End of training

README.md

@@ -1,6 +1,4 @@
 ---
-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 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mi_chatbotV3
 
-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 was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9410
+- Loss: 0.8758
 
 ## Model description
 
@@ -35,8 +33,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- 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
@@ -46,9 +44,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 66   | 1.1849          |
-| No log        | 2.0   | 132  | 1.0079          |
-| No log        | 3.0   | 198  | 0.9410          |
+| No log        | 1.0   | 17   | 0.9423          |
+| No log        | 2.0   | 34   | 0.8513          |
+| No log        | 3.0   | 51   | 0.8758          |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es",
+  "_name_or_path": "mi_chatbotV3",
   "architectures": [
     "BertForQuestionAnswering"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381cb62084ef61466d05e6219e5755ebdc433b95429ce7960def933efaab7502
+oid sha256:1129864c60fbf42ee27fb68657f176af916b823f0dcda7b3803c58c984d30ef7
 size 437070648

runs/Mar01_15-31-18_bec8f75ca57c/events.out.tfevents.1709307079.bec8f75ca57c.1107.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbfd5e902274c31bd887d8329e3a14d36eb2d07c48cc9092105a78c6ea32208
+size 5707

special_tokens_map.json

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

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 384,
-    "strategy": "OnlySecond",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 384
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 1,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -46,12 +46,19 @@
   "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:bc8d8d2c172476cfb628c288ae86caa10be53116ffc5acee87e707263eba1d72
+oid sha256:12aa873e8ddedceee8417a390aad9515d63e5e6fcfd02a4315ffe74b648c6262
 size 4856