| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.6875, |
| "eval_steps": 500, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3125, |
| "grad_norm": 0.2920430898666382, |
| "learning_rate": 0.00045000000000000004, |
| "loss": 3.779199981689453, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 0.43692970275878906, |
| "learning_rate": 0.00095, |
| "loss": 3.7675334930419924, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9375, |
| "grad_norm": 0.3336999714374542, |
| "learning_rate": 0.0009699999999999999, |
| "loss": 3.719318389892578, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 0.294895738363266, |
| "learning_rate": 0.0009366666666666667, |
| "loss": 3.654178237915039, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5625, |
| "grad_norm": 0.2748182713985443, |
| "learning_rate": 0.0009033333333333334, |
| "loss": 3.5974361419677736, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 0.27152398228645325, |
| "learning_rate": 0.00087, |
| "loss": 3.5486209869384764, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.1875, |
| "grad_norm": 0.24925607442855835, |
| "learning_rate": 0.0008366666666666667, |
| "loss": 3.5090667724609377, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.22347407042980194, |
| "learning_rate": 0.0008033333333333333, |
| "loss": 3.472085952758789, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.8125, |
| "grad_norm": 0.21740131080150604, |
| "learning_rate": 0.0007700000000000001, |
| "loss": 3.4486541748046875, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.125, |
| "grad_norm": 0.22403769195079803, |
| "learning_rate": 0.0007366666666666667, |
| "loss": 3.4204822540283204, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.4375, |
| "grad_norm": 0.19044573605060577, |
| "learning_rate": 0.0007033333333333334, |
| "loss": 3.404882049560547, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.75, |
| "grad_norm": 0.17820778489112854, |
| "learning_rate": 0.00067, |
| "loss": 3.3898468017578125, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.0625, |
| "grad_norm": 0.1427871733903885, |
| "learning_rate": 0.0006366666666666667, |
| "loss": 3.378437042236328, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.375, |
| "grad_norm": 0.1541135609149933, |
| "learning_rate": 0.0006033333333333334, |
| "loss": 3.3657516479492187, |
| "step": 140 |
| }, |
| { |
| "epoch": 4.6875, |
| "grad_norm": 0.1267220824956894, |
| "learning_rate": 0.00057, |
| "loss": 3.360360336303711, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 320, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 536393088.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
