Training in progress, step 50

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM-135M",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,9 +23,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "v_proj",
     "k_proj",
-    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3287ecf3f605e3b870ce6959ecd7da17cab4e6c879d7b5ecf469b13831d4cbaf
-size 6316688
+oid sha256:d4a0fc7d6fd2fcbe03e54838b8829e7fa311b60eda112a3c45b3381a1201c14e
+size 1874312

special_tokens_map.json

@@ -1,29 +1,38 @@
 {
   "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": {
-    "content": "<|im_start|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -139,16 +139,31 @@
     }
   },
   "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|>",
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
-  "model_max_length": 8192,
-  "pad_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "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 sha256:7b85bfbc70a0765b49083e10772de4aa6ec753e20bfdb9c80e61c09428b5eb3a
+oid sha256:88660d09dd7b4ebf18d9049c01b24335b86e82962b0a55c970857804e9c824d4
 size 5304