| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0003299799124728282, |
| "eval_steps": 2, |
| "global_step": 5, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 6.599598249456564e-05, |
| "grad_norm": 0.8410126566886902, |
| "learning_rate": 1e-05, |
| "loss": 3.9392, |
| "step": 1 |
| }, |
| { |
| "epoch": 6.599598249456564e-05, |
| "eval_loss": 4.043721675872803, |
| "eval_runtime": 807.9431, |
| "eval_samples_per_second": 31.586, |
| "eval_steps_per_second": 15.793, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00013199196498913128, |
| "grad_norm": 0.7836183309555054, |
| "learning_rate": 2e-05, |
| "loss": 3.7159, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.00013199196498913128, |
| "eval_loss": 4.028029441833496, |
| "eval_runtime": 1231.8544, |
| "eval_samples_per_second": 20.717, |
| "eval_steps_per_second": 10.358, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.00019798794748369694, |
| "grad_norm": 0.8360162377357483, |
| "learning_rate": 3e-05, |
| "loss": 3.6941, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.00026398392997826255, |
| "grad_norm": 0.8355311751365662, |
| "learning_rate": 4e-05, |
| "loss": 3.7915, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.00026398392997826255, |
| "eval_loss": 4.006803035736084, |
| "eval_runtime": 1053.8646, |
| "eval_samples_per_second": 24.216, |
| "eval_steps_per_second": 12.108, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0003299799124728282, |
| "grad_norm": 0.8096919655799866, |
| "learning_rate": 5e-05, |
| "loss": 3.7106, |
| "step": 5 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 5, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 2, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4253997770735616.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
