428633746e-05,
 "loss": 0.0,
 "step": 416
 },
 {
 "epoch": 2.2849315068493152,
 "grad_norm": NaN,
 "learning_rate": 5.913509252636511e-05,
 "loss": 0.0,
 "step": 417
 },
 {
 "epoch": 2.2904109589041095,
 "grad_norm": NaN,
 "learning_rate": 5.856244190067159e-05,
 "loss": 0.0,
 "step": 418
 },
 {
 "epoch": 2.2958904109589042,
 "grad_norm": NaN,
 "learning_rate": 5.799142715881938e-05,
 "loss": 0.0,
 "step": 419
 },
 {
 "epoch": 2.3013698630136985,
 "grad_norm": NaN,
 "learning_rate": 5.7422070843492734e-05,
 "loss": 0.0,
 "step": 420
 },
 {
 "epoch": 2.3068493150684932,
 "grad_norm": NaN,
 "learning_rate": 5.6854395431904094e-05,
 "loss": 0.0,
 "step": 421
 },
 {
 "epoch": 2.3123287671232875,
 "grad_norm": NaN,
 "learning_rate": 5.6288423334906735e-05,
 "loss": 0.0,
 "step": 422
 },
 {
 "epoch": 2.317808219178082,
 "grad_norm": NaN,
 "learning_rate": 5.572417689610987e-05,
 "loss": 0.0,
 "step": 423
 },
 {
 "epoch": 2.323287671232877,
 "grad_norm": NaN,
 "learning_rate": 5.5161678390996796e-05,
 "loss": 0.0,
 "step": 424
 },
 {
 "epoch": 2.328767123287671,
 "grad_norm": NaN,
 "learning_rate": 5.4600950026045326e-05,
 "loss": 0.0,
 "step": 425
 },
 {
 "epoch": 2.334246575342466,
 "grad_norm": NaN,
 "learning_rate": 5.404201393785122e-05,
 "loss": 0.0,
 "step": 426
 },
 {
 "epoch": 2.33972602739726,
 "grad_norm": NaN,
 "learning_rate": 5.348489219225416e-05,
 "loss": 0.0,
 "step": 427
 },
 {
 "epoch": 2.345205479452055,
 "grad_norm": NaN,
 "learning_rate": 5.292960678346675e-05,
 "loss": 0.0,
 "step": 428
 },
 {
 "epoch": 2.350684931506849,
 "grad_norm": NaN,
 "learning_rate": 5.237617963320608e-05,
 "loss": 0.0,
 "step": 429
 },
 {
 "epoch": 2.356164383561644,
 "grad_norm": NaN,
 "learning_rate": 5.182463258982846e-05,
 "loss": 0.0,
 "step": 430
 },
 {
 "epoch": 2.361643835616438,
 "grad_norm": NaN,
 "learning_rate": 5.127498742746675e-05,
 "loss": 0.0,
 "step": 431
 },
 {
 "epoch": 2.367123287671233,
 "grad_norm": NaN,
 "learning_rate": 5.072726584517086e-05,
 "loss": 0.0,
 "step": 432
 },
 {
 "epoch": 2.3726027397260276,
 "grad_norm": NaN,
 "learning_rate": 5.018148946605092e-05,
 "loss": 0.0,
 "step": 433
 },
 {
 "epoch": 2.378082191780822,
 "grad_norm": NaN,
 "learning_rate": 4.9637679836423924e-05,
 "loss": 0.0,
 "step": 434
 },
 {
 "epoch": 2.383561643835616,
 "grad_norm": NaN,
 "learning_rate": 4.909585842496287e-05,
 "loss": 0.0,
 "step": 435
 },
 {
 "epoch": 2.389041095890411,
 "grad_norm": NaN,
 "learning_rate": 4.8556046621849346e-05,
 "loss": 0.0,
 "step": 436
 },
 {
 "epoch": 2.3945205479452056,
 "grad_norm": NaN,
 "learning_rate": 4.8018265737929044e-05,
 "loss": 0.0,
 "step": 437
 },
 {
 "epoch": 2.4,
 "grad_norm": NaN,
 "learning_rate": 4.748253700387042e-05,
 "loss": 0.0,
 "step": 438
 },
 {
 "epoch": 2.4054794520547946,
 "grad_norm": NaN,
 "learning_rate": 4.694888156932658e-05,
 "loss": 0.0,
 "step": 439
 },
 {
 "epoch": 2.410958904109589,
 "grad_norm": NaN,
