Training in progress, step 822

README.md

@@ -1,18 +1,17 @@
 ---
-base_model: Ba2han/experimental4
 library_name: transformers
 model_name: experimental5
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 - unsloth
 licence: license
 ---
 
 # Model Card for experimental5
 
-This model is a fine-tuned version of [Ba2han/experimental4](https://huggingface.co/Ba2han/experimental4).
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 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/batuhan409/huggingface/runs/v26xjatv) 
+[<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/batuhan409/huggingface/runs/zkzppxxs) 
 
 
 This model was trained with SFT.
@@ -37,8 +36,8 @@ This model was trained with SFT.
 
 - TRL: 0.24.0
 - Transformers: 5.5.0
-- Pytorch: 2.11.0
-- Datasets: 4.8.0
+- Pytorch: 2.12.1
+- Datasets: 4.3.0
 - Tokenizers: 0.22.2
 
 ## Citations

chat_template.jinja

@@ -1,3 +1 @@
-{{ bos_token }}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '
-' + message['content'] + '<|im_end|>
-' }}{% endfor %}
+{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}

config.json

@@ -6,7 +6,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 2,
   "dtype": "bfloat16",
-  "eos_token_id": 3,
+  "eos_token_id": 60801,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 1376,
@@ -58,7 +58,7 @@
   ],
   "max_position_embeddings": 8192,
   "max_window_layers": 42,
-  "model_name": "Ba2han/experimental4",
+  "model_name": "p04_linear_90",
   "model_type": "qwen3",
   "num_attention_heads": 16,
   "num_hidden_layers": 42,
@@ -72,8 +72,8 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "transformers_version": "5.5.0",
-  "unsloth_version": "2026.8.18",
+  "unsloth_version": "2026.9.4",
   "use_cache": false,
   "use_sliding_window": false,
-  "vocab_size": 60800
+  "vocab_size": 60802
 }

generation_config.json

@@ -2,9 +2,11 @@
   "_from_model_config": true,
   "bos_token_id": 2,
   "eos_token_id": [
+    60801,
     3
   ],
   "max_length": 8192,
   "pad_token_id": 0,
-  "transformers_version": "5.5.0"
+  "transformers_version": "5.5.0",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89728b0b49f183c91ef0a8def58deeaf7c2d2ac38cbca87b973505768425b4a6
-size 2190141824
+oid sha256:ce741aaf31d238117a7ff858c307c8539f07547978229686ae563f91482a6c87
+size 2190147328

tokenizer.json

@@ -2342,6 +2342,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 60800,
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 60801,
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -2,8 +2,13 @@
   "backend": "tokenizers",
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<eos>",
-  "is_local": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "padding_side": "right",
@@ -2089,6 +2094,22 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    "60800": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "60801": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518019af99dca2d5c7c43aae12847945e94657ae55ee28c02983b7e22cc12e41
+oid sha256:6b7cf699e406378ed0cc2c39a7da9a02952c8ce509894c515cdcea2b3de1e35a
 size 5713