| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 200, |
| "global_step": 206, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.048721071863580996, |
| "grad_norm": 272.0, |
| "learning_rate": 1.9601990049751245e-05, |
| "loss": 24.5887, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.09744214372716199, |
| "grad_norm": 220.0, |
| "learning_rate": 1.8606965174129355e-05, |
| "loss": 13.6105, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.146163215590743, |
| "grad_norm": 250.0, |
| "learning_rate": 1.7611940298507464e-05, |
| "loss": 10.7707, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.19488428745432398, |
| "grad_norm": 227.0, |
| "learning_rate": 1.6616915422885574e-05, |
| "loss": 8.3658, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.243605359317905, |
| "grad_norm": 210.0, |
| "learning_rate": 1.5621890547263684e-05, |
| "loss": 6.3132, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.292326431181486, |
| "grad_norm": 200.0, |
| "learning_rate": 1.4626865671641792e-05, |
| "loss": 4.3675, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.341047503045067, |
| "grad_norm": 164.0, |
| "learning_rate": 1.3631840796019902e-05, |
| "loss": 2.8477, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.38976857490864797, |
| "grad_norm": 115.5, |
| "learning_rate": 1.2636815920398011e-05, |
| "loss": 1.8132, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.438489646772229, |
| "grad_norm": 69.5, |
| "learning_rate": 1.1641791044776121e-05, |
| "loss": 1.1829, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.48721071863581, |
| "grad_norm": 41.25, |
| "learning_rate": 1.064676616915423e-05, |
| "loss": 0.8367, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.535931790499391, |
| "grad_norm": 26.625, |
| "learning_rate": 9.651741293532339e-06, |
| "loss": 0.6523, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.584652862362972, |
| "grad_norm": 18.75, |
| "learning_rate": 8.656716417910447e-06, |
| "loss": 0.5589, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.633373934226553, |
| "grad_norm": 15.125, |
| "learning_rate": 7.661691542288557e-06, |
| "loss": 0.4842, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.682095006090134, |
| "grad_norm": 12.25, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.4625, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.730816077953715, |
| "grad_norm": 10.4375, |
| "learning_rate": 5.671641791044776e-06, |
| "loss": 0.3995, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7795371498172959, |
| "grad_norm": 10.9375, |
| "learning_rate": 4.676616915422886e-06, |
| "loss": 0.4266, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.8282582216808769, |
| "grad_norm": 9.375, |
| "learning_rate": 3.681592039800995e-06, |
| "loss": 0.4098, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.876979293544458, |
| "grad_norm": 9.125, |
| "learning_rate": 2.686567164179105e-06, |
| "loss": 0.3759, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.925700365408039, |
| "grad_norm": 8.375, |
| "learning_rate": 1.6915422885572142e-06, |
| "loss": 0.3749, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.97442143727162, |
| "grad_norm": 8.3125, |
| "learning_rate": 6.965174129353235e-07, |
| "loss": 0.3614, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.97442143727162, |
| "eval_loss": 0.19914911687374115, |
| "eval_runtime": 76.6861, |
| "eval_samples_per_second": 57.625, |
| "eval_steps_per_second": 7.211, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 206, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.89918070479913e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
