| { |
| "best_metric": 2.196078431372549, |
| "best_model_checkpoint": "./simpandnet-finetune/checkpoint-150", |
| "epoch": 1.662049861495845, |
| "eval_steps": 25, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.28, |
| "learning_rate": 4.2000000000000004e-06, |
| "loss": 1.187, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_loss": 0.2987758219242096, |
| "eval_runtime": 312.4773, |
| "eval_samples_per_second": 0.816, |
| "eval_steps_per_second": 0.41, |
| "eval_wer": 3.7647058823529407, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 9.200000000000002e-06, |
| "loss": 0.1612, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.55, |
| "eval_loss": 0.11934595555067062, |
| "eval_runtime": 260.2565, |
| "eval_samples_per_second": 0.98, |
| "eval_steps_per_second": 0.492, |
| "eval_wer": 2.3529411764705883, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 8.6e-06, |
| "loss": 0.0931, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.83, |
| "eval_loss": 0.07363112270832062, |
| "eval_runtime": 258.571, |
| "eval_samples_per_second": 0.986, |
| "eval_steps_per_second": 0.495, |
| "eval_wer": 3.294117647058824, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 6.9333333333333344e-06, |
| "loss": 0.0491, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.11, |
| "eval_loss": 0.07703772187232971, |
| "eval_runtime": 259.0088, |
| "eval_samples_per_second": 0.985, |
| "eval_steps_per_second": 0.494, |
| "eval_wer": 4.313725490196078, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 5.2666666666666665e-06, |
| "loss": 0.0377, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.39, |
| "eval_loss": 0.07970306277275085, |
| "eval_runtime": 276.5028, |
| "eval_samples_per_second": 0.922, |
| "eval_steps_per_second": 0.463, |
| "eval_wer": 2.03921568627451, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 3.6000000000000003e-06, |
| "loss": 0.0472, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.66, |
| "eval_loss": 0.05988682806491852, |
| "eval_runtime": 260.1111, |
| "eval_samples_per_second": 0.98, |
| "eval_steps_per_second": 0.492, |
| "eval_wer": 2.196078431372549, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "total_flos": 2.44843117314048e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
