End of training

README.md

@@ -19,10 +19,10 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6596
-- Precision: 0.6084
-- Recall: 0.9860
-- F1: 0.7525
+- Loss: 0.6688
+- Precision: 0.6014
+- Recall: 1.0
+- F1: 0.7511
 
 ## Model description
 
@@ -54,13 +54,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
-| 0.6713        | 1.0   | 193  | 0.6663          | 0.6023    | 0.9989 | 0.7515 |
-| 0.6613        | 2.0   | 386  | 0.6596          | 0.6084    | 0.9860 | 0.7525 |
-| 0.654         | 3.0   | 579  | 0.6558          | 0.6169    | 0.9386 | 0.7444 |
-| 0.6495        | 4.0   | 772  | 0.6554          | 0.6231    | 0.9138 | 0.7409 |
-| 0.6472        | 5.0   | 965  | 0.6524          | 0.6482    | 0.8438 | 0.7331 |
-| 0.6436        | 6.0   | 1158 | 0.6522          | 0.6455    | 0.8416 | 0.7306 |
-| 0.6419        | 7.0   | 1351 | 0.6517          | 0.6493    | 0.8438 | 0.7338 |
+| 0.6753        | 1.0   | 193  | 0.6688          | 0.6014    | 1.0    | 0.7511 |
+| 0.6661        | 2.0   | 386  | 0.6618          | 0.6045    | 0.9914 | 0.7510 |
+| 0.6588        | 3.0   | 579  | 0.6562          | 0.6154    | 0.9483 | 0.7464 |
+| 0.6532        | 4.0   | 772  | 0.6538          | 0.6242    | 0.8933 | 0.7349 |
+| 0.6498        | 5.0   | 965  | 0.6518          | 0.6533    | 0.8405 | 0.7352 |
+| 0.6459        | 6.0   | 1158 | 0.6517          | 0.6560    | 0.8362 | 0.7352 |
 
 
 ### Framework versions

all_results.json

@@ -1,17 +1,17 @@
 {
-    "epoch": 7.0,
-    "eval_f1": 0.7524671052631579,
-    "eval_loss": 0.659632682800293,
-    "eval_precision": 0.6083776595744681,
-    "eval_recall": 0.9859913793103449,
-    "eval_runtime": 8.0449,
-    "eval_samples_per_second": 191.798,
-    "eval_steps_per_second": 3.108,
-    "test_f1": 0.7560277891295464,
-    "test_loss": 0.6514418721199036,
-    "test_precision": 0.6109643328929987,
-    "test_recall": 0.9914255091103966,
-    "test_runtime": 8.0746,
-    "test_samples_per_second": 191.218,
-    "test_steps_per_second": 3.096
+    "epoch": 6.0,
+    "eval_f1": 0.7511129097531364,
+    "eval_loss": 0.6687906980514526,
+    "eval_precision": 0.6014257939079715,
+    "eval_recall": 1.0,
+    "eval_runtime": 8.3979,
+    "eval_samples_per_second": 183.736,
+    "eval_steps_per_second": 2.977,
+    "test_f1": 0.7533306419055309,
+    "test_loss": 0.6667491793632507,
+    "test_precision": 0.6042746113989638,
+    "test_recall": 1.0,
+    "test_runtime": 8.4272,
+    "test_samples_per_second": 183.217,
+    "test_steps_per_second": 2.967
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 7.0,
-    "eval_f1": 0.7524671052631579,
-    "eval_loss": 0.659632682800293,
-    "eval_precision": 0.6083776595744681,
-    "eval_recall": 0.9859913793103449,
-    "eval_runtime": 8.0449,
-    "eval_samples_per_second": 191.798,
-    "eval_steps_per_second": 3.108
+    "epoch": 6.0,
+    "eval_f1": 0.7511129097531364,
+    "eval_loss": 0.6687906980514526,
+    "eval_precision": 0.6014257939079715,
+    "eval_recall": 1.0,
+    "eval_runtime": 8.3979,
+    "eval_samples_per_second": 183.736,
+    "eval_steps_per_second": 2.977
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64be7724c25b61797a80e42b65a5a30ba7b3a31e1a2ce730e3a3a4a4084d688c
+oid sha256:cb212e73af903c3d1bc4da387ab455937659880d548fdb834d338cca89d06e62
 size 243126200

test_results.json

@@ -1,9 +1,9 @@
 {
-    "test_f1": 0.7560277891295464,
-    "test_loss": 0.6514418721199036,
-    "test_precision": 0.6109643328929987,
-    "test_recall": 0.9914255091103966,
-    "test_runtime": 8.0746,
-    "test_samples_per_second": 191.218,
-    "test_steps_per_second": 3.096
+    "test_f1": 0.7533306419055309,
+    "test_loss": 0.6667491793632507,
+    "test_precision": 0.6042746113989638,
+    "test_recall": 1.0,
+    "test_runtime": 8.4272,
+    "test_samples_per_second": 183.217,
+    "test_steps_per_second": 2.967
 }