End of training

README.md

@@ -29,18 +29,17 @@ print(output["generated_text"])
 
 ## Training procedure
 
- 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.17.0
-- Transformers: 4.52.3
+- TRL: 0.12.1
+- Transformers: 4.46.3
 - Pytorch: 2.7.0+cu118
-- Datasets: 3.6.0
-- Tokenizers: 0.21.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
 
 ## Citations
 
@@ -51,7 +50,7 @@ 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 Gallou{\'e}dec},
+	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 GallouГ©dec},
 	year         = 2020,
 	journal      = {GitHub repository},
 	publisher    = {GitHub},

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -26,13 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers.js_config": {
-    "kv_cache_dtype": {
-      "fp16": "float16",
-      "q4f16": "float16"
-    }
-  },
-  "transformers_version": "4.52.3",
-  "use_cache": false,
+  "transformers_version": "4.46.3",
+  "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": "4.52.3"
+  "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e7d1c158e67b47577eb6e596243054b00f6eb68b0c682d917f232d154627fd
+oid sha256:da3ea6803aa189a04d07724744f709b49e8e0213bd9b0ede6ddf262b05d3c104
 size 538090408

special_tokens_map.json

@@ -1,29 +1,23 @@
 {
   "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
   ],
-  "bos_token": {
-    "content": "<|im_start|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

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

tokenizer_config.json

@@ -143,9 +143,9 @@
     "<|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": {},
   "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:e00e05ded2a7c9505b582c00e03132bbed53490a95eca042a63d9f3a6917544c
-size 6033
+oid sha256:8d1d0ada5422b14973d94b7e8ed9c0d57c236e0f3e1fa230383ad54153118214
+size 5969