End of training

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mental/mental-roberta-base](https://huggingface.co/mental/mental-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7029
-- Accuracy: 0.5
-- F1: 0.3333
-- Precision: 0.25
-- Recall: 0.5
+- Loss: 0.0096
+- Accuracy: 0.9984
+- F1: 0.9984
+- Precision: 0.9984
+- Recall: 0.9984
 
 ## Model description
 
@@ -50,22 +50,19 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step   | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.6983        | 1.0   | 48000  | 0.7029          | 0.5      | 0.3333 | 0.25      | 0.5    |
-| 0.7189        | 2.0   | 96000  | 0.7414          | 0.5      | 0.3333 | 0.25      | 0.5    |
-| 0.5927        | 3.0   | 144000 | 0.7370          | 0.5      | 0.3333 | 0.25      | 0.5    |
-| 0.6274        | 4.0   | 192000 | 0.7668          | 0.5      | 0.3333 | 0.25      | 0.5    |
-| 0.6622        | 5.0   | 240000 | 0.7478          | 0.5      | 0.3333 | 0.25      | 0.5    |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.0006        | 1.0   | 8000  | 0.0239          | 0.9966   | 0.9966 | 0.9966    | 0.9966 |
+| 0.0002        | 2.0   | 16000 | 0.0096          | 0.9984   | 0.9984 | 0.9984    | 0.9984 |
 
 
 ### Framework versions
 
-- Transformers 4.32.1
-- Pytorch 2.1.0+cu121
-- Datasets 2.12.0
-- Tokenizers 0.13.2
+- Transformers 4.38.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.14.7
+- Tokenizers 0.15.2

logs/events.out.tfevents.1709069819.nc16.1514794.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78b51963a4fec8bd8c1f8ac6509d6a3c72d45fff4f896c41292e08ddb969b7f
-size 174022
+oid sha256:d3a0b8e5537872ba9c918ba6a4a246e3464a561b5ce22697e426092e0d139abb
+size 343648

logs/events.out.tfevents.1709108692.nc16.1514794.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b48a606135bc25e1e67059c9c8ed5581f48abf408eb4dd2905ca28b1811bddc
+size 560

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ t
 Ġ a
 h e

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba75d2f8c846db2e65be656b90503be3f187f13efe5fb2a88d41edf031318308
+oid sha256:c8333ae16ffa00d7f00e849df3b52ffe819166aca560c282282755d03ffc11d9
 size 498612824

special_tokens_map.json

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

tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "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,
@@ -94,6 +82,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

tokenizer_config.json

@@ -1,5 +1,47 @@
 {
   "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",