| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03208084372619, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012832337490476, | |
| "eval_loss": 8.74209976196289, | |
| "eval_runtime": 358.1544, | |
| "eval_samples_per_second": 7.737, | |
| "eval_steps_per_second": 7.737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006416168745238, | |
| "grad_norm": 13.014253616333008, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.8911, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012832337490476, | |
| "grad_norm": 6.818251609802246, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.3451, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019248506235714, | |
| "grad_norm": 3.329972505569458, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.4424, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025664674980952, | |
| "grad_norm": 2.9790332317352295, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8727, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03208084372619, | |
| "grad_norm": 3.4033408164978027, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.5326, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03208084372619, | |
| "eval_loss": 1.582451343536377, | |
| "eval_runtime": 349.2215, | |
| "eval_samples_per_second": 7.935, | |
| "eval_steps_per_second": 7.935, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9677225695641600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |