End of training

README.md

@@ -1,13 +1,11 @@
 ---
-license: apache-2.0
-base_model: mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es
+license: mit
+base_model: timpal0l/mdeberta-v3-base-squad2
 tags:
 - generated_from_trainer
 model-index:
 - name: mi_chatbot
   results: []
-language:
-- es
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mi_chatbot
 
-This model is a fine-tuned version of [mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es](https://huggingface.co/mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es) on an unknown dataset.
+This model is a fine-tuned version of [timpal0l/mdeberta-v3-base-squad2](https://huggingface.co/timpal0l/mdeberta-v3-base-squad2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5479
+- Loss: 0.8504
 
 ## Model description
 
@@ -37,24 +35,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 8    | 1.5199          |
-| No log        | 2.0   | 16   | 1.0632          |
-| No log        | 3.0   | 24   | 0.5938          |
-| No log        | 4.0   | 32   | 0.5494          |
-| No log        | 5.0   | 40   | 0.5706          |
-| No log        | 6.0   | 48   | 0.5299          |
-| No log        | 7.0   | 56   | 0.5479          |
+| No log        | 1.0   | 30   | 0.8746          |
+| No log        | 2.0   | 60   | 0.7221          |
+| No log        | 3.0   | 90   | 0.8504          |
 
 
 ### Framework versions
@@ -62,4 +56,4 @@ The following hyperparameters were used during training:
 - Transformers 4.37.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.17.1
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

config.json

@@ -1,26 +1,35 @@
 {
-  "_name_or_path": "mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es",
+  "_name_or_path": "timpal0l/mdeberta-v3-base-squad2",
   "architectures": [
-    "BertForQuestionAnswering"
+    "DebertaV2ForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
+  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "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": "4.37.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 31002
+  "type_vocab_size": 0,
+  "vocab_size": 251000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f0b640da5c1ad66bd065efc82208cf25ed3324ebd1d09b6c6113c7bd560f05
-size 437070648
+oid sha256:c4520902b4bcc3bc8a2780dcf9e9962de13b72140648d7583f0eee53b46cac96
+size 1112905680

runs/Feb25_00-27-24_66a705353b88/events.out.tfevents.1708820844.66a705353b88.1402.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e0be990040f4d225ee6223e70d999ddb97107ce4613909a3eb331997ea88b5
+size 5517

runs/Feb25_00-29-55_66a705353b88/events.out.tfevents.1708820996.66a705353b88.1402.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6366d095873dccfd65f2738c40eda9f705ced1dd562a993aff6d2a3fb6e5c32b
+size 5517

runs/Feb25_00-30-44_66a705353b88/events.out.tfevents.1708821045.66a705353b88.1402.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6a0be20a075107bbfef47158a5c2d3f16f03cd4b3a6fae738d1acc39e8bd7b
+size 5517

runs/Feb25_00-31-12_66a705353b88/events.out.tfevents.1708821073.66a705353b88.1402.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4dbaf4a3bf1c964a62b368f2862fb0beacd1ecbc0ddc56a0202712490440bb1
+size 5517

runs/Feb25_00-31-36_66a705353b88/events.out.tfevents.1708821096.66a705353b88.1402.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a00926dd64979e0a6c2808c9d5ad1a932e10c9d8f29905fc91f36fc8f6359a8
+size 5517

runs/Feb25_00-31-59_66a705353b88/events.out.tfevents.1708821120.66a705353b88.1402.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ea77d94bf2a69fce8f535c46b8b9186f554d81e17f09b3a67146b8a1459122
+size 5517

runs/Feb25_00-33-28_66a705353b88/events.out.tfevents.1708821209.66a705353b88.1402.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae8e4e15c538d772de08da66b2db9820742b0693f79b73c367f0a5379ea4ff7
+size 5517

runs/Feb25_00-46-23_66a705353b88/events.out.tfevents.1708821984.66a705353b88.1402.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f04b77e3dde3864008bccba54b313403f14fd6a50d5c95a6be8d77a939abf8
+size 5517

runs/Feb25_00-57-31_66a705353b88/events.out.tfevents.1708822652.66a705353b88.1402.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd128a3e2d04264f8744dfa2928e5b5b7ad0acac99cbd00fae8338c75e7b4f7
+size 5517

runs/Feb25_00-58-23_66a705353b88/events.out.tfevents.1708822704.66a705353b88.1402.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4238fc01a0f9c9e32c2413db8ff26d7c136a0c2f752ae35232c936f1660ceb05
+size 5517

runs/Feb25_01-18-11_66a705353b88/events.out.tfevents.1708823892.66a705353b88.10659.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624b7f001530b349a871625c6d9ce79af04488a144118414cc8709d3352644f5
+size 5716

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2cb0a433da31658bd79f95e7beabf22a59aaaf0d39513b24f5474cef8edcfd
-size 730166
+oid sha256:a1138eab70286f87e95bdf1fb4f1f173698ab5b130389032f399ea67b917bd07
+size 16316412

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[MASK]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,31 +9,31 @@
       "special": true
     },
     "1": {
-      "content": "[PAD]",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "2": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[CLS]",
+    "3": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "5": {
-      "content": "[SEP]",
+    "250101": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,17 +41,18 @@
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a55afa51176ba0c93b2b9674af553a0ec406f291f5c3c50183cdc1739f6fc7a
+oid sha256:827c255802c4065f64963031fb25cdf5ec823cd41c541f6a1f271c62e06fbc48
 size 4664