End of training

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: fusion_gttbsc_distilbert-uncased-best
+  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-best
+
+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 4.41.1
+- 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",
+  "q_freezed": true,
+  "q_kwargs": {},
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba1db100f2996b8239b9e2babb7bf7694a85f104c5d6e2cd4608c1aa9c19f99
+size 388182868

runs/Jun03_22-58-09_a86869001603/events.out.tfevents.1717455491.a86869001603.1309.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa63797aa4cc00bec5c62d371337c364940d2cedd45b2869fe60bf4a87d4ef71
+size 12217

runs/Jun03_23-15-57_a86869001603/events.out.tfevents.1717456558.a86869001603.1309.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689c59368a932c30f51c1f1d28eb9e1afac4a3d7c73c50a9abc40add32854b30
+size 5003

runs/Jun03_23-16-42_a86869001603/events.out.tfevents.1717456604.a86869001603.1309.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a469f027925857f9064de65c92a9bb5b99eac8f4d6e5f565810defae67da4e3f
+size 5004

runs/Jun03_23-17-24_a86869001603/events.out.tfevents.1717456646.a86869001603.1309.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d40c53c95600743c59edd088bb54c011cf9d8ad743fe03b74ea766382d92b0e
+size 5003

runs/Jun03_23-19-15_a86869001603/events.out.tfevents.1717456757.a86869001603.1309.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c017135c5c6c88e1cef7655414bcf800b76caa9aceaf3e9c4d9354fffb92a9d7
+size 88

runs/Jun03_23-20-03_a86869001603/events.out.tfevents.1717456805.a86869001603.1309.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4edc1b149fd93e5df5afcd66773afb5eab74ed449196b6a2f3f407665ecb7b
+size 88

runs/Jun03_23-22-26_a86869001603/events.out.tfevents.1717456947.a86869001603.19350.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6412fdfb1f505abd7892b931d0ddb46712f23e688ad39cc10e948a94c93ca0
+size 38500

runs/Jun03_23-22-26_a86869001603/events.out.tfevents.1717461122.a86869001603.19350.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffdc7a86327142a6f8cb5f44a03a87019e10298a8e8dad1d09acbb702c2ee201
+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 sha256:51be249df328589c71904ff5bc24feeab4a5b5a81528999adeaf9adb4d17929e
+size 5240