End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: facebook/hubert-xlarge-ll60k
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: hubert-xlarge-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-xlarge-ll60k_arabic
+
+This model is a fine-tuned version of [facebook/hubert-xlarge-ll60k](https://huggingface.co/facebook/hubert-xlarge-ll60k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1133
+- Wer: 0.6646
+- Per: 0.6706
+
+## 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    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
+| 13.7253       | 1.0   | 1637  | 3.3328          | 1.0    | 1.0    |
+| 3.3354        | 2.0   | 3274  | 3.2847          | 1.0    | 1.0    |
+| 3.304         | 3.0   | 4911  | 3.2375          | 1.0    | 1.0    |
+| 3.2655        | 4.0   | 6548  | 3.2143          | 1.0    | 1.0    |
+| 3.2242        | 5.0   | 8185  | 3.1874          | 1.0    | 1.0    |
+| 3.1556        | 6.0   | 9822  | 3.0734          | 1.0    | 1.0    |
+| 3.0485        | 7.0   | 11459 | 2.9548          | 1.0    | 1.0    |
+| 2.935         | 8.0   | 13096 | 2.8378          | 0.9043 | 0.9171 |
+| 2.8158        | 9.0   | 14733 | 2.7023          | 0.8971 | 0.9087 |
+| 2.7185        | 10.0  | 16370 | 2.5982          | 0.8865 | 0.8997 |
+| 2.6406        | 11.0  | 18007 | 2.5032          | 0.8453 | 0.8571 |
+| 2.5721        | 12.0  | 19644 | 2.4385          | 0.8179 | 0.8291 |
+| 2.5136        | 13.0  | 21281 | 2.3810          | 0.7994 | 0.8097 |
+| 2.457         | 14.0  | 22918 | 2.3041          | 0.7792 | 0.7896 |
+| 2.4104        | 15.0  | 24555 | 2.2466          | 0.7588 | 0.7695 |
+| 2.3711        | 16.0  | 26192 | 2.2066          | 0.7321 | 0.7417 |
+| 2.3365        | 17.0  | 27829 | 2.1757          | 0.7002 | 0.7072 |
+| 2.3109        | 18.0  | 29466 | 2.1412          | 0.6771 | 0.6828 |
+| 2.2857        | 19.0  | 31103 | 2.1265          | 0.6722 | 0.6785 |
+| 2.2757        | 20.0  | 32740 | 2.1133          | 0.6646 | 0.6706 |
+
+
+### 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-xlarge-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:ad8cff5099262408302115b12e21c674bae17c32070022bb00fb31a4f52650ba
+size 31484792

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_15-35-20_4935f1e421f7/events.out.tfevents.1701790952.4935f1e421f7.1441.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b20e78f7ae315f7ad3e3840e91cadca910324f67097d270a56f7492ed110c43
+size 16344

