End of training
Browse files
README.md
CHANGED
@@ -14,10 +14,13 @@ model-index:
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
|
|
17 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/rafael-torrestimal-Personal/huggingface/runs/q4cyw2ji)
|
18 |
# falcon7binstruct_fine_tunning_PPF_english_conversations_fake
|
19 |
|
20 |
This model is a fine-tuned version of [vilsonrodrigues/falcon-7b-instruct-sharded](https://huggingface.co/vilsonrodrigues/falcon-7b-instruct-sharded) on the None dataset.
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -45,11 +48,18 @@ The following hyperparameters were used during training:
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: cosine
|
47 |
- lr_scheduler_warmup_ratio: 0.03
|
48 |
-
- training_steps:
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/rafael-torrestimal-Personal/huggingface/runs/q4cyw2ji)
|
18 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/rafael-torrestimal-Personal/huggingface/runs/q4cyw2ji)
|
19 |
# falcon7binstruct_fine_tunning_PPF_english_conversations_fake
|
20 |
|
21 |
This model is a fine-tuned version of [vilsonrodrigues/falcon-7b-instruct-sharded](https://huggingface.co/vilsonrodrigues/falcon-7b-instruct-sharded) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4691
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: cosine
|
50 |
- lr_scheduler_warmup_ratio: 0.03
|
51 |
+
- training_steps: 50
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 0.7389 | 0.0667 | 10 | 0.6081 |
|
59 |
+
| 0.56 | 0.1333 | 20 | 0.5264 |
|
60 |
+
| 0.5216 | 0.2 | 30 | 0.4919 |
|
61 |
+
| 0.4881 | 0.2667 | 40 | 0.4722 |
|
62 |
+
| 0.4646 | 0.3333 | 50 | 0.4691 |
|
63 |
|
64 |
|
65 |
### Framework versions
|