| { |
| "best_global_step": 408, |
| "best_metric": 0.14063987135887146, |
| "best_model_checkpoint": "./finetuned-model-16\\checkpoint-408", |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 408, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9950248756218906, |
| "grad_norm": 0.31391918659210205, |
| "learning_rate": 4.5e-05, |
| "loss": 0.6159, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.22929957509040833, |
| "eval_runtime": 273.8366, |
| "eval_samples_per_second": 0.548, |
| "eval_steps_per_second": 0.548, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.9751243781094527, |
| "grad_norm": 0.20057903230190277, |
| "learning_rate": 4e-05, |
| "loss": 0.1357, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.17504844069480896, |
| "eval_runtime": 266.7975, |
| "eval_samples_per_second": 0.562, |
| "eval_steps_per_second": 0.562, |
| "step": 102 |
| }, |
| { |
| "epoch": 2.955223880597015, |
| "grad_norm": 0.17970038950443268, |
| "learning_rate": 3.5e-05, |
| "loss": 0.1077, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.1577482372522354, |
| "eval_runtime": 272.0022, |
| "eval_samples_per_second": 0.551, |
| "eval_steps_per_second": 0.551, |
| "step": 153 |
| }, |
| { |
| "epoch": 3.935323383084577, |
| "grad_norm": 0.1966184675693512, |
| "learning_rate": 3e-05, |
| "loss": 0.0952, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.1506233513355255, |
| "eval_runtime": 267.0491, |
| "eval_samples_per_second": 0.562, |
| "eval_steps_per_second": 0.562, |
| "step": 204 |
| }, |
| { |
| "epoch": 4.91542288557214, |
| "grad_norm": 0.1875576227903366, |
| "learning_rate": 2.5e-05, |
| "loss": 0.084, |
| "step": 250 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.14753660559654236, |
| "eval_runtime": 270.4534, |
| "eval_samples_per_second": 0.555, |
| "eval_steps_per_second": 0.555, |
| "step": 255 |
| }, |
| { |
| "epoch": 5.895522388059701, |
| "grad_norm": 0.18377818167209625, |
| "learning_rate": 2e-05, |
| "loss": 0.0761, |
| "step": 300 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.1423492133617401, |
| "eval_runtime": 265.4746, |
| "eval_samples_per_second": 0.565, |
| "eval_steps_per_second": 0.565, |
| "step": 306 |
| }, |
| { |
| "epoch": 6.875621890547263, |
| "grad_norm": 0.2825164198875427, |
| "learning_rate": 1.5e-05, |
| "loss": 0.0696, |
| "step": 350 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.14101704955101013, |
| "eval_runtime": 273.874, |
| "eval_samples_per_second": 0.548, |
| "eval_steps_per_second": 0.548, |
| "step": 357 |
| }, |
| { |
| "epoch": 7.855721393034826, |
| "grad_norm": 0.28249576687812805, |
| "learning_rate": 1e-05, |
| "loss": 0.0646, |
| "step": 400 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.14063987135887146, |
| "eval_runtime": 272.1784, |
| "eval_samples_per_second": 0.551, |
| "eval_steps_per_second": 0.551, |
| "step": 408 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5771724147379405e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
