nttx's picture
Training in progress, step 50, checkpoint
4c60c4c verified
raw
history blame
9.93 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.4672897196261682,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.009345794392523364,
"grad_norm": 2.5344741516164504e-05,
"learning_rate": 3.3333333333333333e-06,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.009345794392523364,
"eval_loss": 11.5,
"eval_runtime": 1.1265,
"eval_samples_per_second": 160.679,
"eval_steps_per_second": 80.783,
"step": 1
},
{
"epoch": 0.018691588785046728,
"grad_norm": 2.615838275232818e-05,
"learning_rate": 6.666666666666667e-06,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.028037383177570093,
"grad_norm": 2.7344363843440078e-05,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.037383177570093455,
"grad_norm": 2.452568332955707e-05,
"learning_rate": 1.3333333333333333e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.04672897196261682,
"grad_norm": 3.134661528747529e-05,
"learning_rate": 1.6666666666666667e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.056074766355140186,
"grad_norm": 3.4900876926258206e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.06542056074766354,
"grad_norm": 2.6106856239493936e-05,
"learning_rate": 2.3333333333333336e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.07476635514018691,
"grad_norm": 2.7752683308790438e-05,
"learning_rate": 2.6666666666666667e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.08411214953271028,
"grad_norm": 2.7367219445295632e-05,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.09345794392523364,
"grad_norm": 2.9516531867557205e-05,
"learning_rate": 3.3333333333333335e-05,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.102803738317757,
"grad_norm": 3.180565909133293e-05,
"learning_rate": 3.6666666666666666e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.11214953271028037,
"grad_norm": 2.7306345145916566e-05,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.12149532710280374,
"grad_norm": 3.706616917042993e-05,
"learning_rate": 4.3333333333333334e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.1308411214953271,
"grad_norm": 2.9705503038712777e-05,
"learning_rate": 4.666666666666667e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.14018691588785046,
"grad_norm": 3.355026638018899e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.14953271028037382,
"grad_norm": 3.9220551116159186e-05,
"learning_rate": 5.333333333333333e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.1588785046728972,
"grad_norm": 4.0627914131619036e-05,
"learning_rate": 5.666666666666667e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.16822429906542055,
"grad_norm": 3.929124432033859e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.17757009345794392,
"grad_norm": 2.4858816686901264e-05,
"learning_rate": 6.333333333333333e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.18691588785046728,
"grad_norm": 3.943190677091479e-05,
"learning_rate": 6.666666666666667e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.19626168224299065,
"grad_norm": 4.8376921768067405e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.205607476635514,
"grad_norm": 4.936111145070754e-05,
"learning_rate": 7.333333333333333e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.21495327102803738,
"grad_norm": 5.0592880143085495e-05,
"learning_rate": 7.666666666666667e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.22429906542056074,
"grad_norm": 4.4427615648601204e-05,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.2336448598130841,
"grad_norm": 5.0494058086769655e-05,
"learning_rate": 8.333333333333334e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.24299065420560748,
"grad_norm": 3.8928865251364186e-05,
"learning_rate": 8.666666666666667e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.2523364485981308,
"grad_norm": 4.032924334751442e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.2616822429906542,
"grad_norm": 4.888198964181356e-05,
"learning_rate": 9.333333333333334e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.27102803738317754,
"grad_norm": 3.859275238937698e-05,
"learning_rate": 9.666666666666667e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.2803738317757009,
"grad_norm": 4.155114584136754e-05,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.2897196261682243,
"grad_norm": 3.540813486324623e-05,
"learning_rate": 9.999146252290264e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.29906542056074764,
"grad_norm": 4.2967913032043725e-05,
"learning_rate": 9.996585300715116e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.308411214953271,
"grad_norm": 4.8990899813361466e-05,
"learning_rate": 9.99231801983717e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.3177570093457944,
"grad_norm": 4.408402310218662e-05,
"learning_rate": 9.986345866928941e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.32710280373831774,
"grad_norm": 4.686412648879923e-05,
"learning_rate": 9.978670881475172e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.3364485981308411,
"grad_norm": 5.995184983476065e-05,
"learning_rate": 9.96929568447637e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.34579439252336447,
"grad_norm": 6.438123091356829e-05,
"learning_rate": 9.958223477553714e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.35514018691588783,
"grad_norm": 6.780792318750173e-05,
"learning_rate": 9.94545804185573e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.3644859813084112,
"grad_norm": 6.843348819529638e-05,
"learning_rate": 9.931003736767013e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.37383177570093457,
"grad_norm": 0.00011038873344659805,
"learning_rate": 9.91486549841951e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.38317757009345793,
"grad_norm": 5.5483953474322334e-05,
"learning_rate": 9.89704883800683e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.3925233644859813,
"grad_norm": 8.126490865834057e-05,
"learning_rate": 9.877559839902184e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.40186915887850466,
"grad_norm": 6.556714652106166e-05,
"learning_rate": 9.85640515958057e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.411214953271028,
"grad_norm": 5.473397686728276e-05,
"learning_rate": 9.833592021345937e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.4205607476635514,
"grad_norm": 0.00011574680684134364,
"learning_rate": 9.809128215864097e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.42990654205607476,
"grad_norm": 9.40759273362346e-05,
"learning_rate": 9.783022097502204e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.4392523364485981,
"grad_norm": 0.00010287982877343893,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.4485981308411215,
"grad_norm": 0.00010786245547933504,
"learning_rate": 9.725919140804099e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.45794392523364486,
"grad_norm": 0.00014578491391148418,
"learning_rate": 9.694941803075283e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.4672897196261682,
"grad_norm": 0.00013963892706669867,
"learning_rate": 9.662361147021779e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.4672897196261682,
"eval_loss": 11.5,
"eval_runtime": 1.1298,
"eval_samples_per_second": 160.208,
"eval_steps_per_second": 80.547,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8039615692800.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}