| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004781902338840695, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012261288048309474, | |
| "eval_loss": 2.126044273376465, | |
| "eval_runtime": 130.1913, | |
| "eval_samples_per_second": 26.377, | |
| "eval_steps_per_second": 13.188, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006130644024154737, | |
| "grad_norm": 6.848420143127441, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1182, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012261288048309475, | |
| "grad_norm": 5.057512283325195, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5372, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012261288048309475, | |
| "eval_loss": 0.7549862265586853, | |
| "eval_runtime": 132.8853, | |
| "eval_samples_per_second": 25.842, | |
| "eval_steps_per_second": 12.921, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018391932072464212, | |
| "grad_norm": 3.554645538330078, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4652, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002452257609661895, | |
| "grad_norm": 3.504028797149658, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1416, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002452257609661895, | |
| "eval_loss": 0.0860864594578743, | |
| "eval_runtime": 129.789, | |
| "eval_samples_per_second": 26.458, | |
| "eval_steps_per_second": 13.229, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0030653220120773687, | |
| "grad_norm": 1.3442739248275757, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0971, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0036783864144928425, | |
| "grad_norm": 0.27293071150779724, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0908, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0036783864144928425, | |
| "eval_loss": 0.06376616656780243, | |
| "eval_runtime": 130.313, | |
| "eval_samples_per_second": 26.352, | |
| "eval_steps_per_second": 13.176, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004291450816908317, | |
| "grad_norm": 1.9537981748580933, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0999, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1264763208204288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |