| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3748125937031484, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.018740629685157422, |
| "grad_norm": 1.3957158327102661, |
| "learning_rate": 1.47e-05, |
| "loss": 9.729989013671876, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.037481259370314844, |
| "grad_norm": 1.4920259714126587, |
| "learning_rate": 2.97e-05, |
| "loss": 9.0034130859375, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.05622188905547226, |
| "grad_norm": 1.3049159049987793, |
| "learning_rate": 4.4699999999999996e-05, |
| "loss": 8.466640014648437, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.07496251874062969, |
| "grad_norm": 0.8636816740036011, |
| "learning_rate": 5.97e-05, |
| "loss": 7.869417724609375, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0937031484257871, |
| "grad_norm": 0.46240487694740295, |
| "learning_rate": 7.47e-05, |
| "loss": 7.4413623046875, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.11244377811094453, |
| "grad_norm": 0.42481327056884766, |
| "learning_rate": 8.969999999999998e-05, |
| "loss": 7.2437841796875, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.13118440779610194, |
| "grad_norm": 0.48112183809280396, |
| "learning_rate": 0.00010469999999999998, |
| "loss": 7.021725463867187, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.14992503748125938, |
| "grad_norm": 0.4746127724647522, |
| "learning_rate": 0.0001197, |
| "loss": 6.769576416015625, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1686656671664168, |
| "grad_norm": 0.48956719040870667, |
| "learning_rate": 0.0001347, |
| "loss": 6.538475341796875, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.1874062968515742, |
| "grad_norm": 0.5688585638999939, |
| "learning_rate": 0.00014969999999999998, |
| "loss": 6.308619384765625, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1874062968515742, |
| "eval_loss": 6.167688369750977, |
| "eval_runtime": 1.0817, |
| "eval_samples_per_second": 1849.023, |
| "eval_steps_per_second": 14.792, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.20614692653673164, |
| "grad_norm": 0.7463164925575256, |
| "learning_rate": 0.0001647, |
| "loss": 6.135632934570313, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.22488755622188905, |
| "grad_norm": 0.6867733001708984, |
| "learning_rate": 0.00017969999999999998, |
| "loss": 5.97782470703125, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2436281859070465, |
| "grad_norm": 0.6764475703239441, |
| "learning_rate": 0.0001947, |
| "loss": 5.829049072265625, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.2623688155922039, |
| "grad_norm": 0.8201554417610168, |
| "learning_rate": 0.00020969999999999997, |
| "loss": 5.679007568359375, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.2811094452773613, |
| "grad_norm": 0.7325769662857056, |
| "learning_rate": 0.0002247, |
| "loss": 5.54383056640625, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.29985007496251875, |
| "grad_norm": 0.8120824694633484, |
| "learning_rate": 0.0002397, |
| "loss": 5.398251953125, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.31859070464767614, |
| "grad_norm": 0.8338794708251953, |
| "learning_rate": 0.00025469999999999996, |
| "loss": 5.269853515625, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.3373313343328336, |
| "grad_norm": 0.747706413269043, |
| "learning_rate": 0.0002697, |
| "loss": 5.1615771484375, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.356071964017991, |
| "grad_norm": 1.213719367980957, |
| "learning_rate": 0.0002847, |
| "loss": 5.037232666015625, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.3748125937031484, |
| "grad_norm": 1.0340992212295532, |
| "learning_rate": 0.00029969999999999997, |
| "loss": 4.913594055175781, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.3748125937031484, |
| "eval_loss": 4.758162021636963, |
| "eval_runtime": 1.0759, |
| "eval_samples_per_second": 1858.983, |
| "eval_steps_per_second": 14.872, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 6000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 726862698381312.0, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
