| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005747952291995977, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005747952291995977, | |
| "grad_norm": 0.15190516412258148, | |
| "learning_rate": 2e-05, | |
| "loss": 10.4212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005747952291995977, | |
| "eval_loss": 10.403504371643066, | |
| "eval_runtime": 1.8462, | |
| "eval_samples_per_second": 397.04, | |
| "eval_steps_per_second": 198.791, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011495904583991954, | |
| "grad_norm": 0.12761463224887848, | |
| "learning_rate": 4e-05, | |
| "loss": 10.4308, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001724385687598793, | |
| "grad_norm": 0.1444246619939804, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3983, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001724385687598793, | |
| "eval_loss": 10.403398513793945, | |
| "eval_runtime": 1.8161, | |
| "eval_samples_per_second": 403.602, | |
| "eval_steps_per_second": 202.076, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022991809167983907, | |
| "grad_norm": 0.14821669459342957, | |
| "learning_rate": 8e-05, | |
| "loss": 10.401, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028739761459979883, | |
| "grad_norm": 0.17169639468193054, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3765, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003448771375197586, | |
| "grad_norm": 0.19555452466011047, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3845, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003448771375197586, | |
| "eval_loss": 10.402830123901367, | |
| "eval_runtime": 1.8997, | |
| "eval_samples_per_second": 385.849, | |
| "eval_steps_per_second": 193.188, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0040235666043971835, | |
| "grad_norm": 0.1419612467288971, | |
| "learning_rate": 0.00014, | |
| "loss": 10.4663, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0045983618335967815, | |
| "grad_norm": 0.13743838667869568, | |
| "learning_rate": 0.00016, | |
| "loss": 10.4017, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005173157062796379, | |
| "grad_norm": 0.15415261685848236, | |
| "learning_rate": 0.00018, | |
| "loss": 10.4247, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005173157062796379, | |
| "eval_loss": 10.401864051818848, | |
| "eval_runtime": 1.8876, | |
| "eval_samples_per_second": 388.331, | |
| "eval_steps_per_second": 194.43, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005747952291995977, | |
| "grad_norm": 0.2952269911766052, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3284, | |
| "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": 129309081600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |