Model save
Browse files- README.md +38 -37
- all_results.json +17 -4
- eval_results.json +16 -0
- model.safetensors +1 -1
- runs/Oct05_10-19-21_xe8545-a100-14/events.out.tfevents.1728129481.xe8545-a100-14.960812.1 +3 -0
- runs/Oct06_18-38-13_xe8545-a100-22/events.out.tfevents.1728233315.xe8545-a100-22.2425886.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,6 +3,7 @@ library_name: transformers
|
|
3 |
tags:
|
4 |
- trl
|
5 |
- dpo
|
|
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: OpenELM-1_1B-DPO-full-max-6-reward
|
@@ -16,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model was trained from scratch on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 1.
|
20 |
-
- Rewards/chosen: -
|
21 |
-
- Rewards/rejected: -
|
22 |
-
- Rewards/accuracies: 0.
|
23 |
-
- Rewards/margins: 1.
|
24 |
-
- Logps/rejected: -
|
25 |
-
- Logps/chosen: -
|
26 |
-
- Logits/rejected:
|
27 |
-
- Logits/chosen:
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -61,34 +62,34 @@ The following hyperparameters were used during training:
|
|
61 |
|
62 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
63 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
|
93 |
|
94 |
### Framework versions
|
|
|
3 |
tags:
|
4 |
- trl
|
5 |
- dpo
|
6 |
+
- alignment-handbook
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: OpenELM-1_1B-DPO-full-max-6-reward
|
|
|
17 |
|
18 |
This model was trained from scratch on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.8412
|
21 |
+
- Rewards/chosen: -15.5625
|
22 |
+
- Rewards/rejected: -17.375
|
23 |
+
- Rewards/accuracies: 0.6035
|
24 |
+
- Rewards/margins: 1.7891
|
25 |
+
- Logps/rejected: -2024.0
|
26 |
+
- Logps/chosen: -1872.0
|
27 |
+
- Logits/rejected: 1.625
|
28 |
+
- Logits/chosen: -0.2451
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
+
| 0.5954 | 0.1047 | 100 | 0.6902 | -1.1172 | -1.2578 | 0.5742 | 0.1416 | -414.0 | -430.0 | -10.75 | -11.0625 |
|
66 |
+
| 0.5396 | 0.2094 | 200 | 0.6928 | -2.5156 | -2.8594 | 0.6387 | 0.3438 | -576.0 | -572.0 | -9.6875 | -10.25 |
|
67 |
+
| 0.5587 | 0.3141 | 300 | 0.7014 | -3.7188 | -4.1562 | 0.6094 | 0.4355 | -704.0 | -692.0 | -8.5625 | -9.4375 |
|
68 |
+
| 0.5067 | 0.4188 | 400 | 0.7869 | -3.875 | -4.375 | 0.5996 | 0.4961 | -724.0 | -708.0 | -14.0 | -14.9375 |
|
69 |
+
| 0.525 | 0.5236 | 500 | 0.8500 | -4.625 | -5.3438 | 0.6094 | 0.7109 | -824.0 | -780.0 | -6.8438 | -8.25 |
|
70 |
+
| 0.5173 | 0.6283 | 600 | 0.7292 | -6.25 | -6.7188 | 0.5723 | 0.4688 | -960.0 | -944.0 | -8.875 | -10.0 |
|
71 |
+
| 0.4944 | 0.7330 | 700 | 0.7881 | -5.1562 | -5.7812 | 0.6035 | 0.6445 | -868.0 | -832.0 | -6.4062 | -8.0 |
|
72 |
+
| 0.5113 | 0.8377 | 800 | 0.7106 | -4.7812 | -5.3438 | 0.6113 | 0.5586 | -824.0 | -796.0 | -9.4375 | -10.8125 |
|
73 |
+
| 0.4589 | 0.9424 | 900 | 0.8807 | -7.4375 | -8.1875 | 0.6094 | 0.7656 | -1112.0 | -1064.0 | -6.1875 | -8.125 |
|
74 |
+
| 0.1368 | 1.0471 | 1000 | 1.1006 | -8.375 | -9.4375 | 0.5879 | 1.0547 | -1232.0 | -1160.0 | -3.4531 | -5.375 |
|
75 |
+
| 0.138 | 1.1518 | 1100 | 1.0286 | -8.375 | -9.375 | 0.5977 | 0.9531 | -1224.0 | -1160.0 | -4.0938 | -5.9688 |
|
76 |
+
| 0.1376 | 1.2565 | 1200 | 1.0962 | -8.6875 | -9.75 | 0.6035 | 1.0312 | -1264.0 | -1192.0 | -1.2266 | -3.0781 |
|
77 |
+
| 0.1434 | 1.3613 | 1300 | 1.1220 | -9.375 | -10.5 | 0.5801 | 1.1172 | -1336.0 | -1256.0 | -3.7031 | -5.6875 |
|
78 |
+
| 0.1386 | 1.4660 | 1400 | 1.0638 | -9.4375 | -10.375 | 0.6230 | 0.9570 | -1328.0 | -1256.0 | -3.5 | -5.4688 |
|
79 |
+
| 0.1258 | 1.5707 | 1500 | 1.1923 | -10.5 | -11.75 | 0.6016 | 1.1953 | -1464.0 | -1368.0 | -2.4062 | -4.5625 |
|
80 |
+
| 0.1269 | 1.6754 | 1600 | 1.2009 | -9.4375 | -10.625 | 0.6074 | 1.1562 | -1352.0 | -1264.0 | -2.8438 | -5.2188 |
|
81 |
+
| 0.0967 | 1.7801 | 1700 | 1.1723 | -10.0 | -11.125 | 0.5996 | 1.0859 | -1400.0 | -1320.0 | -1.6328 | -3.6406 |
|
82 |
+
| 0.112 | 1.8848 | 1800 | 1.0807 | -9.75 | -10.75 | 0.5898 | 0.9805 | -1360.0 | -1296.0 | -2.5 | -4.5 |
