Hugging Face's logo

AmberYifan
/
mistral-sft4epoch-spin-v

Safetensors
mistral
Generated from Trainer
Model card Files Community
AmberYifan commited on
Commit
35bbf69
•
1 Parent(s): d045310

Model save

Browse files
Files changed (8) hide show
  1. README.md +24 -16
  2. all_results.json +4 -4
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
  6. train_results.json +4 -4
  7. trainer_state.json +0 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -15,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [AmberYifan/mistral-safe-sft-full](https://huggingface.co/AmberYifan/mistral-safe-sft-full) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.2295
19
- - Rewards/real: 10.1264
20
- - Rewards/generated: -5.0006
21
- - Rewards/accuracies: 0.9922
22
- - Rewards/margins: 15.1270
23
- - Logps/generated: -128.7231
24
- - Logps/real: -111.4173
25
- - Logits/generated: -2.7320
26
- - Logits/real: -2.7332
27
 
28
  ## Model description
29
 
@@ -59,13 +59,21 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
61
  |:-------------:|:------:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
62
- | 0.2262 | 0.1280 | 200 | 0.2435 | 9.5632 | -4.7644 | 0.9922 | 14.3276 | -126.3612 | -117.0495 | -2.8333 | -2.8265 |
63
- | 0.2141 | 0.2559 | 400 | 0.2357 | 9.8979 | -4.9468 | 0.9922 | 14.8447 | -128.1855 | -113.7022 | -2.7752 | -2.7613 |
64
- | 0.2089 | 0.3839 | 600 | 0.2341 | 10.0245 | -4.8956 | 0.9922 | 14.9201 | -127.6730 | -112.4365 | -2.7914 | -2.7984 |
65
- | 0.2148 | 0.5118 | 800 | 0.2309 | 10.0410 | -5.0904 | 0.9922 | 15.1314 | -129.6210 | -112.2710 | -2.8195 | -2.8238 |
66
- | 0.1994 | 0.6398 | 1000 | 0.2303 | 10.1131 | -5.1876 | 0.9922 | 15.3008 | -130.5933 | -111.5497 | -2.7442 | -2.7461 |
67
- | 0.2075 | 0.7678 | 1200 | 0.2304 | 10.1155 | -4.9679 | 0.9922 | 15.0834 | -128.3958 | -111.5260 | -2.7360 | -2.7372 |
68
- | 0.1961 | 0.8957 | 1400 | 0.2295 | 10.1264 | -5.0006 | 0.9922 | 15.1270 | -128.7231 | -111.4173 | -2.7320 | -2.7332 |
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [AmberYifan/mistral-safe-sft-full](https://huggingface.co/AmberYifan/mistral-safe-sft-full) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.2284
19
+ - Rewards/real: 10.1344
20
+ - Rewards/generated: -5.3158
21
+ - Rewards/accuracies: 1.0
22
+ - Rewards/margins: 15.4503
23
+ - Logps/generated: -131.8755
24
+ - Logps/real: -111.3366
25
+ - Logits/generated: -2.7694
26
+ - Logits/real: -2.7499
27
 
