Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/simpo/round1",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/simpo/sft",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.39.3",
   "use_cache": false,
   "vocab_size": 32000
 }

runs/Jun13_10-53-40_n136-129-074/events.out.tfevents.1718247588.n136-129-074.3919414.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1a1b99fd9dfec5b933ab706312c90c27de817882397274856b5c05763d39c2
+size 12293

tokenizer.json

@@ -134,7 +134,6 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
-    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -29,7 +29,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n\n\nHuman: ' + message['content'] + '<|end_of_turn|>' }}{% elif message['role'] == 'assistant' %}{{ '\n\n\nAssistant: '  + message['content'] + '<|end_of_turn|>' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\n\n\nAssistant: ' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c70facc10a0add57b3257c66a9ce0db4d390283c663cd0223999426592e397
-size 6456
+oid sha256:c19b6506f22d215f5ae0a1f0b2f0a8e7cab7d125182ef1c2090886ee3cd44fac
+size 6264