Training in progress, epoch 3

adapter_config.json

@@ -1,9 +1,12 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
+  "arrow_config": null,
   "auto_mapping": null,
   "base_model_name_or_path": "voidful/llm-codec",
   "bias": "none",
   "corda_config": null,
+  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -20,20 +23,24 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
     "o_proj",
+    "k_proj",
+    "down_proj",
     "v_proj",
-    "down_proj"
+    "up_proj",
+    "gate_proj"
   ],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "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 sha256:2ec670faef160266af110492dd83512f76fd0c9d4d739ebbee32a75847acc420
+oid sha256:6a16703691beb3920653d04fcd565151a9415fcd15b74c1c014b7c25cbad0bbf
 size 528550256

tokenizer_config.json

@@ -164071,13 +164071,9 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "max_length": 4096,
   "model_max_length": 1010000,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ef793003aa3f31e0fa9d57c9998371626de0241ae516edb6c9795266860010
+oid sha256:086a4fbc7538a577fb092ba511f7e1a4d6b3867e138da19ed05f63656337f331
 size 5841