| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4618937644341801, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009237875288683603, | |
| "eval_loss": 2.44881272315979, | |
| "eval_runtime": 3.1089, | |
| "eval_samples_per_second": 14.796, | |
| "eval_steps_per_second": 7.398, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.046189376443418015, | |
| "grad_norm": 13.313944816589355, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1038, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09237875288683603, | |
| "grad_norm": 14.019678115844727, | |
| "learning_rate": 0.0001, | |
| "loss": 8.1093, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09237875288683603, | |
| "eval_loss": 2.2830543518066406, | |
| "eval_runtime": 3.3082, | |
| "eval_samples_per_second": 13.905, | |
| "eval_steps_per_second": 6.952, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13856812933025403, | |
| "grad_norm": 15.076180458068848, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.0111, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18475750577367206, | |
| "grad_norm": 14.845409393310547, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.3922, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18475750577367206, | |
| "eval_loss": 2.175680637359619, | |
| "eval_runtime": 3.1376, | |
| "eval_samples_per_second": 14.661, | |
| "eval_steps_per_second": 7.331, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23094688221709006, | |
| "grad_norm": 11.069482803344727, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 9.3983, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27713625866050806, | |
| "grad_norm": 12.325895309448242, | |
| "learning_rate": 5e-05, | |
| "loss": 8.6908, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27713625866050806, | |
| "eval_loss": 2.1261730194091797, | |
| "eval_runtime": 3.4805, | |
| "eval_samples_per_second": 13.216, | |
| "eval_steps_per_second": 6.608, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3233256351039261, | |
| "grad_norm": 11.397773742675781, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 8.3931, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3695150115473441, | |
| "grad_norm": 10.571913719177246, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.8807, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3695150115473441, | |
| "eval_loss": 2.1058173179626465, | |
| "eval_runtime": 3.36, | |
| "eval_samples_per_second": 13.69, | |
| "eval_steps_per_second": 6.845, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.41570438799076215, | |
| "grad_norm": 11.090593338012695, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.4343, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4618937644341801, | |
| "grad_norm": 13.508606910705566, | |
| "learning_rate": 0.0, | |
| "loss": 7.9822, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4618937644341801, | |
| "eval_loss": 2.1012914180755615, | |
| "eval_runtime": 3.3938, | |
| "eval_samples_per_second": 13.554, | |
| "eval_steps_per_second": 6.777, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9070076560932864.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |