| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 37, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0547945205479452, |
| "grad_norm": 180.05765669383916, |
| "learning_rate": 2.242438242175754e-06, |
| "loss": 13.125, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1095890410958904, |
| "grad_norm": 194.9212123528507, |
| "learning_rate": 4.484876484351508e-06, |
| "loss": 13.6562, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.1643835616438356, |
| "grad_norm": 183.5584675658948, |
| "learning_rate": 5.796618766207391e-06, |
| "loss": 13.4375, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2191780821917808, |
| "grad_norm": 172.5618529609364, |
| "learning_rate": 6.727314726527262e-06, |
| "loss": 12.9531, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.273972602739726, |
| "grad_norm": 157.57820334060722, |
| "learning_rate": 7.44921859773347e-06, |
| "loss": 11.875, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3287671232876712, |
| "grad_norm": 137.3144971772426, |
| "learning_rate": 8.039057008383146e-06, |
| "loss": 11.5469, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.3835616438356164, |
| "grad_norm": 133.22523175168658, |
| "learning_rate": 8.53775827875806e-06, |
| "loss": 11.5156, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.4383561643835616, |
| "grad_norm": 144.46175801179288, |
| "learning_rate": 8.969752968703017e-06, |
| "loss": 11.375, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.4931506849315068, |
| "grad_norm": 112.70851635623477, |
| "learning_rate": 9.350799290239027e-06, |
| "loss": 11.4688, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.547945205479452, |
| "grad_norm": 96.66131548816342, |
| "learning_rate": 9.691656839909223e-06, |
| "loss": 11.2188, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6027397260273972, |
| "grad_norm": 89.74411287825117, |
| "learning_rate": 9.999999999999999e-06, |
| "loss": 11.375, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.6575342465753424, |
| "grad_norm": 81.71078858231157, |
| "learning_rate": 9.948453608247423e-06, |
| "loss": 11.1719, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.7123287671232876, |
| "grad_norm": 77.70779884032373, |
| "learning_rate": 9.84536082474227e-06, |
| "loss": 11.2031, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.7671232876712328, |
| "grad_norm": 75.4640906408115, |
| "learning_rate": 9.742268041237114e-06, |
| "loss": 11.0781, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.821917808219178, |
| "grad_norm": 70.56872029649819, |
| "learning_rate": 9.63917525773196e-06, |
| "loss": 10.6562, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.8767123287671232, |
| "grad_norm": 69.4620760741923, |
| "learning_rate": 9.536082474226806e-06, |
| "loss": 10.8906, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.9315068493150684, |
| "grad_norm": 70.70229240835477, |
| "learning_rate": 9.43298969072165e-06, |
| "loss": 10.6562, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.9863013698630136, |
| "grad_norm": 67.07330699280296, |
| "learning_rate": 9.329896907216496e-06, |
| "loss": 10.4219, |
| "step": 36 |
| } |
| ], |
| "logging_steps": 2, |
| "max_steps": 216, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
