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

README.md

@@ -36,15 +36,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.03
-- train_batch_size: 4
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 50
 
 ### Training results
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
     "q_proj",
-    "down_proj",
-    "gate_proj",
     "k_proj",
-    "v_proj"
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298f6f064d29a62d5bdbeb2719ffad322609433466836fd4209cfaf3a63c37ee
+oid sha256:3e0d901582e29e51ac3fe42cd632ac54c292dc375a324909e0b473bbf6f8e8c0
 size 35668592

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 256,
-    "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 sha256:491c785eb77de5386311c15bb9326f4c65422ee0828780379683585fd67f145c
+oid sha256:ba587460b1e9bb0ebe705634e0e0c9d842008091f4354ff63c62bcd5e8bfe684
 size 5432