Training in progress, step 600

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/new_world/v1-ultral",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/hh-rlhf/sft_0521/checkpoint-5500/",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.41.1",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/May28_00-57-45_n136-082-130/events.out.tfevents.1716829733.n136-082-130.1949438.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed6e8ad3a14b123029b2ffb9ca8adda880163d43369f5f99e32ae53014ea566
-size 43736
+oid sha256:f249a9a2ef3c49e47d3a5025d83115ebd39a9cf847919660eafe57e55afe83c3
+size 51356

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:233762ce2f7a1cfa30251c51e84fc095bdb7579faa7bbc23d8ce39a8e51f366d
-size 6328
+oid sha256:cf525e556a4e72ad76dc3263558be495a00b73c02de0b6ea713d4bfeb6a07eb0
+size 6456