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/bizisaida04-fisher-college/huggingface/runs/vk1row6j) 
+[<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/bizisaida04-fisher-college/huggingface/runs/smkafpu0) 
 
 
 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: 0.17.0
+- Transformers: 4.51.3
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.5.1
+- Tokenizers: 0.21.1
 
 ## 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},

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": "4.51.3",
   "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": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40220acb710b334bb2bade89e9fe6bdcbd7a1e99fad1e5a7637e6487b4f0263
+oid sha256:17f2f5309442bd65386c8c1549b58fd9193fd2102a777b72eb9ad972d9694e81
 size 538090408

runs/Apr29_22-20-05_0e5f27e20233/events.out.tfevents.1745965211.0e5f27e20233.608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78424f3684447705bab8bb5b5a8aa97697fac8862ea12df4d04284250c0bf80d
+size 22336

special_tokens_map.json

@@ -1,23 +1,37 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
   ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|im_end|>",
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -139,16 +139,29 @@
     }
   },
   "additional_special_tokens": [
+    "<|endoftext|>",
     "<|im_start|>",
-    "<|im_end|>"
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
   ],
-  "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 %}",
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "model_max_length": 8192,
-  "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f68d1d4171cae1c51c5b07d7a43f60f1e391e85afde25806ae18fc3159392cf
-size 5560
+oid sha256:7987155c04ccd877ada591a422e9c3d8157bb85963cd1eb7da8e47d3a075cd50
+size 5688