| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.005276348766653476, |
| "eval_steps": 13, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00010552697533306952, |
| "eval_loss": 0.6872584223747253, |
| "eval_runtime": 191.271, |
| "eval_samples_per_second": 20.86, |
| "eval_steps_per_second": 10.43, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.001055269753330695, |
| "grad_norm": 1.006353497505188, |
| "learning_rate": 0.0002, |
| "loss": 2.7426, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0013718506793299037, |
| "eval_loss": 0.5626382827758789, |
| "eval_runtime": 191.1719, |
| "eval_samples_per_second": 20.871, |
| "eval_steps_per_second": 10.436, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.00211053950666139, |
| "grad_norm": 1.0054012537002563, |
| "learning_rate": 0.0002, |
| "loss": 2.3127, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0027437013586598074, |
| "eval_loss": 0.5269766449928284, |
| "eval_runtime": 191.3171, |
| "eval_samples_per_second": 20.855, |
| "eval_steps_per_second": 10.428, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.0031658092599920855, |
| "grad_norm": 0.962287425994873, |
| "learning_rate": 0.0002, |
| "loss": 2.0478, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.004115552037989711, |
| "eval_loss": 0.5131546258926392, |
| "eval_runtime": 191.3668, |
| "eval_samples_per_second": 20.85, |
| "eval_steps_per_second": 10.425, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.00422107901332278, |
| "grad_norm": 0.8173459768295288, |
| "learning_rate": 0.0002, |
| "loss": 2.1329, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.005276348766653476, |
| "grad_norm": 0.8819639086723328, |
| "learning_rate": 0.0002, |
| "loss": 2.11, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.302999393632256e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
