Model save

README.md

@@ -0,0 +1,79 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: facebook/mms-1b-all
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: mms_severity_classifier
+  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. -->
+
+# mms_severity_classifier
+
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0834
+- Accuracy: 0.9787
+- F1 Macro: 0.9750
+- F1 Weighted: 0.9786
+- F1 Mild: 0.9581
+- F1 Moderate: 0.9812
+- F1 Normal: 0.9719
+- F1 Severe: 0.9886
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1 Macro | F1 Weighted | F1 Mild | F1 Moderate | F1 Normal | F1 Severe |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-----------:|:-------:|:-----------:|:---------:|:---------:|
+| 0.3997        | 1.0   | 1210  | 0.3725          | 0.8652   | 0.8510   | 0.8637      | 0.7821  | 0.8791      | 0.8618    | 0.8809    |
+| 0.1947        | 2.0   | 2420  | 0.2191          | 0.9193   | 0.9067   | 0.9195      | 0.8594  | 0.9330      | 0.8828    | 0.9517    |
+| 0.1382        | 3.0   | 3630  | 0.1758          | 0.9433   | 0.9336   | 0.9432      | 0.8950  | 0.9519      | 0.9185    | 0.9690    |
+| 0.1204        | 4.0   | 4840  | 0.1432          | 0.9573   | 0.9517   | 0.9575      | 0.9365  | 0.9653      | 0.9324    | 0.9726    |
+| 0.0815        | 5.0   | 6050  | 0.0922          | 0.9726   | 0.9699   | 0.9727      | 0.9639  | 0.9748      | 0.9567    | 0.9841    |
+| 0.0647        | 6.0   | 7260  | 0.0896          | 0.9753   | 0.9710   | 0.9753      | 0.9561  | 0.9819      | 0.9632    | 0.9829    |
+| 0.0864        | 7.0   | 8470  | 0.1191          | 0.9726   | 0.9699   | 0.9726      | 0.9581  | 0.9734      | 0.9652    | 0.9829    |
+| 0.0243        | 8.0   | 9680  | 0.0870          | 0.9787   | 0.9776   | 0.9787      | 0.9821  | 0.9810      | 0.9635    | 0.9840    |
+| 0.0455        | 9.0   | 10890 | 0.0909          | 0.9760   | 0.9715   | 0.9759      | 0.9501  | 0.9795      | 0.9701    | 0.9863    |
+| 0.0452        | 10.0  | 12100 | 0.0834          | 0.9787   | 0.9750   | 0.9786      | 0.9581  | 0.9812      | 0.9719    | 0.9886    |
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.8.0+cu128
+- Datasets 4.5.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,119 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "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,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "id2label": {
+    "0": "Mild",
+    "1": "Moderate",
+    "2": "Normal",
+    "3": "Severe"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "label2id": {
+    "Mild": 0,
+    "Moderate": 1,
+    "Normal": 2,
+    "Severe": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "4.57.6",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3b0d1ede068e358627f77e6f404d0975ca3f9deade05ab16d5d1fe22519cfb
+size 3860048120

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ac139922d475a267d596b5cf9f21bb70737c75a061057064e068e34a7a1af8
+size 5905