marcus2000
commited on
Commit
•
c19c321
1
Parent(s):
4a3fbeb
Saiga_timelist_task20steps
Browse files- README.md +13 -19
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# Saiga_timelist_task20steps
|
15 |
|
16 |
-
This model is a fine-tuned version of [TheBloke/Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -42,28 +42,22 @@ The following hyperparameters were used during training:
|
|
42 |
- total_train_batch_size: 20
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- training_steps:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
|
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
| 1.
|
56 |
-
| 1.
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
-
| 1.5462 | 1.42 | 55 | 1.7606 |
|
62 |
-
| 1.6728 | 1.55 | 60 | 1.7557 |
|
63 |
-
| 1.6285 | 1.68 | 65 | 1.7520 |
|
64 |
-
| 1.5609 | 1.8 | 70 | 1.7508 |
|
65 |
-
| 1.5975 | 1.93 | 75 | 1.7500 |
|
66 |
-
| 1.6035 | 2.06 | 80 | 1.7498 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
|
|
13 |
|
14 |
# Saiga_timelist_task20steps
|
15 |
|
16 |
+
This model is a fine-tuned version of [TheBloke/Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.0584
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
42 |
- total_train_batch_size: 20
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- training_steps: 20
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 2.2298 | 0.37 | 2 | 2.2031 |
|
52 |
+
| 2.0996 | 0.74 | 4 | 2.1519 |
|
53 |
+
| 2.0299 | 1.11 | 6 | 2.1202 |
|
54 |
+
| 2.0007 | 1.48 | 8 | 2.0978 |
|
55 |
+
| 1.9777 | 1.85 | 10 | 2.0817 |
|
56 |
+
| 1.9089 | 2.22 | 12 | 2.0715 |
|
57 |
+
| 1.9379 | 2.59 | 14 | 2.0650 |
|
58 |
+
| 1.9515 | 2.96 | 16 | 2.0610 |
|
59 |
+
| 1.9178 | 3.33 | 18 | 2.0589 |
|
60 |
+
| 1.8801 | 3.7 | 20 | 2.0584 |
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
|
63 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,10 +20,10 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"k_proj",
|
24 |
"v_proj",
|
|
|
25 |
"o_proj",
|
26 |
-
"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"v_proj",
|
24 |
+
"q_proj",
|
25 |
"o_proj",
|
26 |
+
"k_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33589040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:135395a2cd4784a47a927003e74b0c497f45818b038657dae23bc8150a0e0dd8
|
3 |
size 33589040
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f15c661378faf1acf87035a24d714e630dc819d4ea7695c7224a5e79ecc783f
|
3 |
size 4920
|