Training in progress epoch 0

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Eliac11/tinkNLP](https://huggingface.co/Eliac11/tinkNLP) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5899
-- Validation Loss: 2.1619
-- Epoch: 23
+- Train Loss: 5.5514
+- Validation Loss: 4.8451
+- Epoch: 0
 
 ## Model description
 
@@ -42,35 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.7611     | 3.2917          | 0     |
-| 2.5272     | 3.1344          | 1     |
-| 2.3172     | 2.9982          | 2     |
-| 2.1298     | 2.8936          | 3     |
-| 1.9620     | 2.7805          | 4     |
-| 1.8145     | 2.6929          | 5     |
-| 1.6762     | 2.6139          | 6     |
-| 1.5531     | 2.5450          | 7     |
-| 1.4394     | 2.4895          | 8     |
-| 1.3463     | 2.4272          | 9     |
-| 1.2504     | 2.3718          | 10    |
-| 1.1740     | 2.3381          | 11    |
-| 1.0953     | 2.3067          | 12    |
-| 1.0245     | 2.2730          | 13    |
-| 0.9623     | 2.2482          | 14    |
-| 0.9074     | 2.2176          | 15    |
-| 0.8601     | 2.2021          | 16    |
-| 0.8079     | 2.1901          | 17    |
-| 0.7651     | 2.1776          | 18    |
-| 0.7242     | 2.1688          | 19    |
-| 0.6864     | 2.1613          | 20    |
-| 0.6494     | 2.1500          | 21    |
-| 0.6192     | 2.1510          | 22    |
-| 0.5899     | 2.1619          | 23    |
+| 5.5514     | 4.8451          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
-- TensorFlow 2.12.0
-- Datasets 2.14.5
-- Tokenizers 0.13.3
+- Transformers 4.38.2
+- TensorFlow 2.15.0
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -28,7 +28,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 50261
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.33.1"
+  "transformers_version": "4.38.2"
 }

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a08f76e2b8be1216348de2098c78f2645e955866e342de5cd0fa3b48c56702ed
+oid sha256:a3a2028ccd2ea3105af8c5b15022591793468213467cd12bfbb5e5aba742beaf
 size 501093456

tokenizer_config.json

@@ -1,34 +1,63 @@
 {
   "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "@@ПЕРВЫЙ@@",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "@@ВТОРОЙ@@",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "<FIRST_SPEAKER>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "<SECOND_SPEAKER>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "<pad>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "unk_token": "<|endoftext|>",
   "use_fast": true
 }