End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: facebook/hubert-large-ll60k
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: hubert-large-ll60k_arabic
+ results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# hubert-large-ll60k_arabic
+
+This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.0197
+- Wer: 1.0
+- Per: 1.0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer | Per |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
+| 15.0257 | 1.0 | 1637 | 4.0741 | 1.0 | 1.0 |
+| 4.0101 | 2.0 | 3274 | 4.0442 | 1.0 | 1.0 |
+| 3.9446 | 3.0 | 4911 | 4.0444 | 1.0 | 1.0 |
+| 3.9302 | 4.0 | 6548 | 4.0440 | 1.0 | 1.0 |
+| 3.9456 | 5.0 | 8185 | 4.0453 | 1.0 | 1.0 |
+| 4.0388 | 6.0 | 9822 | 4.0415 | 1.0 | 1.0 |
+| 3.9297 | 7.0 | 11459 | 4.0442 | 1.0 | 1.0 |
+| 3.9443 | 8.0 | 13096 | 4.0395 | 1.0 | 1.0 |
+| 3.9362 | 9.0 | 14733 | 4.0647 | 1.0000 | 1.0000 |
+| 3.9785 | 10.0 | 16370 | 4.3751 | 1.0 | 1.0 |
+| 3.9934 | 11.0 | 18007 | 4.0295 | 1.0 | 1.0 |
+| 3.9361 | 12.0 | 19644 | 4.0276 | 1.0 | 1.0 |
+| 3.913 | 13.0 | 21281 | 4.0239 | 1.0 | 1.0 |
+| 3.9023 | 14.0 | 22918 | 4.0227 | 1.0 | 1.0 |
+| 3.8957 | 15.0 | 24555 | 4.0228 | 1.0 | 1.0 |
+| 3.9021 | 16.0 | 26192 | 4.0207 | 1.0 | 1.0 |
+| 3.8897 | 17.0 | 27829 | 4.0213 | 1.0 | 1.0 |
+| 3.8939 | 18.0 | 29466 | 4.0213 | 1.0 | 1.0 |
+| 3.8949 | 19.0 | 31103 | 4.0204 | 1.0 | 1.0 |
+| 3.8987 | 20.0 | 32740 | 4.0197 | 1.0 | 1.0 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": {
+ "base_model_class": "HubertForCTC",
+ "parent_library": "transformers.models.hubert.modeling_hubert"
+ },
+ "base_model_name_or_path": "facebook/hubert-large-ll60k",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "lora_alpha": 64,
+ "lora_dropout": 0.05,
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_proj"
+ ],
+ "task_type": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b0ed5b642b8830efd4d2457451c5e2ea2f6d3f5851385138e66a0ef14e2a11
+size 12596568

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0,
+ "return_attention_mask": true,
+ "sampling_rate": 16000
+}

runs/Dec05_18-40-22_e5559b29b07f/events.out.tfevents.1701801744.e5559b29b07f.352.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e393dd4eb293568972da2fa1e5800de90f07f3674e296dd55bc087b6e38efa
+size 16340

trainer_state.json

@@ -0,0 +1,348 @@
+{
+ "best_metric": 4.375102519989014,
+ "best_model_checkpoint": "nrshoudi/hubert-large-ll60k_arabic/checkpoint-16370",
+ "epoch": 20.0,
+ "eval_steps": 500,
+ "global_step": 32740,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 1.0,
+ "learning_rate": 4.9816737935247405e-05,
+ "loss": 15.0257,
+ "step": 1637
+ },
+ {
+ "epoch": 1.0,
+ "eval_loss": 4.074129104614258,
+ "eval_per": 1.0,
+ "eval_runtime": 81.2424,
+ "eval_samples_per_second": 10.007,
+ "eval_steps_per_second": 5.01,
+ "eval_wer": 1.0,
+ "step": 1637
+ },
+ {
+ "epoch": 2.0,
+ "learning_rate": 9.981673793524741e-05,
+ "loss": 4.0101,
+ "step": 3274
+ },
+ {
+ "epoch": 2.0,
+ "eval_loss": 4.04423189163208,
+ "eval_per": 1.0,
+ "eval_runtime": 83.0026,
+ "eval_samples_per_second": 9.795,
+ "eval_steps_per_second": 4.903,
+ "eval_wer": 1.0,
+ "step": 3274
+ },
+ {
+ "epoch": 3.0,
+ "learning_rate": 9.446480689608362e-05,
+ "loss": 3.9446,
+ "step": 4911
+ },
+ {
+ "epoch": 3.0,
+ "eval_loss": 4.0444488525390625,
+ "eval_per": 1.0,
+ "eval_runtime": 84.4804,
+ "eval_samples_per_second": 9.624,
+ "eval_steps_per_second": 4.818,
+ "eval_wer": 1.0,
+ "step": 4911
+ },
+ {
+ "epoch": 4.0,
+ "learning_rate": 8.890925134052806e-05,
+ "loss": 3.9302,
+ "step": 6548
+ },
+ {
+ "epoch": 4.0,
+ "eval_loss": 4.044007778167725,
+ "eval_per": 1.0,
+ "eval_runtime": 86.94,
+ "eval_samples_per_second": 9.351,
+ "eval_steps_per_second": 4.681,
+ "eval_wer": 1.0,
+ "step": 6548
+ },
+ {
+ "epoch": 5.0,
+ "learning_rate": 8.335369578497252e-05,
+ "loss": 3.9456,
+ "step": 8185
+ },
+ {
+ "epoch": 5.0,
+ "eval_loss": 4.045283317565918,
+ "eval_per": 1.0,
+ "eval_runtime": 86.4841,
+ "eval_samples_per_second": 9.401,
+ "eval_steps_per_second": 4.706,
+ "eval_wer": 1.0,
+ "step": 8185
+ },
+ {
+ "epoch": 6.0,
+ "learning_rate": 7.779814022941696e-05,
+ "loss": 4.0388,
+ "step": 9822
+ },
+ {
+ "epoch": 6.0,
+ "eval_loss": 4.041508197784424,
+ "eval_per": 1.0,
+ "eval_runtime": 88.0752,
+ "eval_samples_per_second": 9.231,
+ "eval_steps_per_second": 4.621,
+ "eval_wer": 1.0,
+ "step": 9822
+ },
+ {
+ "epoch": 7.0,
+ "learning_rate": 7.224597841580127e-05,
+ "loss": 3.9297,
+ "step": 11459
+ },
+ {
+ "epoch": 7.0,
+ "eval_loss": 4.044224739074707,
+ "eval_per": 1.0,
+ "eval_runtime": 88.7389,
+ "eval_samples_per_second": 9.162,
+ "eval_steps_per_second": 4.586,
+ "eval_wer": 1.0,
+ "step": 11459
+ },
+ {
+ "epoch": 8.0,
+ "learning_rate": 6.669042286024571e-05,
+ "loss": 3.9443,
+ "step": 13096
+ },
+ {
+ "epoch": 8.0,
+ "eval_loss": 4.039473533630371,
+ "eval_per": 1.0,
+ "eval_runtime": 88.5683,
+ "eval_samples_per_second": 9.179,
+ "eval_steps_per_second": 4.595,
+ "eval_wer": 1.0,
+ "step": 13096
+ },
+ {
+ "epoch": 9.0,
+ "learning_rate": 6.113486730469016e-05,
+ "loss": 3.9362,
+ "step": 14733
+ },
+ {
+ "epoch": 9.0,
+ "eval_loss": 4.064728260040283,
+ "eval_per": 0.9999764439837935,
+ "eval_runtime": 90.2258,
+ "eval_samples_per_second": 9.011,
+ "eval_steps_per_second": 4.511,
+ "eval_wer": 0.9999533386216228,
+ "step": 14733
+ },
+ {
+ "epoch": 10.0,
+ "learning_rate": 5.558270549107446e-05,
+ "loss": 3.9785,
+ "step": 16370
+ },
+ {
+ "epoch": 10.0,
+ "eval_loss": 4.375102519989014,
+ "eval_per": 1.0,
+ "eval_runtime": 89.0532,
+ "eval_samples_per_second": 9.129,
+ "eval_steps_per_second": 4.57,
+ "eval_wer": 1.0,
+ "step": 16370
+ },
+ {
+ "epoch": 11.0,
+ "learning_rate": 5.003733116133849e-05,
+ "loss": 3.9934,
+ "step": 18007
+ },
+ {
+ "epoch": 11.0,
+ "eval_loss": 4.029526233673096,
+ "eval_per": 1.0,
+ "eval_runtime": 93.2708,
+ "eval_samples_per_second": 8.717,
+ "eval_steps_per_second": 4.364,
+ "eval_wer": 1.0,
+ "step": 18007
+ },
+ {
+ "epoch": 12.0,
+ "learning_rate": 4.448177560578294e-05,
+ "loss": 3.9361,
+ "step": 19644
+ },
+ {
+ "epoch": 12.0,
+ "eval_loss": 4.027557373046875,
+ "eval_per": 1.0,
+ "eval_runtime": 94.3966,
