Training in progress, step 44

README.md

@@ -1,18 +1,17 @@
 ---
 base_model: Qwen/Qwen2-0.5B
-datasets: trl-lib/Capybara
 library_name: transformers
 model_name: Qwen2-0.5B-SFT
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for Qwen2-0.5B-SFT
 
-This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the [trl-lib/Capybara](https://huggingface.co/datasets/trl-lib/Capybara) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,18 +27,18 @@ 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/artiease-muse/huggingface/runs/bljh5gnm) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.15.0
-- Transformers: 4.48.3
-- Pytorch: 2.1.2
-- Datasets: 3.2.0
-- Tokenizers: 0.21.0
+- TRL: 0.19.0
+- Transformers: 4.52.4
+- Pytorch: 2.7.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
 
 ## Citations
 
@@ -50,7 +49,7 @@ 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},

adapter_config.json

@@ -3,6 +3,7 @@
   "auto_mapping": null,
   "base_model_name_or_path": "Qwen/Qwen2-0.5B",
   "bias": "none",
+  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -23,10 +24,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8239c34d1a130318b3079e348acdfd4b8b5f71b7e208d0b4d947a3dbe8d3ac84
-size 4338000
+oid sha256:3894f3fb3a5a22b727ad7f06c1cc34663fcf802d3db8fd18c5b3a8b94f812be7
+size 2175360

added_tokens.json

@@ -1,6 +1,4 @@
 {
-  "<knowledge>": 151646,
-  "<reasoning>": 151647,
   "<|endoftext|>": 151643,
   "<|im_end|>": 151645,
   "<|im_start|>": 151644

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

special_tokens_map.json

@@ -3,13 +3,7 @@
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|im_end|>",
   "pad_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a76737039b6443215ac4073ae60e2fe5381aa22b8720df677dbcc28a13c04d8
-size 11418642
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -24,22 +24,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "151646": {
-      "content": "<knowledge>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151647": {
-      "content": "<reasoning>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "additional_special_tokens": [
@@ -47,9 +31,8 @@
     "<|im_end|>"
   ],
   "bos_token": null,
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|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": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 32768,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894c3c6adae976a4e59a9eb37d5a3fd76181a0baffa8a6c44d8848705d0a886a
-size 5688
+oid sha256:e109e40ff8cd5cf91dd4b8344ee6c396d552c992bb21c510684764f5762838fe
+size 7377