| { |
| "best_global_step": 75, |
| "best_metric": 2.514012575149536, |
| "best_model_checkpoint": "/workspace/scripts/soutputs/fa30d435-3229-4c56-871d-51ad38cfbe7a_8/checkpoint-75", |
| "epoch": 0.5357142857142857, |
| "eval_steps": 500, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03571428571428571, |
| "grad_norm": 4.21875, |
| "learning_rate": 3.889134066642583e-05, |
| "loss": 3.4963, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.07142857142857142, |
| "grad_norm": 2.265625, |
| "learning_rate": 8.750551649945812e-05, |
| "loss": 3.3309, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10714285714285714, |
| "grad_norm": 2.28125, |
| "learning_rate": 0.0001361196923324904, |
| "loss": 3.0425, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 0.7578125, |
| "learning_rate": 0.00013564556765812064, |
| "loss": 2.8682, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.17857142857142858, |
| "grad_norm": 0.55859375, |
| "learning_rate": 0.00013422979941564436, |
| "loss": 2.7456, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17857142857142858, |
| "eval_loss": 2.694664716720581, |
| "eval_runtime": 7.7828, |
| "eval_samples_per_second": 25.569, |
| "eval_steps_per_second": 25.569, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.21428571428571427, |
| "grad_norm": 0.51171875, |
| "learning_rate": 0.00013189211291138414, |
| "loss": 2.6241, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.40234375, |
| "learning_rate": 0.00012866507815291546, |
| "loss": 2.5579, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 0.37890625, |
| "learning_rate": 0.00012459365606478406, |
| "loss": 2.5701, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.32142857142857145, |
| "grad_norm": 0.40234375, |
| "learning_rate": 0.0001197345720667637, |
| "loss": 2.5347, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.35714285714285715, |
| "grad_norm": 0.35546875, |
| "learning_rate": 0.00011415552574232594, |
| "loss": 2.5049, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.35714285714285715, |
| "eval_loss": 2.551506280899048, |
| "eval_runtime": 7.766, |
| "eval_samples_per_second": 25.625, |
| "eval_steps_per_second": 25.625, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.39285714285714285, |
| "grad_norm": 0.427734375, |
| "learning_rate": 0.00010793424760868077, |
| "loss": 2.5086, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.353515625, |
| "learning_rate": 0.00010115741613001611, |
| "loss": 2.4886, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4642857142857143, |
| "grad_norm": 0.361328125, |
| "learning_rate": 9.391945006273741e-05, |
| "loss": 2.5123, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.359375, |
| "learning_rate": 8.632119295845557e-05, |
| "loss": 2.4455, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.5357142857142857, |
| "grad_norm": 0.35546875, |
| "learning_rate": 7.846850815299258e-05, |
| "loss": 2.5067, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.5357142857142857, |
| "eval_loss": 2.514012575149536, |
| "eval_runtime": 7.7897, |
| "eval_samples_per_second": 25.546, |
| "eval_steps_per_second": 25.546, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 280, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 4.75018618208256e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