 "learning_rate": 4.6417320502100316e-05,
 "loss": 0.0,
 "step": 440
 },
 {
 "epoch": 2.4164383561643836,
 "grad_norm": NaN,
 "learning_rate": 4.588787478731242e-05,
 "loss": 0.0,
 "step": 441
 },
 {
 "epoch": 2.421917808219178,
 "grad_norm": NaN,
 "learning_rate": 4.5360565326573104e-05,
 "loss": 0.0,
 "step": 442
 },
 {
 "epoch": 2.4273972602739726,
 "grad_norm": NaN,
 "learning_rate": 4.483541293715698e-05,
 "loss": 0.0,
 "step": 443
 },
 {
 "epoch": 2.432876712328767,
 "grad_norm": NaN,
 "learning_rate": 4.431243835118124e-05,
 "loss": 0.0,
 "step": 444
 },
 {
 "epoch": 2.4383561643835616,
 "grad_norm": NaN,
 "learning_rate": 4.379166221478697e-05,
 "loss": 0.0,
 "step": 445
 },
 {
 "epoch": 2.4438356164383563,
 "grad_norm": NaN,
 "learning_rate": 4.327310508732437e-05,
 "loss": 0.0,
 "step": 446
 },
 {
 "epoch": 2.4493150684931506,
 "grad_norm": NaN,
 "learning_rate": 4.2756787440540936e-05,
 "loss": 0.0,
 "step": 447
 },
 {
 "epoch": 2.4547945205479453,
 "grad_norm": NaN,
 "learning_rate": 4.224272965777326e-05,
 "loss": 0.0,
 "step": 448
 },
 {
 "epoch": 2.4602739726027396,
 "grad_norm": NaN,
 "learning_rate": 4.173095203314241e-05,
 "loss": 0.0,
 "step": 449
 },
 {
 "epoch": 2.4657534246575343,
 "grad_norm": NaN,
 "learning_rate": 4.12214747707527e-05,
 "loss": 0.0,
 "step": 450
 },
 {
 "epoch": 2.4712328767123286,
 "grad_norm": NaN,
 "learning_rate": 4.071431798389408e-05,
 "loss": 0.0,
 "step": 451
 },
 {
 "epoch": 2.4767123287671233,
 "grad_norm": NaN,
 "learning_rate": 4.020950169424815e-05,
 "loss": 0.0,
 "step": 452
 },
 {
 "epoch": 2.4821917808219176,
 "grad_norm": NaN,
 "learning_rate": 3.9707045831097555e-05,
 "loss": 0.0,
 "step": 453
 },
 {
 "epoch": 2.4876712328767123,
 "grad_norm": NaN,
 "learning_rate": 3.920697023053949e-05,
 "loss": 0.0,
 "step": 454
 },
 {
 "epoch": 2.493150684931507,
 "grad_norm": NaN,
 "learning_rate": 3.8709294634702376e-05,
 "loss": 0.0,
 "step": 455
 },
 {
 "epoch": 2.4986301369863013,
 "grad_norm": NaN,
 "learning_rate": 3.821403869096658e-05,
 "loss": 0.0,
 "step": 456
 },
 {
 "epoch": 2.504109589041096,
 "grad_norm": NaN,
 "learning_rate": 3.7721221951188765e-05,
 "loss": 0.0,
 "step": 457
 },
 {
 "epoch": 2.5095890410958903,
 "grad_norm": NaN,
 "learning_rate": 3.7230863870929964e-05,
 "loss": 0.0,
 "step": 458
 },
 {
 "epoch": 2.515068493150685,
 "grad_norm": NaN,
 "learning_rate": 3.674298380868756e-05,
 "loss": 0.0,
 "step": 459
 },
 {
 "epoch": 2.5205479452054793,
 "grad_norm": NaN,
 "learning_rate": 3.6257601025131026e-05,
 "loss": 0.0,
 "step": 460
 },
 {
 "epoch": 2.526027397260274,
 "grad_norm": NaN,
 "learning_rate": 3.577473468234156e-05,
 "loss": 0.0,
 "step": 461
 },
 {
 "epoch": 2.5315068493150683,
 "grad_norm": NaN,
 "learning_rate": 3.52944038430556e-05,
 "loss": 0.0,
 "step": 462
 },
 {
 "epoch": 2.536986301369863,
 "grad_norm": NaN,
 "learning_rate": 3.481662746991214e-05,
 "loss": 0.0,
 "step": 463
 },
 {
 "epoch": 2.5424657534246577,
