Spaces:
No application file
No application file
Upload folder using huggingface_hub
Browse files- project.ipynb +0 -0
- qwen-vl-7b-surf-finetuned-persian/adapter_config.json +3 -3
- qwen-vl-7b-surf-finetuned-persian/adapter_model.safetensors +1 -1
- qwen-vl-7b-surf-finetuned-persian/checkpoint-51/adapter_config.json +3 -3
- qwen-vl-7b-surf-finetuned-persian/checkpoint-51/adapter_model.safetensors +1 -1
- qwen-vl-7b-surf-finetuned-persian/checkpoint-51/optimizer.pt +1 -1
- qwen-vl-7b-surf-finetuned-persian/checkpoint-51/trainer_state.json +10 -10
- qwen-vl-7b-surf-finetuned-persian/checkpoint-51/training_args.bin +1 -1
- qwen-vl-7b-surf-finetuned-persian/training_args.bin +1 -1
project.ipynb
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen-vl-7b-surf-finetuned-persian/adapter_config.json
CHANGED
|
@@ -25,10 +25,10 @@
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
| 28 |
-
"v_proj",
|
| 29 |
-
"q_proj",
|
| 30 |
"o_proj",
|
| 31 |
-
"k_proj"
|
|
|
|
|
|
|
| 32 |
],
|
| 33 |
"target_parameters": null,
|
| 34 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
|
|
|
|
|
|
| 28 |
"o_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"q_proj"
|
| 32 |
],
|
| 33 |
"target_parameters": null,
|
| 34 |
"task_type": "CAUSAL_LM",
|
qwen-vl-7b-surf-finetuned-persian/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40403560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eca95b4216133c6422f15e7ecf1314e03a64ad5b910019f9c100bd5b0dab9390
|
| 3 |
size 40403560
|
qwen-vl-7b-surf-finetuned-persian/checkpoint-51/adapter_config.json
CHANGED
|
@@ -25,10 +25,10 @@
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
| 28 |
-
"v_proj",
|
| 29 |
-
"q_proj",
|
| 30 |
"o_proj",
|
| 31 |
-
"k_proj"
|
|
|
|
|
|
|
| 32 |
],
|
| 33 |
"target_parameters": null,
|
| 34 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
|
|
|
|
|
|
| 28 |
"o_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"q_proj"
|
| 32 |
],
|
| 33 |
"target_parameters": null,
|
| 34 |
"task_type": "CAUSAL_LM",
|
qwen-vl-7b-surf-finetuned-persian/checkpoint-51/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40403560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eca95b4216133c6422f15e7ecf1314e03a64ad5b910019f9c100bd5b0dab9390
|
| 3 |
size 40403560
|
qwen-vl-7b-surf-finetuned-persian/checkpoint-51/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 133
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ffc444ca2f382403310d91f1195e466bce44d6ecab91410d02cbe3d66de882d
|
| 3 |
size 133
|
qwen-vl-7b-surf-finetuned-persian/checkpoint-51/trainer_state.json
CHANGED
|
@@ -11,37 +11,37 @@
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.19801980198019803,
|
| 14 |
-
"grad_norm": 0.
|
| 15 |
"learning_rate": 0.0001647058823529412,
|
| 16 |
-
"loss": 1.
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.39603960396039606,
|
| 21 |
-
"grad_norm": 0.
|
| 22 |
"learning_rate": 0.00012549019607843137,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.594059405940594,
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
"learning_rate": 8.627450980392158e-05,
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.7920792079207921,
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 4.705882352941177e-05,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.9900990099009901,
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
"learning_rate": 7.84313725490196e-06,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 50
|
| 46 |
}
|
| 47 |
],
|
|
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.19801980198019803,
|
| 14 |
+
"grad_norm": 0.8204548358917236,
|
| 15 |
"learning_rate": 0.0001647058823529412,
|
| 16 |
+
"loss": 1.5384,
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.39603960396039606,
|
| 21 |
+
"grad_norm": 0.4262150228023529,
|
| 22 |
"learning_rate": 0.00012549019607843137,
|
| 23 |
+
"loss": 0.4338,
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.594059405940594,
|
| 28 |
+
"grad_norm": 0.11380422115325928,
|
| 29 |
"learning_rate": 8.627450980392158e-05,
|
| 30 |
+
"loss": 0.1321,
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.7920792079207921,
|
| 35 |
+
"grad_norm": 0.09116532653570175,
|
| 36 |
"learning_rate": 4.705882352941177e-05,
|
| 37 |
+
"loss": 0.121,
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.9900990099009901,
|
| 42 |
+
"grad_norm": 0.0850338339805603,
|
| 43 |
"learning_rate": 7.84313725490196e-06,
|
| 44 |
+
"loss": 0.1144,
|
| 45 |
"step": 50
|
| 46 |
}
|
| 47 |
],
|
qwen-vl-7b-surf-finetuned-persian/checkpoint-51/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad66e657ad53b2a1e6dc64e0f1dbf5034ab82733e97ab179a3268026c94cd5f2
|
| 3 |
size 5841
|
qwen-vl-7b-surf-finetuned-persian/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad66e657ad53b2a1e6dc64e0f1dbf5034ab82733e97ab179a3268026c94cd5f2
|
| 3 |
size 5841
|