Training in progress, step 100

config.json

@@ -24,7 +24,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_parallel_residual": true,
   "vocab_size": 50304
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee645992f24ee02b486f2e81b344b7a98df284d1f79aa4f2f1679fdd185f99d
+oid sha256:635f619ab31b0b3348b39a70a64e85d9f0a51fc44cabb2a9a855bcfaf593745d
 size 2829330208

runs/Jul08_12-10-46_42dbe5cf9ed4/events.out.tfevents.1720441204.42dbe5cf9ed4.850889.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1cb9378ead4b421d8f7b99cb7ee5b8cbea5742fb4fc4bb83203e1f5a4aa262
+size 16485

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6512ebaae4617131c502f655a94c28ca877471322e354baceb9f8cb3b89b8f9e
+oid sha256:23e80f0082a759adf7bcdb9e73bc424e6165afc3e651a6c8bd1da644a92e628b
 size 6264