 "grad_norm": NaN,
 "learning_rate": 3.4341424424704375e-05,
 "loss": 0.0,
 "step": 464
 },
 {
 "epoch": 2.547945205479452,
 "grad_norm": NaN,
 "learning_rate": 3.386881346763483e-05,
 "loss": 0.0,
 "step": 465
 },
 {
 "epoch": 2.5534246575342463,
 "grad_norm": NaN,
 "learning_rate": 3.339881325657484e-05,
 "loss": 0.0,
 "step": 466
 },
 {
 "epoch": 2.558904109589041,
 "grad_norm": NaN,
 "learning_rate": 3.2931442346328004e-05,
 "loss": 0.0,
 "step": 467
 },
 {
 "epoch": 2.5643835616438357,
 "grad_norm": NaN,
 "learning_rate": 3.246671918789755e-05,
 "loss": 0.0,
 "step": 468
 },
 {
 "epoch": 2.56986301369863,
 "grad_norm": NaN,
 "learning_rate": 3.200466212775808e-05,
 "loss": 0.0,
 "step": 469
 },
 {
 "epoch": 2.5753424657534247,
 "grad_norm": NaN,
 "learning_rate": 3.154528940713113e-05,
 "loss": 0.0,
 "step": 470
 },
 {
 "epoch": 2.580821917808219,
 "grad_norm": NaN,
 "learning_rate": 3.108861916126518e-05,
 "loss": 0.0,
 "step": 471
 },
 {
 "epoch": 2.5863013698630137,
 "grad_norm": NaN,
 "learning_rate": 3.063466941871952e-05,
 "loss": 0.0,
 "step": 472
 },
 {
 "epoch": 2.5917808219178085,
 "grad_norm": NaN,
 "learning_rate": 3.018345810065275e-05,
 "loss": 0.0,
 "step": 473
 },
 {
 "epoch": 2.5972602739726027,
 "grad_norm": NaN,
 "learning_rate": 2.9735003020115092e-05,
 "loss": 0.0,
 "step": 474
 },
 {
 "epoch": 2.602739726027397,
 "grad_norm": NaN,
 "learning_rate": 2.9289321881345254e-05,
 "loss": 0.0,
 "step": 475
 },
 {
 "epoch": 2.6082191780821917,
 "grad_norm": NaN,
 "learning_rate": 2.8846432279071467e-05,
 "loss": 0.0,
 "step": 476
 },
 {
 "epoch": 2.6136986301369864,
 "grad_norm": NaN,
 "learning_rate": 2.840635169781688e-05,
 "loss": 0.0,
 "step": 477
 },
 {
 "epoch": 2.6191780821917807,
 "grad_norm": NaN,
 "learning_rate": 2.7969097511209308e-05,
 "loss": 0.0,
 "step": 478
 },
 {
 "epoch": 2.6246575342465754,
 "grad_norm": NaN,
 "learning_rate": 2.753468698129533e-05,
 "loss": 0.0,
 "step": 479
 },
 {
 "epoch": 2.6301369863013697,
 "grad_norm": NaN,
 "learning_rate": 2.7103137257858868e-05,
 "loss": 0.0,
 "step": 480
 },
 {
 "epoch": 2.6356164383561644,
 "grad_norm": NaN,
 "learning_rate": 2.6674465377744017e-05,
 "loss": 0.0,
 "step": 481
 },
 {
 "epoch": 2.641095890410959,
 "grad_norm": NaN,
 "learning_rate": 2.624868826418262e-05,
 "loss": 0.0,
 "step": 482
 },
 {
 "epoch": 2.6465753424657534,
 "grad_norm": NaN,
 "learning_rate": 2.582582272612609e-05,
 "loss": 0.0,
 "step": 483
 },
 {
 "epoch": 2.6520547945205477,
 "grad_norm": NaN,
 "learning_rate": 2.540588545758179e-05,
 "loss": 0.0,
 "step": 484
 },
 {
 "epoch": 2.6575342465753424,
 "grad_norm": NaN,
 "learning_rate": 2.4988893036954043e-05,
 "loss": 0.0,
 "step": 485
 },
 {
 "epoch": 2.663013698630137,
 "grad_norm": NaN,
 "learning_rate": 2.4574861926389615e-05,
 "loss": 0.0,
 "step": 486
 },
 {
 "epoch": 2.6684931506849314,
 "grad_norm": NaN,
 "learning_rate": 2.4163808471127812e-05,
 "loss": 0.0,
 "step": 487
 },
 {
