Hugging Face's logo

CharlesLi
/
OpenELM-1_1B-DPO-full-max-14-reward

Text Generation
Transformers
TensorBoard
Safetensors
openelm
trl
dpo
alignment-handbook
Generated from Trainer
conversational
custom_code
Model card Files Metrics Community
CharlesLi commited on
Commit
80c4adf
·
verified ·
1 Parent(s): f021d10

Model save

Browse files
Files changed (9) hide show
  1. README.md +38 -37
  2. all_results.json +17 -4
  3. eval_results.json +16 -0
  4. model.safetensors +1 -1
  5. runs/Oct05_14-26-22_xe8545-a100-15/events.out.tfevents.1728144965.xe8545-a100-15.1049253.1 +3 -0
  6. runs/Oct06_22-45-30_xe8545-a100-15/events.out.tfevents.1728248468.xe8545-a100-15.1088924.0 +3 -0
  7. train_results.json +4 -4
  8. trainer_state.json +0 -0
  9. 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-14-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: 1.1391
20
- - Rewards/chosen: -3.7969
21
- - Rewards/rejected: -4.2188
22
- - Rewards/accuracies: 0.5
23
- - Rewards/margins: 0.4238
24
- - Logps/rejected: -712.0
25
- - Logps/chosen: -696.0
26
- - Logits/rejected: -16.125
27
- - Logits/chosen: -16.375
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
- | 0.0531 | 0.1047 | 100 | 0.7024 | -1.0781 | -1.4297 | 0.5801 | 0.3477 | -432.0 | -426.0 | -9.6875 | -9.9375 |
65
- | 0.0523 | 0.2094 | 200 | 0.7657 | -1.1016 | -1.3125 | 0.5195 | 0.2061 | -420.0 | -428.0 | -13.9375 | -14.3125 |
66
- | 0.0716 | 0.3141 | 300 | 1.2495 | -2.9844 | -3.5156 | 0.5137 | 0.5391 | -640.0 | -616.0 | -13.5 | -13.9375 |
67
- | 0.0472 | 0.4188 | 400 | 0.8801 | -1.7344 | -1.9688 | 0.4961 | 0.2393 | -486.0 | -492.0 | -11.9375 | -12.3125 |
68
- | 0.0394 | 0.5236 | 500 | 0.9541 | -2.7812 | -2.9688 | 0.4922 | 0.1904 | -584.0 | -596.0 | -16.125 | -16.25 |
69
- | 0.0707 | 0.6283 | 600 | 0.8604 | -2.25 | -2.4375 | 0.4922 | 0.1934 | -532.0 | -544.0 | -14.9375 | -15.125 |
70
- | 0.045 | 0.7330 | 700 | 0.9378 | -3.0312 | -3.25 | 0.4863 | 0.2168 | -612.0 | -620.0 | -15.25 | -15.5 |
71
- | 0.0278 | 0.8377 | 800 | 0.9400 | -2.5156 | -2.6719 | 0.4863 | 0.1641 | -556.0 | -568.0 | -18.0 | -17.75 |
72
- | 0.018 | 0.9424 | 900 | 1.1675 | -3.8438 | -4.125 | 0.4902 | 0.2969 | -704.0 | -704.0 | -15.625 | -15.625 |
73
- | 0.0043 | 1.0471 | 1000 | 1.0828 | -3.5156 | -3.9531 | 0.4844 | 0.4336 | -684.0 | -672.0 | -14.25 | -14.4375 |
74
- | 0.0034 | 1.1518 | 1100 | 1.2924 | -4.9062 | -5.375 | 0.5020 | 0.4629 | -828.0 | -808.0 | -14.8125 | -14.9375 |
75
- | 0.0056 | 1.2565 | 1200 | 1.0445 | -3.6562 | -3.9062 | 0.4941 | 0.2412 | -680.0 | -684.0 | -17.25 | -17.125 |
76
- | 0.0049 | 1.3613 | 1300 | 1.0296 | -3.4062 | -3.6562 | 0.4883 | 0.2461 | -656.0 | -660.0 | -16.875 | -16.75 |
77
- | 0.0009 | 1.4660 | 1400 | 1.0903 | -3.8125 | -4.1875 | 0.4902 | 0.3828 | -708.0 | -700.0 | -16.625 | -16.625 |