28
  ## Model description
29
 
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
61
  |:-------------:|:------:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
62
+ | 0.278 | 0.0640 | 100 | 0.2703 | 8.6366 | -3.4251 | 0.9922 | 12.0617 | -112.9675 | -126.3148 | -2.9055 | -2.8963 |
63
+ | 0.2283 | 0.1280 | 200 | 0.2438 | 9.5699 | -4.6271 | 0.9922 | 14.1970 | -124.9880 | -116.9817 | -2.8308 | -2.8192 |
64
+ | 0.2284 | 0.1919 | 300 | 0.2384 | 9.7849 | -5.0781 | 0.9922 | 14.8630 | -129.4981 | -114.8321 | -2.8396 | -2.8204 |
65
+ | 0.2154 | 0.2559 | 400 | 0.2361 | 9.8971 | -4.8914 | 0.9922 | 14.7885 | -127.6311 | -113.7101 | -2.8303 | -2.8085 |
66
+ | 0.2368 | 0.3199 | 500 | 0.2351 | 9.9762 | -5.0488 | 0.9922 | 15.0249 | -129.2045 | -112.9195 | -2.8228 | -2.8083 |
67
+ | 0.2065 | 0.3839 | 600 | 0.2346 | 10.0426 | -4.9610 | 0.9922 | 15.0035 | -128.3267 | -112.2554 | -2.8204 | -2.8086 |
68
+ | 0.2244 | 0.4479 | 700 | 0.2317 | 10.0417 | -5.1299 | 1.0 | 15.1716 | -130.0162 | -112.2640 | -2.8203 | -2.8076 |
69
+ | 0.2161 | 0.5118 | 800 | 0.2297 | 10.0737 | -5.0565 | 1.0 | 15.1303 | -129.2824 | -111.9440 | -2.8437 | -2.8337 |
70
+ | 0.2127 | 0.5758 | 900 | 0.2302 | 10.0913 | -5.0905 | 1.0 | 15.1818 | -129.6217 | -111.7683 | -2.8251 | -2.8150 |
71
+ | 0.2017 | 0.6398 | 1000 | 0.2298 | 10.1245 | -5.2627 | 1.0 | 15.3872 | -131.3441 | -111.4362 | -2.7955 | -2.7831 |
72
+ | 0.2152 | 0.7038 | 1100 | 0.2297 | 10.0889 | -5.3503 | 1.0 | 15.4392 | -132.2204 | -111.7925 | -2.7790 | -2.7609 |
73
+ | 0.2074 | 0.7678 | 1200 | 0.2298 | 10.1143 | -5.3204 | 1.0 | 15.4346 | -131.9209 | -111.5385 | -2.7919 | -2.7734 |
74
+ | 0.2107 | 0.8317 | 1300 | 0.2287 | 10.1349 | -5.3137 | 1.0 | 15.4486 | -131.8539 | -111.3324 | -2.7734 | -2.7524 |
75
+ | 0.1947 | 0.8957 | 1400 | 0.2288 | 10.1265 | -5.3252 | 1.0 | 15.4517 | -131.9686 | -111.4160 | -2.7803 | -2.7613 |
76
+ | 0.2056 | 0.9597 | 1500 | 0.2284 | 10.1344 | -5.3158 | 1.0 | 15.4503 | -131.8755 | -111.3366 | -2.7694 | -2.7499 |
77
 
78
 
79
  ### Framework versions
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.2369839982275618,
5
- "train_runtime": 14627.5004,
6
  "train_samples": 50000,
7
- "train_samples_per_second": 3.418,
8
- "train_steps_per_second": 0.107
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.2371997828675781,
5
+ "train_runtime": 22626.3768,
6
  "train_samples": 50000,
7
+ "train_samples_per_second": 2.21,
8
+ "train_steps_per_second": 0.069
9
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd5ea129095888cb61488bc07d35d63d84d7cf0bc0409fa6a52f4146d1f89d70
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a1942bd55858075b25eb0470befcb6e04ff14f6348397bd2f4fd3752d7c466
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3100e9507b53654435a038b246801d40460deeefe5053c7aba1ec51b782f6da7
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ed86f263a377ae2dabfe1bbae67be544df8a898ded8d30fd221a6b97796387
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:147425527a55cd4bd43c159541ee784cc529fd3ec109e5f5637b1d4f27661e0d
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34bed1a0fb09ea859275db026a93e7fb10f9c943cbd229730a1c7bbb68edc72b
3
  size 4540516344
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.2369839982275618,
5
- "train_runtime": 14627.5004,
6
  "train_samples": 50000,
7
- "train_samples_per_second": 3.418,
8
- "train_steps_per_second": 0.107
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.2371997828675781,
5
+ "train_runtime": 22626.3768,
6
  "train_samples": 50000,
7
+ "train_samples_per_second": 2.21,
8
+ "train_steps_per_second": 0.069
9
  }
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:bb7fef3b5009cc84957ac24fdaf5b48719cef4feeb03a35b7e54145637e04ac8
3
  size 6392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5dc1a07b1f0e5b9bb9903ddc99a2a4669946e91f2f63904650bc346746a90b
3
  size 6392