| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5128205128205128, |
| "grad_norm": 4.0485687255859375, |
| "learning_rate": 0.00012, |
| "loss": 3.7292850494384764, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 7.421485424041748, |
| "learning_rate": 0.00017600000000000002, |
| "loss": 2.370315170288086, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.5128205128205128, |
| "grad_norm": 2.107717990875244, |
| "learning_rate": 0.00013600000000000003, |
| "loss": 1.146452045440674, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.5380945205688477, |
| "learning_rate": 9.6e-05, |
| "loss": 1.0121394157409669, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.5128205128205128, |
| "grad_norm": 1.6221106052398682, |
| "learning_rate": 5.6000000000000006e-05, |
| "loss": 0.9575329780578613, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 3.0580832958221436, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.9462905883789062, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 60, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1474640820043776.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
