Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/chatml/round1-5-beta1",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.1",
   "use_cache": false,
   "vocab_size": 32000
 }

runs/Jun21_17-08-00_n136-082-130/events.out.tfevents.1718961008.n136-082-130.2131127.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d87bcd2015adabd7590ea3adc23577bd5d9d78d9e9d5124943e409f5d4d115
+size 12581

tokenizer.json

@@ -134,6 +134,7 @@
     "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:bec7c8a62a21dfa7db36090d7c7e37914b21f7e60b2a75556ca82856b00326c8
-size 6264
+oid sha256:4a03ea8d0bb33d47ee73aaae32c5621065b110a7f4643bc0e9d555172437c45b
+size 6520