| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9959183673469387, |
| "eval_steps": 500, |
| "global_step": 183, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05442176870748299, |
| "grad_norm": 0.8557426789173155, |
| "learning_rate": 5.263157894736842e-06, |
| "loss": 0.5427, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10884353741496598, |
| "grad_norm": 0.5773100036749792, |
| "learning_rate": 9.999082642158972e-06, |
| "loss": 0.2565, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.16326530612244897, |
| "grad_norm": 0.32703435839603495, |
| "learning_rate": 9.889406426751296e-06, |
| "loss": 0.1904, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.21768707482993196, |
| "grad_norm": 0.2936812973789233, |
| "learning_rate": 9.600859295816708e-06, |
| "loss": 0.1684, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.272108843537415, |
| "grad_norm": 0.28104703021304783, |
| "learning_rate": 9.143997272924974e-06, |
| "loss": 0.1598, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.32653061224489793, |
| "grad_norm": 0.26954904753203757, |
| "learning_rate": 8.535533905932739e-06, |
| "loss": 0.1569, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.291504420774206, |
| "learning_rate": 7.797728829245321e-06, |
| "loss": 0.1457, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.43537414965986393, |
| "grad_norm": 0.25827004955042715, |
| "learning_rate": 6.957573431597646e-06, |
| "loss": 0.1409, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4897959183673469, |
| "grad_norm": 0.24280116398532822, |
| "learning_rate": 6.045803420363085e-06, |
| "loss": 0.1408, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.54421768707483, |
| "grad_norm": 0.24208489602841532, |
| "learning_rate": 5.095774406105572e-06, |
| "loss": 0.1394, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5986394557823129, |
| "grad_norm": 0.2349560405963224, |
| "learning_rate": 4.142241642270109e-06, |
| "loss": 0.1351, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6530612244897959, |
| "grad_norm": 0.25391577143340344, |
| "learning_rate": 3.2200885612338846e-06, |
| "loss": 0.1346, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7074829931972789, |
| "grad_norm": 0.2574709793724405, |
| "learning_rate": 2.363050621141354e-06, |
| "loss": 0.1321, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.2516339669374057, |
| "learning_rate": 1.6024811494939723e-06, |
| "loss": 0.1289, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8163265306122449, |
| "grad_norm": 0.25243707311103075, |
| "learning_rate": 9.662043330828086e-07, |
| "loss": 0.1329, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8707482993197279, |
| "grad_norm": 0.26216650012490306, |
| "learning_rate": 4.77497315746292e-07, |
| "loss": 0.1287, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9251700680272109, |
| "grad_norm": 0.2508304182626654, |
| "learning_rate": 1.542386422372405e-07, |
| "loss": 0.1313, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.9795918367346939, |
| "grad_norm": 0.3217053310284403, |
| "learning_rate": 8.254200983794369e-09, |
| "loss": 0.1287, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.9959183673469387, |
| "step": 183, |
| "total_flos": 47903301959680.0, |
| "train_loss": 0.17143813296745383, |
| "train_runtime": 2778.6239, |
| "train_samples_per_second": 8.458, |
| "train_steps_per_second": 0.066 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 183, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 47903301959680.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
