Training in progress, epoch 1

adapter_config.json

@@ -18,22 +18,15 @@
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "lm_head",
-    "embed_token"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "v_proj",
-    "gate_proj",
-    "up_proj"
+    "all-linear",
+    "embed_tokens",
+    "lm_head"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab2a1a9007e55511e64845888031b39f3eb4c032c348b869d5205b2f8d36d7b
-size 166182928
+oid sha256:12219f2f8147150dfc1d8e25b6f77b694021a35c6ec19a4c5200592e81ee483b
+size 2425469968

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f46a61bfe0182c14cd7d9df91ee608838b4e278fffcc8d77fb4b0038ac8b19
+oid sha256:5fbfb035ddd71a36181b176667fb3ac0191214b5db0ab0761b74ab43cc5814fc
 size 6904