| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0037285607755406414, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007457121551081282, | |
| "grad_norm": 18.96114158630371, | |
| "learning_rate": 1e-05, | |
| "loss": 30.1008, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007457121551081282, | |
| "eval_loss": 1.872941017150879, | |
| "eval_runtime": 138.518, | |
| "eval_samples_per_second": 16.308, | |
| "eval_steps_per_second": 8.158, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014914243102162564, | |
| "grad_norm": 17.143030166625977, | |
| "learning_rate": 2e-05, | |
| "loss": 28.4639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014914243102162564, | |
| "eval_loss": 1.8408173322677612, | |
| "eval_runtime": 128.5098, | |
| "eval_samples_per_second": 17.578, | |
| "eval_steps_per_second": 8.793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022371364653243847, | |
| "grad_norm": 22.41704750061035, | |
| "learning_rate": 3e-05, | |
| "loss": 31.0986, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002982848620432513, | |
| "grad_norm": 20.779956817626953, | |
| "learning_rate": 4e-05, | |
| "loss": 28.7018, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002982848620432513, | |
| "eval_loss": 1.8102129697799683, | |
| "eval_runtime": 338.6501, | |
| "eval_samples_per_second": 6.671, | |
| "eval_steps_per_second": 3.337, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0037285607755406414, | |
| "grad_norm": 21.318023681640625, | |
| "learning_rate": 5e-05, | |
| "loss": 28.5183, | |
| "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": 6332408345395200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |