125 lines
3.3 KiB
JSON
125 lines
3.3 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 199,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 0.9629484385251998,
|
||
|
|
"epoch": 0.10050251256281408,
|
||
|
|
"grad_norm": 4.09375,
|
||
|
|
"learning_rate": 1.9000000000000002e-06,
|
||
|
|
"loss": 0.9181639671325683,
|
||
|
|
"mean_token_accuracy": 0.8306790262460708,
|
||
|
|
"num_tokens": 40960.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.9275371879339218,
|
||
|
|
"epoch": 0.20100502512562815,
|
||
|
|
"grad_norm": 4.28125,
|
||
|
|
"learning_rate": 3.900000000000001e-06,
|
||
|
|
"loss": 0.8665243148803711,
|
||
|
|
"mean_token_accuracy": 0.8379091203212738,
|
||
|
|
"num_tokens": 81920.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8652732700109482,
|
||
|
|
"epoch": 0.3015075376884422,
|
||
|
|
"grad_norm": 3.359375,
|
||
|
|
"learning_rate": 5.9e-06,
|
||
|
|
"loss": 0.7930655002593994,
|
||
|
|
"mean_token_accuracy": 0.8541035562753677,
|
||
|
|
"num_tokens": 122880.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.780908739566803,
|
||
|
|
"epoch": 0.4020100502512563,
|
||
|
|
"grad_norm": 2.6875,
|
||
|
|
"learning_rate": 7.9e-06,
|
||
|
|
"loss": 0.7104530334472656,
|
||
|
|
"mean_token_accuracy": 0.8606008648872375,
|
||
|
|
"num_tokens": 163840.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.598466919362545,
|
||
|
|
"epoch": 0.5025125628140703,
|
||
|
|
"grad_norm": 4.9375,
|
||
|
|
"learning_rate": 9.9e-06,
|
||
|
|
"loss": 0.5393049240112304,
|
||
|
|
"mean_token_accuracy": 0.8908646881580353,
|
||
|
|
"num_tokens": 204800.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40023221969604494,
|
||
|
|
"epoch": 0.6030150753768844,
|
||
|
|
"grad_norm": 2.734375,
|
||
|
|
"learning_rate": 9.118382907149164e-06,
|
||
|
|
"loss": 0.3737324237823486,
|
||
|
|
"mean_token_accuracy": 0.9215437412261963,
|
||
|
|
"num_tokens": 245760.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3805061921477318,
|
||
|
|
"epoch": 0.7035175879396985,
|
||
|
|
"grad_norm": 3.125,
|
||
|
|
"learning_rate": 6.635339816587109e-06,
|
||
|
|
"loss": 0.35905587673187256,
|
||
|
|
"mean_token_accuracy": 0.9224676638841629,
|
||
|
|
"num_tokens": 286652.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.31945948526263235,
|
||
|
|
"epoch": 0.8040201005025126,
|
||
|
|
"grad_norm": 3.125,
|
||
|
|
"learning_rate": 3.5153981233586277e-06,
|
||
|
|
"loss": 0.29033424854278567,
|
||
|
|
"mean_token_accuracy": 0.935295569896698,
|
||
|
|
"num_tokens": 327612.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3433520093560219,
|
||
|
|
"epoch": 0.9045226130653267,
|
||
|
|
"grad_norm": 2.9375,
|
||
|
|
"learning_rate": 9.73648712344707e-07,
|
||
|
|
"loss": 0.32125253677368165,
|
||
|
|
"mean_token_accuracy": 0.930393049120903,
|
||
|
|
"num_tokens": 367708.0,
|
||
|
|
"step": 180
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 20,
|
||
|
|
"max_steps": 199,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 1000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 3757085019549696.0,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|