| { |
| "best_metric": 0.24322812259197235, |
| "best_model_checkpoint": "mistral_sequence_classification/checkpoint-618", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1030, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.3304608464241028, |
| "eval_pearson": 0.9027747531908439, |
| "eval_runtime": 15.8259, |
| "eval_samples_per_second": 58.891, |
| "eval_steps_per_second": 7.393, |
| "step": 206 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.2608998417854309, |
| "eval_pearson": 0.9531635605038489, |
| "eval_runtime": 15.7775, |
| "eval_samples_per_second": 59.071, |
| "eval_steps_per_second": 7.416, |
| "step": 412 |
| }, |
| { |
| "epoch": 2.4271844660194173, |
| "grad_norm": 21.120954513549805, |
| "learning_rate": 5.145631067961165e-05, |
| "loss": 0.4868, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.24322812259197235, |
| "eval_pearson": 0.961136250737733, |
| "eval_runtime": 15.732, |
| "eval_samples_per_second": 59.242, |
| "eval_steps_per_second": 7.437, |
| "step": 618 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.26112988591194153, |
| "eval_pearson": 0.9639457727475045, |
| "eval_runtime": 15.8547, |
| "eval_samples_per_second": 58.784, |
| "eval_steps_per_second": 7.38, |
| "step": 824 |
| }, |
| { |
| "epoch": 4.854368932038835, |
| "grad_norm": 0.005307361483573914, |
| "learning_rate": 2.912621359223301e-06, |
| "loss": 0.0417, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.2666521966457367, |
| "eval_pearson": 0.9703769235281202, |
| "eval_runtime": 15.6636, |
| "eval_samples_per_second": 59.501, |
| "eval_steps_per_second": 7.47, |
| "step": 1030 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 1030, |
| "total_flos": 6.321458643082445e+16, |
| "train_loss": 0.2567840828768258, |
| "train_runtime": 1141.9471, |
| "train_samples_per_second": 28.745, |
| "train_steps_per_second": 0.902 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1030, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 6.321458643082445e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
