End of training

README.md

@@ -19,7 +19,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6434
+- Loss: 0.6502
 - Precision: 0.6500
 - Recall: 1.0
 - F1: 0.7879
@@ -54,12 +54,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
-| 0.6606        | 1.0   | 193  | 0.6434          | 0.6500    | 1.0    | 0.7879 |
-| 0.6455        | 2.0   | 386  | 0.6374          | 0.6500    | 1.0    | 0.7879 |
-| 0.6374        | 3.0   | 579  | 0.6338          | 0.6522    | 0.9890 | 0.7861 |
-| 0.6321        | 4.0   | 772  | 0.6318          | 0.6587    | 0.9661 | 0.7833 |
-| 0.6289        | 5.0   | 965  | 0.6275          | 0.6813    | 0.9272 | 0.7855 |
-| 0.6256        | 6.0   | 1158 | 0.6270          | 0.6791    | 0.9282 | 0.7843 |
+| 0.6701        | 1.0   | 193  | 0.6502          | 0.6500    | 1.0    | 0.7879 |
+| 0.6504        | 2.0   | 386  | 0.6435          | 0.6500    | 1.0    | 0.7879 |
+| 0.643         | 3.0   | 579  | 0.6382          | 0.6494    | 0.9970 | 0.7865 |
+| 0.6379        | 4.0   | 772  | 0.6351          | 0.6504    | 0.9831 | 0.7829 |
+| 0.632         | 5.0   | 965  | 0.6309          | 0.6653    | 0.9511 | 0.7829 |
+| 0.6281        | 6.0   | 1158 | 0.6299          | 0.6695    | 0.9472 | 0.7845 |
 
 
 ### Framework versions

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 6.0,
     "eval_f1": 0.7879025923016496,
-    "eval_loss": 0.6433556079864502,
+    "eval_loss": 0.65016770362854,
     "eval_precision": 0.6500324044069994,
     "eval_recall": 1.0,
-    "eval_runtime": 8.0156,
-    "eval_samples_per_second": 192.5,
-    "eval_steps_per_second": 3.119,
+    "eval_runtime": 8.4133,
+    "eval_samples_per_second": 183.401,
+    "eval_steps_per_second": 2.971,
     "test_f1": 0.7823343848580442,
-    "test_loss": 0.6470437049865723,
+    "test_loss": 0.6548706293106079,
     "test_precision": 0.6424870466321243,
     "test_recall": 1.0,
-    "test_runtime": 8.0727,
-    "test_samples_per_second": 191.262,
-    "test_steps_per_second": 3.097
+    "test_runtime": 8.4053,
+    "test_samples_per_second": 183.694,
+    "test_steps_per_second": 2.974
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 6.0,
     "eval_f1": 0.7879025923016496,
-    "eval_loss": 0.6433556079864502,
+    "eval_loss": 0.65016770362854,
     "eval_precision": 0.6500324044069994,
     "eval_recall": 1.0,
-    "eval_runtime": 8.0156,
-    "eval_samples_per_second": 192.5,
-    "eval_steps_per_second": 3.119
+    "eval_runtime": 8.4133,
+    "eval_samples_per_second": 183.401,
+    "eval_steps_per_second": 2.971
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b4c549cc6af377aa132cb4c037fb6dca31b28c391b60dfaac4db12a7a0c925a
+oid sha256:93808603de3853a585d6628d5dec2d3b7514affc0bf65feb4513b5b057b41f4a
 size 243126200

test_results.json

@@ -1,9 +1,9 @@
 {
     "test_f1": 0.7823343848580442,
-    "test_loss": 0.6470437049865723,
+    "test_loss": 0.6548706293106079,
     "test_precision": 0.6424870466321243,
     "test_recall": 1.0,
-    "test_runtime": 8.0727,
-    "test_samples_per_second": 191.262,
-    "test_steps_per_second": 3.097
+    "test_runtime": 8.4053,
+    "test_samples_per_second": 183.694,
+    "test_steps_per_second": 2.974
 }