amdbook/sanremo-winners-phi-3-mini-4k

README.md

@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "up_proj",
-    "gate_proj",
-    "k_proj",
-    "v_proj",
     "q_proj",
     "down_proj",
-    "o_proj"
+    "gate_proj",
+    "k_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 sha256:68b4f1bb136e042721a59a5f74a4e61d0a736b1a915d3884c811d1d30d7d0b5a
+oid sha256:298f6f064d29a62d5bdbeb2719ffad322609433466836fd4209cfaf3a63c37ee
 size 35668592

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 256,
+    "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:a1f892f6e608de1f7c2e27cf5edf04c8a84a8f480edaab923072ecc751e5f5b3
+oid sha256:491c785eb77de5386311c15bb9326f4c65422ee0828780379683585fd67f145c
 size 5432