| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.7001983895437041, |
| "eval_steps": 250, |
| "global_step": 750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2333994631812347, |
| "grad_norm": 3.1128056049346924, |
| "learning_rate": 8.969068649097766e-05, |
| "loss": 0.2851, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2333994631812347, |
| "eval_loss": 0.15404489636421204, |
| "eval_runtime": 39.3631, |
| "eval_samples_per_second": 2.21, |
| "eval_steps_per_second": 2.21, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.4667989263624694, |
| "grad_norm": 3.4641659259796143, |
| "learning_rate": 5.813544178200335e-05, |
| "loss": 0.1154, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4667989263624694, |
| "eval_loss": 0.11920379847288132, |
| "eval_runtime": 39.2821, |
| "eval_samples_per_second": 2.215, |
| "eval_steps_per_second": 2.215, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7001983895437041, |
| "grad_norm": 2.7316863536834717, |
| "learning_rate": 2.2048719230965166e-05, |
| "loss": 0.1, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7001983895437041, |
| "eval_loss": 0.10999467223882675, |
| "eval_runtime": 39.3617, |
| "eval_samples_per_second": 2.21, |
| "eval_steps_per_second": 2.21, |
| "step": 750 |
| } |
| ], |
| "logging_steps": 250, |
| "max_steps": 1071, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 250, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.012290477060506e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
