End of training

README.md

@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tapt_base_LR-2e-05
 
-This model is a fine-tuned version of [bioformers/bioformer-16L](https://huggingface.co/bioformers/bioformer-16L) on an unknown dataset.
+This model is a fine-tuned version of [bioformers/bioformer-16L](https://huggingface.co/bioformers/bioformer-16L) on the Mardiyyah/TAPT_data_V2_split dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9776
+- Loss: 1.9182
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 49.94117647058823,
+    "eval_loss": 1.9181811809539795,
+    "eval_runtime": 2.5587,
+    "eval_samples": 1945,
+    "eval_samples_per_second": 760.165,
+    "eval_steps_per_second": 12.116,
+    "perplexity": 6.8085636554933355,
+    "total_flos": 1.2548402868338688e+16,
+    "train_loss": 1.8820014402601455,
+    "train_runtime": 2628.924,
+    "train_samples": 9733,
+    "train_samples_per_second": 185.114,
+    "train_steps_per_second": 0.171
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 49.94117647058823,
+    "eval_loss": 1.9181811809539795,
+    "eval_runtime": 2.5587,
+    "eval_samples": 1945,
+    "eval_samples_per_second": 760.165,
+    "eval_steps_per_second": 12.116,
+    "perplexity": 6.8085636554933355,
+    "total_flos": 1.2548402868338688e+16,
+    "train_loss": 1.8820014402601455,
+    "train_runtime": 2628.924,
+    "train_samples": 9733,
+    "train_samples_per_second": 185.114,
+    "train_steps_per_second": 0.171
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 49.94117647058823,
+    "total_flos": 1.2548402868338688e+16,
+    "train_loss": 1.8820014402601455,
+    "train_runtime": 2628.924,
+    "train_samples": 9733,
+    "train_samples_per_second": 185.114,
+    "train_steps_per_second": 0.171
+}