| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008297563388597233, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.1275803560505725e-05, | |
| "eval_loss": 2.515671491622925, | |
| "eval_runtime": 1602.7566, | |
| "eval_samples_per_second": 12.348, | |
| "eval_steps_per_second": 6.174, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010637901780252864, | |
| "grad_norm": 1.4516150951385498, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4158, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021275803560505727, | |
| "grad_norm": 1.6632559299468994, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4992, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00021275803560505727, | |
| "eval_loss": 2.2979066371917725, | |
| "eval_runtime": 1599.5966, | |
| "eval_samples_per_second": 12.372, | |
| "eval_steps_per_second": 6.187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003191370534075859, | |
| "grad_norm": 1.7574139833450317, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3828, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00042551607121011454, | |
| "grad_norm": 1.4096585512161255, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1464, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00042551607121011454, | |
| "eval_loss": 2.1912410259246826, | |
| "eval_runtime": 1602.855, | |
| "eval_samples_per_second": 12.347, | |
| "eval_steps_per_second": 6.174, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005318950890126432, | |
| "grad_norm": 1.3890738487243652, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0921, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0006382741068151718, | |
| "grad_norm": 1.3218567371368408, | |
| "learning_rate": 5e-05, | |
| "loss": 2.161, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006382741068151718, | |
| "eval_loss": 2.1511099338531494, | |
| "eval_runtime": 1610.7205, | |
| "eval_samples_per_second": 12.287, | |
| "eval_steps_per_second": 6.144, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007446531246177005, | |
| "grad_norm": 1.438331127166748, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.172, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7453256523448320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |