End of training

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-large
+tags:
+- generated_from_trainer
+model-index:
+- name: microsoft/deberta-v3-large
+  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. -->
+
+# microsoft/deberta-v3-large
+
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6094
+
+## 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: 8
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.6123        | 1.0   | 3550  | 1.6094          |
+| 1.6124        | 2.0   | 7100  | 1.6094          |
+| 1.6106        | 3.0   | 10650 | 1.6094          |
+| 1.6107        | 4.0   | 14200 | 1.6094          |
+| 1.6104        | 5.0   | 17750 | 1.6094          |
+| 1.6115        | 6.0   | 21300 | 1.6094          |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

added_tokens.json

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7e2e19366e3ae4fc0df3e0fbeea6a1ece6597a5764d20b640cd4e718ecea10
+size 1740387701

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

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

submission.csv

@@ -0,0 +1,201 @@
+id,prediction
+0,C D A
+1,B C E
+2,A B C
+3,D A B
+4,A C E
+5,B C D
+6,A B C
+7,A D B
+8,B D A
+9,A B E
+10,A B C
+11,B D E
+12,A B C
+13,A B C
+14,B D E
+15,A C D
+16,A B C
+17,A C D
+18,A B D
+19,D E A
+20,E A B
+21,D E A
+22,B C D
+23,A D B
+24,A B C
+25,A C E
+26,A C B
+27,C E A
+28,A B C
+29,A B C
+30,A B C
+31,B E A
+32,A B E
+33,C E A
+34,A D B
+35,A B C
+36,B C D
+37,B C D
+38,B C D
+39,B C D
+40,A C D
+41,A B C
+42,D A B
+43,A B C
+44,A B C
+45,A B C
+46,A E C
+47,A D E
+48,A B C
+49,A B C
+50,E A B
+51,B C E
+52,A B C
+53,A B E
+54,A C B
+55,C D A
+56,C D A
+57,A B C
+58,B C D
+59,A B E
+60,C D A
+61,C E A
+62,A C E
+63,C D E
+64,C D E
+65,B D E
+66,A B D
+67,A C D
+68,E B C
+69,A B C
+70,A B D
+71,B D E
+72,D E A
+73,A C D
+74,D E A
+75,B D A
+76,D E A
+77,B D A
+78,D A B
+79,A B E
+80,C A B
+81,A C E
+82,A B D
+83,C D A
+84,D E A
+85,A B C
+86,A C D
+87,B C D
+88,B E A
+89,A B D
+90,A B C
+91,B C E
+92,A E B
+93,A C D
+94,A C D
+95,B C D
+96,D E A
+97,C D E
+98,A B C
+99,A D E
+100,A D E
+101,A B E
+102,A D E
+103,A B C
+104,C D E
+105,A B D
+106,A B E
+107,B C D
+108,A B C
+109,A B C
+110,A B C
+111,E A B
+112,A B C
+113,B C E
+114,C D A
+115,D A B
+116,C D E
+117,A B C
+118,A B C
+119,A B C
+120,C D E
+121,A C D
+122,A C D
+123,A C B
+124,A C E
+125,B E A
+126,A D E
+127,A B D
+128,A B D
+129,A B C
+130,A C B
+131,A B D
+132,B C D
+133,A B C
+134,A B D
+135,A D E
+136,C A B
+137,B C D
+138,A C D
+139,A D B
+140,A B C
+141,B E A
+142,A C D
+143,A B C
+144,A B C
+145,A B D
+146,B C D
+147,D A B
+148,B C D
+149,B A C
+150,A C B
+151,A C D
+152,A E B
+153,A B D
+154,B C D
+155,D E A
+156,E A B
+157,A B C
+158,A B C
+159,A C B
+160,B C D
+161,A B C
+162,A B D
+163,A B C
+164,A D B
+165,A B D
+166,B C E
+167,A B D
+168,E A C
+169,C D E
+170,B C D
+171,A E B
+172,A B C
+173,C A B
+174,A D E
+175,C D E
+176,B C E
+177,B C D
+178,C A B
+179,E A B
+180,A B C
+181,A B C
+182,A B C
+183,A D E
+184,A B C
+185,B C D
+186,D A B
+187,A B C
+188,A C B
+189,A B C
+190,B A C
+191,A B C
+192,B C A
+193,A B C
+194,A D B
+195,A C D
+196,A C D
+197,A B C
+198,E A B
+199,A B C

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "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 sha256:61a003149df66223efefce4a4da29df72d1bdded3739898f170fc86a70ebe274
+size 4027