Training in progress, step 4500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-360M-Instruct",
+  "_name_or_path": "jekunz/smollm-360m-cpt-fineweb-swedish",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -7,6 +7,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 960,
   "initializer_range": 0.02,
@@ -32,7 +33,7 @@
       "q4f16": "float16"
     }
   },
-  "transformers_version": "4.43.4",
+  "transformers_version": "4.49.0.dev0",
   "use_cache": true,
   "vocab_size": 49152
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ab551a982294535e2e5c473b0b146057d57d98ca28ca8712a82d47203655f3
+oid sha256:83ff118f481d3d72f09efaa6d513c4024627c607d0ef144c84e0c1fca58bd885
 size 1447317080

tokenizer_config.json

@@ -146,6 +146,7 @@
   "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": {},
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ff32c9712041a6b763b6df4b8aa8e1514869d60f2cd87e4ae183344217b1bb
-size 5176
+oid sha256:9cd6b7be9efae25acb26addf3a34fec9512932c401de9e0214dc50e934b4a7aa
+size 5368