| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016909744240118367, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "grad_norm": 0.2729155421257019, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1118, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 1.1190849542617798, | |
| "eval_runtime": 121.7665, | |
| "eval_samples_per_second": 20.449, | |
| "eval_steps_per_second": 10.224, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003381948848023674, | |
| "grad_norm": 0.24416583776474, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1154, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 0.2208331823348999, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1442, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "eval_loss": 1.1172444820404053, | |
| "eval_runtime": 120.5538, | |
| "eval_samples_per_second": 20.655, | |
| "eval_steps_per_second": 10.327, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006763897696047348, | |
| "grad_norm": 0.3010044991970062, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0057, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 0.284806489944458, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1429, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 0.29003793001174927, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0333, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "eval_loss": 1.0982697010040283, | |
| "eval_runtime": 120.7198, | |
| "eval_samples_per_second": 20.626, | |
| "eval_steps_per_second": 10.313, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011836820968082857, | |
| "grad_norm": 0.37803396582603455, | |
| "learning_rate": 0.00014, | |
| "loss": 0.9585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "grad_norm": 0.2754577398300171, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0303, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 0.2814156413078308, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9728, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "eval_loss": 1.0302141904830933, | |
| "eval_runtime": 120.596, | |
| "eval_samples_per_second": 20.647, | |
| "eval_steps_per_second": 10.324, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 0.3331586420536041, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0627, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3166204172697600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |