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": "/mnt/bn/xuruijie-llm/checkpoints/0620/zephyr-7b-dpo-full",
   "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/Jun21_20-31-54_n136-112-146/events.out.tfevents.1718973710.n136-112-146.3092207.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da85ed8a9657212f80ad3fb86b6a86b8458074f7431eabcaa48ff2a1d1d3c12
+size 13085

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 sha256:4a03ea8d0bb33d47ee73aaae32c5621065b110a7f4643bc0e9d555172437c45b
-size 6520
+oid sha256:a0eae1fea4984f06e74b13d7802f90f8b3559e3b077c2e07ae0b32e1f90b6569
+size 6328