Training in progress, step 100

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/new_world/v1-distill-round2-0.5-lr58",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.2",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Jun05_23-14-01_n136-112-146/events.out.tfevents.1717600971.n136-112-146.144950.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6883c7dfa3a2614d7aa81b49faaa4c0dffd0e073132fd7768695d7d2f356efa9
+size 12459

tokenizer.json

@@ -152,6 +152,7 @@
     "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:b92372e760a727f6582979303a96b389cee04d00a2f4a6c534c36c4b19bfdc3f
-size 6264
+oid sha256:44368936e8a5f160f38c764acd78a1ed87cb99f1b31bc5a44994e052788c660a
+size 6392