 "epoch": 2.673972602739726,
 "grad_norm": NaN,
 "learning_rate": 2.37557488988552e-05,
 "loss": 0.0,
 "step": 488
 },
 {
 "epoch": 2.6794520547945204,
 "grad_norm": NaN,
 "learning_rate": 2.3350699319065026e-05,
 "loss": 0.0,
 "step": 489
 },
 {
 "epoch": 2.684931506849315,
 "grad_norm": NaN,
 "learning_rate": 2.2948675722421086e-05,
 "loss": 0.0,
 "step": 490
 },
 {
 "epoch": 2.69041095890411,
 "grad_norm": NaN,
 "learning_rate": 2.254969398012663e-05,
 "loss": 0.0,
 "step": 491
 },
 {
 "epoch": 2.695890410958904,
 "grad_norm": NaN,
 "learning_rate": 2.2153769843297667e-05,
 "loss": 0.0,
 "step": 492
 },
 {
 "epoch": 2.7013698630136984,
 "grad_norm": NaN,
 "learning_rate": 2.1760918942341192e-05,
 "loss": 0.0,
 "step": 493
 },
 {
 "epoch": 2.706849315068493,
 "grad_norm": NaN,
 "learning_rate": 2.137115678633811e-05,
 "loss": 0.0,
 "step": 494
 },
 {
 "epoch": 2.712328767123288,
 "grad_norm": NaN,
 "learning_rate": 2.098449876243096e-05,
 "loss": 0.0,
 "step": 495
 },
 {
 "epoch": 2.717808219178082,
 "grad_norm": NaN,
 "learning_rate": 2.0600960135216462e-05,
 "loss": 0.0,
 "step": 496
 },
 {
 "epoch": 2.723287671232877,
 "grad_norm": NaN,
 "learning_rate": 2.0220556046142893e-05,
 "loss": 0.0,
 "step": 497
 },
 {
 "epoch": 2.728767123287671,
 "grad_norm": NaN,
 "learning_rate": 1.9843301512912327e-05,
 "loss": 0.0,
 "step": 498
 },
 {
 "epoch": 2.734246575342466,
 "grad_norm": NaN,
 "learning_rate": 1.946921142888781e-05,
 "loss": 0.0,
 "step": 499
 },
 {
 "epoch": 2.73972602739726,
 "grad_norm": NaN,
 "learning_rate": 1.9098300562505266e-05,
 "loss": 0.0,
 "step": 500
 },
 {
 "epoch": 2.745205479452055,
 "grad_norm": NaN,
 "learning_rate": 1.8730583556690605e-05,
 "loss": 0.0,
 "step": 501
 },
 {
 "epoch": 2.750684931506849,
 "grad_norm": NaN,
 "learning_rate": 1.8366074928281607e-05,
 "loss": 0.0,
 "step": 502
 },
 {
 "epoch": 2.756164383561644,
 "grad_norm": NaN,
 "learning_rate": 1.8004789067454764e-05,
 "loss": 0.0,
 "step": 503
 },
 {
 "epoch": 2.7616438356164386,
 "grad_norm": NaN,
 "learning_rate": 1.7646740237157256e-05,
 "loss": 0.0,
 "step": 504
 },
 {
 "epoch": 2.767123287671233,
 "grad_norm": NaN,
 "learning_rate": 1.7291942572543807e-05,
 "loss": 0.0,
 "step": 505
 },
 {
 "epoch": 2.7726027397260276,
 "grad_norm": NaN,
 "learning_rate": 1.6940410080418723e-05,
 "loss": 0.0,
 "step": 506
 },
 {
 "epoch": 2.778082191780822,
 "grad_norm": NaN,
 "learning_rate": 1.6592156638682886e-05,
 "loss": 0.0,
 "step": 507
 },
 {
 "epoch": 2.7835616438356166,
 "grad_norm": NaN,
 "learning_rate": 1.6247195995785837e-05,
 "loss": 0.0,
 "step": 508
 },
 {
 "epoch": 2.789041095890411,
 "grad_norm": NaN,
 "learning_rate": 1.5905541770183096e-05,
 "loss": 0.0,
 "step": 509
 },
 {
 "epoch": 2.7945205479452055,
 "grad_norm": NaN,
 "learning_rate": 1.5567207449798515e-05,
 "loss": 0.0,
 "step": 510
 },
 {
 "epoch": 2.8,
 "grad_norm": NaN,
 "learning_rate": 1.5232206391491699e-05,
 "loss": 0.0,
