| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 3585, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0002789400278940028, |
| "grad_norm": 6.0320281982421875, |
| "learning_rate": 0.0, |
| "loss": 1.6763, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.2789400278940028, |
| "grad_norm": 5.029699802398682, |
| "learning_rate": 1.7422392745029648e-06, |
| "loss": 1.6731, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.2789400278940028, |
| "eval_cosine_accuracy": 0.9435271620750427, |
| "eval_loss": 1.2452138662338257, |
| "eval_runtime": 22.4585, |
| "eval_samples_per_second": 423.403, |
| "eval_steps_per_second": 3.339, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5578800557880056, |
| "grad_norm": 4.080895900726318, |
| "learning_rate": 3.4862225322636904e-06, |
| "loss": 1.4545, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.5578800557880056, |
| "eval_cosine_accuracy": 0.9491008520126343, |
| "eval_loss": 1.1861090660095215, |
| "eval_runtime": 22.7358, |
| "eval_samples_per_second": 418.239, |
| "eval_steps_per_second": 3.299, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8368200836820083, |
| "grad_norm": 4.531359672546387, |
| "learning_rate": 5.230205790024416e-06, |
| "loss": 1.3514, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.8368200836820083, |
| "eval_cosine_accuracy": 0.9529919028282166, |
| "eval_loss": 1.1497896909713745, |
| "eval_runtime": 22.5649, |
| "eval_samples_per_second": 421.406, |
| "eval_steps_per_second": 3.324, |
| "step": 3000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 28680, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
