Training in progress, step 23
Browse files- README.md +5 -5
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- config.json +29 -29
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- 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 the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 2.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -36,13 +36,13 @@ More information needed
|
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 1e-05
|
38 |
- train_batch_size: 1
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 0
|
41 |
- distributed_type: multi-GPU
|
42 |
-
- num_devices:
|
43 |
- gradient_accumulation_steps: 4
|
44 |
-
- total_train_batch_size:
|
45 |
-
- total_eval_batch_size:
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- training_steps: 1
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.3265
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 1e-05
|
38 |
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 2
|
40 |
- seed: 0
|
41 |
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 3
|
43 |
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 12
|
45 |
+
- total_eval_batch_size: 6
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- training_steps: 1
|
adapter_config.json
CHANGED
@@ -21,9 +21,9 @@
|
|
21 |
"target_modules": [
|
22 |
"down_proj",
|
23 |
"q_proj",
|
24 |
-
"gate_proj",
|
25 |
"v_proj",
|
26 |
-
"up_proj"
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM"
|
29 |
}
|
|
|
21 |
"target_modules": [
|
22 |
"down_proj",
|
23 |
"q_proj",
|
|
|
24 |
"v_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM"
|
29 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 281061608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0e683818f3737d3f621de0742433e36175dd01e4cc1fb3ba73043092a94748a
|
3 |
size 281061608
|
config.json
CHANGED
@@ -23,38 +23,38 @@
|
|
23 |
"rope_theta": 10000.0,
|
24 |
"sliding_window": 4096,
|
25 |
"thresholds": [
|
26 |
-
0.017051145434379578,
|
27 |
0.023069201037287712,
|
28 |
-
0.
|
29 |
-
0.
|
30 |
-
0.
|
31 |
-
0.
|
32 |
-
0.
|
33 |
-
0.
|
34 |
-
0.
|
35 |
-
0.
|
36 |
-
0.
|
37 |
-
0.
|
38 |
-
0.
|
39 |
-
0.
|
40 |
-
0.
|
41 |
-
0.
|
42 |
-
0.
|
43 |
-
0.
|
44 |
-
0.
|
45 |
-
0.
|
46 |
-
0.1995987892150879,
|
47 |
0.2196589708328247,
|
48 |
-
0.2196589708328247,
|
49 |
-
0.23169508576393127,
|
50 |
-
0.2357071191072464,
|
51 |
-
0.23370109498500824,
|
52 |
-
0.225677028298378,
|
53 |
-
0.22968906164169312,
|
54 |
-
0.225677028298378,
|
55 |
0.22768303751945496,
|
56 |
-
0.
|
57 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
],
|
59 |
"tie_word_embeddings": false,
|
60 |
"torch_dtype": "bfloat16",
|
|
|
23 |
"rope_theta": 10000.0,
|
24 |
"sliding_window": 4096,
|
25 |
"thresholds": [
|
|
|
26 |
0.023069201037287712,
|
27 |
+
0.03309928998351097,
|
28 |
+
0.04312938079237938,
|
29 |
+
0.05516548827290535,
|
30 |
+
0.07522567361593246,
|
31 |
+
0.09327983111143112,
|
32 |
+
0.10531593859195709,
|
33 |
+
0.11935807019472122,
|
34 |
+
0.12738214433193207,
|
35 |
+
0.12738214433193207,
|
36 |
+
0.1313941776752472,
|
37 |
+
0.13340020179748535,
|
38 |
+
0.13941824436187744,
|
39 |
+
0.1414242684841156,
|
40 |
+
0.15546639263629913,
|
41 |
+
0.1675025075674057,
|
42 |
+
0.18555666506290436,
|
43 |
+
0.19157472252845764,
|
44 |
+
0.20762285590171814,
|
|
|
45 |
0.2196589708328247,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
0.22768303751945496,
|
47 |
+
0.23771312832832336,
|
48 |
+
0.2357071191072464,
|
49 |
+
0.23771312832832336,
|
50 |
+
0.24172517657279968,
|
51 |
+
0.24172517657279968,
|
52 |
+
0.24172517657279968,
|
53 |
+
0.24172517657279968,
|
54 |
+
0.24172517657279968,
|
55 |
+
0.23971915245056152,
|
56 |
+
0.2357071191072464,
|
57 |
+
0.225677028298378
|
58 |
],
|
59 |
"tie_word_embeddings": false,
|
60 |
"torch_dtype": "bfloat16",
|
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:c33a22761a44ac1bbfcc481e6fa0d5aa9022678c6ccfdac9e824e1e36d01fff9
|
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 sha256:3d22bcdd4a37d68894daa852415cc04d78cfb3a342c02f8e1487315fc33815bb
|
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 sha256:7412e818b679a6d0013cf994db7d8970df225f83a5e429609d2ebf32a832ec8d
|
3 |
size 4540516344
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6456
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62a9254f9424d6ed8aeff2636f645b370874f626a656b2e2b79b552c0a30f8ed
|
3 |
size 6456
|