 "step": 511
 },
 {
 "epoch": 2.8054794520547945,
 "grad_norm": NaN,
 "learning_rate": 1.4900551820530828e-05,
 "loss": 0.0,
 "step": 512
 },
 {
 "epoch": 2.8109589041095893,
 "grad_norm": NaN,
 "learning_rate": 1.4572256830070497e-05,
 "loss": 0.0,
 "step": 513
 },
 {
 "epoch": 2.8164383561643835,
 "grad_norm": NaN,
 "learning_rate": 1.4247334380634792e-05,
 "loss": 0.0,
 "step": 514
 },
 {
 "epoch": 2.821917808219178,
 "grad_norm": NaN,
 "learning_rate": 1.3925797299605647e-05,
 "loss": 0.0,
 "step": 515
 },
 {
 "epoch": 2.8273972602739725,
 "grad_norm": NaN,
 "learning_rate": 1.3607658280716473e-05,
 "loss": 0.0,
 "step": 516
 },
 {
 "epoch": 2.8328767123287673,
 "grad_norm": NaN,
 "learning_rate": 1.3292929883550998e-05,
 "loss": 0.0,
 "step": 517
 },
 {
 "epoch": 2.8383561643835615,
 "grad_norm": NaN,
 "learning_rate": 1.2981624533047432e-05,
 "loss": 0.0,
 "step": 518
 },
 {
 "epoch": 2.8438356164383563,
 "grad_norm": NaN,
 "learning_rate": 1.2673754519008008e-05,
 "loss": 0.0,
 "step": 519
 },
 {
 "epoch": 2.8493150684931505,
 "grad_norm": NaN,
 "learning_rate": 1.2369331995613665e-05,
 "loss": 0.0,
 "step": 520
 },
 {
 "epoch": 2.8547945205479452,
 "grad_norm": NaN,
 "learning_rate": 1.206836898094439e-05,
 "loss": 0.0,
 "step": 521
 },
 {
 "epoch": 2.86027397260274,
 "grad_norm": NaN,
 "learning_rate": 1.1770877356504683e-05,
 "loss": 0.0,
 "step": 522
 },
 {
 "epoch": 2.8657534246575342,
 "grad_norm": NaN,
 "learning_rate": 1.1476868866754486e-05,
 "loss": 0.0,
 "step": 523
 },
 {
 "epoch": 2.8712328767123285,
 "grad_norm": NaN,
 "learning_rate": 1.1186355118645554e-05,
 "loss": 0.0,
 "step": 524
 },
 {
 "epoch": 2.8767123287671232,
 "grad_norm": NaN,
 "learning_rate": 1.0899347581163221e-05,
 "loss": 0.0,
 "step": 525
 },
 {
 "epoch": 2.882191780821918,
 "grad_norm": NaN,
 "learning_rate": 1.0615857584873623e-05,
 "loss": 0.0,
 "step": 526
 },
 {
 "epoch": 2.8876712328767122,
 "grad_norm": NaN,
 "learning_rate": 1.0335896321476413e-05,
 "loss": 0.0,
 "step": 527
 },
 {
 "epoch": 2.893150684931507,
 "grad_norm": NaN,
 "learning_rate": 1.0059474843362892e-05,
 "loss": 0.0,
 "step": 528
 },
 {
 "epoch": 2.8986301369863012,
 "grad_norm": NaN,
 "learning_rate": 9.786604063179728e-06,
 "loss": 0.0,
 "step": 529
 },
 {
 "epoch": 2.904109589041096,
 "grad_norm": NaN,
 "learning_rate": 9.517294753398064e-06,
 "loss": 0.0,
 "step": 530
 },
 {
 "epoch": 2.9095890410958907,
 "grad_norm": NaN,
 "learning_rate": 9.251557545888312e-06,
 "loss": 0.0,
 "step": 531
 },
 {
 "epoch": 2.915068493150685,
 "grad_norm": NaN,
 "learning_rate": 8.989402931500434e-06,
 "loss": 0.0,
 "step": 532
 },
 {
 "epoch": 2.9205479452054792,
 "grad_norm": NaN,
 "learning_rate": 8.730841259649725e-06,
 "loss": 0.0,
 "step": 533
 },
 {
 "epoch": 2.926027397260274,
 "grad_norm": NaN,
 "learning_rate": 8.475882737908248e-06,
 "loss": 0.0,
 "step": 534
 },
 {
 "epoch": 2.9315068493150687,
 "grad_norm": NaN,