|
83 |
+
| 0.1158 | 1.9895 | 1900 | 1.1470 | -10.875 | -12.0625 | 0.5938 | 1.2109 | -1496.0 | -1400.0 | -1.5391 | -3.5625 |
|
84 |
+
| 0.0172 | 2.0942 | 2000 | 1.6192 | -14.1875 | -15.6875 | 0.6055 | 1.5078 | -1864.0 | -1736.0 | 0.8438 | -1.1172 |
|
85 |
+
| 0.012 | 2.1990 | 2100 | 1.7070 | -14.6875 | -16.375 | 0.6016 | 1.6953 | -1928.0 | -1792.0 | 0.5117 | -1.4688 |
|
86 |
+
| 0.0145 | 2.3037 | 2200 | 1.6657 | -14.0625 | -15.625 | 0.5957 | 1.5547 | -1856.0 | -1728.0 | 0.6875 | -1.2891 |
|
87 |
+
| 0.0161 | 2.4084 | 2300 | 1.8217 | -15.5625 | -17.25 | 0.6035 | 1.7344 | -2016.0 | -1872.0 | 1.0 | -0.9141 |
|
88 |
+
| 0.0161 | 2.5131 | 2400 | 1.7852 | -15.0 | -16.625 | 0.6055 | 1.6641 | -1960.0 | -1824.0 | 1.6328 | -0.2471 |
|
89 |
+
| 0.0182 | 2.6178 | 2500 | 1.9600 | -16.25 | -18.125 | 0.5957 | 1.8125 | -2096.0 | -1952.0 | 1.7578 | -0.1089 |
|
90 |
+
| 0.0121 | 2.7225 | 2600 | 1.8076 | -15.125 | -16.875 | 0.6113 | 1.7656 | -1976.0 | -1832.0 | 1.4922 | -0.4238 |
|
91 |
+
| 0.016 | 2.8272 | 2700 | 1.8344 | -15.5 | -17.25 | 0.6055 | 1.7891 | -2016.0 | -1872.0 | 1.6016 | -0.2773 |
|
92 |
+
| 0.0144 | 2.9319 | 2800 | 1.8412 | -15.5625 | -17.375 | 0.6035 | 1.7891 | -2024.0 | -1872.0 | 1.625 | -0.2451 |
|
93 |
|
94 |
|
95 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,9 +1,22 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 61119,
|
7 |
-
"train_samples_per_second": 14.
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": 3.015625,
|
4 |
+
"eval_logits/rejected": 4.75,
|
5 |
+
"eval_logps/chosen": -1784.0,
|
6 |
+
"eval_logps/rejected": -1928.0,
|
7 |
+
"eval_loss": 1.839203119277954,
|
8 |
+
"eval_rewards/accuracies": 0.595703125,
|
9 |
+
"eval_rewards/chosen": -14.6875,
|
10 |
+
"eval_rewards/margins": 1.71875,
|
11 |
+
"eval_rewards/rejected": -16.375,
|
12 |
+
"eval_runtime": 46.9056,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 42.639,
|
15 |
+
"eval_steps_per_second": 0.682,
|
16 |
"total_flos": 0.0,
|
17 |
+
"train_loss": 0.22363413207193944,
|
18 |
+
"train_runtime": 12304.9,
|
19 |
"train_samples": 61119,
|
20 |
+
"train_samples_per_second": 14.901,
|
21 |
+
"train_steps_per_second": 0.233
|
22 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": 3.015625,
|
4 |
+
"eval_logits/rejected": 4.75,
|
5 |
+
"eval_logps/chosen": -1784.0,
|
6 |
+
"eval_logps/rejected": -1928.0,
|
7 |
+
"eval_loss": 1.839203119277954,
|
8 |
+
"eval_rewards/accuracies": 0.595703125,
|
9 |
+
"eval_rewards/chosen": -14.6875,
|
10 |
+
"eval_rewards/margins": 1.71875,
|
11 |
+
"eval_rewards/rejected": -16.375,
|
12 |
+
"eval_runtime": 46.9056,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 42.639,
|
15 |
+
"eval_steps_per_second": 0.682
|
16 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2159808696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde8085f5fc935e0166b933dad4ed4c22bfa1702ff312bd9b85cd0a8582aeee8
|
3 |
size 2159808696
|
runs/Oct05_10-19-21_xe8545-a100-14/events.out.tfevents.1728129481.xe8545-a100-14.960812.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3485f65d26a8df8b67fc932b28d6c0819dfc1c10ec963a33eea1de0d2329e824
|
3 |
+
size 828
|
runs/Oct06_18-38-13_xe8545-a100-22/events.out.tfevents.1728233315.xe8545-a100-22.2425886.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482f164e80096c75b7a397f83f1516669a8495bad7f69327209187761e0435a7
|
3 |
+
size 225707
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 61119,
|
7 |
-
"train_samples_per_second": 14.
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.22363413207193944,
|
5 |
+
"train_runtime": 12304.9,
|
6 |
"train_samples": 61119,
|
7 |
+
"train_samples_per_second": 14.901,
|
8 |
+
"train_steps_per_second": 0.233
|
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:
|
3 |
size 7672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:547a123c1713088e9e5b6c28a6e2a133b83277b263db3cf075ce86652aa78afc
|
3 |
size 7672
|