End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3146
+- Loss: 0.6896
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 4e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -47,8 +47,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2745        | 1.0   | 174  | 0.3146          |
-| 0.2303        | 2.0   | 348  | 1.2237          |
+| 0.6909        | 1.0   | 18   | 0.6931          |
+| 0.6897        | 2.0   | 36   | 0.6896          |
 
 
 ### Framework versions

logs/events.out.tfevents.1711974405.mbptilhendealma.students.clients.local.7155.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b712f26f19bf5a6417792bc4abe05ff73820027a987656cbbe4a6afaf68cc07a
-size 5200
+oid sha256:2e04f90d8144fe64047bee192e2c54e9020cdc1d57dd51521dd6b462265d217d
+size 6228

logs/events.out.tfevents.1711974525.mbptilhendealma.students.clients.local.7155.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b082cf40442b285a757d6c54fb058838daf0b39b8647e446d4996e17e38e5d3f
+size 306

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd60f6d835445f2be0aa3fef49e03dc1786f7b87a1be5f843578fe9fe3f0343e
+oid sha256:eb74071d808cc2ddcb15d9214fec9dc192529d3e44a337640848412e00e6e359
 size 498612824

special_tokens_map.json

@@ -1,25 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -27,25 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 4096,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -48,17 +48,10 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "max_length": 512,
-  "model_max_length": 4096,
-  "pad_to_multiple_of": null,
+  "model_max_length": 512,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "</s>",
-  "stride": 0,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }