End of training

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: prosody_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. -->
+
+# prosody_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: 0.000435261587050942
+- 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 +1,27 @@
+{
+  "architectures": [
+    "CrossAttentionSentenceClassifier"
+  ],
+  "cross_layers": 3,
+  "dropout": 0.3,
+  "embedding_strategy": "self-att",
+  "fp16": false,
+  "heads": 8,
+  "hidden_size": 768,
+  "k_backbone": "transformer-prosody-encoder192",
+  "k_freezed": false,
+  "k_kwargs": {
+    "dropout": 0.3,
+    "heads": 8,
+    "input_size": 5,
+    "num_layers": 2
+  },
+  "labels": 18,
+  "model_type": "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:a8c5dfab4d904dd0510d456e771f2516b381e5fc5470b78571a15a6c803f5b4d
+size 8662540

runs/Jun03_19-14-09_28ffd122acb2/events.out.tfevents.1717442050.28ffd122acb2.1344.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c0a9b48625812e0f9eab14177861353cd10b1bf56d261c249d1ba207aef098b
+size 36579

runs/Jun03_19-14-09_28ffd122acb2/events.out.tfevents.1717443779.28ffd122acb2.1344.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9a07d15080c292755789cfc5ebe1f737277918842bb64a54b9509c8515ac99
+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 sha256:13066fda1a396b76118ebe38c3ed9064e0c689471ba0ffb1e796d34afbf5b220
+size 5240