End of training

README.md

@@ -29,18 +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/25b3nk-eagle-eye-networks/huggingface/runs/b75ck0tz) 
+[<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/25b3nk-eagle-eye-networks/huggingface/runs/t1moa5z7) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.15.2
-- Transformers: 4.48.3
-- Pytorch: 2.5.1+cu124
-- Datasets: 3.3.2
-- Tokenizers: 0.21.0
+- TRL: 0.19.1
+- Transformers: 4.53.3
+- Pytorch: 2.6.0+cu124
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
 
 ## Citations
 
@@ -51,7 +51,7 @@ Cite TRL as:
 ```bibtex
 @misc{vonwerra2022trl,
 	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
 	year         = 2020,
 	journal      = {GitHub repository},
 	publisher    = {GitHub},

chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -27,7 +26,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.53.3",
   "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": "4.48.3"
+  "transformers_version": "4.53.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:933a6c4a30c3f03ac8e9d1e398e01313cde51cc6ab5e82b6b940d562d0a1b7c0
+oid sha256:364c6ac4e942db610f94519fb4bffbde7c832226eca31e9d3968f3a911504afc
 size 538090408

runs/Jul28_11-45-57_1b06f6560f86/events.out.tfevents.1753703201.1b06f6560f86.507.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d973a3eb75065376d52f76aa628f1dbfddadbb8e7966bcd6be15dda545b3ca9f
+size 46615

tokenizer_config.json

@@ -143,7 +143,6 @@
     "<|im_end|>"
   ],
   "bos_token": "<|im_start|>",
-  "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": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac95dbe45e27b5b81d5400cf786b1e95cf88ff3541d557189477e1c61a4a55be
-size 5560
+oid sha256:1440ef4dfe0a4313750b44bd6a0f1a9408b7189e3dfe6077f5560f06582e4f69
+size 5752