Hugging Face's logo

DUAL-GPO-2
/
phi-2-gpo-renew2-i0

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
BraylonDash commited on
Commit
4f984f1
•
1 Parent(s): b6a7236

Model save

Browse files
Files changed (10) hide show
  1. README.md +51 -54
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. all_results.json +16 -16
  5. eval_results.json +12 -12
  6. runs/Apr10_10-50-49_gpu4-119-5/events.out.tfevents.1712710486.gpu4-119-5.349569.0 +3 -0
  7. runs/Apr10_10-50-49_gpu4-119-5/events.out.tfevents.1712711221.gpu4-119-5.349569.1 +3 -0
  8. train_results.json +4 -4
  9. trainer_state.json +21 -21
  10. training_args.bin +1 -1
README.md CHANGED
@@ -2,13 +2,10 @@
2
  license: mit
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
- - generated_from_trainer
7
  - trl
8
  - dpo
 
9
  base_model: microsoft/phi-2
10
- datasets:
11
- - HuggingFaceH4/ultrafeedback_binarized
12
  model-index:
13
  - name: phi-2-gpo-renew2-i0
14
  results: []
@@ -19,17 +16,17 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # phi-2-gpo-renew2-i0
21
 
22
- This model is a fine-tuned version of [lole25/phi-2-sft-lora-ultrachat](https://huggingface.co/lole25/phi-2-sft-lora-ultrachat) on the HuggingFaceH4/ultrafeedback_binarized dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.0346
25
- - Rewards/chosen: -0.0264
26
- - Rewards/rejected: -0.0854
27
- - Rewards/accuracies: 0.6290
28
- - Rewards/margins: 0.0591
29
- - Logps/rejected: -252.3589
30
- - Logps/chosen: -280.1829
31
- - Logits/rejected: 1.0402
32
- - Logits/chosen: 0.9379
33
 
