markat1/mistral-7binstruct-summary-100s
Browse files- README.md +37 -6
- adapter_config.json +1 -1
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -20,12 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
-
|
24 |
-
- eval_runtime: 34.7344
|
25 |
-
- eval_samples_per_second: 2.706
|
26 |
-
- eval_steps_per_second: 0.345
|
27 |
-
- epoch: 0.06
|
28 |
-
- step: 15
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -55,6 +50,42 @@ The following hyperparameters were used during training:
|
|
55 |
- lr_scheduler_warmup_steps: 0.03
|
56 |
- training_steps: 150
|
57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
### Framework versions
|
59 |
|
60 |
- PEFT 0.9.0
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.6323
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
50 |
- lr_scheduler_warmup_steps: 0.03
|
51 |
- training_steps: 150
|
52 |
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 2.5172 | 0.02 | 5 | 2.3926 |
|
58 |
+
| 2.2822 | 0.04 | 10 | 2.1537 |
|
59 |
+
| 2.1109 | 0.06 | 15 | 2.0087 |
|
60 |
+
| 1.8571 | 0.08 | 20 | 1.9020 |
|
61 |
+
| 1.8964 | 0.11 | 25 | 1.8310 |
|
62 |
+
| 1.7335 | 0.13 | 30 | 1.7901 |
|
63 |
+
| 1.7744 | 0.15 | 35 | 1.7607 |
|
64 |
+
| 1.8654 | 0.17 | 40 | 1.7396 |
|
65 |
+
| 1.7379 | 0.19 | 45 | 1.7235 |
|
66 |
+
| 1.7442 | 0.21 | 50 | 1.7113 |
|
67 |
+
| 1.6483 | 0.23 | 55 | 1.7011 |
|
68 |
+
| 1.7006 | 0.25 | 60 | 1.6919 |
|
69 |
+
| 1.6783 | 0.28 | 65 | 1.6833 |
|
70 |
+
| 1.6468 | 0.3 | 70 | 1.6754 |
|
71 |
+
| 1.6116 | 0.32 | 75 | 1.6678 |
|
72 |
+
| 1.5899 | 0.34 | 80 | 1.6605 |
|
73 |
+
| 1.7426 | 0.36 | 85 | 1.6538 |
|
74 |
+
| 1.7244 | 0.38 | 90 | 1.6491 |
|
75 |
+
| 1.6652 | 0.4 | 95 | 1.6457 |
|
76 |
+
| 1.7859 | 0.42 | 100 | 1.6422 |
|
77 |
+
| 1.5836 | 0.44 | 105 | 1.6395 |
|
78 |
+
| 1.6265 | 0.47 | 110 | 1.6374 |
|
79 |
+
| 1.5187 | 0.49 | 115 | 1.6358 |
|
80 |
+
| 1.5989 | 0.51 | 120 | 1.6345 |
|
81 |
+
| 1.684 | 0.53 | 125 | 1.6336 |
|
82 |
+
| 1.6257 | 0.55 | 130 | 1.6329 |
|
83 |
+
| 1.7211 | 0.57 | 135 | 1.6325 |
|
84 |
+
| 1.6235 | 0.59 | 140 | 1.6324 |
|
85 |
+
| 1.5885 | 0.61 | 145 | 1.6323 |
|
86 |
+
| 1.5885 | 0.64 | 150 | 1.6323 |
|
87 |
+
|
88 |
+
|
89 |
### Framework versions
|
90 |
|
91 |
- PEFT 0.9.0
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path":
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:080c32c9d89e81893201d215084cb22ab2f799026d585afbd68f47a470b902f4
|
3 |
+
size 54545360
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf7a5483a6ddb2a94c9643206dd99b771e6991fc0b125c048d43ce7d87461ad4
|
3 |
size 4920
|