End of training

README.md

@@ -0,0 +1,58 @@
+---
+base_model: huggingface/distilbert-base-uncased-finetuned-mnli
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: distilbert-base-uncased-finetuned-mnli-finetuned-voxi-mnli
+  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. -->
+
+# distilbert-base-uncased-finetuned-mnli-finetuned-voxi-mnli
+
+This model is a fine-tuned version of [huggingface/distilbert-base-uncased-finetuned-mnli](https://huggingface.co/huggingface/distilbert-base-uncased-finetuned-mnli) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7457
+- Accuracy: 0.8367
+
+## 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: 5e-05
+- train_batch_size: 48
+- eval_batch_size: 48
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "huggingface/distilbert-base-uncased-finetuned-mnli",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "dim": 768,
+  "dropout": 0.1,
+  "eos_token_ids": 0,
+  "finetuning_task": "mnli",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "contradiction",
+    "1": "entailment",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "contradiction": "0",
+    "entailment": "1",
+    "neutral": "2"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73527e3e493dd2c24a819a04a993019c9c54a6357658f25b7a8564c2ef9cc52f
+size 267835644

runs/Oct28_12-41-55_1007-155517-cc8extdd-10-139-64-4/events.out.tfevents.1730119367.1007-155517-cc8extdd-10-139-64-4.1286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e2886e29298d0b134259619666144f9c1e2863027c14d27b25de25ef8dcf7e
+size 5514

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 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "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 sha256:734463108e806045b5f0994f9516472cdf2cd03f2be592217989269e3103bdce
+size 5240