34
  ## Model description
35
 
@@ -62,46 +59,46 @@ The following hyperparameters were used during training:
62
 
63
  ### Training results
64
 
65
- | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
66
- |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
67
- | 0.0659 | 0.03 | 100 | 0.0536 | -0.0002 | -0.0008 | 0.4745 | 0.0005 | -243.8923 | -277.5683 | 1.0635 | 0.9711 |
68
- | 0.0597 | 0.05 | 200 | 0.0518 | 0.0035 | -0.0015 | 0.5880 | 0.0050 | -243.9651 | -277.1979 | 1.0617 | 0.9688 |
69
- | 0.0564 | 0.08 | 300 | 0.0475 | 0.0104 | -0.0081 | 0.6175 | 0.0185 | -244.6272 | -276.5096 | 1.0440 | 0.9499 |
70
- | 0.0402 | 0.1 | 400 | 0.0438 | 0.0017 | -0.0309 | 0.6325 | 0.0326 | -246.9109 | -277.3771 | 0.9932 | 0.8995 |
71
- | 0.0421 | 0.13 | 500 | 0.0411 | -0.0415 | -0.0810 | 0.6195 | 0.0395 | -251.9139 | -281.6956 | 0.9295 | 0.8362 |
72
- | 0.0439 | 0.16 | 600 | 0.0395 | -0.0701 | -0.1168 | 0.6175 | 0.0468 | -255.5005 | -284.5547 | 0.9520 | 0.8607 |
73
- | 0.0363 | 0.18 | 700 | 0.0390 | -0.0362 | -0.0808 | 0.6310 | 0.0446 | -251.8926 | -281.1619 | 0.9895 | 0.8949 |
74
- | 0.0402 | 0.21 | 800 | 0.0382 | -0.0514 | -0.1006 | 0.6220 | 0.0491 | -253.8720 | -282.6901 | 0.9937 | 0.9001 |
75
- | 0.0381 | 0.24 | 900 | 0.0376 | -0.0554 | -0.1099 | 0.6315 | 0.0545 | -254.8047 | -283.0851 | 1.0465 | 0.9534 |
76
- | 0.0421 | 0.26 | 1000 | 0.0374 | -0.0408 | -0.0930 | 0.6270 | 0.0522 | -253.1114 | -281.6268 | 1.0399 | 0.9448 |
77
- | 0.0393 | 0.29 | 1100 | 0.0370 | -0.0576 | -0.1053 | 0.6285 | 0.0478 | -254.3491 | -283.3031 | 1.0557 | 0.9609 |
78
- | 0.0533 | 0.31 | 1200 | 0.0369 | -0.0606 | -0.1154 | 0.6210 | 0.0548 | -255.3544 | -283.6022 | 1.0368 | 0.9417 |
79
- | 0.0392 | 0.34 | 1300 | 0.0367 | -0.0207 | -0.0714 | 0.6120 | 0.0508 | -250.9576 | -279.6129 | 1.0634 | 0.9660 |
80
- | 0.0432 | 0.37 | 1400 | 0.0367 | -0.0146 | -0.0629 | 0.6260 | 0.0483 | -250.1082 | -279.0112 | 1.0463 | 0.9482 |
81
- | 0.0304 | 0.39 | 1500 | 0.0359 | -0.0523 | -0.1062 | 0.6360 | 0.0539 | -254.4339 | -282.7773 | 1.0471 | 0.9496 |
82
- | 0.0436 | 0.42 | 1600 | 0.0359 | -0.0322 | -0.0845 | 0.6340 | 0.0522 | -252.2616 | -280.7699 | 1.0586 | 0.9585 |
83
- | 0.0405 | 0.44 | 1700 | 0.0355 | -0.0531 | -0.1105 | 0.6335 | 0.0575 | -254.8697 | -282.8529 | 1.0312 | 0.9322 |
84
- | 0.0352 | 0.47 | 1800 | 0.0354 | -0.0369 | -0.0956 | 0.6220 | 0.0586 | -253.3721 | -281.2394 | 1.0533 | 0.9539 |
85
- | 0.0392 | 0.5 | 1900 | 0.0355 | -0.0281 | -0.0860 | 0.6210 | 0.0579 | -252.4193 | -280.3594 | 1.0498 | 0.9508 |
86
- | 0.0368 | 0.52 | 2000 | 0.0354 | -0.0231 | -0.0770 | 0.6300 | 0.0539 | -251.5159 | -279.8615 | 1.0563 | 0.9577 |
87
- | 0.0326 | 0.55 | 2100 | 0.0352 | -0.0360 | -0.0915 | 0.6300 | 0.0555 | -252.9630 | -281.1432 | 1.0751 | 0.9760 |
88
- | 0.0368 | 0.58 | 2200 | 0.0352 | -0.0391 | -0.0965 | 0.6345 | 0.0574 | -253.4691 | -281.4595 | 1.0642 | 0.9640 |
89
- | 0.0315 | 0.6 | 2300 | 0.0351 | -0.0252 | -0.0801 | 0.6330 | 0.0549 | -251.8242 | -280.0628 | 1.0685 | 0.9676 |
90
- | 0.0341 | 0.63 | 2400 | 0.0352 | -0.0240 | -0.0803 | 0.6320 | 0.0563 | -251.8426 | -279.9447 | 1.0420 | 0.9405 |
91
- | 0.0488 | 0.65 | 2500 | 0.0350 | -0.0321 | -0.0918 | 0.6340 | 0.0597 | -252.9968 | -280.7594 | 1.0394 | 0.9378 |
92
- | 0.0279 | 0.68 | 2600 | 0.0349 | -0.0383 | -0.0996 | 0.6315 | 0.0613 | -253.7721 | -281.3765 | 1.0361 | 0.9350 |
93
- | 0.0427 | 0.71 | 2700 | 0.0348 | -0.0312 | -0.0911 | 0.6310 | 0.0600 | -252.9290 | -280.6644 | 1.0336 | 0.9319 |
94
- | 0.0331 | 0.73 | 2800 | 0.0349 | -0.0291 | -0.0872 | 0.6290 | 0.0581 | -252.5369 | -280.4611 | 1.0354 | 0.9335 |
95
- | 0.0415 | 0.76 | 2900 | 0.0349 | -0.0298 | -0.0883 | 0.6315 | 0.0585 | -252.6469 | -280.5276 | 1.0248 | 0.9228 |
96
- | 0.0404 | 0.79 | 3000 | 0.0349 | -0.0268 | -0.0859 | 0.6295 | 0.0590 | -252.4009 | -280.2291 | 1.0305 | 0.9277 |
97
- | 0.0362 | 0.81 | 3100 | 0.0348 | -0.0264 | -0.0849 | 0.6305 | 0.0585 | -252.3079 | -280.1861 | 1.0296 | 0.9270 |
98
- | 0.0412 | 0.84 | 3200 | 0.0348 | -0.0274 | -0.0861 | 0.6260 | 0.0587 | -252.4237 | -280.2876 | 1.0338 | 0.9313 |
99
- | 0.0485 | 0.86 | 3300 | 0.0347 | -0.0242 | -0.0824 | 0.6270 | 0.0582 | -252.0546 | -279.9648 | 1.0359 | 0.9336 |
100
- | 0.0376 | 0.89 | 3400 | 0.0346 | -0.0264 | -0.0854 | 0.6310 | 0.0590 | -252.3589 | -280.1902 | 1.0377 | 0.9354 |
101
- | 0.0352 | 0.92 | 3500 | 0.0346 | -0.0266 | -0.0856 | 0.6260 | 0.0590 | -252.3726 | -280.2037 | 1.0418 | 0.9392 |
102
- | 0.0379 | 0.94 | 3600 | 0.0347 | -0.0263 | -0.0852 | 0.6315 | 0.0589 | -252.3377 | -280.1781 | 1.0414 | 0.9390 |
103
- | 0.0361 | 0.97 | 3700 | 0.0346 | -0.0266 | -0.0856 | 0.6310 | 0.0590 | -252.3741 | -280.2047 | 1.0399 | 0.9377 |
104
- | 0.0298 | 0.99 | 3800 | 0.0347 | -0.0263 | -0.0850 | 0.6275 | 0.0587 | -252.3201 | -280.1767 | 1.0412 | 0.9387 |
105
 
