| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1457725947521866, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029154518950437317, | |
| "eval_loss": 1.0678009986877441, | |
| "eval_runtime": 29.9955, | |
| "eval_samples_per_second": 4.834, | |
| "eval_steps_per_second": 2.434, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014577259475218658, | |
| "grad_norm": 3.4854559898376465, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1082, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.029154518950437316, | |
| "grad_norm": 0.5768101215362549, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8683, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029154518950437316, | |
| "eval_loss": 0.7050144672393799, | |
| "eval_runtime": 16.5492, | |
| "eval_samples_per_second": 8.762, | |
| "eval_steps_per_second": 4.411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.043731778425655975, | |
| "grad_norm": 0.6184126138687134, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6805, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "grad_norm": 0.5680379867553711, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5336, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "eval_loss": 0.4865669906139374, | |
| "eval_runtime": 16.575, | |
| "eval_samples_per_second": 8.748, | |
| "eval_steps_per_second": 4.404, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0728862973760933, | |
| "grad_norm": 0.4368301331996918, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4891, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08746355685131195, | |
| "grad_norm": 0.5589450597763062, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4561, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08746355685131195, | |
| "eval_loss": 0.4273768961429596, | |
| "eval_runtime": 16.5732, | |
| "eval_samples_per_second": 8.749, | |
| "eval_steps_per_second": 4.405, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 0.5327385663986206, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3802, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11661807580174927, | |
| "grad_norm": 0.6949646472930908, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4526, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11661807580174927, | |
| "eval_loss": 0.40451228618621826, | |
| "eval_runtime": 7.7124, | |
| "eval_samples_per_second": 18.801, | |
| "eval_steps_per_second": 9.465, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13119533527696792, | |
| "grad_norm": 0.4946649372577667, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4593, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1457725947521866, | |
| "grad_norm": 0.533318042755127, | |
| "learning_rate": 0.0, | |
| "loss": 0.4382, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1457725947521866, | |
| "eval_loss": 0.40053504705429077, | |
| "eval_runtime": 7.7542, | |
| "eval_samples_per_second": 18.7, | |
| "eval_steps_per_second": 9.414, | |
| "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": 4870304044154880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |