Casper0508
commited on
Commit
•
5fbf70f
1
Parent(s):
ebed6c7
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](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -64,31 +64,31 @@ The following hyperparameters were used during training:
|
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|
|
67 |
-
| 3.
|
68 |
-
| 2.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
|
93 |
|
94 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7698
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|
|
67 |
+
| 3.7636 | 1.36 | 10 | 3.3566 |
|
68 |
+
| 2.8254 | 2.71 | 20 | 2.0280 |
|
69 |
+
| 1.5642 | 4.07 | 30 | 1.2681 |
|
70 |
+
| 1.1877 | 5.42 | 40 | 1.1017 |
|
71 |
+
| 1.0503 | 6.78 | 50 | 1.0240 |
|
72 |
+
| 0.9732 | 8.14 | 60 | 0.9786 |
|
73 |
+
| 0.9065 | 9.49 | 70 | 0.9394 |
|
74 |
+
| 0.8513 | 10.85 | 80 | 0.9004 |
|
75 |
+
| 0.7914 | 12.2 | 90 | 0.8791 |
|
76 |
+
| 0.7408 | 13.56 | 100 | 0.8509 |
|
77 |
+
| 0.6882 | 14.92 | 110 | 0.8191 |
|
78 |
+
| 0.6389 | 16.27 | 120 | 0.7877 |
|
79 |
+
| 0.5855 | 17.63 | 130 | 0.7748 |
|
80 |
+
| 0.5293 | 18.98 | 140 | 0.7502 |
|
81 |
+
| 0.4876 | 20.34 | 150 | 0.7337 |
|
82 |
+
| 0.4619 | 21.69 | 160 | 0.7275 |
|
83 |
+
| 0.4458 | 23.05 | 170 | 0.7315 |
|
84 |
+
| 0.4287 | 24.41 | 180 | 0.7475 |
|
85 |
+
| 0.434 | 25.76 | 190 | 0.7489 |
|
86 |
+
| 0.4186 | 27.12 | 200 | 0.7573 |
|
87 |
+
| 0.4158 | 28.47 | 210 | 0.7618 |
|
88 |
+
| 0.4105 | 29.83 | 220 | 0.7719 |
|
89 |
+
| 0.4039 | 31.19 | 230 | 0.7677 |
|
90 |
+
| 0.4087 | 32.54 | 240 | 0.7692 |
|
91 |
+
| 0.4078 | 33.9 | 250 | 0.7698 |
|
92 |
|
93 |
|
94 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -8,7 +8,7 @@
|
|
8 |
"layers_pattern": null,
|
9 |
"layers_to_transform": null,
|
10 |
"lora_alpha": 64,
|
11 |
-
"lora_dropout": 0.
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
"r": 32,
|
|
|
8 |
"layers_pattern": null,
|
9 |
"layers_to_transform": null,
|
10 |
"lora_alpha": 64,
|
11 |
+
"lora_dropout": 0.3,
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
"r": 32,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 75523312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2396fd1095bb4c7827c0b91569b26ee5a0da7c1bc67d4316e1ed3125d0412e8c
|
3 |
size 75523312
|
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 |
+
2024-07-17T22:00:54,d57424a2-3051-45e7-aa21-4122e466d370,codecarbon,1337.6511194705963,0.0797943164549178,0.11872227543042274,United Kingdom,GBR,scotland,N,,
|
runs/Jul17_21-38-32_msc-modeltrain-pod/events.out.tfevents.1721252316.msc-modeltrain-pod.4064.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a499cb40b2ffb68fb419ee2947907e88110548e71bc461625835eda838a3b37a
|
3 |
+
size 17467
|
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 sha256:7c5748d207260224e60fd82bd6da0e65c6d55013cba7f3cac16494bfcf932da6
|
3 |
size 4984
|