End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,83 @@
+---
+license: mit
+base_model: microsoft/mdeberta-v3-base
+tags:
+- generated_from_trainer
+datasets:
+- pquad
+model-index:
+- name: qa-fa-mdeberta-v3-base
+  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. -->
+
+# qa-fa-mdeberta-v3-base
+
+This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the pquad dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8308
+
+## 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: 0.0001
+- train_batch_size: 5
+- eval_batch_size: 5
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.962         | 0.04  | 500   | 1.3311          |
+| 1.4591        | 0.08  | 1000  | 1.3656          |
+| 1.3366        | 0.12  | 1500  | 1.3459          |
+| 1.2211        | 0.16  | 2000  | 1.2812          |
+| 1.1793        | 0.19  | 2500  | 1.1125          |
+| 1.1316        | 0.23  | 3000  | 1.1440          |
+| 1.0693        | 0.27  | 3500  | 1.1141          |
+| 1.0541        | 0.31  | 4000  | 1.2000          |
+| 1.0774        | 0.35  | 4500  | 1.1321          |
+| 1.0284        | 0.39  | 5000  | 0.9901          |
+| 0.9806        | 0.43  | 5500  | 0.9894          |
+| 0.9341        | 0.47  | 6000  | 0.9512          |
+| 0.9368        | 0.51  | 6500  | 0.9508          |
+| 0.9111        | 0.55  | 7000  | 1.0454          |
+| 0.8872        | 0.58  | 7500  | 0.9940          |
+| 0.8283        | 0.62  | 8000  | 0.8971          |
+| 0.9249        | 0.66  | 8500  | 0.8796          |
+| 0.8478        | 0.7   | 9000  | 0.9074          |
+| 0.8167        | 0.74  | 9500  | 0.8703          |
+| 0.8102        | 0.78  | 10000 | 0.8432          |
+| 0.7354        | 0.82  | 10500 | 0.8772          |
+| 0.7711        | 0.86  | 11000 | 0.8493          |
+| 0.7443        | 0.9   | 11500 | 0.8409          |
+| 0.7156        | 0.94  | 12000 | 0.8420          |
+| 0.7242        | 0.97  | 12500 | 0.8308          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.15.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/mdeberta-v3-base",
+  "architectures": [
+    "DebertaV2ForQuestionAnswering"
+  ],
+  "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": "4.35.2",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48e75323351afb1452a476fed57d69030460efc0388d1ec3a71a5603fef2d48
+size 1112905680

runs/Dec03_16-57-00_Software-AI/events.out.tfevents.1701610021.Software-AI.2080908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ab0a57e1cbf2116e32fb77e0edbae1b436c3ccc42e26bb029e2fa57823e752
+size 116091

runs/Dec04_07-30-57_Software-AI/events.out.tfevents.1701662458.Software-AI.2960647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c7d05aa5fec56f17f3c9d16755d429530b5a5191d490c3db69ec01e2795f54
+size 15424

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 sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aca3ce69a0a35aeb144a52c4f1d41c4246b8785f8f398315cc8fb6b24057810
+size 16331396

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
+    },
+    "250101": {
+      "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:b66819b024f240ea53f002de22c83afa385bfcb7cff678f2f697b5cd7b092f10
+size 4155