| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05486968449931413, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010973936899862825, | |
| "grad_norm": 2.951802968978882, | |
| "learning_rate": 1e-05, | |
| "loss": 1.2819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010973936899862825, | |
| "eval_loss": 1.4376658201217651, | |
| "eval_runtime": 66.4087, | |
| "eval_samples_per_second": 2.319, | |
| "eval_steps_per_second": 1.159, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02194787379972565, | |
| "grad_norm": 2.970388412475586, | |
| "learning_rate": 2e-05, | |
| "loss": 1.27, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02194787379972565, | |
| "eval_loss": 1.389631748199463, | |
| "eval_runtime": 3.8538, | |
| "eval_samples_per_second": 39.96, | |
| "eval_steps_per_second": 19.98, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 1.9156302213668823, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1226, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0438957475994513, | |
| "grad_norm": 2.4562621116638184, | |
| "learning_rate": 4e-05, | |
| "loss": 1.158, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0438957475994513, | |
| "eval_loss": 1.2877274751663208, | |
| "eval_runtime": 3.8666, | |
| "eval_samples_per_second": 39.828, | |
| "eval_steps_per_second": 19.914, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05486968449931413, | |
| "grad_norm": 1.7802428007125854, | |
| "learning_rate": 5e-05, | |
| "loss": 0.89, | |
| "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": 3822182832537600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |