Commit
•
e88703d
1
Parent(s):
3e9e86d
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: 1.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -32,20 +32,6 @@ More information needed
|
|
32 |
|
33 |
## Training procedure
|
34 |
|
35 |
-
|
36 |
-
The following `bitsandbytes` quantization config was used during training:
|
37 |
-
- quant_method: bitsandbytes
|
38 |
-
- _load_in_8bit: False
|
39 |
-
- _load_in_4bit: True
|
40 |
-
- llm_int8_threshold: 6.0
|
41 |
-
- llm_int8_skip_modules: None
|
42 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
43 |
-
- llm_int8_has_fp16_weight: False
|
44 |
-
- bnb_4bit_quant_type: nf4
|
45 |
-
- bnb_4bit_use_double_quant: True
|
46 |
-
- bnb_4bit_compute_dtype: bfloat16
|
47 |
-
- load_in_4bit: True
|
48 |
-
- load_in_8bit: False
|
49 |
### Training hyperparameters
|
50 |
|
51 |
The following hyperparameters were used during training:
|
@@ -64,31 +50,31 @@ The following hyperparameters were used during training:
|
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|
|
67 |
-
| 3.
|
68 |
-
| 1.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
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-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: 1.5909
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
32 |
|
33 |
## Training procedure
|
34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 3.3698 | 1.36 | 10 | 2.0432 |
|
54 |
+
| 1.3777 | 2.71 | 20 | 1.0067 |
|
55 |
+
| 0.8126 | 4.07 | 30 | 0.7822 |
|
56 |
+
| 0.6642 | 5.42 | 40 | 0.7281 |
|
57 |
+
| 0.5708 | 6.78 | 50 | 0.7218 |
|
58 |
+
| 0.5062 | 8.14 | 60 | 0.7360 |
|
59 |
+
| 0.4379 | 9.49 | 70 | 0.7781 |
|
60 |
+
| 0.3924 | 10.85 | 80 | 0.8310 |
|
61 |
+
| 0.3435 | 12.2 | 90 | 0.8856 |
|
62 |
+
| 0.3041 | 13.56 | 100 | 1.0389 |
|
63 |
+
| 0.2787 | 14.92 | 110 | 1.0664 |
|
64 |
+
| 0.2553 | 16.27 | 120 | 1.1655 |
|
65 |
+
| 0.2388 | 17.63 | 130 | 1.2397 |
|
66 |
+
| 0.2288 | 18.98 | 140 | 1.2049 |
|
67 |
+
| 0.2128 | 20.34 | 150 | 1.2746 |
|
68 |
+
| 0.2081 | 21.69 | 160 | 1.3889 |
|
69 |
+
| 0.1998 | 23.05 | 170 | 1.3942 |
|
70 |
+
| 0.1909 | 24.41 | 180 | 1.4383 |
|
71 |
+
| 0.188 | 25.76 | 190 | 1.5012 |
|
72 |
+
| 0.1841 | 27.12 | 200 | 1.5246 |
|
73 |
+
| 0.18 | 28.47 | 210 | 1.5528 |
|
74 |
+
| 0.1794 | 29.83 | 220 | 1.5662 |
|
75 |
+
| 0.1773 | 31.19 | 230 | 1.5788 |
|
76 |
+
| 0.1751 | 32.54 | 240 | 1.5889 |
|
77 |
+
| 0.1756 | 33.9 | 250 | 1.5909 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151020944
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9382c10b3a9a99504ecf742898b679ee9fc30cdb63e8d8ff5303808f175af02
|
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 |
+
2024-07-29T17:37:10,0935c600-22ba-4896-8b40-c37f98e81ea9,codecarbon,653.414971113205,0.03352802686025582,0.04988480152957785,United Kingdom,GBR,scotland,N,,
|
runs/Jul29_17-26-10_msc-modeltrain-pod/events.out.tfevents.1722273977.msc-modeltrain-pod.12449.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21307b2f5d605047cf945e79efa0883a46ce843dd6d3f0e797c3b0b901fc2b89
|
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 sha256:6b0e981c0bd2c889d8920b8e3a15191e82ae2084b87be9b4415afb23e05669c4
|
3 |
size 4984
|