trainer_state.json

@@ -0,0 +1,348 @@
+{
+  "best_metric": 3.3327760696411133,
+  "best_model_checkpoint": "nrshoudi/hubert-xlarge-ll60k_arabic/checkpoint-1637",
+  "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": 4.987782529016494e-05,
+      "loss": 13.7253,
+      "step": 1637
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.3327760696411133,
+      "eval_per": 1.0,
+      "eval_runtime": 121.8139,
+      "eval_samples_per_second": 6.674,
+      "eval_steps_per_second": 3.341,
+      "eval_wer": 1.0,
+      "step": 1637
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.987782529016494e-05,
+      "loss": 3.3354,
+      "step": 3274
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.2846710681915283,
+      "eval_per": 1.0,
+      "eval_runtime": 123.7338,
+      "eval_samples_per_second": 6.571,
+      "eval_steps_per_second": 3.289,
+      "eval_wer": 1.0,
+      "step": 3274
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.44580194122039e-05,
+      "loss": 3.304,
+      "step": 4911
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.2374837398529053,
+      "eval_per": 1.0,
+      "eval_runtime": 124.396,
+      "eval_samples_per_second": 6.536,
+      "eval_steps_per_second": 3.272,
+      "eval_wer": 1.0,
+      "step": 4911
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 8.89058575985882e-05,
+      "loss": 3.2655,
+      "step": 6548
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.2142696380615234,
+      "eval_per": 1.0,
+      "eval_runtime": 124.9199,
+      "eval_samples_per_second": 6.508,
+      "eval_steps_per_second": 3.258,
+      "eval_wer": 1.0,
+      "step": 6548
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 8.335030204303264e-05,
+      "loss": 3.2242,
+      "step": 8185
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.1873738765716553,
+      "eval_per": 1.0,
+      "eval_runtime": 125.5279,
+      "eval_samples_per_second": 6.477,
+      "eval_steps_per_second": 3.242,
+      "eval_wer": 1.0,
+      "step": 8185
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 7.779814022941696e-05,
+      "loss": 3.1556,
+      "step": 9822
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.0734314918518066,
+      "eval_per": 1.0,
+      "eval_runtime": 126.5196,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.217,
+      "eval_wer": 1.0,
+      "step": 9822
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 7.22425846738614e-05,
+      "loss": 3.0485,
+      "step": 11459
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.9547784328460693,
+      "eval_per": 1.0,
+      "eval_runtime": 127.0062,
+      "eval_samples_per_second": 6.401,
+      "eval_steps_per_second": 3.205,
+      "eval_wer": 1.0,
+      "step": 11459
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 6.668702911830585e-05,
+      "loss": 2.935,
+      "step": 13096
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.83778977394104,
+      "eval_per": 0.9171063789691888,
+      "eval_runtime": 127.5426,
+      "eval_samples_per_second": 6.374,
+      "eval_steps_per_second": 3.191,
+      "eval_wer": 0.9043441743269096,
+      "step": 13096
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 6.113826104663001e-05,
+      "loss": 2.8158,
+      "step": 14733
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.702333450317383,
+      "eval_per": 0.9086733251672477,
+      "eval_runtime": 127.7194,
+      "eval_samples_per_second": 6.366,
+      "eval_steps_per_second": 3.187,
+      "eval_wer": 0.8971116606784565,
+      "step": 14733
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 5.558270549107446e-05,
+      "loss": 2.7185,
+      "step": 16370
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.598202705383301,
+      "eval_per": 0.8996749269763498,
+      "eval_runtime": 127.815,
+      "eval_samples_per_second": 6.361,
+      "eval_steps_per_second": 3.184,
+      "eval_wer": 0.8864728664084737,
+      "step": 16370
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 5.00271499355189e-05,
+      "loss": 2.6406,
+      "step": 18007
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 2.5032498836517334,
+      "eval_per": 0.857085649674927,
+      "eval_runtime": 128.216,
+      "eval_samples_per_second": 6.341,
+      "eval_steps_per_second": 3.174,
+      "eval_wer": 0.8452708693014792,
+      "step": 18007
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 4.4478381863843074e-05,
+      "loss": 2.5721,
+      "step": 19644
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 2.4384822845458984,
+      "eval_per": 0.8291011024215584,
+      "eval_runtime": 128.477,
+      "eval_samples_per_second": 6.328,
+      "eval_steps_per_second": 3.168,
+      "eval_wer": 0.8179273015724885,
+      "step": 19644
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 3.892622005022738e-05,
+      "loss": 2.5136,
+      "step": 21281
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 2.381009578704834,
+      "eval_per": 0.8097145010835768,
+      "eval_runtime": 128.3969,
+      "eval_samples_per_second": 6.332,
+      "eval_steps_per_second": 3.17,
+      "eval_wer": 0.7993560729783957,
+      "step": 21281
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.337405823661169e-05,
+      "loss": 2.457,
+      "step": 22918
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 2.304086208343506,
+      "eval_per": 0.7896212192593989,
+      "eval_runtime": 128.5082,
+      "eval_samples_per_second": 6.326,
+      "eval_steps_per_second": 3.167,
+      "eval_wer": 0.779151696141104,
+      "step": 22918
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.7818502681056137e-05,
+      "loss": 2.4104,
+      "step": 24555
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 2.246638536453247,
+      "eval_per": 0.7694808254028078,
+      "eval_runtime": 128.3201,
+      "eval_samples_per_second": 6.336,
+      "eval_steps_per_second": 3.172,
+      "eval_wer": 0.7587606737903038,
+      "step": 24555
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.2262947125500577e-05,
+      "loss": 2.3711,
+      "step": 26192
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 2.2065765857696533,
+      "eval_per": 0.7417318383115048,
+      "eval_runtime": 128.1923,
+      "eval_samples_per_second": 6.342,
+      "eval_steps_per_second": 3.175,
+      "eval_wer": 0.7321170267369698,
+      "step": 26192
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 1.6714179053824745e-05,
+      "loss": 2.3365,
+      "step": 27829
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 2.1757304668426514,
+      "eval_per": 0.7071987185527183,
+      "eval_runtime": 128.7988,
+      "eval_samples_per_second": 6.312,
+      "eval_steps_per_second": 3.16,
+      "eval_wer": 0.7002006439270216,
+      "step": 27829
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 1.1158623498269193e-05,
+      "loss": 2.3109,
+      "step": 29466
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 2.141193389892578,
+      "eval_per": 0.6828182417789503,
+      "eval_runtime": 128.9306,
+      "eval_samples_per_second": 6.306,
+      "eval_steps_per_second": 3.157,
+      "eval_wer": 0.6771499230087257,
+      "step": 29466
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 5.603067942713636e-06,
+      "loss": 2.2857,
+      "step": 31103
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 2.1265432834625244,
+      "eval_per": 0.6784603787807406,
+      "eval_runtime": 129.2068,
+      "eval_samples_per_second": 6.292,
+      "eval_steps_per_second": 3.15,
+      "eval_wer": 0.6722038169007513,
+      "step": 31103
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 5.090612909794339e-08,
+      "loss": 2.2757,
+      "step": 32740
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 2.113328695297241,
+      "eval_per": 0.670616225383963,
+      "eval_runtime": 128.9922,
+      "eval_samples_per_second": 6.303,
+      "eval_steps_per_second": 3.155,
+      "eval_wer": 0.6645980122252811,
+      "step": 32740
+    },
+    {
+      "epoch": 20.0,
+      "step": 32740,
+      "total_flos": 3.2217850292594e+19,
+      "train_loss": 3.285075871508953,
+      "train_runtime": 18041.7674,
+      "train_samples_per_second": 3.628,
+      "train_steps_per_second": 1.815
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 32740,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 3.2217850292594e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8d1353f03fe2c4817abe18f3289723ee673a2ebf6f0da0b6a5c90bad642173
+size 4600