Casper0508
commited on
Commit
•
7234337
1
Parent(s):
7b9a13f
End of training
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 [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,7 +35,7 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- learning_rate:
|
39 |
- train_batch_size: 8
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
@@ -50,31 +50,31 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| 3.
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.4797
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
- train_batch_size: 8
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 3.365 | 1.36 | 10 | 2.0638 |
|
54 |
+
| 1.3671 | 2.71 | 20 | 0.9814 |
|
55 |
+
| 0.817 | 4.07 | 30 | 0.7618 |
|
56 |
+
| 0.6648 | 5.42 | 40 | 0.7134 |
|
57 |
+
| 0.5897 | 6.78 | 50 | 0.6871 |
|
58 |
+
| 0.5076 | 8.14 | 60 | 0.6776 |
|
59 |
+
| 0.4545 | 9.49 | 70 | 0.7360 |
|
60 |
+
| 0.4059 | 10.85 | 80 | 0.7673 |
|
61 |
+
| 0.3544 | 12.2 | 90 | 0.8158 |
|
62 |
+
| 0.3161 | 13.56 | 100 | 0.8801 |
|
63 |
+
| 0.2844 | 14.92 | 110 | 0.9591 |
|
64 |
+
| 0.259 | 16.27 | 120 | 0.9817 |
|
65 |
+
| 0.2405 | 17.63 | 130 | 1.0922 |
|
66 |
+
| 0.2298 | 18.98 | 140 | 1.1705 |
|
67 |
+
| 0.2125 | 20.34 | 150 | 1.1817 |
|
68 |
+
| 0.2073 | 21.69 | 160 | 1.2862 |
|
69 |
+
| 0.1998 | 23.05 | 170 | 1.3352 |
|
70 |
+
| 0.1912 | 24.41 | 180 | 1.3434 |
|
71 |
+
| 0.1883 | 25.76 | 190 | 1.4113 |
|
72 |
+
| 0.1851 | 27.12 | 200 | 1.4113 |
|
73 |
+
| 0.1796 | 28.47 | 210 | 1.4654 |
|
74 |
+
| 0.1805 | 29.83 | 220 | 1.4565 |
|
75 |
+
| 0.1768 | 31.19 | 230 | 1.4650 |
|
76 |
+
| 0.1763 | 32.54 | 240 | 1.4769 |
|
77 |
+
| 0.1752 | 33.9 | 250 | 1.4797 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -7,11 +7,11 @@
|
|
7 |
"init_lora_weights": true,
|
8 |
"layers_pattern": null,
|
9 |
"layers_to_transform": null,
|
10 |
-
"lora_alpha":
|
11 |
-
"lora_dropout": 0.
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
-
"r":
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
"q_proj",
|
|
|
7 |
"init_lora_weights": true,
|
8 |
"layers_pattern": null,
|
9 |
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 128,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
"q_proj",
|
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 sha256:7baefad0749b95301d1ef5729beb829eccb0fff2ef98c4b1dfe752fecdb4b7cf
|
3 |
+
size 151020944
|
emissions.csv
CHANGED
@@ -1,2 +1,2 @@
|
|
1 |
timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
|
2 |
-
2024-07-
|
|
|
1 |
timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
|
2 |
+
2024-07-25T20:07:05,71cb2d14-a3e9-44f2-9adf-aa99d60af3f0,codecarbon,6487.100156784058,0.3647758733647877,0.5427331623606918,United Kingdom,GBR,scotland,N,,
|
runs/Jul25_18-18-54_msc-modeltrain-pod/events.out.tfevents.1721931538.msc-modeltrain-pod.1693.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47731826fc06887da5057a09bf903796b3bbbc0d7f41bc931c955955d7dffb8e
|
3 |
+
size 17035
|
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:fa99f7e0c9cee069a0ee479ad9d6186ca6da7c27642e43b0a7cf82a3fc09d7e6
|
3 |
size 4984
|