Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "BEE-spoke-data/smol_llama-101M-GQA",
+  "_name_or_path": "Felladrin/Smol-Llama-101M-Chat-v1",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -16,6 +16,7 @@
   "num_attention_heads": 24,
   "num_hidden_layers": 6,
   "num_key_value_heads": 8,
+  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e08a4db3ebc119d3d3f1c64d4f8aedfc606992e16f37b79c9d5422b711d78d
+oid sha256:26e06df2a9e6d21d0e60ecc2f11d6c9fdb67031206518f2001b700d60e490db4
 size 405058720

tokenizer_config.json

@@ -28,6 +28,7 @@
     }
   },
   "bos_token": "<s>",
+  "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 %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
@@ -38,5 +39,5 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17be02f6a9bc9a1736833fb00b1baaf2f50320097eb8bc125429911d8418f517
+oid sha256:78a7f8d30243fd618be7bdf260f1089c21ddb21d44e00a0b5a64d452edc06884
 size 4728