Training in progress, step 100

adapter_config.json

@@ -1,15 +1,11 @@
 {
-  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "arrow_config": null,
   "auto_mapping": {
     "base_model_class": "DeepseekOCR2ForCausalLM",
     "parent_library": "transformers_modules.deepseek_ocr2.modeling_deepseekocr2"
   },
   "base_model_name_or_path": "./deepseek_ocr2",
   "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -26,24 +22,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "k_proj",
     "q_proj",
     "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
     "down_proj",
     "v_proj"
   ],
-  "target_parameters": null,
   "task_type": null,
-  "trainable_token_indices": null,
   "use_dora": false,
-  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6141e6930b2ba02d50f56b0f6d730ae4918727e4b5a72a2c192afa1aea9cfc
+oid sha256:740435fbbd2880d9895019e7bc9bdb6f17926ea5ecd566e1dd443c1dbc02d5eb
 size 345908528

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9416e396877b0850e8ad6518e61c5d16443a6734365d95b14708f0237a8ff188
+oid sha256:103ad17e257df3fbfb9f1d8f7c2491e0328e0b3d2ad7c52dba2ad40e1f41572e
 size 5304