Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "princeton-nlp/Mistral-7B-Base-SFT-DPO",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/chatml/round1-5",
   "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/Jun18_00-07-46_n136-112-146/events.out.tfevents.1718641358.n136-112-146.1268905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b264db35cac5853603554e9e3f92c5b8127f63d24358da09a2da08b3e077bb
+size 12323

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

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 sha256:0758e05223e23ca98d29f00c11f03495f5254cd8f6b8ab05a5eb205e1a25f069
-size 6520
+oid sha256:5ca14e00ceee0c3ab88b979e867f6b742a5f002d09608006b9acb2a73e99e73d
+size 6328