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: 2
+- num_epochs: 3
 
 ### Training results
 

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "embed_tokens",
+    "o_proj",
     "down_proj",
     "gate_up_proj",
-    "o_proj",
+    "embed_tokens",
     "qkv_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15654e261b2c2bb681cb59d639ca38987bf78b337083ddd18a1623d40f27c50
+oid sha256:005ddc8a510ec0191faa1cd3876b22d6f921c0ecd1a7086cdae20fbd4779050c
 size 496949808

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 sha256:8ed40a522c2dd8cd8e86b600861b11e1f0e97a63bd99327b5f65c54b0e7d8044
+oid sha256:1080a01b32f3081a6496eb343a90ca037ebaeedb38fa916277a702a4fdf21d9e
 size 5368