 "learning_rate": 8.224537431601886e-06,
 "loss": 0.0,
 "step": 535
 },
 {
 "epoch": 2.936986301369863,
 "grad_norm": NaN,
 "learning_rate": 7.976815263412963e-06,
 "loss": 0.0,
 "step": 536
 },
 {
 "epoch": 2.9424657534246577,
 "grad_norm": NaN,
 "learning_rate": 7.73272601298851e-06,
 "loss": 0.0,
 "step": 537
 },
 {
 "epoch": 2.947945205479452,
 "grad_norm": NaN,
 "learning_rate": 7.492279316554207e-06,
 "loss": 0.0,
 "step": 538
 },
 {
 "epoch": 2.9534246575342467,
 "grad_norm": NaN,
 "learning_rate": 7.255484666533874e-06,
 "loss": 0.0,
 "step": 539
 },
 {
 "epoch": 2.958904109589041,
 "grad_norm": NaN,
 "learning_rate": 7.022351411174866e-06,
 "loss": 0.0,
 "step": 540
 },
 {
 "epoch": 2.9643835616438357,
 "grad_norm": NaN,
 "learning_rate": 6.7928887541789055e-06,
 "loss": 0.0,
 "step": 541
 },
 {
 "epoch": 2.96986301369863,
 "grad_norm": NaN,
 "learning_rate": 6.5671057543387985e-06,
 "loss": 0.0,
 "step": 542
 },
 {
 "epoch": 2.9753424657534246,
 "grad_norm": NaN,
 "learning_rate": 6.345011325180772e-06,
 "loss": 0.0,
 "step": 543
 },
 {
 "epoch": 2.9808219178082194,
 "grad_norm": NaN,
 "learning_rate": 6.126614234612593e-06,
 "loss": 0.0,
 "step": 544
 },
 {
 "epoch": 2.9863013698630136,
 "grad_norm": NaN,
 "learning_rate": 5.911923104577455e-06,
 "loss": 0.0,
 "step": 545
 },
 {
 "epoch": 2.9917808219178084,
 "grad_norm": NaN,
 "learning_rate": 5.700946410713548e-06,
 "loss": 0.0,
 "step": 546
 },
 {
 "epoch": 2.9972602739726026,
 "grad_norm": NaN,
 "learning_rate": 5.49369248201953e-06,
 "loss": 0.0,
 "step": 547
 },
 {
 "epoch": 2.9972602739726026,
 "eval_loss": NaN,
 "eval_runtime": 18.511,
 "eval_samples_per_second": 66.393,
 "eval_steps_per_second": 2.107,
 "step": 547
 },
 {
 "epoch": 3.0027397260273974,
 "grad_norm": NaN,
 "learning_rate": 5.290169500525577e-06,
 "loss": 0.0,
 "step": 548
 },
 {
 "epoch": 3.0082191780821916,
 "grad_norm": NaN,
 "learning_rate": 5.0903855009705514e-06,
 "loss": 0.0,
 "step": 549
 },
 {
 "epoch": 3.0136986301369864,
 "grad_norm": NaN,
 "learning_rate": 4.8943483704846475e-06,
 "loss": 0.0,
 "step": 550
 },
 {
 "epoch": 3.0191780821917806,
 "grad_norm": NaN,
 "learning_rate": 4.702065848278126e-06,
 "loss": 0.0,
 "step": 551
 },
 {
 "epoch": 3.0246575342465754,
 "grad_norm": NaN,
 "learning_rate": 4.513545525335705e-06,
 "loss": 0.0,
 "step": 552
 },
 {
 "epoch": 3.03013698630137,
 "grad_norm": NaN,
 "learning_rate": 4.328794844116946e-06,
 "loss": 0.0,
 "step": 553
 },
 {
 "epoch": 3.0356164383561643,
 "grad_norm": NaN,
 "learning_rate": 4.147821098262405e-06,
 "loss": 0.0,
 "step": 554
 },
 {
 "epoch": 3.041095890410959,
 "grad_norm": NaN,
 "learning_rate": 3.970631432305694e-06,
 "loss": 0.0,
 "step": 555
 },
 {
 "epoch": 3.0465753424657533,
 "grad_norm": NaN,
 "learning_rate": 3.797232841391407e-06,
 "loss": 0.0,
 "step": 556
 },
 {
 "epoch": 3.052054794520548,
 "grad_norm": NaN,
 "learning_rate": 3.627632170999029e-06,
 "loss": 0.0,
 "step": 557
 },
 {
