aug_arb_emo

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7403
+- Loss: 1.1212
 
 ## Model description
 
@@ -48,18 +48,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 0.7135        | 1.0   | 6036  | 0.6917          |
-| 0.6619        | 2.0   | 12072 | 0.6907          |
-| 0.5675        | 3.0   | 18108 | 0.7124          |
-| 0.5077        | 4.0   | 24144 | 0.7403          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7811        | 1.0   | 1469 | 1.0575          |
+| 0.7979        | 2.0   | 2938 | 1.0676          |
+| 0.8273        | 3.0   | 4407 | 1.0935          |
+| 0.7819        | 4.0   | 5876 | 1.1212          |
 
 
 ### Framework versions
 
 - PEFT 0.7.2.dev0
-- Transformers 4.38.2
+- Transformers 4.36.2
 - Pytorch 2.2.1
 - Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9865a569a666b4638d33d00f2145d1e9dabd4f7c4abba2fa66e67b5fcd651e
+oid sha256:a42f65759f75dcf1f986bf69d17d476ef941f4463199b4270c0b217355df0079
 size 1182877280

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

runs/Apr11_06-55-31_DESKTOP-5GR7SN9/events.out.tfevents.1712789740.DESKTOP-5GR7SN9.21012.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d3e66eaf052cc0344e6464e2837dfe757d68cdbf3023566a76c64c62f1b4c5
+size 43107

special_tokens_map.json

@@ -1,14 +1,14 @@
 {
   "additional_special_tokens": [
     {
-      "content": "<|im_start|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<|im_end|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -37,7 +32,7 @@
     },
     {
       "id": 32000,
-      "content": "<|im_start|>",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -46,7 +41,7 @@
     },
     {
       "id": 32001,
-      "content": "<|im_end|>",
+      "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -27,7 +27,7 @@
       "special": true
     },
     "32000": {
-      "content": "<|im_start|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -35,7 +35,7 @@
       "special": true
     },
     "32001": {
-      "content": "<|im_end|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -44,8 +44,8 @@
     }
   },
   "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
+    "<|im_end|>",
+    "<|im_start|>"
   ],
   "bos_token": "<|im_start|>",
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f03402ad5c8e6635fd0439e097d486bec9986606122c72f5e94813a1439af77
-size 4920
+oid sha256:ea506a77b77f0a3215de7e3e6a6d9c7316d190a7a78d99becb0beb5a005d1844
+size 4728