Commit
•
26c0502
1
Parent(s):
2b8d399
End of training
Browse files- README.md +13 -18
- adapter_config.json +1 -1
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
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 [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,36 +35,31 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 0.0001
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 42
|
41 |
- gradient_accumulation_steps: 10
|
42 |
-
- total_train_batch_size:
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 50
|
46 |
- num_epochs: 2
|
47 |
-
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
-
| Training Loss | Epoch
|
52 |
-
|
53 |
-
| 1.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.5819 | 1.4 | 266 | 0.6903 |
|
60 |
-
| 0.5948 | 1.6 | 304 | 0.6849 |
|
61 |
-
| 0.5858 | 1.8 | 342 | 0.6780 |
|
62 |
-
| 0.5539 | 2.0 | 380 | 0.6739 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
- Transformers 4.41.0.dev0
|
68 |
-
- Pytorch
|
69 |
- Datasets 2.19.1
|
70 |
- Tokenizers 0.19.1
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.6872
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 0.0001
|
38 |
+
- train_batch_size: 3
|
39 |
+
- eval_batch_size: 3
|
40 |
- seed: 42
|
41 |
- gradient_accumulation_steps: 10
|
42 |
+
- total_train_batch_size: 30
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 50
|
46 |
- num_epochs: 2
|
|
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:------:|:----:|:---------------:|
|
52 |
+
| 1.4399 | 0.2999 | 38 | 0.7745 |
|
53 |
+
| 0.8072 | 0.5998 | 76 | 0.7329 |
|
54 |
+
| 0.7577 | 0.8998 | 114 | 0.7067 |
|
55 |
+
| 0.6603 | 1.1997 | 152 | 0.7081 |
|
56 |
+
| 0.6099 | 1.4996 | 190 | 0.6960 |
|
57 |
+
| 0.6045 | 1.7995 | 228 | 0.6872 |
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
- Transformers 4.41.0.dev0
|
63 |
+
- Pytorch 2.0.1
|
64 |
- Datasets 2.19.1
|
65 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -21,6 +21,6 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
|
23 |
"task_type": null,
|
24 |
-
"use_dora":
|
25 |
"use_rslora": false
|
26 |
}
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
|
23 |
"task_type": null,
|
24 |
+
"use_dora": true,
|
25 |
"use_rslora": false
|
26 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7da3396b30bb4afe2e4eb2206a34b4bebdde289c521757d8f98d916f74b527eb
|
3 |
+
size 49840864
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4731
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b65e69b9f16929f9153aeb81074223e10d976406a3610f8b175bcc5c85163483
|
3 |
size 4731
|