Training in progress, epoch 1

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6a3250ca9b0c37867b89baa5540f1dcc1271477f7327a64fb8965923e00ef3
-size 988097824
+oid sha256:14c1ef0b9af54c80f51f20e71da98112fb93483799179a98376c9beb2ac34f19
+size 1260367448

runs/Sep26_14-36-39_nlu12a2/events.out.tfevents.1727329099.nlu12a2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b389919c8539983f0fd9ca7e74aa75e1dc5b0f95a8dcc33f9b9a955682bd855a
+size 6092

runs/Sep26_14-42-15_nlu12a2/events.out.tfevents.1727329413.nlu12a2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88157a163fa71d794ddedbec99b0dfb125c2fdfc3d9f0f73964dba15f1a9c5cc
+size 6092

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1280df1c6aba4358994617c56f8bac67de81470952b833eea0b7461236fd43
-size 5560
+oid sha256:051d4ace407445bcb7930cb25f6b4df860754048a35709fe247388ace3a72b7b
+size 7032