| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 21, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.047619047619047616, |
| "grad_norm": 9.599432945251465, |
| "learning_rate": 1e-05, |
| "loss": 6.80078125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 8.148159980773926, |
| "learning_rate": 9.944154131125643e-06, |
| "loss": 6.8515625, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 6.047433376312256, |
| "learning_rate": 9.777864028930705e-06, |
| "loss": 6.14453125, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 6.6827216148376465, |
| "learning_rate": 9.504844339512096e-06, |
| "loss": 6.16796875, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 5.580530166625977, |
| "learning_rate": 9.131193871579975e-06, |
| "loss": 5.45703125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 5.624956130981445, |
| "learning_rate": 8.665259359149132e-06, |
| "loss": 5.234375, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 6.428897857666016, |
| "learning_rate": 8.117449009293668e-06, |
| "loss": 5.23046875, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 5.244049549102783, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 4.513671875, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 5.302546977996826, |
| "learning_rate": 6.8267051218319766e-06, |
| "loss": 4.18359375, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 5.031486511230469, |
| "learning_rate": 6.112604669781572e-06, |
| "loss": 4.056640625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 4.652087688446045, |
| "learning_rate": 5.373650467932122e-06, |
| "loss": 3.783203125, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 4.174100875854492, |
| "learning_rate": 4.626349532067879e-06, |
| "loss": 3.58984375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 3.762723207473755, |
| "learning_rate": 3.887395330218429e-06, |
| "loss": 3.517578125, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 2.9314193725585938, |
| "learning_rate": 3.173294878168025e-06, |
| "loss": 3.287109375, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 2.969510316848755, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 3.271484375, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 2.8350284099578857, |
| "learning_rate": 1.8825509907063328e-06, |
| "loss": 3.298828125, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 2.646651029586792, |
| "learning_rate": 1.3347406408508695e-06, |
| "loss": 3.201171875, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 2.98238205909729, |
| "learning_rate": 8.688061284200266e-07, |
| "loss": 3.2890625, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 2.782482624053955, |
| "learning_rate": 4.951556604879049e-07, |
| "loss": 3.203125, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 2.1630375385284424, |
| "learning_rate": 2.2213597106929608e-07, |
| "loss": 2.99609375, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.174567222595215, |
| "learning_rate": 5.584586887435739e-08, |
| "loss": 3.2060546875, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 3.16015625, |
| "eval_runtime": 0.5069, |
| "eval_samples_per_second": 3.945, |
| "eval_steps_per_second": 1.973, |
| "step": 21 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 21, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.6048152817696768e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
