| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0007343424422393773, |
| "eval_steps": 8, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.6717122111968867e-05, |
| "eval_loss": 3.2656073570251465, |
| "eval_runtime": 1460.1195, |
| "eval_samples_per_second": 7.854, |
| "eval_steps_per_second": 3.927, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00011015136633590659, |
| "grad_norm": 5.594817161560059, |
| "learning_rate": 6e-05, |
| "loss": 3.7059, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.00022030273267181319, |
| "grad_norm": 5.5571393966674805, |
| "learning_rate": 0.00012, |
| "loss": 2.8477, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.00029373697689575093, |
| "eval_loss": 1.1682640314102173, |
| "eval_runtime": 1465.6652, |
| "eval_samples_per_second": 7.824, |
| "eval_steps_per_second": 3.912, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.00033045409900771977, |
| "grad_norm": 3.6698296070098877, |
| "learning_rate": 0.00018, |
| "loss": 1.6419, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.00044060546534362637, |
| "grad_norm": 7.199770927429199, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 0.877, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.000550756831679533, |
| "grad_norm": 2.474736452102661, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 0.7117, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0005874739537915019, |
| "eval_loss": 0.5969021916389465, |
| "eval_runtime": 1466.0408, |
| "eval_samples_per_second": 7.822, |
| "eval_steps_per_second": 3.911, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.0006609081980154395, |
| "grad_norm": 2.2165749073028564, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 0.5978, |
| "step": 18 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7418872835604480.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
