| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07497656982193064, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01499531396438613, | |
| "grad_norm": 12.217650413513184, | |
| "learning_rate": 1e-05, | |
| "loss": 3.4609, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01499531396438613, | |
| "eval_loss": 3.578394889831543, | |
| "eval_runtime": 101.6781, | |
| "eval_samples_per_second": 1.111, | |
| "eval_steps_per_second": 0.561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02999062792877226, | |
| "grad_norm": 10.89513111114502, | |
| "learning_rate": 2e-05, | |
| "loss": 3.3984, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02999062792877226, | |
| "eval_loss": 3.4646522998809814, | |
| "eval_runtime": 1.506, | |
| "eval_samples_per_second": 75.032, | |
| "eval_steps_per_second": 37.848, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04498594189315839, | |
| "grad_norm": 9.607409477233887, | |
| "learning_rate": 3e-05, | |
| "loss": 3.4362, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05998125585754452, | |
| "grad_norm": 10.251847267150879, | |
| "learning_rate": 4e-05, | |
| "loss": 3.2573, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05998125585754452, | |
| "eval_loss": 2.9723637104034424, | |
| "eval_runtime": 1.5083, | |
| "eval_samples_per_second": 74.918, | |
| "eval_steps_per_second": 37.79, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07497656982193064, | |
| "grad_norm": 7.836271286010742, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0178, | |
| "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": 1000194661416960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |