| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0032928759894459104, |
| "eval_steps": 10, |
| "global_step": 39, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 8.443271767810026e-05, |
| "eval_loss": 6.900400638580322, |
| "eval_runtime": 415.9031, |
| "eval_samples_per_second": 11.991, |
| "eval_steps_per_second": 5.997, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00042216358839050134, |
| "grad_norm": 225.8194580078125, |
| "learning_rate": 5e-05, |
| "loss": 26.3712, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0008443271767810027, |
| "grad_norm": 205.8764190673828, |
| "learning_rate": 0.0001, |
| "loss": 10.7889, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0008443271767810027, |
| "eval_loss": 1.4552971124649048, |
| "eval_runtime": 425.3753, |
| "eval_samples_per_second": 11.724, |
| "eval_steps_per_second": 5.863, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.001266490765171504, |
| "grad_norm": 58.67621994018555, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 3.2996, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0016886543535620053, |
| "grad_norm": 22.526634216308594, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.414, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0016886543535620053, |
| "eval_loss": 0.269288033246994, |
| "eval_runtime": 425.2416, |
| "eval_samples_per_second": 11.727, |
| "eval_steps_per_second": 5.865, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0021108179419525065, |
| "grad_norm": 40.498443603515625, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.8166, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.002532981530343008, |
| "grad_norm": 13.02916431427002, |
| "learning_rate": 5e-05, |
| "loss": 0.2817, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.002532981530343008, |
| "eval_loss": 0.07939723134040833, |
| "eval_runtime": 425.447, |
| "eval_samples_per_second": 11.722, |
| "eval_steps_per_second": 5.862, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0029551451187335093, |
| "grad_norm": 25.84929656982422, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.1741, |
| "step": 35 |
| } |
| ], |
| "logging_steps": 5, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6835420016934912.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
