Training in progress, epoch 5

README.md

@@ -35,7 +35,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.1
+- Transformers: 4.55.2
 - Pytorch: 2.6.0+cu124
 - Datasets: 4.0.0
 - Tokenizers: 0.21.4

config.json

@@ -47,7 +47,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": 512,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.1",
+  "transformers_version": "4.55.2",
   "use_bidirectional_attention": false,
   "use_cache": true,
   "vocab_size": 262144

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d76f8b5cb0d9f3795dd22921263fce7af6a8c363f7eee1dee3f4b1f1a0bb5a8
+oid sha256:bb4ca1b5f96d173ea8c44e0028e64f54e564bba616d65d116573d5959705ca02
 size 536223056

runs/Aug18_17-10-36_fd93b3634552/events.out.tfevents.1755537038.fd93b3634552.1151.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e0f85b60680f2728ef9c0cbc64629aff1881e0fff3097b178bce198fd141ba
+size 238729

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36aa2ac62f34f4e686e45834b6948fc4257a7fc7eeb3ce9115cbe05a7e5da31
+oid sha256:62d6495b51ea19bc40493f457c9ca180b9d52731b7e28f9781560f2894a370d9
 size 5816