End of training

README.md

@@ -36,8 +36,8 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.12.1
-- Transformers: 4.46.3
-- Pytorch: 2.5.1
+- Transformers: 4.46.2
+- Pytorch: 2.5.1+cu121
 - Datasets: 3.1.0
 - Tokenizers: 0.20.3
 

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.46.2",
   "use_cache": true,
   "vocab_size": 49152
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf5a2c8862094b449811397f6f90284daf968ce7bdc65e661133fb4269b96db0
+oid sha256:be79b273f32f2f2c235edffc5a2ca653bb06bfd71e351df6a998001c5aa62301
 size 538090408

runs/Dec05_12-24-52_3830c6d8182c/events.out.tfevents.1733401498.3830c6d8182c.652.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c601f3cebf6f3c5298406f908931d09a4f4bc4ba3a60187cd2ab0572a78b9500
+size 5569

runs/Dec05_12-36-01_3830c6d8182c/events.out.tfevents.1733402170.3830c6d8182c.3269.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:961ed16cc6ec0b3047a29d49d0115539def84b273c30a9dab229ab8a8146a0e0
+size 17186

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cdcb7f63f93bea6dcab848a1a1bf81d9ed4443960fc2571f9583651c8b185f9
+oid sha256:d5db95f7edbbd660dabdfadd417347343295bc1a10d9840b82bbfbe585151fa0
 size 5560