| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 12.7424, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.64, |
| "grad_norm": 1.137086033821106, |
| "learning_rate": 7.8416e-05, |
| "loss": 6.348446655273437, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.2752, |
| "grad_norm": 1.0378036499023438, |
| "learning_rate": 7.6816e-05, |
| "loss": 5.243690185546875, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.9152, |
| "grad_norm": 0.9749150276184082, |
| "learning_rate": 7.5216e-05, |
| "loss": 4.91364013671875, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.5504, |
| "grad_norm": 1.0230515003204346, |
| "learning_rate": 7.361600000000001e-05, |
| "loss": 4.62632568359375, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.1856, |
| "grad_norm": 1.0212266445159912, |
| "learning_rate": 7.201600000000001e-05, |
| "loss": 4.4673223876953125, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.8256, |
| "grad_norm": 1.1937462091445923, |
| "learning_rate": 7.0416e-05, |
| "loss": 4.2712399291992185, |
| "step": 600 |
| }, |
| { |
| "epoch": 4.4608, |
| "grad_norm": 1.0884040594100952, |
| "learning_rate": 6.8816e-05, |
| "loss": 4.08659423828125, |
| "step": 700 |
| }, |
| { |
| "epoch": 5.096, |
| "grad_norm": 1.1558771133422852, |
| "learning_rate": 6.7216e-05, |
| "loss": 3.9976934814453124, |
| "step": 800 |
| }, |
| { |
| "epoch": 5.736, |
| "grad_norm": 1.2531368732452393, |
| "learning_rate": 6.5616e-05, |
| "loss": 3.7825747680664064, |
| "step": 900 |
| }, |
| { |
| "epoch": 6.3712, |
| "grad_norm": 1.2680810689926147, |
| "learning_rate": 6.4016e-05, |
| "loss": 3.675318298339844, |
| "step": 1000 |
| }, |
| { |
| "epoch": 7.0064, |
| "grad_norm": 1.3131264448165894, |
| "learning_rate": 6.241600000000001e-05, |
| "loss": 3.5979290771484376, |
| "step": 1100 |
| }, |
| { |
| "epoch": 7.6464, |
| "grad_norm": 1.3655059337615967, |
| "learning_rate": 6.0816e-05, |
| "loss": 3.389007873535156, |
| "step": 1200 |
| }, |
| { |
| "epoch": 8.2816, |
| "grad_norm": 1.4736028909683228, |
| "learning_rate": 5.9216000000000004e-05, |
| "loss": 3.2966958618164064, |
| "step": 1300 |
| }, |
| { |
| "epoch": 8.9216, |
| "grad_norm": 1.445204496383667, |
| "learning_rate": 5.7616e-05, |
| "loss": 3.194217529296875, |
| "step": 1400 |
| }, |
| { |
| "epoch": 9.556799999999999, |
| "grad_norm": 1.5872318744659424, |
| "learning_rate": 5.601600000000001e-05, |
| "loss": 3.0272833251953126, |
| "step": 1500 |
| }, |
| { |
| "epoch": 10.192, |
| "grad_norm": 1.6559168100357056, |
| "learning_rate": 5.441600000000001e-05, |
| "loss": 2.9672927856445312, |
| "step": 1600 |
| }, |
| { |
| "epoch": 10.832, |
| "grad_norm": 1.7011806964874268, |
| "learning_rate": 5.2816000000000004e-05, |
| "loss": 2.835576477050781, |
| "step": 1700 |
| }, |
| { |
| "epoch": 11.4672, |
| "grad_norm": 1.7928874492645264, |
| "learning_rate": 5.1216000000000006e-05, |
| "loss": 2.706945495605469, |
| "step": 1800 |
| }, |
| { |
| "epoch": 12.1024, |
| "grad_norm": 1.7846620082855225, |
| "learning_rate": 4.9616e-05, |
| "loss": 2.6535516357421876, |
| "step": 1900 |
| }, |
| { |
| "epoch": 12.7424, |
| "grad_norm": 1.8277227878570557, |
| "learning_rate": 4.8016e-05, |
| "loss": 2.49991943359375, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 5000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 32, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.018085351456768e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
