| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.041990342221289105, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000839806844425782, | |
| "eval_loss": 0.9849448800086975, | |
| "eval_runtime": 46.1601, | |
| "eval_samples_per_second": 10.875, | |
| "eval_steps_per_second": 5.438, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008398068444257821, | |
| "grad_norm": 1.8189576864242554, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3683, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010917488977535167, | |
| "eval_loss": 0.6001940369606018, | |
| "eval_runtime": 46.1258, | |
| "eval_samples_per_second": 10.883, | |
| "eval_steps_per_second": 5.442, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016796136888515643, | |
| "grad_norm": 1.4079079627990723, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2937, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021834977955070334, | |
| "eval_loss": 0.5132611989974976, | |
| "eval_runtime": 46.1458, | |
| "eval_samples_per_second": 10.879, | |
| "eval_steps_per_second": 5.439, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.025194205332773462, | |
| "grad_norm": 1.608473300933838, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1019, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0327524669326055, | |
| "eval_loss": 0.4722355604171753, | |
| "eval_runtime": 46.1649, | |
| "eval_samples_per_second": 10.874, | |
| "eval_steps_per_second": 5.437, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.033592273777031285, | |
| "grad_norm": 1.2640838623046875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9473, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.041990342221289105, | |
| "grad_norm": 1.2049702405929565, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8443, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 3.1662041726976e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |