Casper0508
commited on
Commit
•
ebed6c7
1
Parent(s):
78294d5
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 |
|
@@ -50,10 +50,10 @@ The following `bitsandbytes` quantization config was used during training:
|
|
50 |
|
51 |
The following hyperparameters were used during training:
|
52 |
- learning_rate: 5e-05
|
53 |
-
- train_batch_size:
|
54 |
- eval_batch_size: 8
|
55 |
- seed: 42
|
56 |
-
- gradient_accumulation_steps:
|
57 |
- total_train_batch_size: 64
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: cosine
|
@@ -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: 0.7284
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
50 |
|
51 |
The following hyperparameters were used during training:
|
52 |
- learning_rate: 5e-05
|
53 |
+
- train_batch_size: 8
|
54 |
- eval_batch_size: 8
|
55 |
- seed: 42
|
56 |
+
- gradient_accumulation_steps: 8
|
57 |
- total_train_batch_size: 64
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: cosine
|
|
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|
|
67 |
+
| 3.7573 | 1.36 | 10 | 3.3722 |
|
68 |
+
| 2.8144 | 2.71 | 20 | 2.0325 |
|
69 |
+
| 1.5867 | 4.07 | 30 | 1.2586 |
|
70 |
+
| 1.1875 | 5.42 | 40 | 1.0898 |
|
71 |
+
| 1.0487 | 6.78 | 50 | 1.0168 |
|
72 |
+
| 0.9716 | 8.14 | 60 | 0.9688 |
|
73 |
+
| 0.9134 | 9.49 | 70 | 0.9304 |
|
74 |
+
| 0.8505 | 10.85 | 80 | 0.8940 |
|
75 |
+
| 0.7963 | 12.2 | 90 | 0.8640 |
|
76 |
+
| 0.7497 | 13.56 | 100 | 0.8379 |
|
77 |
+
| 0.7067 | 14.92 | 110 | 0.8080 |
|
78 |
+
| 0.6484 | 16.27 | 120 | 0.7751 |
|
79 |
+
| 0.5945 | 17.63 | 130 | 0.7385 |
|
80 |
+
| 0.5349 | 18.98 | 140 | 0.6990 |
|
81 |
+
| 0.4854 | 20.34 | 150 | 0.6956 |
|
82 |
+
| 0.4729 | 21.69 | 160 | 0.6990 |
|
83 |
+
| 0.4496 | 23.05 | 170 | 0.6885 |
|
84 |
+
| 0.4405 | 24.41 | 180 | 0.7089 |
|
85 |
+
| 0.435 | 25.76 | 190 | 0.7215 |
|
86 |
+
| 0.4243 | 27.12 | 200 | 0.7162 |
|
87 |
+
| 0.418 | 28.47 | 210 | 0.7205 |
|
88 |
+
| 0.4156 | 29.83 | 220 | 0.7296 |
|
89 |
+
| 0.4153 | 31.19 | 230 | 0.7275 |
|
90 |
+
| 0.4146 | 32.54 | 240 | 0.7292 |
|
91 |
+
| 0.4094 | 33.9 | 250 | 0.7284 |
|
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": 0.2,
|
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:dcd4cce18bd06fc14145a73cf25cd3cab8a326057bc4fba56c7d5e68c2670d70
|
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 |
+
2024-07-17T21:26:16,875bb1fb-55b3-4654-806d-76f2ddaca959,codecarbon,1335.8051824569702,0.07996877307198384,0.1189818413677245,United Kingdom,GBR,scotland,N,,
|
runs/Jul17_21-03-56_msc-modeltrain-pod/events.out.tfevents.1721250240.msc-modeltrain-pod.3569.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84044fa5e8f3c3e61b99b3d2f370c81abeb4740e93268e34f7384e7720a962c2
|
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 sha256:1f116e75b2c681e3d8ef6631a40874a06edfdccef281260daae484fdda3bebfd
|
3 |
size 4984
|