Upload folder using huggingface_hub

coding-0.2/q/latest/README.md

@@ -31,7 +31,7 @@ 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/kstaron-/huggingface/runs/8rxpc2rv) 
+[<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/kstaron-/huggingface/runs/0t2a41t5) 
 
 
 This model was trained with SFT.

coding-0.2/q/latest/adapter_config.json

@@ -20,7 +20,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
     "q_proj",
-    "down_proj",
-    "gate_proj",
     "v_proj",
-    "o_proj"
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

coding-0.2/q/latest/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6bbb916dc12a2fca99fee550382057f9199d8894073c49e3d57821194b22e4f
+oid sha256:121954251f213ee58d7c89ce3881ff28da0b7fc8c7a3c91b614a0e07361d2b00
 size 645975704

coding-0.2/q/latest/base_adapter/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
+  "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": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

coding-0.2/q/latest/base_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae9dcce72b493a3d3c471d5fa8f933a33eb74a58dbf7aff65bdb623a2706468
+size 645975704

coding-0.2/q/latest/checkpoint-1/adapter_config.json

@@ -20,7 +20,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
     "q_proj",
-    "down_proj",
-    "gate_proj",
     "v_proj",
-    "o_proj"
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

coding-0.2/q/latest/checkpoint-1/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6bbb916dc12a2fca99fee550382057f9199d8894073c49e3d57821194b22e4f
+oid sha256:121954251f213ee58d7c89ce3881ff28da0b7fc8c7a3c91b614a0e07361d2b00
 size 645975704

coding-0.2/q/latest/checkpoint-1/base_adapter/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
+  "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": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

coding-0.2/q/latest/checkpoint-1/base_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae9dcce72b493a3d3c471d5fa8f933a33eb74a58dbf7aff65bdb623a2706468
+size 645975704

coding-0.2/q/latest/checkpoint-1/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c82eb3590ed9fcceb5d6294bdce16feff6612301207b8d6d2c50b29ed5275d52
+oid sha256:9d44113f9e85a36b16d1d84fa20b1ae07f1f8e3e540d40c71897d0399407dfa3
 size 328468869

coding-0.2/q/latest/checkpoint-1/trainer_state.json

@@ -26,7 +26,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2221701070848000.0,
+  "total_flos": 36553862209536.0,
   "train_batch_size": 90,
   "trial_name": null,
   "trial_params": null

coding-0.2/q/latest/checkpoint-1/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe48554188b058f1d7a48c8dcc13f932912a9314fdd8092cf4127cbf0a284433
+oid sha256:910cad4b749ef8c4803d0a741d767850043ac438f5ae0d643857592dff05dd07
 size 6225