End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.2765
-- Accuracy: 0.2614
-- F1: 0.0104
+- Loss: 3.4697
+- Accuracy: 0.4535
+- F1: 0.0330
 
 ## Model description
 
@@ -40,19 +40,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 40
+- eval_batch_size: 40
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 5
 - label_smoothing_factor: 0.1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 4.713         | 1.0   | 25   | 4.2765          | 0.2614   | 0.0104 |
+| 4.6623        | 1.0   | 20   | 4.0312          | 0.3023   | 0.0122 |
+| 4.1733        | 2.0   | 40   | 3.9241          | 0.3721   | 0.0265 |
+| 4.0474        | 3.0   | 60   | 3.8249          | 0.4419   | 0.0324 |
+| 3.8755        | 4.0   | 80   | 3.5504          | 0.4651   | 0.0357 |
+| 3.6768        | 5.0   | 100  | 3.4697          | 0.4535   | 0.0330 |
 
 
 ### Framework versions

emissions.csv

@@ -1,2 +1,2 @@
 timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
-2025-08-11T09:41:07,codecarbon,c7946fe2-006d-49c1-87e3-8e64888f7f4f,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,12.5743139218539,0.00022532905383394798,1.791978912203955e-05,42.5,476.50199247942726,94.34468364715576,0.000148328986798232,0.0016630429970234673,0.00032925723854464,0.002140629222366339,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-60-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.58582305908203,machine,N,1.0
+2025-08-11T10:14:28,codecarbon,d2500f10-db48-48f0-93da-6c6855365939,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,61.5074503980577,0.001099743166948356,1.787983666744678e-05,42.5,383.1514374431581,94.34468364715576,0.0007257662079355215,0.008110773433116947,0.0016110361163205477,0.010447575757373017,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-60-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.58582305908203,machine,N,1.0

metrics.json

@@ -1,9 +1,9 @@
 {
-    "eval_loss": 4.276517868041992,
-    "eval_accuracy": 0.26136363636363635,
-    "eval_f1": 0.01036036036036036,
-    "eval_runtime": 0.4791,
-    "eval_samples_per_second": 183.688,
-    "eval_steps_per_second": 6.262,
-    "epoch": 1.0
+    "eval_loss": 3.4697318077087402,
+    "eval_accuracy": 0.45348837209302323,
+    "eval_f1": 0.03298874813820767,
+    "eval_runtime": 0.294,
+    "eval_samples_per_second": 292.517,
+    "eval_steps_per_second": 10.204,
+    "epoch": 5.0
 }