pristineaiforall
commited on
Commit
•
ebe385a
1
Parent(s):
5cdba33
End of training
Browse files- README.md +15 -10
- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [HuggingFaceM4/idefics-9b](https://huggingface.co/HuggingFaceM4/idefics-9b) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -36,25 +36,30 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0002
|
39 |
-
- train_batch_size:
|
40 |
-
- eval_batch_size:
|
41 |
- seed: 42
|
42 |
- gradient_accumulation_steps: 8
|
43 |
-
- total_train_batch_size:
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- training_steps:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| 2.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
56 |
-
|
|
57 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [HuggingFaceM4/idefics-9b](https://huggingface.co/HuggingFaceM4/idefics-9b) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.6189
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0002
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
- seed: 42
|
42 |
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 8
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- training_steps: 100
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 2.1253 | 2.76 | 10 | 1.8248 |
|
54 |
+
| 1.3929 | 5.52 | 20 | 1.6206 |
|
55 |
+
| 1.1155 | 8.28 | 30 | 1.6422 |
|
56 |
+
| 0.8392 | 11.03 | 40 | 1.6946 |
|
57 |
+
| 0.5928 | 13.79 | 50 | 1.8916 |
|
58 |
+
| 0.4053 | 16.55 | 60 | 2.0038 |
|
59 |
+
| 0.2454 | 19.31 | 70 | 2.2366 |
|
60 |
+
| 0.1412 | 22.07 | 80 | 2.3802 |
|
61 |
+
| 0.0798 | 24.83 | 90 | 2.5553 |
|
62 |
+
| 0.0667 | 27.59 | 100 | 2.6189 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": {
|
4 |
-
"base_model_class": "
|
5 |
-
"parent_library": "
|
6 |
},
|
7 |
-
"base_model_name_or_path":
|
8 |
"bias": "none",
|
9 |
"fan_in_fan_out": false,
|
10 |
"inference_mode": true,
|
@@ -22,8 +22,8 @@
|
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
-
"q_proj",
|
26 |
"k_proj",
|
|
|
27 |
"v_proj"
|
28 |
],
|
29 |
"task_type": null,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": {
|
4 |
+
"base_model_class": "PeftModel",
|
5 |
+
"parent_library": "peft.peft_model"
|
6 |
},
|
7 |
+
"base_model_name_or_path": null,
|
8 |
"bias": "none",
|
9 |
"fan_in_fan_out": false,
|
10 |
"inference_mode": true,
|
|
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
|
|
25 |
"k_proj",
|
26 |
+
"q_proj",
|
27 |
"v_proj"
|
28 |
],
|
29 |
"task_type": null,
|
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:fe616c8491deb0cdf6fd5b3ff9a99486ef268706b98e5165368325a435d4e847
|
3 |
+
size 79079832
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cef17a836f55cf409b325d56fb8d39d2211c0f2bb273039da8778d321ead7395
|
3 |
size 4856
|