Training in progress, step 50

README.md

@@ -1,18 +1,18 @@
 ---
-base_model: unsloth/Nemotron-3-Nano-30B-A3B
+base_model: owenisas/nemotron-3-nano-reasoning
 library_name: transformers
 model_name: temp
 tags:
 - generated_from_trainer
+- sft
 - unsloth
 - trl
-- sft
 licence: license
 ---
 
 # Model Card for temp
 
-This model is a fine-tuned version of [unsloth/Nemotron-3-Nano-30B-A3B](https://huggingface.co/unsloth/Nemotron-3-Nano-30B-A3B).
+This model is a fine-tuned version of [owenisas/nemotron-3-nano-reasoning](https://huggingface.co/owenisas/nemotron-3-nano-reasoning).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +28,7 @@ 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/reunifylabs-reunify-labs/huggingface/runs/mxxmtahg) 
+[<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/reunifylabs-reunify-labs/huggingface/runs/q6wkq2x5) 
 
 
 This model was trained with SFT.
@@ -37,7 +37,7 @@ This model was trained with SFT.
 
 - TRL: 0.22.2
 - Transformers: 4.56.2
-- Pytorch: 2.9.0+cu128
+- Pytorch: 2.8.0+cu128
 - Datasets: 4.3.0
 - Tokenizers: 0.22.2
 

adapter_config.json

@@ -4,10 +4,10 @@
   "arrow_config": null,
   "auto_mapping": {
     "base_model_class": "NemotronHForCausalLM",
-    "parent_library": "transformers_modules.unsloth.Nemotron-3-Nano-30B-A3B.b93ba8494bf95b9e5dd7aed6b5d07517db195743.modeling_nemotron_h",
+    "parent_library": "transformers_modules.owenisas.nemotron-3-nano-reasoning.c06798b01704b3d322954056e8de8bf6cae11e38.modeling_nemotron_h",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/Nemotron-3-Nano-30B-A3B",
+  "base_model_name_or_path": "owenisas/nemotron-3-nano-reasoning",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -27,21 +27,21 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.0",
+  "peft_version": "0.18.1",
   "qalora_group_size": 16,
   "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "in_proj",
+    "q_proj",
     "k_proj",
-    "down_proj",
-    "gate_proj",
     "out_proj",
-    "o_proj",
-    "q_proj",
     "up_proj",
-    "in_proj",
-    "v_proj"
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c2a5ff429f650539cd5c6ad9ea7f9569fd24863056cad28726290ed985d9fea
+oid sha256:1c302dc1f7d4b868ed2fec7fb599c56ab89a9be3b061d10a09c33f91bc884118
 size 3537299144

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908a527816bc09fbe07f310e4f80e352792f6417bc1abafa58d2254bddc3d1db
-size 6225
+oid sha256:702294f2ba6032bb021dc32bbc9dbd5ee8f2ef55f4eb6c78b41cc0994567f4e2
+size 6289