78
- | 0.0026 | 1.5707 | 1500 | 0.9407 | -3.0781 | -3.3594 | 0.4980 | 0.2910 | -624.0 | -624.0 | -16.75 | -16.75 |
79
- | 0.0009 | 1.6754 | 1600 | 0.9907 | -3.3438 | -3.6719 | 0.4980 | 0.3418 | -656.0 | -652.0 | -16.75 | -17.0 |
80
- | 0.0078 | 1.7801 | 1700 | 0.9547 | -3.3281 | -3.625 | 0.4941 | 0.2910 | -652.0 | -652.0 | -12.5 | -12.75 |
81
- | 0.0022 | 1.8848 | 1800 | 0.9916 | -3.0 | -3.3281 | 0.4922 | 0.3281 | -620.0 | -616.0 | -15.5625 | -15.875 |
82
- | 0.0041 | 1.9895 | 1900 | 0.9828 | -2.8594 | -3.1562 | 0.5059 | 0.2969 | -604.0 | -604.0 | -16.125 | -16.25 |
83
- | 0.0002 | 2.0942 | 2000 | 1.0311 | -3.1562 | -3.4688 | 0.4961 | 0.3184 | -636.0 | -636.0 | -16.0 | -16.25 |
84
- | 0.0004 | 2.1990 | 2100 | 1.0823 | -3.4688 | -3.8438 | 0.5 | 0.3691 | -672.0 | -664.0 | -16.125 | -16.375 |
85
- | 0.0003 | 2.3037 | 2200 | 1.1156 | -3.625 | -4.0312 | 0.4941 | 0.4004 | -692.0 | -680.0 | -16.25 | -16.375 |
86
- | 0.0003 | 2.4084 | 2300 | 1.1278 | -3.7031 | -4.125 | 0.4980 | 0.4141 | -700.0 | -688.0 | -16.25 | -16.375 |
87
- | 0.0001 | 2.5131 | 2400 | 1.1339 | -3.7344 | -4.1562 | 0.5020 | 0.4180 | -704.0 | -692.0 | -16.25 | -16.5 |
88
- | 0.0001 | 2.6178 | 2500 | 1.1372 | -3.7656 | -4.1875 | 0.5020 | 0.4219 | -708.0 | -696.0 | -16.125 | -16.375 |
89
- | 0.0017 | 2.7225 | 2600 | 1.1389 | -3.7812 | -4.2188 | 0.5020 | 0.4219 | -708.0 | -696.0 | -16.125 | -16.375 |
90
- | 0.0002 | 2.8272 | 2700 | 1.1391 | -3.7812 | -4.2188 | 0.5059 | 0.4238 | -712.0 | -696.0 | -16.125 | -16.375 |
91
- | 0.0005 | 2.9319 | 2800 | 1.1391 | -3.7969 | -4.2188 | 0.5 | 0.4238 | -712.0 | -696.0 | -16.125 | -16.375 |
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-14-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: 1.1518
21
+ - Rewards/chosen: -4.0625
22
+ - Rewards/rejected: -4.5312
23
+ - Rewards/accuracies: 0.4980
24
+ - Rewards/margins: 0.4824
25
+ - Logps/rejected: -744.0
26
+ - Logps/chosen: -724.0
27
+ - Logits/rejected: -15.25
28
+ - Logits/chosen: -15.5625
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
+ | 0.05 | 0.1047 | 100 | 0.8594 | -2.0469 | -2.3906 | 0.5488 | 0.3496 | -528.0 | -524.0 | -9.3125 | -9.5625 |
66
+ | 0.0695 | 0.2094 | 200 | 0.7369 | -1.2031 | -1.3984 | 0.4883 | 0.1953 | -428.0 | -438.0 | -12.9375 | -13.3125 |
67
+ | 0.0402 | 0.3141 | 300 | 1.4284 | -4.5938 | -5.0 | 0.5195 | 0.4297 | -792.0 | -776.0 | -9.125 | -9.75 |
68
+ | 0.0373 | 0.4188 | 400 | 0.8732 | -2.3906 | -2.5156 | 0.4902 | 0.1279 | -540.0 | -556.0 | -13.375 | -13.5625 |
69
+ | 0.0289 | 0.5236 | 500 | 0.9761 | -3.5938 | -3.8906 | 0.4902 | 0.2871 | -676.0 | -680.0 | -15.0 | -15.25 |
70
+ | 0.0549 | 0.6283 | 600 | 0.9004 | -2.3594 | -2.6094 | 0.4805 | 0.2539 | -548.0 | -556.0 | -15.0625 | -15.1875 |
