Commit
•
4c5deca
1
Parent(s):
beceece
Model save
Browse files- README.md +2 -2
- all_results.json +7 -7
- eval_results.json +4 -4
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- runs/Nov18_08-54-00_j004-ds/events.out.tfevents.1700319321.j004-ds.1903041.0 +3 -0
- runs/Nov18_08-54-00_j004-ds/events.out.tfevents.1700320817.j004-ds.1903041.1 +3 -0
- train_results.json +3 -3
- trainer_state.json +13 -13
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
| 1.
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.0683
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 1.0771 | 0.26 | 31 | 1.0666 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 0.26,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 6.
|
5 |
"eval_samples": 1000,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 1.
|
8 |
-
"train_loss": 1.
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 61966,
|
11 |
-
"train_samples_per_second": 41.
|
12 |
"train_steps_per_second": 0.081
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.26,
|
3 |
+
"eval_loss": 1.0683468580245972,
|
4 |
+
"eval_runtime": 6.6188,
|
5 |
"eval_samples": 1000,
|
6 |
+
"eval_samples_per_second": 151.085,
|
7 |
+
"eval_steps_per_second": 1.209,
|
8 |
+
"train_loss": 1.2071462215915802,
|
9 |
+
"train_runtime": 1490.1678,
|
10 |
"train_samples": 61966,
|
11 |
+
"train_samples_per_second": 41.583,
|
12 |
"train_steps_per_second": 0.081
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.26,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 6.
|
5 |
"eval_samples": 1000,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.26,
|
3 |
+
"eval_loss": 1.0683468580245972,
|
4 |
+
"eval_runtime": 6.6188,
|
5 |
"eval_samples": 1000,
|
6 |
+
"eval_samples_per_second": 151.085,
|
7 |
+
"eval_steps_per_second": 1.209
|
8 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9807e76613b2db37f0898e9a732f39ec4491d65735a97423d0e7bfed386b4ef
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e0abde6f22f4baadb136891b425b532d77c7c8fc09a10d5dec6441ce659c73c
|
3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6a2b4b503bc04ae15796eba94e15b1a94a44bd44c594d49015382134ee46383
|
3 |
size 4540516344
|
runs/Nov18_08-54-00_j004-ds/events.out.tfevents.1700319321.j004-ds.1903041.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bd536d3a0a5002fcd2c3c04ba7087d35dc6518ad8005111094efab8ab7a9ef7
|
3 |
+
size 5921
|
runs/Nov18_08-54-00_j004-ds/events.out.tfevents.1700320817.j004-ds.1903041.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8eb2163a1dc8a6abd142d51a2b57573820d34fec8b39027c452e7cc1d2bffbe6
|
3 |
+
size 354
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.26,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 61966,
|
6 |
-
"train_samples_per_second": 41.
|
7 |
"train_steps_per_second": 0.081
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.26,
|
3 |
+
"train_loss": 1.2071462215915802,
|
4 |
+
"train_runtime": 1490.1678,
|
5 |
"train_samples": 61966,
|
6 |
+
"train_samples_per_second": 41.583,
|
7 |
"train_steps_per_second": 0.081
|
8 |
}
|
trainer_state.json
CHANGED
@@ -23,55 +23,55 @@
|
|
23 |
{
|
24 |
"epoch": 0.08,
|
25 |
"learning_rate": 1.966483553946637e-05,
|
26 |
-
"loss": 1.
|
27 |
"step": 10
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.12,
|
31 |
"learning_rate": 1.9251166435386837e-05,
|
32 |
-
"loss": 1.
|
33 |
"step": 15
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.16,
|
37 |
"learning_rate": 1.868180920098644e-05,
|
38 |
-
"loss": 1.
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.21,
|
43 |
"learning_rate": 1.796634556457236e-05,
|
44 |
-
"loss": 1.
|
45 |
"step": 25
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.25,
|
49 |
"learning_rate": 1.7116816083045603e-05,
|
50 |
-
"loss": 1.
|
51 |
"step": 30
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.26,
|
55 |
-
"eval_loss": 1.
|
56 |
-
"eval_runtime": 6.
|
57 |
-
"eval_samples_per_second":
|
58 |
-
"eval_steps_per_second": 1.
|
59 |
"step": 31
|
60 |
},
|
61 |
{
|
62 |
"epoch": 0.26,
|
63 |
"step": 31,
|
64 |
"total_flos": 50905428787200.0,
|
65 |
-
"train_loss": 1.
|
66 |
-
"train_runtime":
|
67 |
-
"train_samples_per_second": 41.
|
68 |
"train_steps_per_second": 0.081
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
72 |
"max_steps": 121,
|
73 |
"num_train_epochs": 1,
|
74 |
-
"save_steps":
|
75 |
"total_flos": 50905428787200.0,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
|
|
23 |
{
|
24 |
"epoch": 0.08,
|
25 |
"learning_rate": 1.966483553946637e-05,
|
26 |
+
"loss": 1.3001,
|
27 |
"step": 10
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.12,
|
31 |
"learning_rate": 1.9251166435386837e-05,
|
32 |
+
"loss": 1.1836,
|
33 |
"step": 15
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.16,
|
37 |
"learning_rate": 1.868180920098644e-05,
|
38 |
+
"loss": 1.1287,
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.21,
|
43 |
"learning_rate": 1.796634556457236e-05,
|
44 |
+
"loss": 1.093,
|
45 |
"step": 25
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.25,
|
49 |
"learning_rate": 1.7116816083045603e-05,
|
50 |
+
"loss": 1.0771,
|
51 |
"step": 30
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.26,
|
55 |
+
"eval_loss": 1.0666340589523315,
|
56 |
+
"eval_runtime": 6.8061,
|
57 |
+
"eval_samples_per_second": 146.926,
|
58 |
+
"eval_steps_per_second": 1.175,
|
59 |
"step": 31
|
60 |
},
|
61 |
{
|
62 |
"epoch": 0.26,
|
63 |
"step": 31,
|
64 |
"total_flos": 50905428787200.0,
|
65 |
+
"train_loss": 1.2071462215915802,
|
66 |
+
"train_runtime": 1490.1678,
|
67 |
+
"train_samples_per_second": 41.583,
|
68 |
"train_steps_per_second": 0.081
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
72 |
"max_steps": 121,
|
73 |
"num_train_epochs": 1,
|
74 |
+
"save_steps": 50,
|
75 |
"total_flos": 50905428787200.0,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a76446f98f2efebc3742cb697a455c19f8e656d97426c4e9ce3a189d1b2c484c
|
3 |
size 5624
|