| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.873, | |
| "eval_f1 score": 0.8653944242728573, | |
| "eval_loss": 0.4448868930339813, | |
| "eval_runtime": 2.5176, | |
| "eval_samples_per_second": 794.416, | |
| "eval_steps_per_second": 6.355, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9265, | |
| "eval_f1 score": 0.9269527312677431, | |
| "eval_loss": 0.2165956199169159, | |
| "eval_runtime": 2.544, | |
| "eval_samples_per_second": 786.152, | |
| "eval_steps_per_second": 6.289, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.933, | |
| "eval_f1 score": 0.9338650823124836, | |
| "eval_loss": 0.17256759107112885, | |
| "eval_runtime": 2.5585, | |
| "eval_samples_per_second": 781.698, | |
| "eval_steps_per_second": 6.254, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9385, | |
| "eval_f1 score": 0.9386048187212848, | |
| "eval_loss": 0.15524688363075256, | |
| "eval_runtime": 2.5676, | |
| "eval_samples_per_second": 778.947, | |
| "eval_steps_per_second": 6.232, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.938, | |
| "eval_f1 score": 0.9382616136983211, | |
| "eval_loss": 0.14387381076812744, | |
| "eval_runtime": 2.5374, | |
| "eval_samples_per_second": 788.208, | |
| "eval_steps_per_second": 6.306, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.937, | |
| "eval_f1 score": 0.9370370279908306, | |
| "eval_loss": 0.14351172745227814, | |
| "eval_runtime": 2.5532, | |
| "eval_samples_per_second": 783.329, | |
| "eval_steps_per_second": 6.267, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9355, | |
| "eval_f1 score": 0.9355950438866585, | |
| "eval_loss": 0.14806246757507324, | |
| "eval_runtime": 2.566, | |
| "eval_samples_per_second": 779.421, | |
| "eval_steps_per_second": 6.235, | |
| "step": 875 | |
| } | |
| ], | |
| "logging_steps": 16000, | |
| "max_steps": 1250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2881371446784000.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |