Training in progress, epoch 0
Browse files
README.md
CHANGED
@@ -9,11 +9,6 @@ base_model: TheBloke/typhoon-7B-GPTQ
|
|
9 |
model-index:
|
10 |
- name: typhoon-7b-chat-alpaca
|
11 |
results: []
|
12 |
-
datasets:
|
13 |
-
- Thaweewat/alpaca-cleaned-52k-th
|
14 |
-
language:
|
15 |
-
- th
|
16 |
-
pipeline_tag: text-generation
|
17 |
---
|
18 |
|
19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -23,6 +18,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
23 |
|
24 |
This model is a fine-tuned version of [TheBloke/typhoon-7B-GPTQ](https://huggingface.co/TheBloke/typhoon-7B-GPTQ) on the None dataset.
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
## Training procedure
|
27 |
|
28 |
### Training hyperparameters
|
@@ -34,8 +41,13 @@ The following hyperparameters were used during training:
|
|
34 |
- seed: 42
|
35 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
36 |
- lr_scheduler_type: cosine
|
|
|
37 |
- mixed_precision_training: Native AMP
|
38 |
|
|
|
|
|
|
|
|
|
39 |
### Framework versions
|
40 |
|
41 |
- PEFT 0.7.1
|
|
|
9 |
model-index:
|
10 |
- name: typhoon-7b-chat-alpaca
|
11 |
results: []
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [TheBloke/typhoon-7B-GPTQ](https://huggingface.co/TheBloke/typhoon-7B-GPTQ) on the None dataset.
|
20 |
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
## Training procedure
|
34 |
|
35 |
### Training hyperparameters
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
+
- training_steps: 250
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
### Framework versions
|
52 |
|
53 |
- PEFT 0.7.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 27280152
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fe67be2965b74fa7cfb2afd00a2bbed409294c2e62ce34b099975b83b28c79a
|
3 |
size 27280152
|
runs/Dec25_06-50-05_1c9e386753e4/events.out.tfevents.1703487013.1c9e386753e4.17257.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47758c47d7252804e4b837f0d03427db9a13bcce685a44dfbb99dc646adec85
|
3 |
+
size 7191
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 2048,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32c36b2db91be1a9cfe369f94423bbdca908ccbfb0846507d66e4874e8eea906
|
3 |
size 4728
|