dada22231's picture
Training in progress, step 50, checkpoint
801e3a0 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.06452653653815131,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0012905307307630263,
"grad_norm": 2.093479871749878,
"learning_rate": 5e-05,
"loss": 0.4083,
"step": 1
},
{
"epoch": 0.0012905307307630263,
"eval_loss": NaN,
"eval_runtime": 3.8475,
"eval_samples_per_second": 12.996,
"eval_steps_per_second": 3.379,
"step": 1
},
{
"epoch": 0.0025810614615260526,
"grad_norm": 0.0,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.003871592192289079,
"grad_norm": 0.0,
"learning_rate": 9.990365154573717e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.005162122923052105,
"grad_norm": 0.0,
"learning_rate": 9.961501876182148e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.006452653653815131,
"grad_norm": 0.0,
"learning_rate": 9.913533761814537e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.007743184384578158,
"grad_norm": 0.0,
"learning_rate": 9.846666218300807e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.009033715115341184,
"grad_norm": 0.0,
"learning_rate": 9.761185582727977e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.01032424584610421,
"grad_norm": 0.0,
"learning_rate": 9.657457896300791e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.011614776576867237,
"grad_norm": 0.0,
"learning_rate": 9.535927336897098e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.012905307307630263,
"grad_norm": 0.0,
"learning_rate": 9.397114317029975e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.014195838038393289,
"grad_norm": 0.0,
"learning_rate": 9.241613255361455e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.015486368769156315,
"grad_norm": 0.0,
"learning_rate": 9.070090031310558e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.016776899499919343,
"grad_norm": 1.0929203033447266,
"learning_rate": 8.883279133655399e-05,
"loss": 0.1135,
"step": 13
},
{
"epoch": 0.018067430230682368,
"grad_norm": 0.0,
"learning_rate": 8.681980515339464e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.019357960961445396,
"grad_norm": 0.0,
"learning_rate": 8.467056167950311e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.02064849169220842,
"grad_norm": 0.0,
"learning_rate": 8.239426430539243e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.02193902242297145,
"grad_norm": 0.0,
"learning_rate": 8.000066048588211e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.023229553153734473,
"grad_norm": 0.0,
"learning_rate": 7.75e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.0245200838844975,
"grad_norm": 0.0,
"learning_rate": 7.490299105985507e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.025810614615260526,
"grad_norm": 0.0,
"learning_rate": 7.222075445642904e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.027101145346023554,
"grad_norm": 0.0,
"learning_rate": 6.946477593864228e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.028391676076786578,
"grad_norm": 0.0,
"learning_rate": 6.664685702961344e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.029682206807549606,
"grad_norm": 0.0,
"learning_rate": 6.377906449072578e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.03097273753831263,
"grad_norm": 0.0,
"learning_rate": 6.087367864990233e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.032263268269075655,
"grad_norm": 0.0,
"learning_rate": 5.794314081535644e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.032263268269075655,
"eval_loss": NaN,
"eval_runtime": 3.4766,
"eval_samples_per_second": 14.382,
"eval_steps_per_second": 3.739,
"step": 25
},
{
"epoch": 0.03355379899983869,
"grad_norm": 0.7012822031974792,
"learning_rate": 5.500000000000001e-05,
"loss": 0.0063,
"step": 26
},
{
"epoch": 0.03484432973060171,
"grad_norm": 0.0,
"learning_rate": 5.205685918464356e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.036134860461364736,
"grad_norm": 0.0,
"learning_rate": 4.912632135009769e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.03742539119212776,
"grad_norm": 0.0,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.03871592192289079,
"grad_norm": 0.0,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.040006452653653816,
"grad_norm": 0.0,
"learning_rate": 4.053522406135775e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.04129698338441684,
"grad_norm": 0.0,
"learning_rate": 3.777924554357096e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.042587514115179866,
"grad_norm": 0.0,
"learning_rate": 3.509700894014496e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.0438780448459429,
"grad_norm": 0.0,
"learning_rate": 3.250000000000001e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.04516857557670592,
"grad_norm": 0.0,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.046459106307468946,
"grad_norm": 0.0,
"learning_rate": 2.760573569460757e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.04774963703823197,
"grad_norm": 0.0,
"learning_rate": 2.53294383204969e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.049040167768995,
"grad_norm": 2.208824396133423,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.0403,
"step": 38
},
{
"epoch": 0.05033069849975803,
"grad_norm": 0.0,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.05162122923052105,
"grad_norm": 0.0,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.052911759961284076,
"grad_norm": 0.0,
"learning_rate": 1.758386744638546e-05,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.05420229069204711,
"grad_norm": 0.0,
"learning_rate": 1.602885682970026e-05,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.05549282142281013,
"grad_norm": 0.0,
"learning_rate": 1.464072663102903e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.056783352153573156,
"grad_norm": 0.0,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.05807388288433618,
"grad_norm": 0.0,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.05936441361509921,
"grad_norm": 0.0,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.06065494434586224,
"grad_norm": 0.0,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.06194547507662526,
"grad_norm": 0.0,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.06323600580738829,
"grad_norm": 0.0,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.06452653653815131,
"grad_norm": 0.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.06452653653815131,
"eval_loss": NaN,
"eval_runtime": 3.4858,
"eval_samples_per_second": 14.344,
"eval_steps_per_second": 3.729,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.968083617316864e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}