| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004333850987756871, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001444616995918957, | |
| "eval_loss": 4.278669834136963, | |
| "eval_runtime": 415.7947, | |
| "eval_samples_per_second": 7.011, | |
| "eval_steps_per_second": 3.507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004333850987756871, | |
| "grad_norm": 17.955181121826172, | |
| "learning_rate": 6e-05, | |
| "loss": 17.2571, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008667701975513742, | |
| "grad_norm": 30.18239974975586, | |
| "learning_rate": 0.00012, | |
| "loss": 15.1908, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011556935967351656, | |
| "eval_loss": 3.6038780212402344, | |
| "eval_runtime": 418.3512, | |
| "eval_samples_per_second": 6.968, | |
| "eval_steps_per_second": 3.485, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013001552963270613, | |
| "grad_norm": 15.820569038391113, | |
| "learning_rate": 0.00018, | |
| "loss": 17.5655, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017335403951027485, | |
| "grad_norm": 16.057815551757812, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.0606, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021669254938784356, | |
| "grad_norm": 16.6131534576416, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.8011, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002311387193470331, | |
| "eval_loss": 1.762964129447937, | |
| "eval_runtime": 418.1522, | |
| "eval_samples_per_second": 6.971, | |
| "eval_steps_per_second": 3.487, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0026003105926541226, | |
| "grad_norm": 16.49802017211914, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.0382, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0030336956914298096, | |
| "grad_norm": 26.29454803466797, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 5.618, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003467080790205497, | |
| "grad_norm": 17.33134651184082, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 5.131, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003467080790205497, | |
| "eval_loss": 1.1837964057922363, | |
| "eval_runtime": 418.1468, | |
| "eval_samples_per_second": 6.971, | |
| "eval_steps_per_second": 3.487, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003900465888981184, | |
| "grad_norm": 11.797550201416016, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 4.2143, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004333850987756871, | |
| "grad_norm": 26.031042098999023, | |
| "learning_rate": 0.0, | |
| "loss": 4.1061, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9772495452241920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |