| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00388651379712398, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000777302759424796, | |
| "grad_norm": 2.1583316326141357, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000777302759424796, | |
| "eval_loss": 2.1645443439483643, | |
| "eval_runtime": 450.4919, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 2.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001554605518849592, | |
| "grad_norm": 2.0188801288604736, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0553, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001554605518849592, | |
| "eval_loss": 2.1477506160736084, | |
| "eval_runtime": 156.8741, | |
| "eval_samples_per_second": 13.814, | |
| "eval_steps_per_second": 6.91, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002331908278274388, | |
| "grad_norm": 2.5796680450439453, | |
| "learning_rate": 3e-05, | |
| "loss": 2.18, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003109211037699184, | |
| "grad_norm": 1.7780840396881104, | |
| "learning_rate": 4e-05, | |
| "loss": 2.046, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003109211037699184, | |
| "eval_loss": 2.0639281272888184, | |
| "eval_runtime": 152.8888, | |
| "eval_samples_per_second": 14.174, | |
| "eval_steps_per_second": 7.09, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00388651379712398, | |
| "grad_norm": 1.4887142181396484, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0311, | |
| "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": 4566575798550528.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |