neo-blockchain-assistant / trainer_state.json
TooKeen's picture
Upload folder using huggingface_hub
ae29d7b verified
raw
history blame
13.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 0,
"global_step": 76,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013157894736842105,
"grad_norm": 3.5969951152801514,
"learning_rate": 9.868421052631579e-06,
"loss": 3.5568,
"step": 1
},
{
"epoch": 0.02631578947368421,
"grad_norm": 4.185197830200195,
"learning_rate": 9.736842105263159e-06,
"loss": 4.0349,
"step": 2
},
{
"epoch": 0.039473684210526314,
"grad_norm": 3.4948582649230957,
"learning_rate": 9.605263157894737e-06,
"loss": 3.4982,
"step": 3
},
{
"epoch": 0.05263157894736842,
"grad_norm": 3.7073941230773926,
"learning_rate": 9.473684210526315e-06,
"loss": 3.6487,
"step": 4
},
{
"epoch": 0.06578947368421052,
"grad_norm": 4.189187049865723,
"learning_rate": 9.342105263157895e-06,
"loss": 3.9381,
"step": 5
},
{
"epoch": 0.07894736842105263,
"grad_norm": 4.8404541015625,
"learning_rate": 9.210526315789474e-06,
"loss": 4.1107,
"step": 6
},
{
"epoch": 0.09210526315789473,
"grad_norm": 3.8595361709594727,
"learning_rate": 9.078947368421054e-06,
"loss": 3.3677,
"step": 7
},
{
"epoch": 0.10526315789473684,
"grad_norm": 4.151785373687744,
"learning_rate": 8.947368421052632e-06,
"loss": 3.4079,
"step": 8
},
{
"epoch": 0.11842105263157894,
"grad_norm": 3.8082962036132812,
"learning_rate": 8.81578947368421e-06,
"loss": 3.3549,
"step": 9
},
{
"epoch": 0.13157894736842105,
"grad_norm": 3.9419312477111816,
"learning_rate": 8.68421052631579e-06,
"loss": 3.4935,
"step": 10
},
{
"epoch": 0.14473684210526316,
"grad_norm": 4.361544132232666,
"learning_rate": 8.552631578947368e-06,
"loss": 3.448,
"step": 11
},
{
"epoch": 0.15789473684210525,
"grad_norm": 3.8608157634735107,
"learning_rate": 8.421052631578948e-06,
"loss": 3.3588,
"step": 12
},
{
"epoch": 0.17105263157894737,
"grad_norm": 4.809046745300293,
"learning_rate": 8.289473684210526e-06,
"loss": 3.7738,
"step": 13
},
{
"epoch": 0.18421052631578946,
"grad_norm": 3.825930118560791,
"learning_rate": 8.157894736842106e-06,
"loss": 3.4686,
"step": 14
},
{
"epoch": 0.19736842105263158,
"grad_norm": 4.184592247009277,
"learning_rate": 8.026315789473685e-06,
"loss": 3.388,
"step": 15
},
{
"epoch": 0.21052631578947367,
"grad_norm": 4.1753668785095215,
"learning_rate": 7.894736842105265e-06,
"loss": 3.2729,
"step": 16
},
{
"epoch": 0.2236842105263158,
"grad_norm": 4.188427925109863,
"learning_rate": 7.763157894736843e-06,
"loss": 3.3862,
"step": 17
},
{
"epoch": 0.23684210526315788,
"grad_norm": 3.5322694778442383,
"learning_rate": 7.631578947368423e-06,
"loss": 3.1601,
"step": 18
},
{
"epoch": 0.25,
"grad_norm": 4.3005595207214355,
"learning_rate": 7.500000000000001e-06,
"loss": 3.2731,
"step": 19
},
{
"epoch": 0.2631578947368421,
"grad_norm": 4.415473461151123,
"learning_rate": 7.368421052631579e-06,
"loss": 3.1474,
"step": 20
},
{
"epoch": 0.27631578947368424,
"grad_norm": 4.977243900299072,
"learning_rate": 7.236842105263158e-06,
"loss": 3.227,
"step": 21
},
{
"epoch": 0.2894736842105263,
"grad_norm": 4.110137462615967,
"learning_rate": 7.1052631578947375e-06,
"loss": 2.8902,
"step": 22
},
{
"epoch": 0.3026315789473684,
"grad_norm": 4.749568939208984,
"learning_rate": 6.973684210526316e-06,
"loss": 3.2829,
"step": 23
},
{
"epoch": 0.3157894736842105,
"grad_norm": 4.500365257263184,
"learning_rate": 6.842105263157896e-06,
"loss": 2.9448,
"step": 24
},
{
"epoch": 0.32894736842105265,
"grad_norm": 4.0608744621276855,
"learning_rate": 6.710526315789474e-06,
"loss": 3.0899,
"step": 25
},
{
"epoch": 0.34210526315789475,
"grad_norm": 4.095396518707275,
"learning_rate": 6.578947368421054e-06,
"loss": 2.9888,
"step": 26
},
{
"epoch": 0.35526315789473684,
"grad_norm": 4.954774379730225,
"learning_rate": 6.447368421052632e-06,
"loss": 3.4578,
"step": 27
},
{
"epoch": 0.3684210526315789,
"grad_norm": 4.0194597244262695,
"learning_rate": 6.31578947368421e-06,
"loss": 2.807,
"step": 28
},
{
"epoch": 0.3815789473684211,
"grad_norm": 4.574712753295898,
"learning_rate": 6.18421052631579e-06,
"loss": 3.3466,
"step": 29
},
{
"epoch": 0.39473684210526316,
"grad_norm": 5.773961544036865,
"learning_rate": 6.0526315789473685e-06,
"loss": 3.519,
"step": 30
},
{
"epoch": 0.40789473684210525,
"grad_norm": 3.523261070251465,
"learning_rate": 5.921052631578948e-06,
"loss": 2.7265,
"step": 31
},
{
"epoch": 0.42105263157894735,
"grad_norm": 4.2967963218688965,
"learning_rate": 5.789473684210527e-06,
"loss": 2.9817,
"step": 32
},
{
"epoch": 0.4342105263157895,
"grad_norm": 4.2323689460754395,
"learning_rate": 5.657894736842106e-06,
"loss": 2.9753,
"step": 33
},
{
"epoch": 0.4473684210526316,
"grad_norm": 3.893044948577881,
"learning_rate": 5.526315789473685e-06,
"loss": 2.6951,
"step": 34
},
{
"epoch": 0.4605263157894737,
"grad_norm": 4.018922328948975,
"learning_rate": 5.394736842105264e-06,
"loss": 2.7226,
"step": 35
},
{
"epoch": 0.47368421052631576,
"grad_norm": 4.34171199798584,
"learning_rate": 5.263157894736842e-06,
"loss": 3.0148,
"step": 36
},
{
"epoch": 0.4868421052631579,
"grad_norm": 4.391392230987549,
"learning_rate": 5.131578947368422e-06,
"loss": 2.8676,
"step": 37
},
{
"epoch": 0.5,
"grad_norm": 4.058086395263672,
"learning_rate": 5e-06,
"loss": 2.9084,
"step": 38
},
{
"epoch": 0.5131578947368421,
"grad_norm": 4.01865816116333,
"learning_rate": 4.8684210526315795e-06,
"loss": 2.7218,
"step": 39
},
{
"epoch": 0.5263157894736842,
"grad_norm": 4.012227535247803,
"learning_rate": 4.736842105263158e-06,
"loss": 2.8061,
"step": 40
},
{
"epoch": 0.5394736842105263,
"grad_norm": 4.107736110687256,
"learning_rate": 4.605263157894737e-06,
"loss": 2.796,
"step": 41
},
{
"epoch": 0.5526315789473685,
"grad_norm": 4.0551862716674805,
"learning_rate": 4.473684210526316e-06,
"loss": 2.6791,
"step": 42
},
{
"epoch": 0.5657894736842105,
"grad_norm": 4.386580944061279,
"learning_rate": 4.342105263157895e-06,
"loss": 2.9243,
"step": 43
},
{
"epoch": 0.5789473684210527,
"grad_norm": 4.859345436096191,
"learning_rate": 4.210526315789474e-06,
"loss": 2.8425,
"step": 44
},
{
"epoch": 0.5921052631578947,
"grad_norm": 4.436668395996094,
"learning_rate": 4.078947368421053e-06,
"loss": 2.8771,
"step": 45
},
{
"epoch": 0.6052631578947368,
"grad_norm": 4.006519794464111,
"learning_rate": 3.947368421052632e-06,
"loss": 2.7562,
"step": 46
},
{
"epoch": 0.618421052631579,
"grad_norm": 3.805677652359009,
"learning_rate": 3.815789473684211e-06,
"loss": 2.6883,
"step": 47
},
{
"epoch": 0.631578947368421,
"grad_norm": 4.111331939697266,
"learning_rate": 3.6842105263157896e-06,
"loss": 2.686,
"step": 48
},
{
"epoch": 0.6447368421052632,
"grad_norm": 3.323714017868042,
"learning_rate": 3.5526315789473687e-06,
"loss": 2.3828,
"step": 49
},
{
"epoch": 0.6578947368421053,
"grad_norm": 4.244898319244385,
"learning_rate": 3.421052631578948e-06,
"loss": 2.865,
"step": 50
},
{
"epoch": 0.6710526315789473,
"grad_norm": 5.01881742477417,
"learning_rate": 3.289473684210527e-06,
"loss": 2.8533,
"step": 51
},
{
"epoch": 0.6842105263157895,
"grad_norm": 4.621983528137207,
"learning_rate": 3.157894736842105e-06,
"loss": 2.764,
"step": 52
},
{
"epoch": 0.6973684210526315,
"grad_norm": 4.3757710456848145,
"learning_rate": 3.0263157894736843e-06,
"loss": 2.6274,
"step": 53
},
{
"epoch": 0.7105263157894737,
"grad_norm": 4.757716655731201,
"learning_rate": 2.8947368421052634e-06,
"loss": 2.7931,
"step": 54
},
{
"epoch": 0.7236842105263158,
"grad_norm": 4.184610843658447,
"learning_rate": 2.7631578947368424e-06,
"loss": 2.7153,
"step": 55
},
{
"epoch": 0.7368421052631579,
"grad_norm": 3.97389554977417,
"learning_rate": 2.631578947368421e-06,
"loss": 2.6493,
"step": 56
},
{
"epoch": 0.75,
"grad_norm": 4.303612232208252,
"learning_rate": 2.5e-06,
"loss": 2.6206,
"step": 57
},
{
"epoch": 0.7631578947368421,
"grad_norm": 3.8477213382720947,
"learning_rate": 2.368421052631579e-06,
"loss": 2.4336,
"step": 58
},
{
"epoch": 0.7763157894736842,
"grad_norm": 4.191899299621582,
"learning_rate": 2.236842105263158e-06,
"loss": 2.6239,
"step": 59
},
{
"epoch": 0.7894736842105263,
"grad_norm": 3.8120546340942383,
"learning_rate": 2.105263157894737e-06,
"loss": 2.3935,
"step": 60
},
{
"epoch": 0.8026315789473685,
"grad_norm": 4.68777322769165,
"learning_rate": 1.973684210526316e-06,
"loss": 2.8501,
"step": 61
},
{
"epoch": 0.8157894736842105,
"grad_norm": 4.091485023498535,
"learning_rate": 1.8421052631578948e-06,
"loss": 2.4697,
"step": 62
},
{
"epoch": 0.8289473684210527,
"grad_norm": 4.707141399383545,
"learning_rate": 1.710526315789474e-06,
"loss": 2.7696,
"step": 63
},
{
"epoch": 0.8421052631578947,
"grad_norm": 4.358771324157715,
"learning_rate": 1.5789473684210526e-06,
"loss": 2.5899,
"step": 64
},
{
"epoch": 0.8552631578947368,
"grad_norm": 3.9348034858703613,
"learning_rate": 1.4473684210526317e-06,
"loss": 2.568,
"step": 65
},
{
"epoch": 0.868421052631579,
"grad_norm": 4.441805362701416,
"learning_rate": 1.3157894736842106e-06,
"loss": 2.5547,
"step": 66
},
{
"epoch": 0.881578947368421,
"grad_norm": 4.700938701629639,
"learning_rate": 1.1842105263157894e-06,
"loss": 2.7651,
"step": 67
},
{
"epoch": 0.8947368421052632,
"grad_norm": 3.856534957885742,
"learning_rate": 1.0526315789473685e-06,
"loss": 2.4805,
"step": 68
},
{
"epoch": 0.9078947368421053,
"grad_norm": 4.3660149574279785,
"learning_rate": 9.210526315789474e-07,
"loss": 2.5027,
"step": 69
},
{
"epoch": 0.9210526315789473,
"grad_norm": 4.625879287719727,
"learning_rate": 7.894736842105263e-07,
"loss": 3.0098,
"step": 70
},
{
"epoch": 0.9342105263157895,
"grad_norm": 3.837646007537842,
"learning_rate": 6.578947368421053e-07,
"loss": 2.4544,
"step": 71
},
{
"epoch": 0.9473684210526315,
"grad_norm": 3.6256585121154785,
"learning_rate": 5.263157894736843e-07,
"loss": 2.2905,
"step": 72
},
{
"epoch": 0.9605263157894737,
"grad_norm": 4.403687000274658,
"learning_rate": 3.9473684210526315e-07,
"loss": 2.7397,
"step": 73
},
{
"epoch": 0.9736842105263158,
"grad_norm": 3.8329477310180664,
"learning_rate": 2.6315789473684213e-07,
"loss": 2.4028,
"step": 74
},
{
"epoch": 0.9868421052631579,
"grad_norm": 3.729228973388672,
"learning_rate": 1.3157894736842107e-07,
"loss": 2.4891,
"step": 75
},
{
"epoch": 1.0,
"grad_norm": 3.699434995651245,
"learning_rate": 0.0,
"loss": 2.4679,
"step": 76
}
],
"logging_steps": 1.0,
"max_steps": 76,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 1.0656232298564813e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}