71
+ | 0.0385 | 0.7330 | 700 | 0.9997 | -3.125 | -3.25 | 0.4746 | 0.1299 | -612.0 | -632.0 | -11.5 | -11.875 |
72
+ | 0.0303 | 0.8377 | 800 | 1.0037 | -2.7656 | -2.9375 | 0.4785 | 0.1748 | -584.0 | -596.0 | -13.75 | -14.0625 |
73
+ | 0.0147 | 0.9424 | 900 | 1.1243 | -3.6094 | -3.7656 | 0.4824 | 0.1553 | -664.0 | -680.0 | -13.8125 | -14.1875 |
74
+ | 0.0038 | 1.0471 | 1000 | 1.0635 | -3.5781 | -3.7969 | 0.4941 | 0.2158 | -668.0 | -676.0 | -13.8125 | -14.125 |
75
+ | 0.0192 | 1.1518 | 1100 | 1.2317 | -4.1875 | -4.5625 | 0.4941 | 0.3711 | -744.0 | -736.0 | -14.0 | -14.25 |
76
+ | 0.0035 | 1.2565 | 1200 | 1.1275 | -3.8125 | -4.0938 | 0.5195 | 0.2676 | -696.0 | -700.0 | -13.6875 | -14.0625 |
77
+ | 0.0014 | 1.3613 | 1300 | 1.1072 | -3.8281 | -4.1875 | 0.5039 | 0.3672 | -708.0 | -700.0 | -10.3125 | -11.0 |
78
+ | 0.0009 | 1.4660 | 1400 | 1.2158 | -4.1562 | -4.5938 | 0.5039 | 0.4570 | -748.0 | -732.0 | -15.6875 | -16.0 |
79
+ | 0.0047 | 1.5707 | 1500 | 0.9804 | -3.4062 | -3.7656 | 0.5 | 0.3672 | -664.0 | -660.0 | -14.625 | -15.0625 |
80
+ | 0.0009 | 1.6754 | 1600 | 1.0340 | -4.0312 | -4.4688 | 0.5137 | 0.4219 | -736.0 | -724.0 | -10.6875 | -11.4375 |
81
+ | 0.0053 | 1.7801 | 1700 | 0.9808 | -3.4531 | -3.8125 | 0.5215 | 0.3730 | -672.0 | -664.0 | -16.125 | -16.25 |
82
+ | 0.0006 | 1.8848 | 1800 | 0.9781 | -3.2812 | -3.5312 | 0.5098 | 0.2578 | -640.0 | -644.0 | -16.125 | -16.25 |
83
+ | 0.0086 | 1.9895 | 1900 | 1.1759 | -4.1562 | -4.6562 | 0.5020 | 0.5195 | -756.0 | -732.0 | -15.4375 | -15.6875 |
84
+ | 0.0001 | 2.0942 | 2000 | 1.1181 | -3.8594 | -4.3125 | 0.5 | 0.4473 | -720.0 | -704.0 | -15.4375 | -15.6875 |
85
+ | 0.0145 | 2.1990 | 2100 | 1.1573 | -4.0312 | -4.5312 | 0.4980 | 0.4941 | -740.0 | -720.0 | -15.625 | -15.875 |
86
+ | 0.0002 | 2.3037 | 2200 | 1.1923 | -4.2188 | -4.7188 | 0.4961 | 0.5234 | -760.0 | -740.0 | -15.0625 | -15.4375 |
87
+ | 0.0005 | 2.4084 | 2300 | 1.1497 | -4.0 | -4.5 | 0.4902 | 0.4824 | -736.0 | -720.0 | -15.3125 | -15.5625 |
88
+ | 0.0002 | 2.5131 | 2400 | 1.1575 | -4.0312 | -4.5312 | 0.4961 | 0.4902 | -740.0 | -720.0 | -15.375 | -15.6875 |
89
+ | 0.0001 | 2.6178 | 2500 | 1.1676 | -4.0938 | -4.5938 | 0.4922 | 0.5039 | -748.0 | -728.0 | -15.25 | -15.5625 |
90
+ | 0.0014 | 2.7225 | 2600 | 1.1490 | -4.0312 | -4.5 | 0.5020 | 0.4785 | -740.0 | -720.0 | -15.3125 | -15.625 |
91
+ | 0.0002 | 2.8272 | 2700 | 1.1505 | -4.0312 | -4.5312 | 0.4961 | 0.4824 | -740.0 | -720.0 | -15.25 | -15.5625 |
92
+ | 0.0002 | 2.9319 | 2800 | 1.1518 | -4.0625 | -4.5312 | 0.4980 | 0.4824 | -744.0 | -724.0 | -15.25 | -15.5625 |
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": 0.022635619988056292,
5
- "train_runtime": 12425.7414,
6
