chaski-7B

README.md

@@ -36,12 +36,10 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
-    "v_proj",
     "o_proj",
-    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
     "down_proj",
-    "gate_proj"
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

runs/Mar20_12-06-25_lab/events.out.tfevents.1710936385.lab.30819.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3c5bc6590490f6da5c9abdef8db0b0cd1af88127ad8755212d7dd98aa45984
+size 5234

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": {
     "strategy": "BatchLongest",
     "direction": "Right",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a97ba7e1072f706bf6b294dafa5f60def641f1e0976127d07b5c0d8e6b850199
+oid sha256:990aae14fbee58b82bc9875a5070f80d8226c4bdaed43fd024ecca7d1820e735
 size 4664