wi2c-llama3-1 / trainer_state.json
mistakeknot's picture
Upload WI2C Llama 3.1 70B Absurdist LoRA adapter
a85382d verified
Raw History Blame Contribute Delete
14.9 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 0,
"global_step": 87,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.034482758620689655,
"grad_norm": 7.4375,
"learning_rate": 0.0,
"loss": 5.0222,
"step": 1
},
{
"epoch": 0.06896551724137931,
"grad_norm": 7.9375,
"learning_rate": 6.666666666666667e-06,
"loss": 5.1147,
"step": 2
},
{
"epoch": 0.10344827586206896,
"grad_norm": 6.09375,
"learning_rate": 1.3333333333333333e-05,
"loss": 4.6125,
"step": 3
},
{
"epoch": 0.13793103448275862,
"grad_norm": 5.375,
"learning_rate": 2e-05,
"loss": 4.611,
"step": 4
},
{
"epoch": 0.1724137931034483,
"grad_norm": 2.5,
"learning_rate": 1.9993007047883988e-05,
"loss": 4.4752,
"step": 5
},
{
"epoch": 0.20689655172413793,
"grad_norm": 1.5703125,
"learning_rate": 1.9972037971811802e-05,
"loss": 4.1858,
"step": 6
},
{
"epoch": 0.2413793103448276,
"grad_norm": 1.2578125,
"learning_rate": 1.9937122098932428e-05,
"loss": 4.025,
"step": 7
},
{
"epoch": 0.27586206896551724,
"grad_norm": 1.1796875,
"learning_rate": 1.9888308262251286e-05,
"loss": 4.2741,
"step": 8
},
{
"epoch": 0.3103448275862069,
"grad_norm": 0.8046875,
"learning_rate": 1.9825664732332886e-05,
"loss": 3.9291,
"step": 9
},
{
"epoch": 0.3448275862068966,
"grad_norm": 0.66015625,
"learning_rate": 1.9749279121818235e-05,
"loss": 3.8237,
"step": 10
},
{
"epoch": 0.3793103448275862,
"grad_norm": 0.7890625,
"learning_rate": 1.9659258262890683e-05,
"loss": 3.786,
"step": 11
},
{
"epoch": 0.41379310344827586,
"grad_norm": 1.4609375,
"learning_rate": 1.955572805786141e-05,
"loss": 3.9016,
"step": 12
},
{
"epoch": 0.4482758620689655,
"grad_norm": 1.3984375,
"learning_rate": 1.9438833303083677e-05,
"loss": 4.0912,
"step": 13
},
{
"epoch": 0.4827586206896552,
"grad_norm": 0.53515625,
"learning_rate": 1.9308737486442045e-05,
"loss": 3.8579,
"step": 14
},
{
"epoch": 0.5172413793103449,
"grad_norm": 0.53125,
"learning_rate": 1.9165622558699763e-05,
"loss": 3.9025,
"step": 15
},
{
"epoch": 0.5517241379310345,
"grad_norm": 0.51953125,
"learning_rate": 1.900968867902419e-05,
"loss": 3.7475,
"step": 16
},
{
"epoch": 0.5862068965517241,
"grad_norm": 0.458984375,
"learning_rate": 1.8841153935046098e-05,
"loss": 3.8074,
"step": 17
},
{
"epoch": 0.6206896551724138,
"grad_norm": 0.3984375,
"learning_rate": 1.866025403784439e-05,
"loss": 3.8109,
"step": 18
},
{
"epoch": 0.6551724137931034,
"grad_norm": 0.8671875,
"learning_rate": 1.8467241992282842e-05,
"loss": 4.0508,
"step": 19
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.404296875,
"learning_rate": 1.826238774315995e-05,
"loss": 3.9091,
"step": 20
},
{
"epoch": 0.7241379310344828,
"grad_norm": 0.5859375,
"learning_rate": 1.8045977797666685e-05,
"loss": 3.63,
"step": 21
},
{
"epoch": 0.7586206896551724,
"grad_norm": 0.447265625,
"learning_rate": 1.78183148246803e-05,
"loss": 3.7721,
"step": 22
},
{
"epoch": 0.7931034482758621,
"grad_norm": 0.37890625,
"learning_rate": 1.757971723145453e-05,
"loss": 3.7469,
"step": 23
},
{
"epoch": 0.8275862068965517,
"grad_norm": 0.84765625,
"learning_rate": 1.7330518718298263e-05,
"loss": 3.9459,
"step": 24
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.345703125,
"learning_rate": 1.7071067811865477e-05,
"loss": 3.6702,
"step": 25
},
{
"epoch": 0.896551724137931,
"grad_norm": 0.3359375,
"learning_rate": 1.6801727377709195e-05,
"loss": 3.6578,
"step": 26
},
{
"epoch": 0.9310344827586207,
"grad_norm": 0.7578125,
"learning_rate": 1.6522874112781213e-05,
"loss": 4.0356,
"step": 27
},
{
"epoch": 0.9655172413793104,
"grad_norm": 0.326171875,
"learning_rate": 1.6234898018587336e-05,
"loss": 3.6688,
"step": 28
},
{
"epoch": 1.0,
"grad_norm": 0.486328125,
"learning_rate": 1.5938201855735017e-05,
"loss": 3.5728,
"step": 29
},
{
"epoch": 1.0344827586206897,
"grad_norm": 0.283203125,
"learning_rate": 1.563320058063622e-05,
"loss": 3.7259,
"step": 30
},
{
"epoch": 1.0689655172413792,
"grad_norm": 0.41796875,
"learning_rate": 1.5320320765153367e-05,
"loss": 3.6079,
"step": 31
},
{
"epoch": 1.103448275862069,
"grad_norm": 0.3203125,
"learning_rate": 1.5000000000000002e-05,
"loss": 3.7737,
"step": 32
},
{
"epoch": 1.1379310344827587,
"grad_norm": 0.271484375,
"learning_rate": 1.4672686282730622e-05,
"loss": 3.6476,
"step": 33
},
{
"epoch": 1.1724137931034484,
"grad_norm": 0.3984375,
"learning_rate": 1.4338837391175582e-05,
"loss": 3.7189,
"step": 34
},
{
"epoch": 1.206896551724138,
"grad_norm": 0.25390625,
"learning_rate": 1.3998920243197408e-05,
"loss": 3.5989,
"step": 35
},
{
"epoch": 1.2413793103448276,
"grad_norm": 0.259765625,
"learning_rate": 1.3653410243663953e-05,
"loss": 3.6077,
"step": 36
},
{
"epoch": 1.2758620689655173,
"grad_norm": 0.255859375,
"learning_rate": 1.3302790619551673e-05,
"loss": 3.6065,
"step": 37
},
{
"epoch": 1.3103448275862069,
"grad_norm": 0.3046875,
"learning_rate": 1.2947551744109044e-05,
"loss": 3.6663,
"step": 38
},
{
"epoch": 1.3448275862068966,
"grad_norm": 0.7734375,
"learning_rate": 1.2588190451025209e-05,
"loss": 3.7774,
"step": 39
},
{
"epoch": 1.3793103448275863,
"grad_norm": 0.271484375,
"learning_rate": 1.2225209339563144e-05,
"loss": 3.6278,
"step": 40
},
{
"epoch": 1.4137931034482758,
"grad_norm": 0.341796875,
"learning_rate": 1.1859116071629148e-05,
"loss": 3.7917,
"step": 41
},
{
"epoch": 1.4482758620689655,
"grad_norm": 0.29296875,
"learning_rate": 1.1490422661761744e-05,
"loss": 3.747,
"step": 42
},
{
"epoch": 1.4827586206896552,
"grad_norm": 0.58203125,
"learning_rate": 1.1119644761033079e-05,
"loss": 3.4494,
"step": 43
},
{
