Training in progress, step 2511

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: qwen
 library_name: transformers
 model_name: m_augment
 tags:
@@ -11,7 +12,7 @@ licence: license
 
 # Model Card for m_augment
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [qwen](https://huggingface.co/qwen).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -27,16 +28,16 @@ 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/z2vn1gzd) 
+[<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/071qygqt) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.24.0
-- Transformers: 5.0.0rc0
-- Pytorch: 2.10.0
+- TRL: 0.23.1
+- Transformers: 5.0.0rc3
+- Pytorch: 2.9.0+cu128
 - Datasets: 4.3.0
 - Tokenizers: 0.22.2
 

config.json

@@ -63,7 +63,7 @@
   },
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "5.0.0rc0",
+  "transformers_version": "5.0.0rc3",
   "unsloth_fixed": true,
   "unsloth_version": "2026.1.4",
   "use_cache": false,

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 32768,
   "max_new_tokens": 2048,
   "pad_token_id": 151654,
-  "transformers_version": "5.0.0rc0"
+  "transformers_version": "5.0.0rc3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ccc6d630ae94b4b0fda1ce65496b67e2ba63fed1ae6e445c51e0bc0949814b0
-size 8503547592
+oid sha256:0e2f6602b647b6ae3c25f1ebda28e9aa5daf2d58d7880d0be2b7ae1ba68e83b3
+size 8044982080

tokenizer_config.json

@@ -1,6 +1,5 @@
 {
   "add_prefix_space": false,
-  "additional_special_tokens": null,
   "backend": "tokenizers",
   "bos_token": null,
   "clean_up_tokenization_spaces": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a337fecbc72e6682bf3825f64d837b02914079469b6ef65ca41926f41735f3
+oid sha256:ba50acf1c289ca1b1bbc51d05917542bda392b68bdd6b780ff099a38b6470364
 size 5713