| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 4, |
| "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": 0.43169543147087097, |
| "learning_rate": 0.0, |
| "loss": 1.51171875, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 0.410955548286438, |
| "learning_rate": 5e-05, |
| "loss": 1.579833984375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 0.6624472141265869, |
| "learning_rate": 4.97229876633906e-05, |
| "loss": 1.60009765625, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 0.4703623056411743, |
| "learning_rate": 4.889877161664096e-05, |
| "loss": 1.463623046875, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 0.35136279463768005, |
| "learning_rate": 4.7547646794238276e-05, |
| "loss": 1.486328125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "eval_loss": 1.4140625, |
| "eval_runtime": 5.1445, |
| "eval_samples_per_second": 0.194, |
| "eval_steps_per_second": 0.194, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 0.40738654136657715, |
| "learning_rate": 4.570288237343632e-05, |
| "loss": 1.33544921875, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.4430812895298004, |
| "learning_rate": 4.340990257669732e-05, |
| "loss": 1.56640625, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.4507165253162384, |
| "learning_rate": 4.072516817658065e-05, |
| "loss": 1.44091796875, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.5336745977401733, |
| "learning_rate": 3.771478624413981e-05, |
| "loss": 1.314697265625, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "eval_loss": 1.328125, |
| "eval_runtime": 5.0725, |
| "eval_samples_per_second": 0.197, |
| "eval_steps_per_second": 0.197, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 0.3681015372276306, |
| "learning_rate": 3.4452882373436316e-05, |
| "loss": 1.433349609375, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 0.3549262583255768, |
| "learning_rate": 3.1019775463405195e-05, |
| "loss": 1.31689453125, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.2255212664604187, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 0.7911376953125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 0.36084261536598206, |
| "learning_rate": 2.3980224536594803e-05, |
| "loss": 1.3671875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "eval_loss": 1.28125, |
| "eval_runtime": 5.0728, |
| "eval_samples_per_second": 0.197, |
| "eval_steps_per_second": 0.197, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.32899197936058044, |
| "learning_rate": 2.054711762656369e-05, |
| "loss": 1.302734375, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.34358394145965576, |
| "learning_rate": 1.72852137558602e-05, |
| "loss": 1.3017578125, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.2757423520088196, |
| "learning_rate": 1.427483182341936e-05, |
| "loss": 1.3701171875, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 0.3158814311027527, |
| "learning_rate": 1.1590097423302684e-05, |
| "loss": 1.449951171875, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "eval_loss": 1.2578125, |
| "eval_runtime": 5.0981, |
| "eval_samples_per_second": 0.196, |
| "eval_steps_per_second": 0.196, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 0.36973994970321655, |
| "learning_rate": 9.297117626563687e-06, |
| "loss": 1.319580078125, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 0.3462851941585541, |
| "learning_rate": 7.452353205761725e-06, |
| "loss": 1.38818359375, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.34591546654701233, |
| "learning_rate": 6.1012283833590465e-06, |
| "loss": 1.3006591796875, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.2838385999202728, |
| "learning_rate": 5.277012336609403e-06, |
| "loss": 1.298583984375, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.2578125, |
| "eval_runtime": 5.0709, |
| "eval_samples_per_second": 0.197, |
| "eval_steps_per_second": 0.197, |
| "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": 1.0123420506469171e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
