Add HuggingFaceH4/mistral-7b-cai-v20.0.grokai.3.2 checkpoint
Browse files- README.md +15 -52
- all_results.json +12 -19
- config.json +1 -1
- eval_results.json +7 -14
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- special_tokens_map.json +1 -7
- train_results.json +6 -6
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,33 +1,25 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- alignment-handbook
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
-
- HuggingFaceH4/ultrafeedback_binarized_fixed
|
9 |
- HuggingFaceH4/grok-conversation-harmless
|
|
|
10 |
model-index:
|
11 |
-
- name: mistral-7b-
|
12 |
results: []
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
-
# mistral-7b-
|
19 |
|
20 |
-
This model is a fine-tuned version of [
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
-
- Rewards/chosen: -7.6611
|
24 |
-
- Rewards/rejected: -12.0970
|
25 |
-
- Rewards/accuracies: 0.6925
|
26 |
-
- Rewards/margins: 4.4359
|
27 |
-
- Logps/rejected: -310.5013
|
28 |
-
- Logps/chosen: -278.5390
|
29 |
-
- Logits/rejected: -2.1614
|
30 |
-
- Logits/chosen: -2.1988
|
31 |
|
32 |
## Model description
|
33 |
|
@@ -46,54 +38,25 @@ More information needed
|
|
46 |
### Training hyperparameters
|
47 |
|
48 |
The following hyperparameters were used during training:
|
49 |
-
- learning_rate:
|
50 |
-
- train_batch_size:
|
51 |
- eval_batch_size: 8
|
52 |
- seed: 42
|
53 |
- distributed_type: multi-GPU
|
54 |
- num_devices: 8
|
55 |
-
-
|
|
|
56 |
- total_eval_batch_size: 64
|
57 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
-
- lr_scheduler_type:
|
59 |
- lr_scheduler_warmup_ratio: 0.1
|
60 |
-
- num_epochs:
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
-
| Training Loss | Epoch | Step
|
65 |
-
|
66 |
-
| 0.
|
67 |
-
| 0.5024 | 0.19 | 800 | 0.5112 | -0.1278 | -1.0425 | 0.6675 | 0.9147 | -199.9562 | -203.2059 | -2.5093 | -2.5329 |
|
68 |
-
| 0.5728 | 0.29 | 1200 | 0.5324 | -0.7435 | -1.7880 | 0.6425 | 1.0445 | -207.4112 | -209.3627 | -2.4771 | -2.5058 |
|
69 |
-
| 0.7378 | 0.39 | 1600 | 0.5213 | -1.6390 | -2.9308 | 0.6650 | 1.2918 | -218.8383 | -218.3174 | -2.4237 | -2.4525 |
|
70 |
-
| 0.7467 | 0.48 | 2000 | 0.5788 | -2.2099 | -3.4247 | 0.6575 | 1.2148 | -223.7781 | -224.0264 | -2.4106 | -2.4441 |
|
71 |
-
| 0.4646 | 0.58 | 2400 | 0.5309 | -1.1360 | -2.6997 | 0.6500 | 1.5638 | -216.5279 | -213.2871 | -2.3683 | -2.3994 |
|
72 |
-
| 0.7454 | 0.67 | 2800 | 0.5290 | -1.9997 | -3.5594 | 0.6700 | 1.5597 | -225.1247 | -221.9242 | -2.4289 | -2.4575 |
|
73 |
-
| 0.6092 | 0.77 | 3200 | 0.5124 | -1.6120 | -3.1452 | 0.6850 | 1.5332 | -220.9823 | -218.0472 | -2.4755 | -2.5024 |
|
74 |
-
| 0.674 | 0.87 | 3600 | 0.5134 | -2.9907 | -4.6954 | 0.6750 | 1.7046 | -236.4846 | -231.8350 | -2.2564 | -2.2885 |
|
75 |
-
| 0.5585 | 0.96 | 4000 | 0.5065 | -2.5232 | -4.1851 | 0.6725 | 1.6619 | -231.3815 | -227.1594 | -2.3968 | -2.4273 |
|
76 |
-
| 0.0829 | 1.06 | 4400 | 0.5306 | -3.8333 | -6.1055 | 0.6950 | 2.2723 | -250.5862 | -240.2602 | -2.2149 | -2.2565 |
|
77 |
-
