Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/new_world/v1-distill-prefix2-0.5",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/new_world/10-9-round2",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.38.2",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Jun11_20-45-25_n136-100-194/events.out.tfevents.1718110156.n136-100-194.3719830.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ea4bec15ae790b1bcd703b701c8e94489e7b95a34a4b10b5b14cf736f95e55
+size 12315

tokenizer.json

@@ -152,7 +152,6 @@
     "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 sha256:7803e3f5d8581db26a308bbdaa3271a678b31874765616fd09174a3d3c44b026
-size 6328
+oid sha256:16edf0d5fed8efa4c443f7dad2dc6604d5b4bc312040d7965f4bee8ee9215478
+size 6264