| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.7894736842105265, |
| "eval_steps": 500, |
| "global_step": 18, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2631578947368421, |
| "grad_norm": 3.5652554035186768, |
| "learning_rate": 5.0000000000000004e-08, |
| "loss": 1.5774, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 3.7139198780059814, |
| "learning_rate": 1.0000000000000001e-07, |
| "loss": 1.5864, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.7894736842105263, |
| "grad_norm": 3.7932980060577393, |
| "learning_rate": 1.5000000000000002e-07, |
| "loss": 1.5906, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.263157894736842, |
| "grad_norm": 6.177077770233154, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 3.199, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.526315789473684, |
| "grad_norm": 3.647991418838501, |
| "learning_rate": 2.5000000000000004e-07, |
| "loss": 1.5871, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.7894736842105263, |
| "grad_norm": 3.688812255859375, |
| "learning_rate": 3.0000000000000004e-07, |
| "loss": 1.5946, |
| "step": 6 |
| }, |
| { |
| "epoch": 2.263157894736842, |
| "grad_norm": 6.196962356567383, |
| "learning_rate": 3.5000000000000004e-07, |
| "loss": 3.1457, |
| "step": 7 |
| }, |
| { |
| "epoch": 2.526315789473684, |
| "grad_norm": 3.6825690269470215, |
| "learning_rate": 4.0000000000000003e-07, |
| "loss": 1.584, |
| "step": 8 |
| }, |
| { |
| "epoch": 2.7894736842105265, |
| "grad_norm": 3.705153465270996, |
| "learning_rate": 4.5000000000000003e-07, |
| "loss": 1.6018, |
| "step": 9 |
| }, |
| { |
| "epoch": 3.263157894736842, |
| "grad_norm": 5.746488571166992, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 3.143, |
| "step": 10 |
| }, |
| { |
| "epoch": 3.526315789473684, |
| "grad_norm": 3.4327023029327393, |
| "learning_rate": 5.5e-07, |
| "loss": 1.5699, |
| "step": 11 |
| }, |
| { |
| "epoch": 3.7894736842105265, |
| "grad_norm": 3.488701105117798, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 1.5862, |
| "step": 12 |
| }, |
| { |
| "epoch": 4.2631578947368425, |
| "grad_norm": 4.868501663208008, |
| "learning_rate": 6.5e-07, |
| "loss": 3.1116, |
| "step": 13 |
| }, |
| { |
| "epoch": 4.526315789473684, |
| "grad_norm": 3.20448637008667, |
| "learning_rate": 7.000000000000001e-07, |
| "loss": 1.5744, |
| "step": 14 |
| }, |
| { |
| "epoch": 4.7894736842105265, |
| "grad_norm": 3.1134121417999268, |
| "learning_rate": 7.5e-07, |
| "loss": 1.5543, |
| "step": 15 |
| }, |
| { |
| "epoch": 5.2631578947368425, |
| "grad_norm": 5.291584014892578, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 3.0701, |
| "step": 16 |
| }, |
| { |
| "epoch": 5.526315789473684, |
| "grad_norm": 2.974121332168579, |
| "learning_rate": 8.500000000000001e-07, |
| "loss": 1.546, |
| "step": 17 |
| }, |
| { |
| "epoch": 5.7894736842105265, |
| "grad_norm": 2.9589760303497314, |
| "learning_rate": 9.000000000000001e-07, |
| "loss": 1.5158, |
| "step": 18 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 18, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.641923852894208e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
