| { |
| "best_global_step": 110, |
| "best_metric": 0.85, |
| "best_model_checkpoint": "./results/checkpoint-110", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 220, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 6.09375, |
| "learning_rate": 1.5545454545454547e-05, |
| "loss": 0.652421875, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 3.265625, |
| "learning_rate": 1.1000000000000001e-05, |
| "loss": 0.5743359375, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.85, |
| "eval_f1_macro": 0.8474214220323466, |
| "eval_loss": 0.5274999737739563, |
| "eval_runtime": 28.0555, |
| "eval_samples_per_second": 7.129, |
| "eval_steps_per_second": 0.463, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 6.0625, |
| "learning_rate": 6.454545454545456e-06, |
| "loss": 0.52328125, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 3.453125, |
| "learning_rate": 1.9090909090909095e-06, |
| "loss": 0.5030078125, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.85, |
| "eval_f1_macro": 0.8474214220323466, |
| "eval_loss": 0.4975000023841858, |
| "eval_runtime": 28.0852, |
| "eval_samples_per_second": 7.121, |
| "eval_steps_per_second": 0.463, |
| "step": 220 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 220, |
| "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": 4.966406914690253e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
