Training in progress, step 300

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/new_world/v1-distill-round2-0.5-lr58",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/new_world/v1-ultral",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.38.2",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Jun06_13-29-12_n136-129-074/events.out.tfevents.1717652376.n136-129-074.1035360.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781925ad12a034471da45a889edc54b22aaf657193ec47d43325eb9dc28eff39
-size 19158
+oid sha256:6bef81b7e8e08e6c2ab3fc2c505cd33b52117067ed55425ef435ce56bd7ccb9a
+size 26038

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 sha256:512adc2137770b57e7ddb69d1de095538b32cce7dd07b1838622c10c27d98439
-size 6520
+oid sha256:0fca5a261a54300d1452b13f8cd6d979be181e6f4026bf678536b29a267ee051
+size 6264