End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: timpal0l/mdeberta-v3-base-squad2
+license: apache-2.0
+base_model: mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mi_chatbot
 
-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.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 4.5928
+- Loss: 4.7305
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 7    | 4.9219          |
-| No log        | 2.0   | 14   | 4.6609          |
-| No log        | 3.0   | 21   | 4.5928          |
+| No log        | 1.0   | 7    | 5.2821          |
+| No log        | 2.0   | 14   | 4.8369          |
+| No log        | 3.0   | 21   | 4.7305          |
 
 
 ### Framework versions

config.json

@@ -1,35 +1,26 @@
 {
-  "_name_or_path": "timpal0l/mdeberta-v3-base-squad2",
+  "_name_or_path": "mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es",
   "architectures": [
-    "DebertaV2ForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
   "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-07,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
+  "model_type": "bert",
   "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,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "type_vocab_size": 0,
-  "vocab_size": 251000
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b037a1c5e4e62595e30daeeaacdd7988444420be59da6c9533273e4d26cb7784
-size 1112905680
+oid sha256:b1ddcef21642c9afe80154e815f8f60243ccb343f0a9982ad57dc8fdb66540c6
+size 437070648

runs/Feb18_00-20-52_ab13d288f27c/events.out.tfevents.1708215653.ab13d288f27c.1146.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d2800c5f3e446fd3631d259a858f587cf91eac72beb4eb0479d61ebcadbd94
+size 5378

special_tokens_map.json

@@ -1,7 +1,5 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

tokenizer.json

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

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf60988174988baf53a4076b5e34e8cf6d1d6de0e1f079b81ade2937807256e
+oid sha256:b0c4327c5a0233e76ccb3004547c83b4801f293d50f6770a80ceac56a0091d51
 size 4536