End of training

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: facebook/hubert-large-ls960-ft
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: hubert_arabic_mdd
+  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_arabic_mdd
+
+This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5404
+- Wer: 0.0859
+- Per: 0.0671
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    | Per    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
+| 6.3943        | 1.0   | 1637  | 1.2722          | 0.4693 | 0.4456 |
+| 0.7962        | 2.0   | 3274  | 0.5990          | 0.1377 | 0.1185 |
+| 0.4245        | 3.0   | 4911  | 0.6075          | 0.0899 | 0.0674 |
+| 0.2898        | 4.0   | 6548  | 0.5285          | 0.0979 | 0.0738 |
+| 0.2262        | 5.0   | 8185  | 0.5600          | 0.0977 | 0.0758 |
+| 0.1803        | 6.0   | 9822  | 0.5504          | 0.0808 | 0.0603 |
+| 0.1488        | 7.0   | 11459 | 0.5854          | 0.0898 | 0.0700 |
+| 0.1267        | 8.0   | 13096 | 0.5438          | 0.0914 | 0.0722 |
+| 0.1156        | 9.0   | 14733 | 0.5395          | 0.0866 | 0.0671 |
+| 0.0993        | 10.0  | 16370 | 0.5404          | 0.0859 | 0.0671 |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/hubert-large-ls960-ft",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 37,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 40
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e1feb28658dec91aefb393dfcfcb493935e45bb90b786f5599d7b3a49cecc0
+size 1261970648

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_metric": 0.5284518003463745,
+  "best_model_checkpoint": "nrshoudi/hubert_arabic_mdd/checkpoint-6548",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 16370,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 6.3943,
+      "step": 1637
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.2721797227859497,
+      "eval_per": 0.4456091585791011,
+      "eval_runtime": 117.745,
+      "eval_samples_per_second": 6.905,
+      "eval_steps_per_second": 3.457,
+      "eval_wer": 0.4692734823386683,
+      "step": 1637
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.7962,
+      "step": 3274
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5990138053894043,
+      "eval_per": 0.11846320550268538,
+      "eval_runtime": 118.7347,
+      "eval_samples_per_second": 6.847,
+      "eval_steps_per_second": 3.428,
+      "eval_wer": 0.13774438896925015,
+      "step": 3274
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 0.4245,
+      "step": 4911
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6075053811073303,
+      "eval_per": 0.06744087439932159,
+      "eval_runtime": 118.3123,
+      "eval_samples_per_second": 6.872,
+      "eval_steps_per_second": 3.44,
+      "eval_wer": 0.08991647613270495,
+      "step": 4911
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.2898,
+      "step": 6548
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5284518003463745,
+      "eval_per": 0.07384811080750024,
+      "eval_runtime": 121.2465,
+      "eval_samples_per_second": 6.705,
+      "eval_steps_per_second": 3.357,
+      "eval_wer": 0.09789557183519201,
+      "step": 6548
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.2262,
+      "step": 8185
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5600156784057617,
+      "eval_per": 0.07577970413643645,
+      "eval_runtime": 119.4374,
+      "eval_samples_per_second": 6.807,
+      "eval_steps_per_second": 3.408,
+      "eval_wer": 0.09770892632168354,
+      "step": 8185
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.1803,
+      "step": 9822
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.5504231452941895,
+      "eval_per": 0.060279845472533684,
+      "eval_runtime": 119.1759,
+      "eval_samples_per_second": 6.822,
+      "eval_steps_per_second": 3.415,
+      "eval_wer": 0.08077084597078998,
+      "step": 9822
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.1488,
+      "step": 11459
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.5854084491729736,
+      "eval_per": 0.06998492414962781,
+      "eval_runtime": 119.0832,
+      "eval_samples_per_second": 6.827,
+      "eval_steps_per_second": 3.418,
+      "eval_wer": 0.08982315337595073,
+      "step": 11459
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.1267,
+      "step": 13096
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.5438163876533508,
+      "eval_per": 0.07222274568924904,
+      "eval_runtime": 119.6311,
+      "eval_samples_per_second": 6.796,
+      "eval_steps_per_second": 3.402,
+      "eval_wer": 0.09140964024077271,
+      "step": 13096
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.1156,
+      "step": 14733
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.5394747257232666,
+      "eval_per": 0.06713464618863657,
+      "eval_runtime": 119.6655,
+      "eval_samples_per_second": 6.794,
+      "eval_steps_per_second": 3.401,
+      "eval_wer": 0.08660351826792964,
+      "step": 14733
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0993,
+      "step": 16370
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.5404430627822876,
+      "eval_per": 0.06713464618863657,
+      "eval_runtime": 120.5761,
+      "eval_samples_per_second": 6.743,
+      "eval_steps_per_second": 3.375,
+      "eval_wer": 0.08590359759227288,
+      "step": 16370
+    },
+    {
+      "epoch": 10.0,
+      "step": 16370,
+      "total_flos": 5.23722142955399e+18,
+      "train_loss": 0.8801708410189657,
+      "train_runtime": 9837.0244,
+      "train_samples_per_second": 3.327,
+      "train_steps_per_second": 1.664
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16370,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5.23722142955399e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df396eb2305401892bce240be3383c2e51e3c16ab0698dab7a388cc695d3d602
+size 4600