Training in progress, step 1000

README.md

@@ -1,18 +1,17 @@
 ---
-base_model: unsloth/Qwen2-1.5B-Instruct
+base_model: unsloth/SmolLM2-135M
 library_name: transformers
 model_name: ebd3853f-27cd-4553-82ef-b572dab7b9c1
 tags:
 - generated_from_trainer
 - dpo
 - trl
-- unsloth
 licence: license
 ---
 
 # Model Card for ebd3853f-27cd-4553-82ef-b572dab7b9c1
 
-This model is a fine-tuned version of [unsloth/Qwen2-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct).
+This model is a fine-tuned version of [unsloth/SmolLM2-135M](https://huggingface.co/unsloth/SmolLM2-135M).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +27,7 @@ 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/buikhacminh1804/sn56-dpo-train/runs/oovhw4uw) 
+[<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/buikhacminh1804/sn56-sft-before-dpo-train/runs/tyf3o6gd) 
 
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
@@ -36,8 +35,8 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.0
-- Pytorch: 2.7.0
+- Transformers: 4.55.2
+- Pytorch: 2.8.0
 - Datasets: 3.6.0
 - Tokenizers: 0.21.4
 

added_tokens.json

@@ -1,5 +1,3 @@
 {
-  "<|endoftext|>": 151643,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644
+  "<|PAD_TOKEN|>": 49152
 }

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 49152,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 49153
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cfa75e60f7b29cf99a9016382a75ec744d038c7b2ca07e627e04a3ea6498199
+size 269061704

special_tokens_map.json

@@ -1,20 +1,43 @@
 {
   "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|PAD_TOKEN|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  }
+  },
+  "unk_token": "�"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
-size 11418266
+oid sha256:a110eb4e3c8d6a542225a738a2acf1f67b348131d3dd49c926f13223462fff13
+size 3523027

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "151643": {
+    "0": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
@@ -9,7 +9,7 @@
       "single_word": false,
       "special": true
     },
-    "151644": {
+    "1": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -17,28 +17,170 @@
       "single_word": false,
       "special": true
     },
-    "151645": {
+    "2": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24211": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "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": null,
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
+  "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
-  "pad_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "pad_token": "<|PAD_TOKEN|>",
   "padding_side": "left",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�",
+  "vocab_size": 49152
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3744309d5bd91cbc003e477210afa9af9f0354355d4a241bce89dc6653e3143
+oid sha256:16a9de1ce5b6087ef3ef71d0a4cf4c75f3c4832a07e2ccce4492f15c69dd7aec
 size 6993