"epoch": 1.5172413793103448,
"grad_norm": 0.345703125,
"learning_rate": 1.0747300935864245e-05,
"loss": 3.6524,
"step": 44
},
{
"epoch": 1.5517241379310345,
"grad_norm": 0.4296875,
"learning_rate": 1.037391194276326e-05,
"loss": 3.5445,
"step": 45
},
{
"epoch": 1.5862068965517242,
"grad_norm": 0.419921875,
"learning_rate": 1e-05,
"loss": 3.4137,
"step": 46
},
{
"epoch": 1.6206896551724137,
"grad_norm": 0.330078125,
"learning_rate": 9.626088057236745e-06,
"loss": 3.4652,
"step": 47
},
{
"epoch": 1.6551724137931034,
"grad_norm": 0.2578125,
"learning_rate": 9.252699064135759e-06,
"loss": 3.4672,
"step": 48
},
{
"epoch": 1.6896551724137931,
"grad_norm": 0.267578125,
"learning_rate": 8.880355238966923e-06,
"loss": 3.4507,
"step": 49
},
{
"epoch": 1.7241379310344827,
"grad_norm": 0.306640625,
"learning_rate": 8.509577338238255e-06,
"loss": 3.4844,
"step": 50
},
{
"epoch": 1.7586206896551724,
"grad_norm": 0.66015625,
"learning_rate": 8.140883928370855e-06,
"loss": 3.6069,
"step": 51
},
{
"epoch": 1.793103448275862,
"grad_norm": 0.7265625,
"learning_rate": 7.774790660436857e-06,
"loss": 3.6394,
"step": 52
},
{
"epoch": 1.8275862068965516,
"grad_norm": 0.3515625,
"learning_rate": 7.411809548974792e-06,
"loss": 3.5789,
"step": 53
},
{
"epoch": 1.8620689655172413,
"grad_norm": 0.26953125,
"learning_rate": 7.052448255890958e-06,
"loss": 3.5094,
"step": 54
},
{
"epoch": 1.896551724137931,
"grad_norm": 0.765625,
"learning_rate": 6.697209380448333e-06,
"loss": 3.8513,
"step": 55
},
{
"epoch": 1.9310344827586206,
"grad_norm": 0.2490234375,
"learning_rate": 6.34658975633605e-06,
"loss": 3.5786,
"step": 56
},
{
"epoch": 1.9655172413793105,
"grad_norm": 0.279296875,
"learning_rate": 6.001079756802592e-06,
"loss": 3.5573,
"step": 57
},
{
"epoch": 2.0,
"grad_norm": 0.298828125,
"learning_rate": 5.66116260882442e-06,
"loss": 3.5882,
"step": 58
},
{
"epoch": 2.0344827586206895,
"grad_norm": 0.390625,
"learning_rate": 5.32731371726938e-06,
"loss": 3.4628,
"step": 59
},
{
"epoch": 2.0689655172413794,
"grad_norm": 0.36328125,
"learning_rate": 5.000000000000003e-06,
"loss": 3.5358,
"step": 60
},
{
"epoch": 2.103448275862069,
"grad_norm": 0.423828125,
"learning_rate": 4.679679234846636e-06,
"loss": 3.4965,
"step": 61
},
{
"epoch": 2.1379310344827585,
"grad_norm": 0.302734375,
"learning_rate": 4.3667994193637794e-06,
"loss": 3.5483,
"step": 62
},
{
"epoch": 2.1724137931034484,
"grad_norm": 0.443359375,
"learning_rate": 4.061798144264986e-06,
"loss": 3.4162,
"step": 63
},
{
"epoch": 2.206896551724138,
"grad_norm": 0.345703125,
"learning_rate": 3.7651019814126656e-06,
"loss": 3.5583,
"step": 64
},
{
"epoch": 2.2413793103448274,
"grad_norm": 0.3125,
"learning_rate": 3.4771258872187917e-06,
"loss": 3.5236,
"step": 65
},
{
"epoch": 2.2758620689655173,
"grad_norm": 0.765625,
"learning_rate": 3.1982726222908046e-06,