 "epoch": 3.0575342465753423,
 "grad_norm": NaN,
 "learning_rate": 3.461836116672612e-06,
 "loss": 0.0,
 "step": 558
 },
 {
 "epoch": 3.063013698630137,
 "grad_norm": NaN,
 "learning_rate": 3.2998512237565005e-06,
 "loss": 0.0,
 "step": 559
 },
 {
 "epoch": 3.0684931506849313,
 "grad_norm": NaN,
 "learning_rate": 3.1416838871368924e-06,
 "loss": 0.0,
 "step": 560
 },
 {
 "epoch": 3.073972602739726,
 "grad_norm": NaN,
 "learning_rate": 2.9873403509894203e-06,
 "loss": 0.0,
 "step": 561
 },
 {
 "epoch": 3.0794520547945208,
 "grad_norm": NaN,
 "learning_rate": 2.836826708532603e-06,
 "loss": 0.0,
 "step": 562
 },
 {
 "epoch": 3.084931506849315,
 "grad_norm": NaN,
 "learning_rate": 2.690148901787337e-06,
 "loss": 0.0,
 "step": 563
 },
 {
 "epoch": 3.0904109589041098,
 "grad_norm": NaN,
 "learning_rate": 2.5473127213422763e-06,
 "loss": 0.0,
 "step": 564
 },
 {
 "epoch": 3.095890410958904,
 "grad_norm": NaN,
 "learning_rate": 2.4083238061252567e-06,
 "loss": 0.0,
 "step": 565
 },
 {
 "epoch": 3.1013698630136988,
 "grad_norm": NaN,
 "learning_rate": 2.273187643180652e-06,
 "loss": 0.0,
 "step": 566
 },
 {
 "epoch": 3.106849315068493,
 "grad_norm": NaN,
 "learning_rate": 2.141909567452793e-06,
 "loss": 0.0,
 "step": 567
 },
 {
 "epoch": 3.1123287671232878,
 "grad_norm": NaN,
 "learning_rate": 2.014494761575314e-06,
 "loss": 0.0,
 "step": 568
 },
 {
 "epoch": 3.117808219178082,
 "grad_norm": NaN,
 "learning_rate": 1.8909482556666024e-06,
 "loss": 0.0,
 "step": 569
 },
 {
 "epoch": 3.1232876712328768,
 "grad_norm": NaN,
 "learning_rate": 1.771274927131139e-06,
 "loss": 0.0,
 "step": 570
 },
 {
 "epoch": 3.128767123287671,
 "grad_norm": NaN,
 "learning_rate": 1.6554795004670388e-06,
 "loss": 0.0,
 "step": 571
 },
 {
 "epoch": 3.1342465753424658,
 "grad_norm": NaN,
 "learning_rate": 1.543566547079467e-06,
 "loss": 0.0,
 "step": 572
 },
 {
 "epoch": 3.1397260273972605,
 "grad_norm": NaN,
 "learning_rate": 1.4355404851001952e-06,
 "loss": 0.0,
 "step": 573
 },
 {
 "epoch": 3.1452054794520548,
 "grad_norm": NaN,
 "learning_rate": 1.3314055792131964e-06,
 "loss": 0.0,
 "step": 574
 },
 {
 "epoch": 3.1506849315068495,
 "grad_norm": NaN,
 "learning_rate": 1.231165940486234e-06,
 "loss": 0.0,
 "step": 575
 },
 {
 "epoch": 3.1561643835616437,
 "grad_norm": NaN,
 "learning_rate": 1.134825526208605e-06,
 "loss": 0.0,
 "step": 576
 },
 {
 "epoch": 3.1616438356164385,
 "grad_norm": NaN,
 "learning_rate": 1.0423881397349068e-06,
 "loss": 0.0,
 "step": 577
 },
 {
 "epoch": 3.1671232876712327,
 "grad_norm": NaN,
 "learning_rate": 9.538574303348813e-07,
 "loss": 0.0,
 "step": 578
 },
 {
 "epoch": 3.1726027397260275,
 "grad_norm": NaN,
 "learning_rate": 8.692368930493521e-07,
 "loss": 0.0,
 "step": 579
 },
 {
 "epoch": 3.1780821917808217,
 "grad_norm": NaN,
 "learning_rate": 7.885298685522235e-07,
 "loss": 0.0,
 "step": 580
 },
 {
 "epoch": 3.1835616438356165,
 "grad_norm": NaN,
 "learning_rate": 7.117395430186414e-07,
