End of training

README.md

@@ -29,17 +29,18 @@ print(output["generated_text"])
 
 ## Training procedure
 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.1
-- Transformers: 4.46.3
-- Pytorch: 2.5.1+rocm6.2
-- Datasets: 3.1.0
-- Tokenizers: 0.20.3
+- TRL: 0.14.0
+- Transformers: 4.47.1
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.2.0
+- 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": "4.47.1",
   "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": "4.47.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192dbbeaa658a4d577b220cc4180d0b24623d58a071b6e7c8574362a5d68d013
+oid sha256:88a477395ddd5b14fd8ce2f1ee4ddbe59327a13f77ddb4809d98aced18f6aad3
 size 538090408

runs/Feb03_16-51-59_aa386aba1a26/events.out.tfevents.1738601524.aa386aba1a26.3263.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d770b1fe514f07cdb462c486ffb10138fe27be93d3b708ba42dd5ab9151e778
+size 11261

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 sha256:2c43a02c56178f80894791429dae3f88e5882c152a20d4bada3a04c18a27ac9a
+oid sha256:7f9d40ed8846c1aeaa845283e8f2253bb3cf696196fb0b641866380583faafea
 size 5560