Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -27,6 +27,12 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
   "transformers_version": "4.47.1",
   "use_cache": true,
   "vocab_size": 49152

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2b2fd6d73a55ff975616b4f77e864a4f2c6d2dea9e4d867d4973ff293196ec
+oid sha256:064b7d77fb166985d7e1a0f599f32df7f2a6afcd904c4e875980bf1e2358ff8e
 size 538090408

runs/Jan08_13-00-48_ae0a6acb9436/events.out.tfevents.1736341249.ae0a6acb9436.2906.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16196bc3fca2880839d0900da5e80d17c01cea9dbf279c49e101bd895b724300
-size 26766
+oid sha256:1ce52a7ed8e31045b86e2afcc86dc1c7516ab48e3c9873fa84ffdca8d5e22c4e
+size 29441

runs/Jan08_13-13-38_ae0a6acb9436/events.out.tfevents.1736342019.ae0a6acb9436.2906.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90460f28261a64f926c06e491e26e997078f784d0b086bd90e9e4df96ad53350
+size 16381

special_tokens_map.json

@@ -1,23 +1,29 @@
 {
   "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
-    }
+    "<|im_start|>",
+    "<|im_end|>"
   ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|im_end|>",
+  "bos_token": {
+    "content": "<|im_start|>",
+    "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|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -143,7 +143,7 @@
     "<|im_end|>"
   ],
   "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 %}",
+  "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 %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ca6be4fa24e77026046eeaf9e4bd2b7f6fc906cef65eddb0e41d79adfd7893
+oid sha256:bbd141e19c33d5896f562899ed0884cdfa7c359f01f2622f5a76475c215644e7
 size 5624