| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004276519768212628, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.553039536425257e-05, | |
| "eval_loss": 2.381143808364868, | |
| "eval_runtime": 144.1703, | |
| "eval_samples_per_second": 34.147, | |
| "eval_steps_per_second": 17.077, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008553039536425257, | |
| "grad_norm": 5.450172424316406, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 9.0162, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017106079072850514, | |
| "grad_norm": 4.5537848472595215, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 8.8664, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002565911860927577, | |
| "grad_norm": 7.618182182312012, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 9.0587, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003421215814570103, | |
| "grad_norm": 5.113912582397461, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 8.1141, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004276519768212628, | |
| "grad_norm": 7.7498955726623535, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 8.7842, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004276519768212628, | |
| "eval_loss": 2.1146717071533203, | |
| "eval_runtime": 142.2534, | |
| "eval_samples_per_second": 34.607, | |
| "eval_steps_per_second": 17.307, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9101065021292544.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |