| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1908, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5687096774193549, | |
| "eval_loss": 0.1982271522283554, | |
| "eval_runtime": 5.4428, | |
| "eval_samples_per_second": 569.563, | |
| "eval_steps_per_second": 11.942, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 0.5293694734573364, | |
| "learning_rate": 1.4758909853249476e-05, | |
| "loss": 0.3141, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8093548387096774, | |
| "eval_loss": 0.10087499022483826, | |
| "eval_runtime": 5.7931, | |
| "eval_samples_per_second": 535.119, | |
| "eval_steps_per_second": 11.22, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8661290322580645, | |
| "eval_loss": 0.07097209990024567, | |
| "eval_runtime": 5.4004, | |
| "eval_samples_per_second": 574.028, | |
| "eval_steps_per_second": 12.036, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 0.45407164096832275, | |
| "learning_rate": 9.517819706498952e-06, | |
| "loss": 0.1164, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.89, | |
| "eval_loss": 0.05795975774526596, | |
| "eval_runtime": 5.4937, | |
| "eval_samples_per_second": 564.279, | |
| "eval_steps_per_second": 11.832, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.716981132075472, | |
| "grad_norm": 0.3293832242488861, | |
| "learning_rate": 4.276729559748428e-06, | |
| "loss": 0.0802, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8938709677419355, | |
| "eval_loss": 0.05106966942548752, | |
| "eval_runtime": 5.6501, | |
| "eval_samples_per_second": 548.662, | |
| "eval_steps_per_second": 11.504, | |
| "step": 1590 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1908, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 391368939443328.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.9950904439220233, | |
| "num_train_epochs": 6, | |
| "temperature": 16 | |
| } | |
| } | |