| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0047875523638539795, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011968880909634949, | |
| "grad_norm": 2.2473669052124023, | |
| "learning_rate": 1e-05, | |
| "loss": 5.577, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011968880909634949, | |
| "eval_loss": 5.6682515144348145, | |
| "eval_runtime": 38.3475, | |
| "eval_samples_per_second": 36.717, | |
| "eval_steps_per_second": 18.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023937761819269898, | |
| "grad_norm": 2.4328646659851074, | |
| "learning_rate": 2e-05, | |
| "loss": 5.6463, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023937761819269898, | |
| "eval_loss": 5.646688461303711, | |
| "eval_runtime": 14.2706, | |
| "eval_samples_per_second": 98.664, | |
| "eval_steps_per_second": 49.332, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003590664272890485, | |
| "grad_norm": 2.2526326179504395, | |
| "learning_rate": 3e-05, | |
| "loss": 5.5169, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "grad_norm": 2.3443996906280518, | |
| "learning_rate": 4e-05, | |
| "loss": 5.508, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "eval_loss": 5.598637104034424, | |
| "eval_runtime": 13.9238, | |
| "eval_samples_per_second": 101.122, | |
| "eval_steps_per_second": 50.561, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 783164469411840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |