| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0051105148843746005, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010221029768749201, | |
| "grad_norm": 0.5549950003623962, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3765, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010221029768749201, | |
| "eval_loss": 0.44058656692504883, | |
| "eval_runtime": 91.6327, | |
| "eval_samples_per_second": 17.985, | |
| "eval_steps_per_second": 8.992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020442059537498403, | |
| "grad_norm": 0.6277570128440857, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3879, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020442059537498403, | |
| "eval_loss": 0.43155425786972046, | |
| "eval_runtime": 44.5676, | |
| "eval_samples_per_second": 36.978, | |
| "eval_steps_per_second": 18.489, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030663089306247606, | |
| "grad_norm": 0.4633312225341797, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0040884119074996806, | |
| "grad_norm": 0.5206245183944702, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4496, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0040884119074996806, | |
| "eval_loss": 0.4164319336414337, | |
| "eval_runtime": 44.4583, | |
| "eval_samples_per_second": 37.068, | |
| "eval_steps_per_second": 18.534, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0051105148843746005, | |
| "grad_norm": 0.38588643074035645, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3634, | |
| "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": 902045682892800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |