| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05188067444876784, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010376134889753566, | |
| "grad_norm": 4.774520397186279, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3251, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010376134889753566, | |
| "eval_loss": 2.4496688842773438, | |
| "eval_runtime": 88.7797, | |
| "eval_samples_per_second": 1.836, | |
| "eval_steps_per_second": 0.924, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020752269779507133, | |
| "grad_norm": 5.171838760375977, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3992, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020752269779507133, | |
| "eval_loss": 2.2595393657684326, | |
| "eval_runtime": 2.988, | |
| "eval_samples_per_second": 54.552, | |
| "eval_steps_per_second": 27.443, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": 4.842017650604248, | |
| "learning_rate": 3e-05, | |
| "loss": 2.288, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.041504539559014265, | |
| "grad_norm": 4.57513427734375, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1472, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.041504539559014265, | |
| "eval_loss": 2.0156710147857666, | |
| "eval_runtime": 3.0141, | |
| "eval_samples_per_second": 54.079, | |
| "eval_steps_per_second": 27.205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05188067444876784, | |
| "grad_norm": 4.248907089233398, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9631, | |
| "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": 1640097329971200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |