Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "princeton-nlp/Mistral-7B-Base-SFT-SimPO",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/chatml/round1-5-beta1",
   "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/Jun19_21-36-55_n136-100-194/events.out.tfevents.1718804244.n136-100-194.4102142.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e574164c61f65a2104293ed3f2c5fc5feaa08cc35f82ed560eb6dc4272e807fc
+size 5600

runs/Jun19_21-42-20_n136-100-194/events.out.tfevents.1718804567.n136-100-194.4105091.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b93c0d28830d06bf9f2f72615aa690eb3c5f1d30df3dea995484a7f2e9aedb
+size 12360

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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d43daf6967bdbc93130e5fa6570c72d0feeace742e348e0392bb90c6689eda8
-size 6520
+oid sha256:3b98319cc7f8f873aaf0e58666d771b84128c64476049571b0dcb80f9fec032c
+size 6328