ninagroot/Llama-360Mtest
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss:
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -33,14 +33,14 @@ More information needed
|
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
- learning_rate: 0.0003
|
| 36 |
-
- train_batch_size:
|
| 37 |
- eval_batch_size: 8
|
| 38 |
- seed: 42
|
| 39 |
-
- gradient_accumulation_steps:
|
| 40 |
-
- total_train_batch_size:
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: cosine
|
| 43 |
-
- lr_scheduler_warmup_steps:
|
| 44 |
- num_epochs: 4
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
|
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
-
|
|
| 52 |
-
|
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 4.2830
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
- learning_rate: 0.0003
|
| 36 |
+
- train_batch_size: 2
|
| 37 |
- eval_batch_size: 8
|
| 38 |
- seed: 42
|
| 39 |
+
- gradient_accumulation_steps: 2
|
| 40 |
+
- total_train_batch_size: 4
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: cosine
|
| 43 |
+
- lr_scheduler_warmup_steps: 100
|
| 44 |
- num_epochs: 4
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 6.0238 | 1.0 | 69 | 5.9202 |
|
| 52 |
+
| 5.2632 | 2.0 | 138 | 4.8940 |
|
| 53 |
+
| 4.012 | 3.0 | 207 | 4.3873 |
|
| 54 |
+
| 3.7681 | 4.0 | 276 | 4.2830 |
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1344172280
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17e02de6cf127178a8946722392615d442e0df7968a1e9ab13a0d4d88d6e43af
|
| 3 |
size 1344172280
|
runs/Mar22_11-50-54_gcn28.local.snellius.surf.nl/events.out.tfevents.1711104666.gcn28.local.snellius.surf.nl.3128590.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d9334804460e1e285b9578397974be082570a28417e61320192816c23547e35
|
| 3 |
+
size 7774
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73705c12fe404124335ca72adf269875cc3fb90a1d3dea5008ffa660c0f4f512
|
| 3 |
size 4728
|