Training in progress, step 50

adapter_config.json

@@ -20,7 +20,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
@@ -29,7 +29,7 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj)))",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc5e6f877044a9a2247b534a4906475793707ed0d18c6f0670c3881604b4e429
-size 69838856
+oid sha256:9591371aa3f6764f33f83577b43bbc786105b7d0ac819218d0e842725f07ff15
+size 139602808

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e56766bc58067b50d0b42b6d9abfb149a6862e706abb3c0a345b273d421eac3
+size 5201