End of training

README.md

@@ -1,11 +1,11 @@
 ---
+license: apache-2.0
+base_model: mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es
 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
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mi_chatbot
 
-This model was trained from scratch 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: 3.0442
+- Loss: 0.5479
 
 ## Model description
 
@@ -35,8 +35,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 3
-- eval_batch_size: 3
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,18 +46,18 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 37   | 3.8093          |
-| No log        | 2.0   | 74   | 3.3021          |
-| No log        | 3.0   | 111  | 3.0845          |
-| No log        | 4.0   | 148  | 2.9462          |
-| No log        | 5.0   | 185  | 2.8879          |
-| No log        | 6.0   | 222  | 2.9819          |
-| No log        | 7.0   | 259  | 3.0442          |
+| 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          |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.37.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.17.1
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mi_chatbot",
+  "_name_or_path": "mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es",
   "architectures": [
     "BertForQuestionAnswering"
   ],
@@ -19,7 +19,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.37.2",
   "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:b4dc30c35f08dcdc6e9d152bfc16aa49674cefecbd73afd7faa7bc6cdf4bcaad
+oid sha256:10f0b640da5c1ad66bd065efc82208cf25ed3324ebd1d09b6c6113c7bd560f05
 size 437070648

runs/Feb24_20-36-28_ed064940385f/events.out.tfevents.1708806990.ed064940385f.1370.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9342400a35d4b887a30d13feb992328dd873ebcea40f509a5e28660726b15858
+size 6581

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "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
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4056a4d5a06c624704768773c8dc416691a520cc01120993ab138124d4ea9b
-size 729903
+oid sha256:0b2cb0a433da31658bd79f95e7beabf22a59aaaf0d39513b24f5474cef8edcfd
+size 730166

tokenizer_config.json

@@ -46,19 +46,12 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 384,
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "only_second",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76aba73107fc0595dcf4b3c219f0c566f2504e5aeb6b738b662ae66f6f1eab51
-size 4536
+oid sha256:5a55afa51176ba0c93b2b9674af553a0ec406f291f5c3c50183cdc1739f6fc7a
+size 4664