"loss": 3.7135,
"step": 66
},
{
"epoch": 2.310344827586207,
"grad_norm": 0.376953125,
"learning_rate": 2.9289321881345257e-06,
"loss": 3.6926,
"step": 67
},
{
"epoch": 2.344827586206897,
"grad_norm": 0.263671875,
"learning_rate": 2.669481281701739e-06,
"loss": 3.5238,
"step": 68
},
{
"epoch": 2.3793103448275863,
"grad_norm": 0.287109375,
"learning_rate": 2.420282768545469e-06,
"loss": 3.4981,
"step": 69
},
{
"epoch": 2.413793103448276,
"grad_norm": 0.287109375,
"learning_rate": 2.1816851753197023e-06,
"loss": 3.4575,
"step": 70
},
{
"epoch": 2.4482758620689653,
"grad_norm": 0.91796875,
"learning_rate": 1.9540222023333165e-06,
"loss": 3.8734,
"step": 71
},
{
"epoch": 2.4827586206896552,
"grad_norm": 0.25390625,
"learning_rate": 1.7376122568400533e-06,
"loss": 3.4957,
"step": 72
},
{
"epoch": 2.5172413793103448,
"grad_norm": 0.26953125,
"learning_rate": 1.5327580077171589e-06,
"loss": 3.4607,
"step": 73
},
{
"epoch": 2.5517241379310347,
"grad_norm": 0.265625,
"learning_rate": 1.339745962155613e-06,
"loss": 3.4951,
"step": 74
},
{
"epoch": 2.586206896551724,
"grad_norm": 0.255859375,
"learning_rate": 1.1588460649539036e-06,
"loss": 3.6463,
"step": 75
},
{
"epoch": 2.6206896551724137,
"grad_norm": 0.419921875,
"learning_rate": 9.903113209758098e-07,
"loss": 3.7225,
"step": 76
},
{
"epoch": 2.655172413793103,
"grad_norm": 0.28125,
"learning_rate": 8.343774413002382e-07,
"loss": 3.5069,
"step": 77
},
{
"epoch": 2.689655172413793,
"grad_norm": 0.23828125,
"learning_rate": 6.912625135579587e-07,
"loss": 3.5515,
"step": 78
},
{
"epoch": 2.7241379310344827,
"grad_norm": 0.265625,
"learning_rate": 5.611666969163243e-07,
"loss": 3.5939,
"step": 79
},
{
"epoch": 2.7586206896551726,
"grad_norm": 0.326171875,
"learning_rate": 4.4427194213859216e-07,
"loss": 3.5626,
"step": 80
},
{
"epoch": 2.793103448275862,
"grad_norm": 0.2333984375,
"learning_rate": 3.4074173710931804e-07,
"loss": 3.5161,
"step": 81
},
{
"epoch": 2.8275862068965516,
"grad_norm": 0.2421875,
"learning_rate": 2.507208781817638e-07,
"loss": 3.5366,
"step": 82
},
{
"epoch": 2.862068965517241,
"grad_norm": 0.259765625,
"learning_rate": 1.7433526766711727e-07,
"loss": 3.5442,
"step": 83
},
{
"epoch": 2.896551724137931,
"grad_norm": 0.30859375,
"learning_rate": 1.1169173774871478e-07,
"loss": 3.6514,
"step": 84
},
{
"epoch": 2.9310344827586206,
"grad_norm": 0.275390625,
"learning_rate": 6.287790106757396e-08,
"loss": 3.4944,
"step": 85
},
{
"epoch": 2.9655172413793105,
"grad_norm": 0.341796875,
"learning_rate": 2.796202818819871e-08,
"loss": 3.4597,
"step": 86
},
{
"epoch": 3.0,
"grad_norm": 0.255859375,
"learning_rate": 6.992952116013918e-09,
"loss": 3.5197,
"step": 87
}
],
"logging_steps": 1.0,
"max_steps": 87,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.9935982612158874e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}