End of training

README.md

@@ -44,8 +44,8 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
-- training_steps: 60
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
 
 ### Training results
 

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "up_proj",
+    "k_proj",
     "v_proj",
-    "q_proj",
     "down_proj",
     "gate_proj",
-    "k_proj",
+    "q_proj",
+    "up_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36539b943f7bc9dfcf3f579444a72b6bd0c7e724afc59ed6e1537fd45878f40
+oid sha256:880164f25a53cecbb5942a45b963d8723174505cc3db0d8132f23a4f233fbdfc
 size 161533192

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Left",
-    "pad_to_multiple_of": null,
-    "pad_id": 151646,
-    "pad_type_id": 0,
-    "pad_token": "<|PAD_TOKEN|>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 151643,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311ba225e042fa59e6938352847121dd14efc63af608ff7525da7ea11a670783
+oid sha256:086422d791c615e387c20b19208d2788ee0e4bdf6b0efb8e5c6e950c2f3058c2
 size 5048