End of training

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: fusion_gttbsc_distilbert-uncased-ft
+  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. -->
+
+# fusion_gttbsc_distilbert-uncased-ft
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## 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: 0.0007
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "FusionCrossAttentionSentenceClassifier"
+  ],
+  "dropout": 0.3,
+  "embedding_strategy": "self-att",
+  "fp16": true,
+  "fusion_layers": 2,
+  "fusion_strategy": "dense",
+  "heads": 8,
+  "hidden_size": 768,
+  "k1_backbone": "whisper-encoder-small",
+  "k1_freezed": true,
+  "k1_kwargs": {
+    "load_in_4bit": false
+  },
+  "k2_backbone": "transformer-prosody-encoder192",
+  "k2_freezed": false,
+  "k2_kwargs": {
+    "dropout": 0.3,
+    "heads": 8,
+    "input_size": 5,
+    "num_layers": 2
+  },
+  "labels": 18,
+  "model_type": "fusion-cross-attention-sentence-classifier",
+  "multilabel": true,
+  "q_backbone": "distilbert-base-uncased-lora",
+  "q_freezed": false,
+  "q_kwargs": {},
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0046141292b9c1fe21afecd9322b0af37d8046d43fd127e8dbdba2b4c183307
+size 388182868

runs/Jun09_20-54-49_4c70ee357d9f/events.out.tfevents.1717966490.4c70ee357d9f.4846.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f12a36dc11aa9cb030fc82cdfc3f3d03be9472d7f83afa75b35506b6bfd054e
+size 4704

runs/Jun09_20-55-35_4c70ee357d9f/events.out.tfevents.1717966537.4c70ee357d9f.4846.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064c047027223b6e14494dd377becaad6b9be6d231750cb9d40627dc0f89c632
+size 43909

runs/Jun09_20-55-35_4c70ee357d9f/events.out.tfevents.1717975023.4c70ee357d9f.4846.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e6456bf72ce4e73665e590c59dffb36e978ccdfff717f4998535d0ad69fd88
+size 1548

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a085bc7a64153754f0cac53b494bc846faa3b01daa2683edf352a6aa48b5ae91
+size 5240