| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 82, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 2.4350972054221836, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5769, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 1.9409665743940592, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0321, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.6373853834505803, | |
| "learning_rate": 4.685866540361456e-05, | |
| "loss": 0.5324, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.4835656030978697, | |
| "learning_rate": 3.822410025817406e-05, | |
| "loss": 0.4983, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 1.0227452253571707, | |
| "learning_rate": 2.6266229220967818e-05, | |
| "loss": 0.4741, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 0.3163433503926468, | |
| "learning_rate": 1.399014621105914e-05, | |
| "loss": 0.4467, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.7073170731707317, | |
| "grad_norm": 0.5876366568682337, | |
| "learning_rate": 4.480913969818098e-06, | |
| "loss": 0.4471, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 0.6629601353362649, | |
| "learning_rate": 1.2826691520262114e-07, | |
| "loss": 0.4108, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 82, | |
| "total_flos": 31250490392576.0, | |
| "train_loss": 0.6762613843126994, | |
| "train_runtime": 441.8557, | |
| "train_samples_per_second": 2.96, | |
| "train_steps_per_second": 0.186 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 82, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 31250490392576.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |