Training in progress, step 250

config.json

@@ -146,7 +146,7 @@
   ],
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4fbc814e9ae3295d6856471f0fbd1a388a3ba7a879f7f7540d63c3e74ab5ff
+oid sha256:97bec62d1b29c2166944bae8b9e8272fba607c6d21ab2a983714fc302b1b68e8
 size 966995080

runs/Apr19_08-18-37_5b967a9dce61/events.out.tfevents.1713514751.5b967a9dce61.11660.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb5f234c93c561c48fe2a0a8570a1536ed7e3596518cf2653e43046f36a70ac
-size 11295
+oid sha256:0b5bbaf059234face7cc127ebaa91ea9ac0275fa344b7349b858df72b8861de4
+size 12983

runs/Apr19_09-33-42_5b967a9dce61/events.out.tfevents.1713519226.5b967a9dce61.11660.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc2cfd5c97cdd8c5032f61a32601aae93efb00c4283462f84c2677c9bec0e19
+size 8866

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17244178df0a6028e79c4f5f94408a8aa7224a7efa3064af43dd404bf9582c93
+oid sha256:6c2d7263092719e210cda3c8e6505c4bbd5f3eb7902be91a0fbd424276bc3439
 size 5176