| { |
| "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": 0.4860995586357801, |
| "learning_rate": 9.558232931726908e-06, |
| "loss": 0.0082, |
| "step": 12 |
| }, |
| { |
| "epoch": 24.0, |
| "grad_norm": 4.313934355896622, |
| "learning_rate": 9.076305220883535e-06, |
| "loss": -0.0144, |
| "step": 24 |
| }, |
| { |
| "epoch": 36.0, |
| "grad_norm": 7.468621419664652, |
| "learning_rate": 8.594377510040161e-06, |
| "loss": -0.163, |
| "step": 36 |
| }, |
| { |
| "epoch": 48.0, |
| "grad_norm": 7.412152938079811, |
| "learning_rate": 8.112449799196788e-06, |
| "loss": -0.4668, |
| "step": 48 |
| }, |
| { |
| "epoch": 60.0, |
| "grad_norm": 7.975524292587363, |
| "learning_rate": 7.630522088353415e-06, |
| "loss": -0.7993, |
| "step": 60 |
| }, |
| { |
| "epoch": 72.0, |
| "grad_norm": 9.244668942414044, |
| "learning_rate": 7.148594377510041e-06, |
| "loss": -1.1621, |
| "step": 72 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 13.968697759303414, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": -1.5627, |
| "step": 84 |
| }, |
| { |
| "epoch": 96.0, |
| "grad_norm": 15.845120868555094, |
| "learning_rate": 6.184738955823294e-06, |
| "loss": -2.1119, |
| "step": 96 |
| }, |
| { |
| "epoch": 108.0, |
| "grad_norm": 19.140979092262373, |
| "learning_rate": 5.70281124497992e-06, |
| "loss": -2.7546, |
| "step": 108 |
| }, |
| { |
| "epoch": 120.0, |
| "grad_norm": 20.766269890017348, |
| "learning_rate": 5.220883534136547e-06, |
| "loss": -3.4757, |
| "step": 120 |
| }, |
| { |
| "epoch": 132.0, |
| "grad_norm": 16.74671233940738, |
| "learning_rate": 4.7389558232931736e-06, |
| "loss": -4.1677, |
| "step": 132 |
| }, |
| { |
| "epoch": 144.0, |
| "grad_norm": 16.145213875962945, |
| "learning_rate": 4.2570281124497995e-06, |
| "loss": -4.7178, |
| "step": 144 |
| }, |
| { |
| "epoch": 156.0, |
| "grad_norm": 17.514184865686715, |
| "learning_rate": 3.7751004016064258e-06, |
| "loss": -5.2022, |
| "step": 156 |
| }, |
| { |
| "epoch": 168.0, |
| "grad_norm": 26.558265416388117, |
| "learning_rate": 3.2931726907630525e-06, |
| "loss": -5.6767, |
| "step": 168 |
| }, |
| { |
| "epoch": 180.0, |
| "grad_norm": 22.017444052817833, |
| "learning_rate": 2.811244979919679e-06, |
| "loss": -6.236, |
| "step": 180 |
| }, |
| { |
| "epoch": 192.0, |
| "grad_norm": 18.523037775087772, |
| "learning_rate": 2.3293172690763055e-06, |
| "loss": -6.7542, |
| "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 |
| } |
|
|
