| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06019563581640331, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012039127163280662, | |
| "grad_norm": 4.038699626922607, | |
| "learning_rate": 1e-05, | |
| "loss": 22.6172, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012039127163280662, | |
| "eval_loss": 1.4534040689468384, | |
| "eval_runtime": 26.6155, | |
| "eval_samples_per_second": 5.26, | |
| "eval_steps_per_second": 2.63, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024078254326561323, | |
| "grad_norm": 3.4756643772125244, | |
| "learning_rate": 2e-05, | |
| "loss": 23.25, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024078254326561323, | |
| "eval_loss": 1.4511160850524902, | |
| "eval_runtime": 1.9936, | |
| "eval_samples_per_second": 70.226, | |
| "eval_steps_per_second": 35.113, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03611738148984198, | |
| "grad_norm": 3.8015787601470947, | |
| "learning_rate": 3e-05, | |
| "loss": 23.6953, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04815650865312265, | |
| "grad_norm": 4.418179988861084, | |
| "learning_rate": 4e-05, | |
| "loss": 21.4062, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04815650865312265, | |
| "eval_loss": 1.4460937976837158, | |
| "eval_runtime": 2.0099, | |
| "eval_samples_per_second": 69.655, | |
| "eval_steps_per_second": 34.827, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06019563581640331, | |
| "grad_norm": 3.912907838821411, | |
| "learning_rate": 5e-05, | |
| "loss": 23.9453, | |
| "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": 1194289476403200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |