Model save

README.md

@@ -37,11 +37,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "k_proj",
-    "v_proj",
     "gate_proj",
+    "o_proj",
     "q_proj",
-    "down_proj",
     "up_proj",
-    "o_proj"
+    "k_proj",
+    "down_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047fe78e1e3f21ab4e0595a19bc7e25780602d8305792ba322d7df902abce0a5
+oid sha256:6c79555c8a3b67d1862f0e73ed6694a2c2e4386acbfbd4cadfb75030326018d1
 size 159967880

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df80b8e13ea13cda04c01234baa8cd80e5966c0a0bd1ded5e38597b8b967ff3
+oid sha256:181f599c7d65f4b016c3acc152cd6651bede12224c25f07ff5d5e095e2a827fd
 size 5176