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/v1-distill-round2-0.5-diff-lr58",
   "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/Jun04_11-43-48_n136-100-194/events.out.tfevents.1717472990.n136-100-194.3983374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5941f4750df327c11d9045a1fe54b137808102976abcc232e5363bdd3392ede2
+size 13101

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:a43f1ec98d2c131b691a4a61be956ba111c56fde1b5474a028ba22f1faa2a663
-size 6520
+oid sha256:55a5fe1d8e345fca3fd945298a735f70df317cac7a0afe275b3577c9f2008a69
+size 6264