End of training

README.md

@@ -35,9 +35,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 10
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10

adapter_config.json

@@ -23,9 +23,9 @@
     "k_proj",
     "q_proj",
     "gate_proj",
-    "o_proj",
+    "up_proj",
     "v_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 sha256:2e3485c943cee14098d5bd1592126a1216c3c18370375e41316c6e3678dff401
+oid sha256:c48873b8fa6cdc3a391309a09ad4b4e66895d6e1a9ba3f0dc9520cd19a28108d
 size 159967880

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253517883442119825155070a778bbb2efd74f2f8dc84e45dc905af5e8778b8f
+oid sha256:68547dc7e1f8914185132eff899291ac4da98be6632c706b011a5608ae8f4409
 size 5048