Commit
•
aa08ade
1
Parent(s):
c80e762
Model save
Browse files- README.md +4 -5
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- all_results.json +7 -7
- eval_results.json +4 -4
- mm_projector.bin +3 -0
- train_results.json +3 -3
- trainer_state.json +11 -11
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,11 +2,10 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
- generated_from_trainer
|
7 |
base_model: mistralai/Mistral-7B-v0.1
|
8 |
datasets:
|
9 |
-
-
|
10 |
model-index:
|
11 |
- name: Test_with_new_script
|
12 |
results: []
|
@@ -17,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# Test_with_new_script
|
19 |
|
20 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -55,7 +54,7 @@ The following hyperparameters were used during training:
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
-
| 1.
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
base_model: mistralai/Mistral-7B-v0.1
|
7 |
datasets:
|
8 |
+
- generator
|
9 |
model-index:
|
10 |
- name: Test_with_new_script
|
11 |
results: []
|
|
|
16 |
|
17 |
# Test_with_new_script
|
18 |
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.9987
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 1.0053 | 1.0 | 22 | 0.9987 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"gate_proj",
|
23 |
-
"
|
24 |
"v_proj",
|
25 |
-
"k_proj",
|
26 |
"o_proj",
|
27 |
-
"
|
28 |
-
"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
"gate_proj",
|
24 |
+
"up_proj",
|
25 |
"v_proj",
|
|
|
26 |
"o_proj",
|
27 |
+
"down_proj",
|
28 |
+
"q_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83946192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e3290b10cd48b06f8e4c3717bcf1e5e588fbb91f09c87a04308168b73d4eb2
|
3 |
size 83946192
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_loss": 0.
|
4 |
-
"eval_runtime": 10.
|
5 |
"eval_samples": 154,
|
6 |
-
"eval_samples_per_second": 14.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"train_loss": 1.
|
9 |
-
"train_runtime": 330.
|
10 |
"train_samples": 1383,
|
11 |
-
"train_samples_per_second": 4.
|
12 |
"train_steps_per_second": 0.067
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.9987491965293884,
|
4 |
+
"eval_runtime": 10.4357,
|
5 |
"eval_samples": 154,
|
6 |
+
"eval_samples_per_second": 14.757,
|
7 |
+
"eval_steps_per_second": 0.958,
|
8 |
+
"train_loss": 1.0528897643089294,
|
9 |
+
"train_runtime": 330.7732,
|
10 |
"train_samples": 1383,
|
11 |
+
"train_samples_per_second": 4.181,
|
12 |
"train_steps_per_second": 0.067
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_loss": 0.
|
4 |
-
"eval_runtime": 10.
|
5 |
"eval_samples": 154,
|
6 |
-
"eval_samples_per_second": 14.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.9987491965293884,
|
4 |
+
"eval_runtime": 10.4357,
|
5 |
"eval_samples": 154,
|
6 |
+
"eval_samples_per_second": 14.757,
|
7 |
+
"eval_steps_per_second": 0.958
|
8 |
}
|
mm_projector.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45b9a8fa1054e5d16c0a47352800b7953c51d48a0adb004c95f427c7e37f6481
|
3 |
+
size 16795126
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime": 330.
|
5 |
"train_samples": 1383,
|
6 |
-
"train_samples_per_second": 4.
|
7 |
"train_steps_per_second": 0.067
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 1.0528897643089294,
|
4 |
+
"train_runtime": 330.7732,
|
5 |
"train_samples": 1383,
|
6 |
+
"train_samples_per_second": 4.181,
|
7 |
"train_steps_per_second": 0.067
|
8 |
}
|
trainer_state.json
CHANGED
@@ -17,42 +17,42 @@
|
|
17 |
{
|
18 |
"epoch": 0.23,
|
19 |
"learning_rate": 0.00019458172417006347,
|
20 |
-
"loss": 1.
|
21 |
"step": 5
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.45,
|
25 |
"learning_rate": 0.00014016954246529696,
|
26 |
-
"loss": 1.
|
27 |
"step": 10
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.68,
|
31 |
"learning_rate": 5.983045753470308e-05,
|
32 |
-
"loss": 1.
|
33 |
"step": 15
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.91,
|
37 |
"learning_rate": 5.418275829936537e-06,
|
38 |
-
"loss": 1.
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
42 |
"epoch": 1.0,
|
43 |
-
"eval_loss": 0.
|
44 |
-
"eval_runtime": 10.
|
45 |
-
"eval_samples_per_second": 14.
|
46 |
-
"eval_steps_per_second": 0.
|
47 |
"step": 22
|
48 |
},
|
49 |
{
|
50 |
"epoch": 1.0,
|
51 |
"step": 22,
|
52 |
"total_flos": 1.2907203290936115e+17,
|
53 |
-
"train_loss": 1.
|
54 |
-
"train_runtime": 330.
|
55 |
-
"train_samples_per_second": 4.
|
56 |
"train_steps_per_second": 0.067
|
57 |
}
|
58 |
],
|
|
|
17 |
{
|
18 |
"epoch": 0.23,
|
19 |
"learning_rate": 0.00019458172417006347,
|
20 |
+
"loss": 1.1528,
|
21 |
"step": 5
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.45,
|
25 |
"learning_rate": 0.00014016954246529696,
|
26 |
+
"loss": 1.0601,
|
27 |
"step": 10
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.68,
|
31 |
"learning_rate": 5.983045753470308e-05,
|
32 |
+
"loss": 1.0094,
|
33 |
"step": 15
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.91,
|
37 |
"learning_rate": 5.418275829936537e-06,
|
38 |
+
"loss": 1.0053,
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
42 |
"epoch": 1.0,
|
43 |
+
"eval_loss": 0.9987491965293884,
|
44 |
+
"eval_runtime": 10.4464,
|
45 |
+
"eval_samples_per_second": 14.742,
|
46 |
+
"eval_steps_per_second": 0.957,
|
47 |
"step": 22
|
48 |
},
|
49 |
{
|
50 |
"epoch": 1.0,
|
51 |
"step": 22,
|
52 |
"total_flos": 1.2907203290936115e+17,
|
53 |
+
"train_loss": 1.0528897643089294,
|
54 |
+
"train_runtime": 330.7732,
|
55 |
+
"train_samples_per_second": 4.181,
|
56 |
"train_steps_per_second": 0.067
|
57 |
}
|
58 |
],
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:451e31abe3ca5507ccd26609911512762408195c872245e20da2022bdd8ebc40
|
3 |
size 4856
|