End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0165
+- Loss: 2.0132
 
 ## Model description
 

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
-    "v"
+    "v",
+    "q"
   ],
   "task_type": "SEQ_2_SEQ_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6e68767a6f43fb3405b1ebdb1ea8d02ace5ca3694c16e9c1b017c8c4206e336
+oid sha256:7abf776b267b0c58899d9a969c540c4e504a596cbc7deb1dd8b8a2b2ecc08e94
 size 2765880

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 0.02,
-    "eval_loss": 2.0164880752563477,
-    "eval_runtime": 13.431,
-    "eval_samples_per_second": 584.99,
-    "eval_steps_per_second": 36.632,
-    "train_loss": 2.7404227256774902,
-    "train_runtime": 0.7364,
-    "train_samples_per_second": 0.136,
-    "train_steps_per_second": 1.358
+    "eval_loss": 2.013211250305176,
+    "eval_runtime": 30.1204,
+    "eval_samples_per_second": 260.853,
+    "eval_steps_per_second": 16.334,
+    "train_loss": 2.6519699096679688,
+    "train_runtime": 0.8829,
+    "train_samples_per_second": 0.114,
+    "train_steps_per_second": 1.133
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.02,
-    "eval_loss": 2.0164880752563477,
-    "eval_runtime": 13.431,
-    "eval_samples_per_second": 584.99,
-    "eval_steps_per_second": 36.632
+    "eval_loss": 2.013211250305176,
+    "eval_runtime": 30.1204,
+    "eval_samples_per_second": 260.853,
+    "eval_steps_per_second": 16.334
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.02,
-    "train_loss": 2.7404227256774902,
-    "train_runtime": 0.7364,
-    "train_samples_per_second": 0.136,
-    "train_steps_per_second": 1.358
+    "train_loss": 2.6519699096679688,
+    "train_runtime": 0.8829,
+    "train_samples_per_second": 0.114,
+    "train_steps_per_second": 1.133
 }

trainer_state.json

@@ -12,10 +12,10 @@
       "epoch": 0.02,
       "step": 1,
       "total_flos": 517012193280.0,
-      "train_loss": 2.7404227256774902,
-      "train_runtime": 0.7364,
-      "train_samples_per_second": 0.136,
-      "train_steps_per_second": 1.358
+      "train_loss": 2.6519699096679688,
+      "train_runtime": 0.8829,
+      "train_samples_per_second": 0.114,
+      "train_steps_per_second": 1.133
     }
   ],
   "logging_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6ed97205b4dbbede8dac24843fbdb4afca06c505286112ab8eede4793e06de
+oid sha256:978b974810dba6e34d7bdba8c9b0d92c06267a7f9209d97354683ef27b6bb4f0
 size 5112