| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.05, |
| "eval_steps": 100, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0125, |
| "grad_norm": 0.14176353812217712, |
| "learning_rate": 0.0004, |
| "loss": 1.1525, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 0.1460508555173874, |
| "learning_rate": 0.0004998852503731983, |
| "loss": 1.047, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0375, |
| "grad_norm": 0.2368021011352539, |
| "learning_rate": 0.0004993848168027977, |
| "loss": 0.8529, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.14488168060779572, |
| "learning_rate": 0.0004984880506341147, |
| "loss": 0.9756, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.05, |
| "eval_loss": 0.9470569491386414, |
| "eval_runtime": 845.9115, |
| "eval_samples_per_second": 1.297, |
| "eval_steps_per_second": 0.021, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 2000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0079315433619456e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
