| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.005580530150364285, |
| "eval_steps": 3, |
| "global_step": 9, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0006200589055960316, |
| "grad_norm": 0.18599237501621246, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.9319, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0012401178111920632, |
| "grad_norm": 0.09086523950099945, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.6463, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0018601767167880949, |
| "grad_norm": 0.09325356036424637, |
| "learning_rate": 1.2e-05, |
| "loss": 0.575, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0018601767167880949, |
| "eval_loss": 0.7272388935089111, |
| "eval_runtime": 33.9288, |
| "eval_samples_per_second": 2.947, |
| "eval_steps_per_second": 2.947, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0024802356223841263, |
| "grad_norm": 0.09707680344581604, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.7038, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0031002945279801583, |
| "grad_norm": 0.10810782760381699, |
| "learning_rate": 2e-05, |
| "loss": 0.5471, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0037203534335761897, |
| "grad_norm": 0.13030411303043365, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 0.6735, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0037203534335761897, |
| "eval_loss": 0.7256982922554016, |
| "eval_runtime": 33.9528, |
| "eval_samples_per_second": 2.945, |
| "eval_steps_per_second": 2.945, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.004340412339172222, |
| "grad_norm": 0.12336976826190948, |
| "learning_rate": 1.8400000000000003e-05, |
| "loss": 0.654, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.004960471244768253, |
| "grad_norm": 0.16046489775180817, |
| "learning_rate": 1.76e-05, |
| "loss": 0.6301, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.005580530150364285, |
| "grad_norm": 0.11589628458023071, |
| "learning_rate": 1.6800000000000002e-05, |
| "loss": 0.5326, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.005580530150364285, |
| "eval_loss": 0.723076343536377, |
| "eval_runtime": 34.5303, |
| "eval_samples_per_second": 2.896, |
| "eval_steps_per_second": 2.896, |
| "step": 9 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2809460652720128e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