| 0.1383 | 1.16 | 4800 | 0.5432 | -3.8147 | -5.7333 | 0.6675 | 1.9186 | -246.8635 | -240.0743 | -2.3301 | -2.3643 |
|
78 |
-
| 0.1425 | 1.25 | 5200 | 0.5238 | -4.7732 | -7.0560 | 0.6650 | 2.2827 | -260.0906 | -249.6600 | -2.1705 | -2.2021 |
|
79 |
-
| 0.1053 | 1.35 | 5600 | 0.5298 | -4.8922 | -7.5361 | 0.6900 | 2.6439 | -264.8917 | -250.8497 | -2.2597 | -2.2978 |
|
80 |
-
| 0.1301 | 1.44 | 6000 | 0.5190 | -4.0353 | -6.5781 | 0.6850 | 2.5428 | -255.3118 | -242.2802 | -2.1606 | -2.1992 |
|
81 |
-
| 0.0789 | 1.54 | 6400 | 0.5184 | -4.6125 | -7.3571 | 0.6775 | 2.7446 | -263.1015 | -248.0527 | -2.2220 | -2.2593 |
|
82 |
-
| 0.1274 | 1.64 | 6800 | 0.5138 | -3.9081 | -6.5224 | 0.6650 | 2.6143 | -254.7549 | -241.0087 | -2.3238 | -2.3653 |
|
83 |
-
| 0.1095 | 1.73 | 7200 | 0.5153 | -4.1355 | -6.9746 | 0.6750 | 2.8392 | -259.2772 | -243.2823 | -2.2983 | -2.3396 |
|
84 |
-
| 0.1515 | 1.83 | 7600 | 0.5242 | -4.5052 | -7.4464 | 0.6625 | 2.9412 | -263.9946 | -246.9796 | -2.2513 | -2.2896 |
|
85 |
-
| 0.1152 | 1.93 | 8000 | 0.5280 | -4.5281 | -7.5632 | 0.6825 | 3.0351 | -265.1628 | -247.2084 | -2.2822 | -2.3185 |
|
86 |
-
| 0.0385 | 2.02 | 8400 | 0.5478 | -4.9592 | -8.1827 | 0.6800 | 3.2235 | -271.3580 | -251.5196 | -2.2850 | -2.3214 |
|
87 |
-
| 0.0401 | 2.12 | 8800 | 0.5999 | -6.1863 | -10.0632 | 0.6800 | 3.8769 | -290.1624 | -263.7904 | -2.1925 | -2.2326 |
|
88 |
-
| 0.0327 | 2.21 | 9200 | 0.6190 | -5.6591 | -9.4406 | 0.6925 | 3.7815 | -283.9365 | -258.5182 | -2.1369 | -2.1748 |
|
89 |
-
| 0.0425 | 2.31 | 9600 | 0.6298 | -7.3701 | -11.3769 | 0.6925 | 4.0068 | -303.3002 | -275.6286 | -2.1410 | -2.1775 |
|
90 |
-
| 0.0387 | 2.41 | 10000 | 0.6269 | -7.3259 | -11.5280 | 0.6975 | 4.2020 | -304.8104 | -275.1870 | -2.1791 | -2.2169 |
|
91 |
-
| 0.043 | 2.5 | 10400 | 0.6376 | -7.2239 | -11.5783 | 0.6925 | 4.3544 | -305.3137 | -274.1667 | -2.2301 | -2.2663 |
|
92 |
-
| 0.0577 | 2.6 | 10800 | 0.6290 | -7.6726 | -11.9683 | 0.6925 | 4.2956 | -309.2136 | -278.6540 | -2.1968 | -2.2342 |
|
93 |
-
| 0.019 | 2.7 | 11200 | 0.6260 | -7.2301 | -11.5298 | 0.6825 | 4.2997 | -304.8287 | -274.2284 | -2.1623 | -2.2006 |
|
94 |
-
| 0.0328 | 2.79 | 11600 | 0.6325 | -7.6096 | -12.0115 | 0.6950 | 4.4019 | -309.6460 | -278.0234 | -2.1388 | -2.1767 |
|
95 |
-
| 0.036 | 2.89 | 12000 | 0.6312 | -7.8237 | -12.2628 | 0.6900 | 4.4391 | -312.1590 | -280.1643 | -2.1641 | -2.2011 |
|
96 |
-
| 0.0216 | 2.98 | 12400 | 0.6283 | -7.6679 | -12.0919 | 0.6900 | 4.4240 | -310.4496 | -278.6061 | -2.1613 | -2.1986 |
|
97 |
|
98 |
|
99 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
4 |
tags:
|
5 |
- alignment-handbook
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
|
|
8 |
- HuggingFaceH4/grok-conversation-harmless
|
9 |
+
- HuggingFaceH4/ultrachat_200k
|
10 |
model-index:
|
11 |
+
- name: mistral-7b-ift-v20.0.grokai.3.2
|
12 |
results: []
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
+
# mistral-7b-ift-v20.0.grokai.3.2
|
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 HuggingFaceH4/grok-conversation-harmless and the HuggingFaceH4/ultrachat_200k datasets.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.9348
