| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002971459135008246, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.9429182700164916e-05, | |
| "grad_norm": 0.23633639514446259, | |
| "learning_rate": 1e-05, | |
| "loss": 5.3875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.9429182700164916e-05, | |
| "eval_loss": 5.477420330047607, | |
| "eval_runtime": 448.3626, | |
| "eval_samples_per_second": 63.208, | |
| "eval_steps_per_second": 31.604, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011885836540032983, | |
| "grad_norm": 0.2184629589319229, | |
| "learning_rate": 2e-05, | |
| "loss": 5.487, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011885836540032983, | |
| "eval_loss": 5.471240997314453, | |
| "eval_runtime": 325.0871, | |
| "eval_samples_per_second": 87.177, | |
| "eval_steps_per_second": 43.588, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00017828754810049474, | |
| "grad_norm": 0.19975675642490387, | |
| "learning_rate": 3e-05, | |
| "loss": 5.4583, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023771673080065966, | |
| "grad_norm": 0.20301611721515656, | |
| "learning_rate": 4e-05, | |
| "loss": 5.4742, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023771673080065966, | |
| "eval_loss": 5.463846206665039, | |
| "eval_runtime": 325.4787, | |
| "eval_samples_per_second": 87.072, | |
| "eval_steps_per_second": 43.536, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002971459135008246, | |
| "grad_norm": 0.20360742509365082, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4755, | |
| "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": 689133799342080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |