nightner/roberta2roberta_financial_lora_v1_small

README.md

@@ -16,16 +16,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [google/roberta2roberta_L-24_cnn_daily_mail](https://huggingface.co/google/roberta2roberta_L-24_cnn_daily_mail) on the None dataset.
+This model is a fine-tuned version of [google/roberta2roberta_L-24_cnn_daily_mail](https://huggingface.co/google/roberta2roberta_L-24_cnn_daily_mail) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3415
-- Rouge1: 39.24
-- Rouge2: 20.62
-- Rougel: 29.42
-- Rougelsum: 29.35
-- Bertscore P: 84.82
-- Bertscore R: 85.16
-- Bertscore F1: 84.9
+- Loss: 6.7395
+- Rouge1: 33.11
+- Rouge2: 20.39
+- Rougel: 27.32
+- Rougelsum: 27.42
+- Bertscore P: 87.57
+- Bertscore R: 83.35
+- Bertscore F1: 85.27
 
 ## Model description
 
@@ -45,22 +45,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- total_train_batch_size: 8
 - 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: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore P | Bertscore R | Bertscore F1 |
-|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-----------:|:-----------:|:------------:|
-| 13.8236       | 0.7251 | 300  | 2.8115          | 36.62  | 19.66  | 27.32  | 27.25     | 83.21       | 84.38       | 83.62        |
-| 10.8258       | 1.4495 | 600  | 2.3415          | 39.24  | 20.62  | 29.42  | 29.35     | 84.82       | 85.16       | 84.9         |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore P | Bertscore R | Bertscore F1 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-----------:|:-----------:|:------------:|
+| 36.5558       | 0.8   | 20   | 7.8969          | 32.35  | 20.37  | 27.74  | 27.82     | 87.74       | 83.51       | 85.43        |
+| 32.2661       | 1.6   | 40   | 7.0747          | 34.94  | 21.86  | 29.83  | 30.04     | 87.7        | 83.93       | 85.62        |
+| 30.3129       | 2.4   | 60   | 6.7395          | 33.11  | 20.39  | 27.32  | 27.42     | 87.57       | 83.35       | 85.27        |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76885af14102f0fcc29d0c8dbb0b27b2e1d39760a59551a69fd98a1063d65526
+oid sha256:0b9de919c6a1c38c9cd8fd0d1b2c9b59b7a64ab050fffda96b5a59b49d82d803
 size 12611432

runs/Feb17_12-24-42_0bfd00035eae/events.out.tfevents.1739795132.0bfd00035eae.2888.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1a8e71f4544298c4c105d3c9bfc75397e0a344f352d607201a7f9025ab89a7
+size 9384

runs/Feb17_12-30-54_0bfd00035eae/events.out.tfevents.1739795476.0bfd00035eae.2888.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5658e7395cbb99f57ebf5d20ace7031d79bffa2b9129db5c306723c24e1d4926
+size 13272

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e16beb67675cca3530aabca05d390cc84b64ffac7516c9386be2263bca9606c
+oid sha256:13b7c44cc55c6c221920be5f2abeaac3412ad878f406b2e5e2f5d78b4a89c1a9
 size 5432