Training in progress, step 381

README.md

@@ -1,18 +1,17 @@
 ---
-base_model: Ba2han/exp4
 library_name: transformers
 model_name: experimental4
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 - unsloth
 licence: license
 ---
 
 # Model Card for experimental4
 
-This model is a fine-tuned version of [Ba2han/exp4](https://huggingface.co/Ba2han/exp4).
+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/eelm7qij) 
+[<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/dsj9s07q) 
 
 
 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+cu126
-- Datasets: 4.3.0
+- Pytorch: 2.11.0
+- Datasets: 4.8.0
 - Tokenizers: 0.22.2
 
 ## Citations

config.json

@@ -5,7 +5,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 2,
-  "dtype": "float32",
+  "dtype": "bfloat16",
   "eos_token_id": 3,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -58,7 +58,7 @@
   ],
   "max_position_embeddings": 8192,
   "max_window_layers": 42,
-  "model_name": "Ba2han/exp4",
+  "model_name": "./checkpoint-19950",
   "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": "2026.8.19",
+  "unsloth_version": "2026.8.18",
   "use_cache": false,
   "use_sliding_window": false,
-  "vocab_size": 60802
+  "vocab_size": 60800
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861bd3b8c152597e6f530ca164c72d571d4461f3c424669df1cf60b76910f7bf
-size 4379733312
+oid sha256:37d6e95c98936fab8c8afd2e2683627d3bec1d3e74e4c9c493103eb30fbb86bd
+size 2190141824

tokenizer.json

@@ -2342,24 +2342,6 @@
       "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

@@ -3,11 +3,7 @@
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
-  "extra_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "is_local": false,
+  "is_local": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "padding_side": "right",
@@ -2093,22 +2089,6 @@
       "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 sha256:4684db991fbf0ea6569081eae9692ae8ad7aae52d976969bfe2b63252ba5f95c
-size 5777
+oid sha256:13fa61fe403b6422841e37249e904cec613858fa5db70069bf460fac44c0db28
+size 5713