End of training

.ipynb_checkpoints/chat_template-checkpoint.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

README.md

@@ -4,10 +4,10 @@ library_name: transformers
 model_name: math-SmolLM2-360M
 tags:
 - generated_from_trainer
-- camel-math
 - finetune
-- trl
+- camel-math
 - sft
+- trl
 licence: license
 ---
 

adapter_config.json

@@ -25,12 +25,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "o_proj",
     "up_proj",
-    "gate_proj",
     "q_proj",
     "v_proj",
-    "down_proj",
+    "gate_proj",
     "k_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15514aefbe1f79fb4df924da0e43549a539dca4fabd3b4a3bebdb829ab640549
+oid sha256:556b015fcaf13e4682d92b6171209887c9d3088ced3a7612d9cf0911875386a8
 size 8741392

special_tokens_map.json

@@ -1,23 +1,38 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
   ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|im_end|>",
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -139,15 +139,30 @@
     }
   },
   "additional_special_tokens": [
+    "<|endoftext|>",
     "<|im_start|>",
-    "<|im_end|>"
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
   ],
-  "bos_token": "<|im_start|>",
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "model_max_length": 8192,
-  "pad_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9792dd56196fc092e61bf4d4b40a15ba6cc93bcfd6285722f47c6f31460dad12
+oid sha256:20db55b968a3c53f5dde9056413f58b86eb9ddf3bec0abe9827977712150c8ee
 size 6161