| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.737864077669903, |
| "eval_steps": 500, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.3576171875, |
| "epoch": 0.1941747572815534, |
| "grad_norm": 1.4468644857406616, |
| "learning_rate": 0.00019991110182465032, |
| "loss": 2.4723321914672853, |
| "mean_token_accuracy": 0.48485579565167425, |
| "num_tokens": 32726.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.86201171875, |
| "epoch": 0.3883495145631068, |
| "grad_norm": 1.8271902799606323, |
| "learning_rate": 0.00019681623029976588, |
| "loss": 1.8011039733886718, |
| "mean_token_accuracy": 0.6076911687850952, |
| "num_tokens": 65640.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.4529296875, |
| "epoch": 0.5825242718446602, |
| "grad_norm": 0.8124955296516418, |
| "learning_rate": 0.00018943324918225494, |
| "loss": 1.473008918762207, |
| "mean_token_accuracy": 0.6781924746930599, |
| "num_tokens": 98479.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.4251953125, |
| "epoch": 0.7766990291262136, |
| "grad_norm": 0.6854525208473206, |
| "learning_rate": 0.00017808915976161362, |
| "loss": 1.3831080436706542, |
| "mean_token_accuracy": 0.6932718701660633, |
| "num_tokens": 131059.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.33134765625, |
| "epoch": 0.970873786407767, |
| "grad_norm": 0.6705339550971985, |
| "learning_rate": 0.0001632864056726917, |
| "loss": 1.352787971496582, |
| "mean_token_accuracy": 0.6971824139356613, |
| "num_tokens": 163507.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.3499177631578947, |
| "epoch": 1.1553398058252426, |
| "grad_norm": 0.6946712732315063, |
| "learning_rate": 0.00014568061905081875, |
| "loss": 1.3419328689575196, |
| "mean_token_accuracy": 0.698928923983323, |
| "num_tokens": 194484.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.32880859375, |
| "epoch": 1.3495145631067962, |
| "grad_norm": 0.7143179178237915, |
| "learning_rate": 0.00012605158178034654, |
| "loss": 1.341660499572754, |
| "mean_token_accuracy": 0.6985750392079353, |
| "num_tokens": 226829.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.352734375, |
| "epoch": 1.5436893203883495, |
| "grad_norm": 0.7239959836006165, |
| "learning_rate": 0.00010526868799852796, |
| "loss": 1.3237122535705566, |
| "mean_token_accuracy": 0.7004663117229939, |
| "num_tokens": 259643.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.34208984375, |
| "epoch": 1.737864077669903, |
| "grad_norm": 0.8467059135437012, |
| "learning_rate": 8.425243756279824e-05, |
| "loss": 1.328163242340088, |
| "mean_token_accuracy": 0.6974119216203689, |
| "num_tokens": 292638.0, |
| "step": 90 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 156, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 913882704047232.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
