| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9335978527249388, |
| "eval_steps": 250, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2333994631812347, |
| "grad_norm": 8.46024227142334, |
| "learning_rate": 8.969068649097766e-05, |
| "loss": 0.3738, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2333994631812347, |
| "eval_loss": 0.20793108642101288, |
| "eval_runtime": 15.7808, |
| "eval_samples_per_second": 5.513, |
| "eval_steps_per_second": 5.513, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.4667989263624694, |
| "grad_norm": 4.400637626647949, |
| "learning_rate": 5.79860922155139e-05, |
| "loss": 0.1638, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4667989263624694, |
| "eval_loss": 0.13212710618972778, |
| "eval_runtime": 15.6918, |
| "eval_samples_per_second": 5.544, |
| "eval_steps_per_second": 5.544, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7001983895437041, |
| "grad_norm": 3.2916624546051025, |
| "learning_rate": 2.1923372839080146e-05, |
| "loss": 0.1173, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7001983895437041, |
| "eval_loss": 0.11467555165290833, |
| "eval_runtime": 15.7005, |
| "eval_samples_per_second": 5.541, |
| "eval_steps_per_second": 5.541, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.9335978527249388, |
| "grad_norm": 2.817092180252075, |
| "learning_rate": 1.1824717285160991e-06, |
| "loss": 0.1002, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9335978527249388, |
| "eval_loss": 0.11014445126056671, |
| "eval_runtime": 15.8191, |
| "eval_samples_per_second": 5.5, |
| "eval_steps_per_second": 5.5, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 250, |
| "max_steps": 1071, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 250, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.700152153473843e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
