AT-Llama-2-7b-chat-Tweet-Sentiment
Browse files
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 [TheBloke/Llama-2-7B-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GPTQ) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 1.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -51,27 +51,27 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:------:|:----:|:---------------:|
|
54 |
-
| 5.422 | 0.0457 | 2 | 5.
|
55 |
-
|
|
56 |
-
| 4.
|
57 |
-
| 3.
|
58 |
-
|
|
59 |
-
|
|
60 |
-
| 2.
|
61 |
-
| 2.
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
| 1.
|
66 |
-
| 1.
|
67 |
-
| 1.
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 1.
|
73 |
-
| 1.
|
74 |
-
| 1.
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [TheBloke/Llama-2-7B-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GPTQ) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.6657
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:------:|:----:|:---------------:|
|
54 |
+
| 5.422 | 0.0457 | 2 | 5.1721 |
|
55 |
+
| 5.1534 | 0.0914 | 4 | 4.6225 |
|
56 |
+
| 4.5268 | 0.1371 | 6 | 4.0415 |
|
57 |
+
| 3.9455 | 0.1829 | 8 | 3.5294 |
|
58 |
+
| 3.4478 | 0.2286 | 10 | 3.1964 |
|
59 |
+
| 3.1897 | 0.2743 | 12 | 2.9354 |
|
60 |
+
| 2.8951 | 0.32 | 14 | 2.6721 |
|
61 |
+
| 2.5987 | 0.3657 | 16 | 2.4219 |
|
62 |
+
| 2.3629 | 0.4114 | 18 | 2.2606 |
|
63 |
+
| 2.1553 | 0.4571 | 20 | 2.1368 |
|
64 |
+
| 2.109 | 0.5029 | 22 | 2.0289 |
|
65 |
+
| 1.9611 | 0.5486 | 24 | 1.9382 |
|
66 |
+
| 1.8992 | 0.5943 | 26 | 1.8638 |
|
67 |
+
| 1.794 | 0.64 | 28 | 1.8066 |
|
68 |
+
| 1.7374 | 0.6857 | 30 | 1.7621 |
|
69 |
+
| 1.7599 | 0.7314 | 32 | 1.7268 |
|
70 |
+
| 1.769 | 0.7771 | 34 | 1.7006 |
|
71 |
+
| 1.6442 | 0.8229 | 36 | 1.6834 |
|
72 |
+
| 1.6242 | 0.8686 | 38 | 1.6730 |
|
73 |
+
| 1.7367 | 0.9143 | 40 | 1.6677 |
|
74 |
+
| 1.6649 | 0.96 | 42 | 1.6657 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -10,13 +10,13 @@
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
-
"lora_dropout": 0.
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
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 sha256:7add42742d1884f0e22aebc80542c459d27314d61c4bb215cb02cf8f9c576eed
|
3 |
+
size 134235048
|
runs/May11_22-15-49_ebd9bc4e0c63/events.out.tfevents.1715465784.ebd9bc4e0c63.22644.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1db416514964659892ae149249992da4860a1e2776efb0466c7b76d0f5c0ba22
|
3 |
+
size 15642
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45c97bd6b5b73d80c710fee45dcc56ec5821a919ff71ab7c456ce65cf7c553c5
|
3 |
size 4984
|