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 8
|
43 |
- eval_batch_size: 8
|
44 |
- seed: 42
|
45 |
- distributed_type: multi-GPU
|
46 |
- num_devices: 8
|
47 |
+
- gradient_accumulation_steps: 4
|
48 |
+
- total_train_batch_size: 256
|
49 |
- total_eval_batch_size: 64
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: cosine
|
52 |
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- num_epochs: 1
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
59 |
+
| 0.9326 | 1.0 | 545 | 0.9348 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,21 +1,14 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"eval_samples_per_second": 23.796,
|
15 |
-
"eval_steps_per_second": 0.377,
|
16 |
-
"train_loss": 0.24049862180692672,
|
17 |
-
"train_runtime": 20948.1804,
|
18 |
-
"train_samples": 82424,
|
19 |
-
"train_samples_per_second": 9.519,
|
20 |
-
"train_steps_per_second": 0.595
|
21 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.934799313545227,
|
4 |
+
"eval_runtime": 142.2532,
|
5 |
+
"eval_samples": 24266,
|
6 |
+
"eval_samples_per_second": 109.024,
|
7 |
+
"eval_steps_per_second": 1.708,
|
8 |
+
"perplexity": 2.5467023177917714,
|
9 |
+
"train_loss": 0.9725383741046311,
|
10 |
+
"train_runtime": 5277.8235,
|
11 |
+
"train_samples": 211055,
|
12 |
+
"train_samples_per_second": 26.46,
|
13 |
+
"train_steps_per_second": 0.103
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
eval_results.json
CHANGED
@@ -1,16 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"eval_rewards/chosen": -7.6611433029174805,
|
10 |
-
"eval_rewards/margins": 4.435902118682861,
|
11 |
-
"eval_rewards/rejected": -12.0970458984375,
|
12 |
-
"eval_runtime": 132.6261,
|
13 |
-
"eval_samples": 3156,
|
14 |
-
"eval_samples_per_second": 23.796,
|
15 |
-
"eval_steps_per_second": 0.377
|
16 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.934799313545227,
|
4 |
+
"eval_runtime": 142.2532,
|
5 |
+
"eval_samples": 24266,
|
6 |
+
"eval_samples_per_second": 109.024,
|
7 |
+
"eval_steps_per_second": 1.708,
|
8 |
+
"perplexity": 2.5467023177917714
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
}
|
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 sha256:1c8e5d6996e054b7c10c1f891947d59e5e462db78fc33252fa58424451d706ea
|
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:ed331b509cdee31d8323097ac2b434359b7d8fae383c530753695b221139108c
|
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 sha256:95a38af2f763dfd084506059d5663c66a2410432723f91502dc3d828cad3d822
|
3 |
size 4540516344
|
special_tokens_map.json
CHANGED
@@ -13,13 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
17 |
-
"content": "</s>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.9725383741046311,
|
4 |
+
"train_runtime": 5277.8235,
|
5 |
+
"train_samples": 211055,
|
6 |
+
"train_samples_per_second": 26.46,
|
7 |
+
"train_steps_per_second": 0.103
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6264
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97393c2a78f330ed3bfc7e5d7c10eb73f641d9d68463a042f14a4296fc7f29d8
|
3 |
size 6264
|