| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1305, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.1457993728773934, |
| "las": 70.0495582848524, |
| "step": 261, |
| "uas": 76.8368886015945 |
| }, |
| { |
| "epoch": 1.9157088122605364, |
| "grad_norm": 2.0245819091796875, |
| "learning_rate": 0.00012337164750957856, |
| "loss": 0.6341, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.0447277224489622, |
| "las": 72.65675500969618, |
| "step": 522, |
| "uas": 78.91618185735832 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.9961422878716674, |
| "las": 75.01616031027795, |
| "step": 783, |
| "uas": 80.69381598793363 |
| }, |
| { |
| "epoch": 3.8314176245210727, |
| "grad_norm": 1.2272472381591797, |
| "learning_rate": 4.674329501915709e-05, |
| "loss": 0.2031, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 1.0721387245825358, |
| "las": 75.97500538677009, |
| "step": 1044, |
| "uas": 81.59879336349924 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1305, |
| "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": 2.857315085508096e+16, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
