Training in progress, step 500

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "bias": "none",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc7b4007976a8c74a93a9bdc8d935d3d9a415e438b12592bd5fced8311fd821
+size 1383576

runs/Feb01_20-31-41_3dfee59a4f60/events.out.tfevents.1738441935.3dfee59a4f60.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfca1510fd11fa70aa26b9cdda43a8766d30a60254a7397027c0a2100b943df
+size 5635

runs/Feb01_20-31-41_3dfee59a4f60/events.out.tfevents.1738442464.3dfee59a4f60.31.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89810ccc5ab4fc8e447e56e10662a2ecfe0df88d888ea0741f2f62f61dcb19f6
+size 29154

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2b88b0e2a91db097658058e760c34fd25298a93bb784142eb6b5f473b059f7
+size 5304