+ "eval_samples_per_second": 8.613,
+ "eval_steps_per_second": 4.312,
+ "eval_wer": 1.0,
+ "step": 19644
+ },
+ {
+ "epoch": 13.0,
+ "learning_rate": 3.893300753410711e-05,
+ "loss": 3.913,
+ "step": 21281
+ },
+ {
+ "epoch": 13.0,
+ "eval_loss": 4.023890972137451,
+ "eval_per": 1.0,
+ "eval_runtime": 96.1974,
+ "eval_samples_per_second": 8.451,
+ "eval_steps_per_second": 4.231,
+ "eval_wer": 1.0,
+ "step": 21281
+ },
+ {
+ "epoch": 14.0,
+ "learning_rate": 3.337745197855155e-05,
+ "loss": 3.9023,
+ "step": 22918
+ },
+ {
+ "epoch": 14.0,
+ "eval_loss": 4.022657871246338,
+ "eval_per": 1.0,
+ "eval_runtime": 97.2278,
+ "eval_samples_per_second": 8.362,
+ "eval_steps_per_second": 4.186,
+ "eval_wer": 1.0,
+ "step": 22918
+ },
+ {
+ "epoch": 15.0,
+ "learning_rate": 2.7821896422995997e-05,
+ "loss": 3.8957,
+ "step": 24555
+ },
+ {
+ "epoch": 15.0,
+ "eval_loss": 4.022843360900879,
+ "eval_per": 1.0,
+ "eval_runtime": 97.5296,
+ "eval_samples_per_second": 8.336,
+ "eval_steps_per_second": 4.173,
+ "eval_wer": 1.0,
+ "step": 24555
+ },
+ {
+ "epoch": 16.0,
+ "learning_rate": 2.226634086744044e-05,
+ "loss": 3.9021,
+ "step": 26192
+ },
+ {
+ "epoch": 16.0,
+ "eval_loss": 4.02068567276001,
+ "eval_per": 1.0,
+ "eval_runtime": 96.5808,
+ "eval_samples_per_second": 8.418,
+ "eval_steps_per_second": 4.214,
+ "eval_wer": 1.0,
+ "step": 26192
+ },
+ {
+ "epoch": 17.0,
+ "learning_rate": 1.6714179053824745e-05,
+ "loss": 3.8897,
+ "step": 27829
+ },
+ {
+ "epoch": 17.0,
+ "eval_loss": 4.02132511138916,
+ "eval_per": 1.0,
+ "eval_runtime": 97.8428,
+ "eval_samples_per_second": 8.309,
+ "eval_steps_per_second": 4.16,
+ "eval_wer": 1.0,
+ "step": 27829
+ },
+ {
+ "epoch": 18.0,
+ "learning_rate": 1.1158623498269193e-05,
+ "loss": 3.8939,
+ "step": 29466
+ },
+ {
+ "epoch": 18.0,
+ "eval_loss": 4.0213165283203125,
+ "eval_per": 1.0,
+ "eval_runtime": 97.7024,
+ "eval_samples_per_second": 8.321,
+ "eval_steps_per_second": 4.166,
+ "eval_wer": 1.0,
+ "step": 29466
+ },
+ {
+ "epoch": 19.0,
+ "learning_rate": 5.609855426593362e-06,
+ "loss": 3.8949,
+ "step": 31103
+ },
+ {
+ "epoch": 19.0,
+ "eval_loss": 4.020359992980957,
+ "eval_per": 1.0,
+ "eval_runtime": 96.6299,
+ "eval_samples_per_second": 8.414,
+ "eval_steps_per_second": 4.212,
+ "eval_wer": 1.0,
+ "step": 31103
+ },
+ {
+ "epoch": 20.0,
+ "learning_rate": 5.429987103780629e-08,
+ "loss": 3.8987,
+ "step": 32740
+ },
+ {
+ "epoch": 20.0,
+ "eval_loss": 4.019679069519043,
+ "eval_per": 1.0,
+ "eval_runtime": 98.2061,
+ "eval_samples_per_second": 8.279,
+ "eval_steps_per_second": 4.144,
+ "eval_wer": 1.0,
+ "step": 32740
+ },
+ {
+ "epoch": 20.0,
+ "step": 32740,
+ "total_flos": 1.0578414234417158e+19,
+ "train_loss": 4.4901714383208615,
+ "train_runtime": 11782.1292,
+ "train_samples_per_second": 5.556,
+ "train_steps_per_second": 2.779
+ }
+ ],
+ "logging_steps": 25,
+ "max_steps": 32740,
+ "num_train_epochs": 20,
+ "save_steps": 500,
+ "total_flos": 1.0578414234417158e+19,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be727e4381e03890c2d2508718271dd8083c30dad89e8e47d838cc7b867a384f
+size 4600