| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001463057790782736, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "grad_norm": 3.346130688441917e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.8024, | |
| "eval_samples_per_second": 154.204, | |
| "eval_steps_per_second": 77.132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 6.7522555582399946e-06, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 1.1659415577014443e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 15.9028, | |
| "eval_samples_per_second": 162.927, | |
| "eval_steps_per_second": 81.495, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 2.7541331292013638e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 1.3674974979949184e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 1.627303754503373e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.5082, | |
| "eval_samples_per_second": 156.952, | |
| "eval_steps_per_second": 78.507, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011379338372754612, | |
| "grad_norm": 1.4965375157771632e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 3.0348479413078167e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 5.874972430319758e-06, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.3866, | |
| "eval_samples_per_second": 158.117, | |
| "eval_steps_per_second": 79.089, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 263978139648.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |