End of training

README.md

@@ -36,10 +36,10 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.12.1
-- Transformers: 4.46.3
+- Transformers: 4.48.1
 - Pytorch: 2.5.1
 - Datasets: 3.1.0
-- Tokenizers: 0.20.3
+- Tokenizers: 0.21.0
 
 ## Citations
 

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.48.1",
   "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": "4.48.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de5ab8e0f709614d4637a730f54ef44c71d399e67c1adfd9a5147699d11c151
+oid sha256:01a5e83afe9216e394601c17eaa1cc803e78c1ba65e2fe80aa0d7e2bfed91ab9
 size 538090408

runs/Jan21_07-08-35_rft-0/events.out.tfevents.1737443316.rft-0.52468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea2f00005c2d7244b14bfb1fa49641df96d19951f9af1ee1b7cc507e7859d85
+size 8567

runs/Jan21_07-10-23_rft-0/events.out.tfevents.1737443423.rft-0.55658.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264a41925ba6686845470b15c0bb330b192e54025a3cd943c969319d311e1abf
+size 32367

tokenizer.json

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

tokenizer_config.json

@@ -146,6 +146,7 @@
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20ec2ee9a3fe7c8e26a618d23e9f873e7d9c9fd47954a66c15e143bfc81ae375
-size 5560
+oid sha256:e5cc7232eb61982f2e7634aae20d29ed56e684a0d1b1d5a10c28781cce1bd975
+size 5624