End of training

README.md

@@ -29,17 +29,18 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ssg-plabon-fidelity-investments/huggingface/runs/jfvq780l)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ssg-plabon-fidelity-investments/huggingface/runs/p3jzjwwe) 
+
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.2
-- Transformers: 4.46.3
+- TRL: 0.13.0
+- Transformers: 4.47.0
 - Pytorch: 2.5.1+cu121
 - Datasets: 3.2.0
-- 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": "4.47.0",
   "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": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86545a8e845d5a5ed160a76320ace59b0e2ad5d78b809c4ad88ffa5e76ac2971
+oid sha256:ba241aa7802dad18ba306ded9a8798aab4c7bf7e8853c0d9f85e37dd5708aa1f
 size 538090408

runs/Dec17_04-50-23_8763990c91f5/events.out.tfevents.1734411025.8763990c91f5.642.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7aaf313b1a7fe8f615e461993416e90d3ced66e8bf6f228c82d5bf595db06b
+size 32385

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 sha256:9a1d7a48a0d5eedddee16e7082777918cd9911a479a2d8916888fd0f9e63c05c
-size 5560
+oid sha256:1f9c41d480b033627e7a4a7fd5503bede2163f6e808a24f481aefc9e70716164
+size 5624