| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.9375, |
| "eval_steps": 500, |
| "global_step": 18, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10416666666666667, |
| "grad_norm": 1.5762656927108765, |
| "learning_rate": 5.0000000000000004e-08, |
| "loss": 1.1189, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.20833333333333334, |
| "grad_norm": 1.5815638303756714, |
| "learning_rate": 1.0000000000000001e-07, |
| "loss": 1.1288, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.3125, |
| "grad_norm": 1.5717893838882446, |
| "learning_rate": 1.5000000000000002e-07, |
| "loss": 1.115, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.4166666666666667, |
| "grad_norm": 1.5886478424072266, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 1.1272, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.5208333333333334, |
| "grad_norm": 1.6140114068984985, |
| "learning_rate": 2.5000000000000004e-07, |
| "loss": 1.1297, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 1.531928300857544, |
| "learning_rate": 3.0000000000000004e-07, |
| "loss": 1.0938, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.7291666666666666, |
| "grad_norm": 1.651231288909912, |
| "learning_rate": 3.5000000000000004e-07, |
| "loss": 1.1527, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 1.581553339958191, |
| "learning_rate": 4.0000000000000003e-07, |
| "loss": 1.1459, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.9375, |
| "grad_norm": 1.597037434577942, |
| "learning_rate": 4.5000000000000003e-07, |
| "loss": 1.1213, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.1041666666666667, |
| "grad_norm": 2.725217819213867, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 2.2635, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.2083333333333333, |
| "grad_norm": 1.5833462476730347, |
| "learning_rate": 5.5e-07, |
| "loss": 1.1192, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.3125, |
| "grad_norm": 1.4980436563491821, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 1.1164, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.4166666666666667, |
| "grad_norm": 1.4632362127304077, |
| "learning_rate": 6.5e-07, |
| "loss": 1.1132, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.5208333333333335, |
| "grad_norm": 1.5239213705062866, |
| "learning_rate": 7.000000000000001e-07, |
| "loss": 1.1396, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.625, |
| "grad_norm": 1.3787108659744263, |
| "learning_rate": 7.5e-07, |
| "loss": 1.1137, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.7291666666666665, |
| "grad_norm": 1.3480465412139893, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 1.0939, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.8333333333333335, |
| "grad_norm": 1.2965192794799805, |
| "learning_rate": 8.500000000000001e-07, |
| "loss": 1.0985, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.9375, |
| "grad_norm": 1.2198084592819214, |
| "learning_rate": 9.000000000000001e-07, |
| "loss": 1.0928, |
| "step": 18 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 54, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 9, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3664872029172531e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
