| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4, |
| "grad_norm": 4.253427505493164, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.3123, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 5.989475727081299, |
| "learning_rate": 1.2e-05, |
| "loss": 0.2298, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9698, |
| "eval_loss": 0.10075412690639496, |
| "eval_runtime": 73.2779, |
| "eval_samples_per_second": 68.233, |
| "eval_steps_per_second": 4.271, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 11.917862892150879, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.1791, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 6.352814674377441, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.1424, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 3.428704023361206, |
| "learning_rate": 0.0, |
| "loss": 0.1345, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9774, |
| "eval_loss": 0.08082816004753113, |
| "eval_runtime": 73.6205, |
| "eval_samples_per_second": 67.916, |
| "eval_steps_per_second": 4.252, |
| "step": 2500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 5239934236117440.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
