| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 200.0, |
| "eval_steps": 0, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.5073969347858434, |
| "learning_rate": 9.558232931726908e-06, |
| "loss": 0.001, |
| "step": 12 |
| }, |
| { |
| "epoch": 24.0, |
| "grad_norm": 1.3503912802892561, |
| "learning_rate": 9.076305220883535e-06, |
| "loss": -0.0129, |
| "step": 24 |
| }, |
| { |
| "epoch": 36.0, |
| "grad_norm": 1.854609943172517, |
| "learning_rate": 8.594377510040161e-06, |
| "loss": -0.0685, |
| "step": 36 |
| }, |
| { |
| "epoch": 48.0, |
| "grad_norm": 2.067406353200125, |
| "learning_rate": 8.112449799196788e-06, |
| "loss": -0.1541, |
| "step": 48 |
| }, |
| { |
| "epoch": 60.0, |
| "grad_norm": 3.3334780954086294, |
| "learning_rate": 7.630522088353415e-06, |
| "loss": -0.2562, |
| "step": 60 |
| }, |
| { |
| "epoch": 72.0, |
| "grad_norm": 5.415361295099896, |
| "learning_rate": 7.148594377510041e-06, |
| "loss": -0.424, |
| "step": 72 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 6.4650536015631825, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": -0.6868, |
| "step": 84 |
| }, |
| { |
| "epoch": 96.0, |
| "grad_norm": 6.215404607797948, |
| "learning_rate": 6.184738955823294e-06, |
| "loss": -0.9969, |
| "step": 96 |
| }, |
| { |
| "epoch": 108.0, |
| "grad_norm": 6.6277143031089105, |
| "learning_rate": 5.70281124497992e-06, |
| "loss": -1.2661, |
| "step": 108 |
| }, |
| { |
| "epoch": 120.0, |
| "grad_norm": 12.560595267385791, |
| "learning_rate": 5.220883534136547e-06, |
| "loss": -1.5605, |
| "step": 120 |
| }, |
| { |
| "epoch": 132.0, |
| "grad_norm": 14.018267248085293, |
| "learning_rate": 4.7389558232931736e-06, |
| "loss": -2.0211, |
| "step": 132 |
| }, |
| { |
| "epoch": 144.0, |
| "grad_norm": 19.887879276388983, |
| "learning_rate": 4.2570281124497995e-06, |
| "loss": -2.5442, |
| "step": 144 |
| }, |
| { |
| "epoch": 156.0, |
| "grad_norm": 21.970926743356817, |
| "learning_rate": 3.7751004016064258e-06, |
| "loss": -3.1809, |
| "step": 156 |
| }, |
| { |
| "epoch": 168.0, |
| "grad_norm": 18.949655992756448, |
| "learning_rate": 3.2931726907630525e-06, |
| "loss": -3.8333, |
| "step": 168 |
| }, |
| { |
| "epoch": 180.0, |
| "grad_norm": 20.75361602485232, |
| "learning_rate": 2.811244979919679e-06, |
| "loss": -4.374, |
| "step": 180 |
| }, |
| { |
| "epoch": 192.0, |
| "grad_norm": 23.648962763567656, |
| "learning_rate": 2.3293172690763055e-06, |
| "loss": -4.8569, |
| "step": 192 |
| } |
| ], |
| "logging_steps": 12, |
| "max_steps": 250, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 250, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
