| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007136485280999108, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007136485280999108, | |
| "grad_norm": 2.565769910812378, | |
| "learning_rate": 2e-05, | |
| "loss": 4.013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007136485280999108, | |
| "eval_loss": 1.0286985635757446, | |
| "eval_runtime": 17.539, | |
| "eval_samples_per_second": 33.639, | |
| "eval_steps_per_second": 16.82, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014272970561998216, | |
| "grad_norm": 2.4501543045043945, | |
| "learning_rate": 4e-05, | |
| "loss": 3.8374, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0021409455842997323, | |
| "grad_norm": 2.5484728813171387, | |
| "learning_rate": 6e-05, | |
| "loss": 3.6732, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021409455842997323, | |
| "eval_loss": 1.0234894752502441, | |
| "eval_runtime": 16.8432, | |
| "eval_samples_per_second": 35.029, | |
| "eval_steps_per_second": 17.514, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002854594112399643, | |
| "grad_norm": 2.547969341278076, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5426, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003568242640499554, | |
| "grad_norm": 3.16939115524292, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6063, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004281891168599465, | |
| "grad_norm": 2.922910451889038, | |
| "learning_rate": 0.00012, | |
| "loss": 4.0793, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004281891168599465, | |
| "eval_loss": 0.964386522769928, | |
| "eval_runtime": 17.3746, | |
| "eval_samples_per_second": 33.958, | |
| "eval_steps_per_second": 16.979, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0049955396966993755, | |
| "grad_norm": 2.464360475540161, | |
| "learning_rate": 0.00014, | |
| "loss": 3.3777, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005709188224799286, | |
| "grad_norm": 2.4393444061279297, | |
| "learning_rate": 0.00016, | |
| "loss": 3.2954, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006422836752899197, | |
| "grad_norm": 1.8291572332382202, | |
| "learning_rate": 0.00018, | |
| "loss": 3.0691, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006422836752899197, | |
| "eval_loss": 0.8526744842529297, | |
| "eval_runtime": 17.3767, | |
| "eval_samples_per_second": 33.954, | |
| "eval_steps_per_second": 16.977, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007136485280999108, | |
| "grad_norm": 2.2370080947875977, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7027, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1289574914457600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |