phi-3-ele

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "embed_tokens",
     "down_proj",
     "gate_up_proj",
     "o_proj",
-    "qkv_proj",
-    "embed_tokens"
+    "qkv_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a746574534c3473a3ae7ebbceba05bb493d1b83319d1c42d6cfed2c245eea18
+oid sha256:e15654e261b2c2bb681cb59d639ca38987bf78b337083ddd18a1623d40f27c50
 size 496949808

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 100,
-    "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 sha256:36ac85f5df4f685308acd5a89427c01048abecd0c43eddb218745723a855ba88
+oid sha256:8ed40a522c2dd8cd8e86b600861b11e1f0e97a63bd99327b5f65c54b0e7d8044
 size 5368