| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011963511290563781, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002392702258112756, | |
| "grad_norm": 1.433709979057312, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002392702258112756, | |
| "eval_loss": 1.6420891284942627, | |
| "eval_runtime": 79.1902, | |
| "eval_samples_per_second": 8.89, | |
| "eval_steps_per_second": 4.445, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004785404516225512, | |
| "grad_norm": 1.4838870763778687, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6299, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004785404516225512, | |
| "eval_loss": 1.622260332107544, | |
| "eval_runtime": 7.1147, | |
| "eval_samples_per_second": 98.951, | |
| "eval_steps_per_second": 49.475, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007178106774338268, | |
| "grad_norm": 1.0888347625732422, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3673, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009570809032451024, | |
| "grad_norm": 1.33967125415802, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5068, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009570809032451024, | |
| "eval_loss": 1.5901814699172974, | |
| "eval_runtime": 7.106, | |
| "eval_samples_per_second": 99.072, | |
| "eval_steps_per_second": 49.536, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011963511290563781, | |
| "grad_norm": 1.2530596256256104, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4694, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 505145582419968.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |