End of training

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: deberta_v3_finetune_hellaswag
+  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. -->
+
+# deberta_v3_finetune_hellaswag
+
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3999
+- Accuracy: 0.8765
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.5083        | 0.9996 | 1247 | 0.3641          | 0.8622   |
+| 0.193         | 1.9992 | 2494 | 0.3999          | 0.8765   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad195ccb2f5e7fd2fc820f8b8ffa5a52f7c71aa914e4df9dccdb3b26622b43a7
+size 737716196

runs/Jun04_20-25-41_25dc6887868e/events.out.tfevents.1717532743.25dc6887868e.99.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584b2a3402d43cee0f24edaf92889f9a015534ffc68954436f88f7a6996f8c7f
+size 5001

runs/Jun04_20-28-15_25dc6887868e/events.out.tfevents.1717532896.25dc6887868e.99.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55e5294086d8e8f26ef2430664ed756642dded7d96c61fef84aea923cddf6a1
+size 5001

runs/Jun04_20-29-56_25dc6887868e/events.out.tfevents.1717532997.25dc6887868e.99.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8afb15bfca9f231e89ae8d83bb208423c38b3712fcaf94d197ad0211badf19e
+size 5001

runs/Jun04_20-44-17_25dc6887868e/events.out.tfevents.1717533858.25dc6887868e.99.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8263518e5a1e0982149d24d357438fc26c7d47b8522c1accd6f8173f181b5a83
+size 5001

runs/Jun04_20-45-18_25dc6887868e/events.out.tfevents.1717533918.25dc6887868e.99.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1550748dd71dd908a65a1d0a173c42e92e0744bd7f8bdc488f43be11d53c2454
+size 5001

runs/Jun04_20-45-51_25dc6887868e/events.out.tfevents.1717533952.25dc6887868e.99.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c990ee9705df08c81f9d830bb40c08575c8be0010a13c0403edbdad21e40f9a3
+size 4999

runs/Jun04_20-46-29_25dc6887868e/events.out.tfevents.1717533990.25dc6887868e.99.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a1f2ee94a59a0e0975a18f6be5f54bacaca4292124b8c727ed79223d66d1af
+size 4999

runs/Jun04_20-46-37_25dc6887868e/events.out.tfevents.1717533998.25dc6887868e.99.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9ac30ce14fafba10c6d0d881e791aae33b4ecae742d0408732189bf53dd776
+size 4999

runs/Jun04_20-47-40_25dc6887868e/events.out.tfevents.1717534060.25dc6887868e.99.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ab5e2d713c00e5ca436d14b7a8cc5c1c41746bb71568d0e90929056adbd497
+size 5000

runs/Jun04_20-47-45_25dc6887868e/events.out.tfevents.1717534066.25dc6887868e.99.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3627936f74a281519f1bf89160807b6f796e69223d2efa44a58e778252b8879
+size 6844

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc1a7eae4c2df0a8ff2d88fc27b6e00b78d85896f96ac86849ebe4cfa3c893f
+size 5176