End of training

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2966
-- F1 Macro: 0.0453
+- Loss: 0.9139
+- F1 Macro: 0.0
 - Exact Match: 0.0
 
 ## Model description
@@ -37,23 +37,38 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 1e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - 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: 5
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1 Macro | Exact Match |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|
-| 1.1881        | 1.0   | 25   | 2.2966          | 0.0453   | 0.0         |
-| 1.1994        | 2.0   | 50   | 2.6744          | 0.0336   | 0.0         |
-| 0.9102        | 3.0   | 75   | 3.0701          | 0.0566   | 0.0         |
-| 1.339         | 4.0   | 100  | 3.0234          | 0.0436   | 0.0         |
-| 1.5817        | 5.0   | 125  | 3.0559          | 0.0428   | 0.0         |
+| 1.1458        | 1.0   | 25   | 1.0204          | 0.0      | 0.0         |
+| 1.4553        | 2.0   | 50   | 0.9139          | 0.0      | 0.0         |
+| 1.0412        | 3.0   | 75   | 0.9696          | 0.0      | 0.0         |
+| 1.7656        | 4.0   | 100  | 1.0281          | 0.0      | 0.0         |
+| 1.3778        | 5.0   | 125  | 1.0019          | 0.0      | 0.0         |
+| 1.7337        | 6.0   | 150  | 0.9519          | 0.0      | 0.0         |
+| 0.9857        | 7.0   | 175  | 0.9220          | 0.0      | 0.0         |
+| 1.3225        | 8.0   | 200  | 1.0009          | 0.0      | 0.0         |
+| 0.917         | 9.0   | 225  | 0.9627          | 0.0      | 0.0         |
+| 1.0001        | 10.0  | 250  | 0.9457          | 0.0      | 0.0         |
+| 1.1714        | 11.0  | 275  | 0.9520          | 0.0      | 0.0         |
+| 0.6841        | 12.0  | 300  | 0.9900          | 0.0      | 0.0         |
+| 1.0138        | 13.0  | 325  | 0.9969          | 0.0      | 0.0         |
+| 0.9479        | 14.0  | 350  | 0.9998          | 0.0      | 0.0         |
+| 0.6735        | 15.0  | 375  | 0.9824          | 0.0      | 0.0         |
+| 0.7927        | 16.0  | 400  | 0.9319          | 0.0      | 0.0         |
+| 0.7996        | 17.0  | 425  | 0.9437          | 0.0      | 0.0         |
+| 0.7804        | 18.0  | 450  | 0.9582          | 0.0      | 0.0         |
+| 0.7048        | 19.0  | 475  | 0.9473          | 0.0      | 0.0         |
+| 0.5819        | 20.0  | 500  | 0.9483          | 0.0      | 0.0         |
 
 
 ### 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
-2025-08-28T13:34:12,codecarbon,7961b0e1-5620-405c-8f72-d9579535c0d6,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,40.892827729927376,0.0005375164639497293,1.314451686979691e-05,42.5,273.5641178292843,94.34468507766725,0.0004821247777324364,0.0035540981210573364,0.0010701911683537544,0.005106414067143528,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-71-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.5858268737793,machine,N,1.0
+2025-08-28T15:26:15,codecarbon,06fc693e-38ce-4d5d-a96c-77e37117eab8,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,163.80096963886172,0.002178447438859299,1.3299356186121522e-05,42.5,334.8005306981818,94.34468507766725,0.0019328194311220108,0.014472036299842728,0.004290425981121169,0.020695281712085907,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-71-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.5858268737793,machine,N,1.0

metrics.json

@@ -1,9 +1,9 @@
 {
-    "eval_loss": 2.2966420650482178,
-    "eval_f1_macro": 0.04526290158667233,
+    "eval_loss": 0.913872480392456,
+    "eval_f1_macro": 0.0,
     "eval_exact_match": 0.0,
-    "eval_runtime": 0.2635,
-    "eval_samples_per_second": 333.949,
-    "eval_steps_per_second": 11.385,
-    "epoch": 5.0
+    "eval_runtime": 0.2852,
+    "eval_samples_per_second": 312.098,
+    "eval_steps_per_second": 10.52,
+    "epoch": 20.0
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6644e79c48eace962ccc9b0cce93a51a339335161a8be725339345c6918bc14f
+oid sha256:a737ace796d1b8954d97df062c0627a4e7f25c051d513682392a9965495346f2
 size 498686824

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8c8385d269758f0f939fe421ef7d4f05d8c7b30b35fc1b818deb58cc93fc39
+oid sha256:9117c3932030aab1b8f74d8133701e67323d2a56bbff0959ca18e70793e19209
 size 498747403