End of training
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Rocketknight1/falcon-rw-1b](https://huggingface.co/Rocketknight1/falcon-rw-1b) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -43,15 +43,33 @@ The following hyperparameters were used during training:
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_ratio: 0.03
|
| 46 |
-
- num_epochs:
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
-
|
|
| 54 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Rocketknight1/falcon-rw-1b](https://huggingface.co/Rocketknight1/falcon-rw-1b) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.4504
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_ratio: 0.03
|
| 46 |
+
- num_epochs: 20
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.7984 | 0.99 | 77 | 0.7167 |
|
| 54 |
+
| 0.7175 | 1.99 | 155 | 0.6955 |
|
| 55 |
+
| 0.6092 | 2.99 | 233 | 0.6690 |
|
| 56 |
+
| 0.5426 | 3.99 | 311 | 0.6549 |
|
| 57 |
+
| 0.7676 | 5.0 | 389 | 0.6416 |
|
| 58 |
+
| 0.6552 | 6.0 | 467 | 0.6216 |
|
| 59 |
+
| 0.5989 | 7.0 | 545 | 0.6039 |
|
| 60 |
+
| 0.4944 | 8.0 | 623 | 0.5810 |
|
| 61 |
+
| 0.4591 | 8.99 | 700 | 0.5615 |
|
| 62 |
+
| 0.5415 | 9.99 | 778 | 0.5429 |
|
| 63 |
+
| 0.4794 | 10.99 | 856 | 0.5187 |
|
| 64 |
+
| 0.4347 | 11.99 | 934 | 0.4982 |
|
| 65 |
+
| 0.3487 | 13.0 | 1012 | 0.4845 |
|
| 66 |
+
| 0.3229 | 14.0 | 1090 | 0.4724 |
|
| 67 |
+
| 0.3946 | 15.0 | 1168 | 0.4624 |
|
| 68 |
+
| 0.3689 | 16.0 | 1246 | 0.4574 |
|
| 69 |
+
| 0.3191 | 16.99 | 1323 | 0.4529 |
|
| 70 |
+
| 0.2793 | 17.99 | 1401 | 0.4509 |
|
| 71 |
+
| 0.3675 | 18.99 | 1479 | 0.4504 |
|
| 72 |
+
| 0.3215 | 19.78 | 1540 | 0.4504 |
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50338848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc19e395d7f6b67842c666af55496b7db515bd745e73ce617094a108affa6d75
|
| 3 |
size 50338848
|
runs/Apr22_01-30-18_e46554ad8bbb/events.out.tfevents.1713749420.e46554ad8bbb.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e3fdb156be6fd6649343bfb31a5a77fbe76dd1e47bc82f8831980ea8d062895
|
| 3 |
+
size 4854
|
runs/Apr22_01-30-37_e46554ad8bbb/events.out.tfevents.1713749439.e46554ad8bbb.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b27964b5ffc4852b0adde2a4f981a4338545cdc51c92f3d67a049cedf179d2b5
|
| 3 |
+
size 34766
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4219
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59ea154c7aa26fea7d2b9d9bc0c78f52e4d0fa97cbc8a322b6478d69ac67716d
|
| 3 |
size 4219
|