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: 2.0212
+- Loss: 2.0165
 
 ## Model description
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16efe7c59c1f33264f91c3830bfee57bf553e59565235c0f9983250a18a044cc
+oid sha256:b6e68767a6f43fb3405b1ebdb1ea8d02ace5ca3694c16e9c1b017c8c4206e336
 size 2765880

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 0.02,
-    "eval_loss": 2.021235942840576,
-    "eval_runtime": 13.6322,
-    "eval_samples_per_second": 576.357,
-    "eval_steps_per_second": 36.091,
-    "train_loss": 2.7679789066314697,
-    "train_runtime": 0.7741,
-    "train_samples_per_second": 0.129,
-    "train_steps_per_second": 1.292
+    "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_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.02,
-    "eval_loss": 2.021235942840576,
-    "eval_runtime": 13.6322,
-    "eval_samples_per_second": 576.357,
-    "eval_steps_per_second": 36.091
+    "eval_loss": 2.0164880752563477,
+    "eval_runtime": 13.431,
+    "eval_samples_per_second": 584.99,
+    "eval_steps_per_second": 36.632
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.02,
-    "train_loss": 2.7679789066314697,
-    "train_runtime": 0.7741,
-    "train_samples_per_second": 0.129,
-    "train_steps_per_second": 1.292
+    "train_loss": 2.7404227256774902,
+    "train_runtime": 0.7364,
+    "train_samples_per_second": 0.136,
+    "train_steps_per_second": 1.358
 }

trainer_state.json

@@ -12,10 +12,10 @@
       "epoch": 0.02,
       "step": 1,
       "total_flos": 517012193280.0,
-      "train_loss": 2.7679789066314697,
-      "train_runtime": 0.7741,
-      "train_samples_per_second": 0.129,
-      "train_steps_per_second": 1.292
+      "train_loss": 2.7404227256774902,
+      "train_runtime": 0.7364,
+      "train_samples_per_second": 0.136,
+      "train_steps_per_second": 1.358
     }
   ],
   "logging_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74488b18d20dbece30122b479f6a82eed7b40924e1e168cff126996090640485
+oid sha256:1f6ed97205b4dbbede8dac24843fbdb4afca06c505286112ab8eede4793e06de
 size 5112