| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05239030779305828, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010478061558611657, | |
| "grad_norm": 105.40110778808594, | |
| "learning_rate": 1e-05, | |
| "loss": 150.9038, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010478061558611657, | |
| "eval_loss": 9.500138282775879, | |
| "eval_runtime": 26.4016, | |
| "eval_samples_per_second": 6.098, | |
| "eval_steps_per_second": 3.068, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020956123117223315, | |
| "grad_norm": 66.07787322998047, | |
| "learning_rate": 2e-05, | |
| "loss": 149.5806, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020956123117223315, | |
| "eval_loss": 9.392487525939941, | |
| "eval_runtime": 5.6955, | |
| "eval_samples_per_second": 28.268, | |
| "eval_steps_per_second": 14.222, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03143418467583497, | |
| "grad_norm": 53.52432632446289, | |
| "learning_rate": 3e-05, | |
| "loss": 152.0958, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04191224623444663, | |
| "grad_norm": 88.83341217041016, | |
| "learning_rate": 4e-05, | |
| "loss": 159.5014, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04191224623444663, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.8211, | |
| "eval_samples_per_second": 27.658, | |
| "eval_steps_per_second": 13.915, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05239030779305828, | |
| "grad_norm": 119.91407012939453, | |
| "learning_rate": 5e-05, | |
| "loss": 150.8875, | |
| "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": 3257498484080640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |