Training in progress epoch 0

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: distilbert-base-uncased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -11,15 +13,15 @@ probably proofread and complete it, then remove this comment. -->
 
 # LexFerrinson/FirulaiModel
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2572
-- Validation Loss: 0.2342
+- Train Loss: 1.0504
+- Validation Loss: 0.8975
 - Train Precision: 0.0
 - Train Recall: 0.0
 - Train F1: 0.0
-- Train Accuracy: 0.9082
-- Epoch: 1
+- Train Accuracy: 0.7563
+- Epoch: 0
 
 ## Model description
 
@@ -45,8 +47,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
 |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
-| 0.2941     | 0.2539          | 0.0             | 0.0          | 0.0      | 0.9082         | 0     |
-| 0.2572     | 0.2342          | 0.0             | 0.0          | 0.0      | 0.9082         | 1     |
+| 1.0504     | 0.8975          | 0.0             | 0.0          | 0.0      | 0.7563         | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "LexFerrinson/FirulaiModel",
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForTokenClassification"

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]"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5e53acfc9948d37237021b807728a6b052122dfcd0854445302d479965ee18
+oid sha256:e5cb6cb57463ae3df4485e601ea4511702b0786158ec6da24084f42ba011792d
 size 265587984

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -45,15 +45,11 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }