Training in progress, step 10

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "google/mt5-small",
+  "base_model_name_or_path": "google/mt5-base",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -16,23 +16,27 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head"
+  ],
   "peft_type": "LORA",
   "peft_version": "0.18.0",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q",
-    "o",
+    "v",
     "k",
-    "v"
+    "wi_1",
+    "wi_0",
+    "wo"
   ],
   "target_parameters": null,
   "task_type": "SEQ_2_SEQ_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773536de88447595b67a1d37ffb7c112d6c9a139a54bf929540bde4d49c877f8
-size 5531800
+oid sha256:008544ce963eb3d5056775af96004ba688d133021d742a107ceafe07070e4ccf
+size 815581456

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a522bc2d1d1079fb198e48926a65db109911f8c0fe54c0a30d01e91079a1687d
-size 6097
+oid sha256:aa3522c0523845f65b29d7fd5f1f6653fe6516b7bdbd22510a99199b6e2e1ef6
+size 5688