| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0723860589812333, |
| "eval_steps": 200, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 2.9598, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 2.3436, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_loss": 1.8791261911392212, |
| "eval_runtime": 1327.8534, |
| "eval_samples_per_second": 0.753, |
| "eval_steps_per_second": 0.047, |
| "eval_wer": 0.8870904221802143, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 6e-06, |
| "loss": 1.5788, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.1682, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.71, |
| "eval_loss": 1.0307379961013794, |
| "eval_runtime": 1238.5009, |
| "eval_samples_per_second": 0.807, |
| "eval_steps_per_second": 0.051, |
| "eval_wer": 0.5047652804032766, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 1e-05, |
| "loss": 0.9354, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 9.987820251299121e-06, |
| "loss": 0.7321, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.07, |
| "eval_loss": 0.6299881935119629, |
| "eval_runtime": 830.7332, |
| "eval_samples_per_second": 1.204, |
| "eval_steps_per_second": 0.076, |
| "eval_wer": 0.36645400126023947, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 5000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "save_steps": 200, |
| "total_flos": 2.237506430017536e+19, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