 "loss": 0.0,
 "step": 581
 },
 {
 "epoch": 3.1890410958904107,
 "grad_norm": NaN,
 "learning_rate": 6.388689479991605e-07,
 "loss": 0.0,
 "step": 582
 },
 {
 "epoch": 3.1945205479452055,
 "grad_norm": NaN,
 "learning_rate": 5.699209603001076e-07,
 "loss": 0.0,
 "step": 583
 },
 {
 "epoch": 3.2,
 "grad_norm": NaN,
 "learning_rate": 5.048983018699827e-07,
 "loss": 0.0,
 "step": 584
 },
 {
 "epoch": 3.2054794520547945,
 "grad_norm": NaN,
 "learning_rate": 4.438035396920004e-07,
 "loss": 0.0,
 "step": 585
 },
 {
 "epoch": 3.210958904109589,
 "grad_norm": NaN,
 "learning_rate": 3.866390856827495e-07,
 "loss": 0.0,
 "step": 586
 },
 {
 "epoch": 3.2164383561643834,
 "grad_norm": NaN,
 "learning_rate": 3.3340719659701313e-07,
 "loss": 0.0,
 "step": 587
 },
 {
 "epoch": 3.221917808219178,
 "grad_norm": NaN,
 "learning_rate": 2.841099739386066e-07,
 "loss": 0.0,
 "step": 588
 },
 {
 "epoch": 3.2273972602739724,
 "grad_norm": NaN,
 "learning_rate": 2.387493638774774e-07,
 "loss": 0.0,
 "step": 589
 },
 {
 "epoch": 3.232876712328767,
 "grad_norm": NaN,
 "learning_rate": 1.973271571728441e-07,
 "loss": 0.0,
 "step": 590
 },
 {
 "epoch": 3.2383561643835614,
 "grad_norm": NaN,
 "learning_rate": 1.598449891024978e-07,
 "loss": 0.0,
 "step": 591
 },
 {
 "epoch": 3.243835616438356,
 "grad_norm": NaN,
 "learning_rate": 1.2630433939825327e-07,
 "loss": 0.0,
 "step": 592
 },
 {
 "epoch": 3.249315068493151,
 "grad_norm": NaN,
 "learning_rate": 9.670653218752934e-08,
 "loss": 0.0,
 "step": 593
 },
 {
 "epoch": 3.254794520547945,
 "grad_norm": NaN,
 "learning_rate": 7.105273594107953e-08,
 "loss": 0.0,
 "step": 594
 },
 {
 "epoch": 3.26027397260274,
 "grad_norm": NaN,
 "learning_rate": 4.934396342684e-08,
 "loss": 0.0,
 "step": 595
 },
 {
 "epoch": 3.265753424657534,
 "grad_norm": NaN,
 "learning_rate": 3.1581071670006015e-08,
 "loss": 0.0,
 "step": 596
 },
 {
 "epoch": 3.271232876712329,
 "grad_norm": NaN,
 "learning_rate": 1.7764761919103477e-08,
 "loss": 0.0,
 "step": 597
 },
 {
 "epoch": 3.276712328767123,
 "grad_norm": NaN,
 "learning_rate": 7.895579618388827e-09,
 "loss": 0.0,
 "step": 598
 },
 {
 "epoch": 3.282191780821918,
 "grad_norm": NaN,
 "learning_rate": 1.973914386288467e-09,
 "loss": 0.0,
 "step": 599
 },
 {
 "epoch": 3.287671232876712,
 "grad_norm": NaN,
 "learning_rate": 0.0,
 "loss": 0.0,
 "step": 600
 },
 {
 "epoch": 3.287671232876712,
 "eval_loss": NaN,
 "eval_runtime": 17.4551,
 "eval_samples_per_second": 70.409,
 "eval_steps_per_second": 2.234,
 "step": 600
 }
 ],
 "logging_steps": 1,
 "max_steps": 600,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 4,
 "save_steps": 500,
 "stateful_callbacks": {
 "TrainerControl": {
 "args": {
 "should_epoch_stop": false,
 "should_evaluate": false,
 "should_log": false,
 "should_save": true,
 "should_training_stop": true
 },
 "attributes": {}
 }
 },
 "total_flos": 1.5158791158722724e+18,
 "train_batch_size": 4,
 "trial_name": null,
 "trial_params": null
}