Training in progress, step 291

README.md

@@ -1,18 +1,18 @@
 ---
-base_model: qwen
+base_model: Ba2han/qwen-augment-2511
 library_name: transformers
 model_name: m_augment
 tags:
 - generated_from_trainer
 - trl
-- unsloth
 - sft
+- unsloth
 licence: license
 ---
 
 # Model Card for m_augment
 
-This model is a fine-tuned version of [qwen](https://huggingface.co/qwen).
+This model is a fine-tuned version of [Ba2han/qwen-augment-2511](https://huggingface.co/Ba2han/qwen-augment-2511).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,16 +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/stynr6zo) 
+[<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/s1imxy2a) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.23.1
-- Transformers: 5.0.0rc2
-- Pytorch: 2.9.0+cu128
+- TRL: 0.24.0
+- Transformers: 5.0.0
+- Pytorch: 2.10.0
 - Datasets: 4.3.0
 - Tokenizers: 0.22.2
 

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Ba2han/qwen-augment-2511",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a82542a3e6c5ad0ca85df359d7d9aff75e81685dbd375c3f64d3c0945757c3f
+size 533009160

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
-size 11422650
+oid sha256:476870a1f2fb6f6a2759a6ede2383bf9d5d738f17844563b65c91965b722ae09
+size 11422924

tokenizer_config.json

@@ -20,7 +20,7 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "is_local": true,
+  "is_local": false,
   "model_max_length": 32768,
   "model_specific_special_tokens": {},
   "pad_token": "<|vision_pad|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79d9e3b60f9ae736e60257b55244a1f4a487531095b2990f156ad6ec799a46d
+oid sha256:943c26076dfdedd9e28c802520a1c026bc1af685198b510701a3ead07fd3b809
 size 5713