Training in progress, step 372

adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Salesforce/codegen-350M-mono",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "h.14.attn.qkv_proj",
+    "h.4.attn.qkv_proj",
+    "h.1.attn.qkv_proj",
+    "h.9.attn.qkv_proj",
+    "h.2.attn.qkv_proj",
+    "h.12.attn.qkv_proj",
+    "h.3.attn.qkv_proj",
+    "h.18.attn.qkv_proj",
+    "h.8.attn.qkv_proj",
+    "h.7.attn.qkv_proj",
+    "h.17.attn.qkv_proj",
+    "h.15.attn.qkv_proj",
+    "h.6.attn.qkv_proj",
+    "h.11.attn.qkv_proj",
+    "h.13.attn.qkv_proj",
+    "h.5.attn.qkv_proj",
+    "h.16.attn.qkv_proj",
+    "h.10.attn.qkv_proj",
+    "h.0.attn.qkv_proj",
+    "h.19.attn.qkv_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:ece989c240a0eb3f6695828c7049be303361a4e08d4b19b96bc31d7227b66556
+size 2626624

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33a2a5eb2b2a7a46af549cfb06d72bafc428bc13512f4b58b9824de3f3249a1
+size 5176