Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/chatml/round1-5-beta1",
+  "_name_or_path": "princeton-nlp/Mistral-7B-Base-SFT-SimPO",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.1",
   "use_cache": false,
   "vocab_size": 32000
 }

runs/Jun19_20-41-56_n136-082-130/events.out.tfevents.1718800988.n136-082-130.1048308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5313c6e1143d7eadc883204862a77f98a1d90bc816e834e945664ec5e7aa994
+size 12513

tokenizer.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f623fa5935a72470062cad184e0e3e0f86960a46611a37e110567aac9230c51
-size 6328
+oid sha256:1d43daf6967bdbc93130e5fa6570c72d0feeace742e348e0392bb90c6689eda8
+size 6520