  "train_samples": 61119,
7
- "train_samples_per_second": 14.756,
8
- "train_steps_per_second": 0.231
9
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_logits/chosen": -16.375,
4
+ "eval_logits/rejected": -16.125,
5
+ "eval_logps/chosen": -696.0,
6
+ "eval_logps/rejected": -712.0,
7
+ "eval_loss": 1.1395312547683716,
8
+ "eval_rewards/accuracies": 0.5,
9
+ "eval_rewards/chosen": -3.796875,
10
+ "eval_rewards/margins": 0.423828125,
11
+ "eval_rewards/rejected": -4.21875,
12
+ "eval_runtime": 46.5036,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 43.007,
15
+ "eval_steps_per_second": 0.688,
16
  "total_flos": 0.0,
17
+ "train_loss": 0.02262802565294394,
18
+ "train_runtime": 12206.3813,
19
  "train_samples": 61119,
20
+ "train_samples_per_second": 15.021,
21
+ "train_steps_per_second": 0.235
22
  }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -16.375,
4
+ "eval_logits/rejected": -16.125,
5
+ "eval_logps/chosen": -696.0,
6
+ "eval_logps/rejected": -712.0,
7
+ "eval_loss": 1.1395312547683716,
8
+ "eval_rewards/accuracies": 0.5,
9
+ "eval_rewards/chosen": -3.796875,
10
+ "eval_rewards/margins": 0.423828125,
11
+ "eval_rewards/rejected": -4.21875,
12
+ "eval_runtime": 46.5036,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 43.007,
15
+ "eval_steps_per_second": 0.688
16
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5754786595921cf1141f812a1a7c971cd25a9336649fbbbef1a3d49f88c4ce8
3
  size 2159808696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf2937f29cb80286d7a56a7beb972ce360d8c0a0a643f3c8124e0732cfb69a45
3
  size 2159808696
runs/Oct05_14-26-22_xe8545-a100-15/events.out.tfevents.1728144965.xe8545-a100-15.1049253.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d480fd082e4e5583cb867a6bb8f40a0e89d69818ea5793b1cb8696105c62063e
3
+ size 828
runs/Oct06_22-45-30_xe8545-a100-15/events.out.tfevents.1728248468.xe8545-a100-15.1088924.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42f26bba72717e7376b96b5f96861d5ee405e776f798a1cde598f3c89aceb540
3
+ size 225711
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.022635619988056292,
5
- "train_runtime": 12425.7414,
6
  "train_samples": 61119,
7
- "train_samples_per_second": 14.756,
8
- "train_steps_per_second": 0.231
9
  }
 
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.02262802565294394,
5
+ "train_runtime": 12206.3813,
6
  "train_samples": 61119,
7
+ "train_samples_per_second": 15.021,
8
+ "train_steps_per_second": 0.235
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 sha256:07e4d96ca6b830df4676f6214a3b4e222535d6d35da37130cdb19b17bd990b62
3
  size 7672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74664c52c33ab8fd3db13e007e605b6bd6cb321f2f77fb849d5fd3737670608c
3
  size 7672