| { |
| "best_global_step": 200, |
| "best_metric": 40.680564071122014, |
| "best_model_checkpoint": "./whisper-tunisian-lora/checkpoint-200", |
| "epoch": 3.4188034188034186, |
| "eval_steps": 100, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21367521367521367, |
| "grad_norm": 0.4574618339538574, |
| "learning_rate": 0.00048, |
| "loss": 1.0657, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.42735042735042733, |
| "grad_norm": 0.4719775915145874, |
| "learning_rate": 0.00098, |
| "loss": 0.8277, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6410256410256411, |
| "grad_norm": 0.4478321075439453, |
| "learning_rate": 0.0009466666666666667, |
| "loss": 0.727, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.8547008547008547, |
| "grad_norm": 0.5259848833084106, |
| "learning_rate": 0.0008911111111111111, |
| "loss": 0.6485, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8547008547008547, |
| "eval_loss": 0.6768606901168823, |
| "eval_runtime": 590.6537, |
| "eval_samples_per_second": 0.176, |
| "eval_steps_per_second": 0.022, |
| "eval_wer": 46.413243408951566, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0683760683760684, |
| "grad_norm": 0.6370269656181335, |
| "learning_rate": 0.0008355555555555556, |
| "loss": 0.5682, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.282051282051282, |
| "grad_norm": 0.5759462714195251, |
| "learning_rate": 0.0007800000000000001, |
| "loss": 0.4578, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.4957264957264957, |
| "grad_norm": 0.47142961621284485, |
| "learning_rate": 0.0007244444444444444, |
| "loss": 0.468, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.7094017094017095, |
| "grad_norm": 0.36835190653800964, |
| "learning_rate": 0.0006688888888888889, |
| "loss": 0.5021, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.7094017094017095, |
| "eval_loss": 0.6350020170211792, |
| "eval_runtime": 508.4596, |
| "eval_samples_per_second": 0.205, |
| "eval_steps_per_second": 0.026, |
| "eval_wer": 40.680564071122014, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.9230769230769231, |
| "grad_norm": 0.399702250957489, |
| "learning_rate": 0.0006133333333333334, |
| "loss": 0.5935, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.1367521367521367, |
| "grad_norm": 0.43302881717681885, |
| "learning_rate": 0.0005577777777777778, |
| "loss": 0.3065, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.3504273504273505, |
| "grad_norm": 0.5065337419509888, |
| "learning_rate": 0.0005022222222222223, |
| "loss": 0.3235, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.564102564102564, |
| "grad_norm": 0.499609112739563, |
| "learning_rate": 0.00044666666666666666, |
| "loss": 0.3312, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.564102564102564, |
| "eval_loss": 0.6243518590927124, |
| "eval_runtime": 723.1956, |
| "eval_samples_per_second": 0.144, |
| "eval_steps_per_second": 0.018, |
| "eval_wer": 93.93010423053342, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 0.4077036380767822, |
| "learning_rate": 0.0003911111111111111, |
| "loss": 0.304, |
| "step": 325 |
| }, |
| { |
| "epoch": 2.9914529914529915, |
| "grad_norm": 0.3863629996776581, |
| "learning_rate": 0.0003355555555555556, |
| "loss": 0.2962, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.2051282051282053, |
| "grad_norm": 0.43283241987228394, |
| "learning_rate": 0.00028000000000000003, |
| "loss": 0.1706, |
| "step": 375 |
| }, |
| { |
| "epoch": 3.4188034188034186, |
| "grad_norm": 0.38285499811172485, |
| "learning_rate": 0.00022444444444444446, |
| "loss": 0.1935, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.4188034188034186, |
| "eval_loss": 0.6525424718856812, |
| "eval_runtime": 660.1882, |
| "eval_samples_per_second": 0.158, |
| "eval_steps_per_second": 0.02, |
| "eval_wer": 55.54874310239117, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.092615143030784e+19, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
