pilotj/distilbert-base-uncased-fibe-v9-finetuned
Browse files
README.md
CHANGED
|
@@ -1,26 +1,21 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: biggy-smiley/distilbert-base-uncased-fibe-v5
|
| 3 |
library_name: transformers
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
-
- name: distilbert-base-uncased-fibe-
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
-
# distilbert-base-uncased-fibe-
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
-
|
| 19 |
-
- eval_runtime: 50.1816
|
| 20 |
-
- eval_samples_per_second: 103.624
|
| 21 |
-
- eval_steps_per_second: 0.817
|
| 22 |
-
- epoch: 1.8606
|
| 23 |
-
- step: 8888
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -45,7 +40,25 @@ The following hyperparameters were used during training:
|
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
### Framework versions
|
| 51 |
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
+
base_model: pilotj/distilbert-base-uncased-fibe-v8-finetuned
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
+
- name: distilbert-base-uncased-fibe-v9-finetuned
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# distilbert-base-uncased-fibe-v9-finetuned
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [pilotj/distilbert-base-uncased-fibe-v8-finetuned](https://huggingface.co/pilotj/distilbert-base-uncased-fibe-v8-finetuned) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.8968
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 1
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 49 |
+
| 0.5704 | 0.0779 | 1000 | 1.0604 |
|
| 50 |
+
| 0.5614 | 0.1558 | 2000 | 1.1759 |
|
| 51 |
+
| 0.5481 | 0.2338 | 3000 | 1.0633 |
|
| 52 |
+
| 0.5417 | 0.3117 | 4000 | 1.0108 |
|
| 53 |
+
| 0.5257 | 0.3896 | 5000 | 0.9514 |
|
| 54 |
+
| 0.5106 | 0.4675 | 6000 | 0.9228 |
|
| 55 |
+
| 0.492 | 0.5455 | 7000 | 0.9493 |
|
| 56 |
+
| 0.5033 | 0.6234 | 8000 | 0.9060 |
|
| 57 |
+
| 0.4688 | 0.7013 | 9000 | 0.8691 |
|
| 58 |
+
| 0.483 | 0.7792 | 10000 | 0.8291 |
|
| 59 |
+
| 0.4679 | 0.8572 | 11000 | 0.8628 |
|
| 60 |
+
| 0.4368 | 0.9351 | 12000 | 0.8968 |
|
| 61 |
+
|
| 62 |
|
| 63 |
### Framework versions
|
| 64 |
|