106
 
107
  ### Framework versions
 
2
  license: mit
3
  library_name: peft
4
  tags:
 
 
5
  - trl
6
  - dpo
7
+ - generated_from_trainer
8
  base_model: microsoft/phi-2
 
 
9
  model-index:
10
  - name: phi-2-gpo-renew2-i0
11
  results: []
 
16
 
17
  # phi-2-gpo-renew2-i0
18
 
19
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0391
22
+ - Rewards/chosen: -0.0132
23
+ - Rewards/rejected: -0.0427
24
+ - Rewards/accuracies: 0.6330
25
+ - Rewards/margins: 0.0295
26
+ - Logps/rejected: -252.3540
27
+ - Logps/chosen: -280.1870
28
+ - Logits/rejected: 1.0400
29
+ - Logits/chosen: 0.9376
30
 
31
  ## Model description
32
 
 
59
 
60
  ### Training results
61
 
62
+ | Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
63
+ |:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
64
+ | 0.0659 | 0.03 | 100 | 0.9711 | 1.0635 | -277.5683 | -243.8923 | 0.0536 | 0.4745 | -0.0002 | 0.0005 | -0.0008 |
65
+ | 0.0597 | 0.05 | 200 | 0.9688 | 1.0617 | -277.1979 | -243.9651 | 0.0518 | 0.5880 | 0.0035 | 0.0050 | -0.0015 |
66
+ | 0.0564 | 0.08 | 300 | 0.9499 | 1.0440 | -276.5096 | -244.6272 | 0.0475 | 0.6175 | 0.0104 | 0.0185 | -0.0081 |
67
+ | 0.0402 | 0.1 | 400 | 0.8995 | 0.9932 | -277.3771 | -246.9109 | 0.0438 | 0.6325 | 0.0017 | 0.0326 | -0.0309 |
68
+ | 0.0421 | 0.13 | 500 | 0.8362 | 0.9295 | -281.6956 | -251.9139 | 0.0411 | 0.6195 | -0.0415 | 0.0395 | -0.0810 |
69
+ | 0.0439 | 0.16 | 600 | 0.8607 | 0.9520 | -284.5547 | -255.5005 | 0.0395 | 0.6175 | -0.0701 | 0.0468 | -0.1168 |
70
+ | 0.0363 | 0.18 | 700 | 0.8949 | 0.9895 | -281.1619 | -251.8926 | 0.0390 | 0.6310 | -0.0362 | 0.0446 | -0.0808 |
71
+ | 0.0402 | 0.21 | 800 | 0.9001 | 0.9937 | -282.6901 | -253.8720 | 0.0382 | 0.6220 | -0.0514 | 0.0491 | -0.1006 |
72
+ | 0.0381 | 0.24 | 900 | 0.9534 | 1.0465 | -283.0851 | -254.8047 | 0.0376 | 0.6315 | -0.0554 | 0.0545 | -0.1099 |
73
+ | 0.0421 | 0.26 | 1000 | 0.9448 | 1.0399 | -281.6268 | -253.1114 | 0.0374 | 0.6270 | -0.0408 | 0.0522 | -0.0930 |
74
+ | 0.0393 | 0.29 | 1100 | 0.9609 | 1.0557 | -283.3031 | -254.3491 | 0.0370 | 0.6285 | -0.0576 | 0.0478 | -0.1053 |
75
+ | 0.0533 | 0.31 | 1200 | 0.9417 | 1.0368 | -283.6022 | -255.3544 | 0.0369 | 0.6210 | -0.0606 | 0.0548 | -0.1154 |
76
+ | 0.0392 | 0.34 | 1300 | 0.9660 | 1.0634 | -279.6129 | -250.9576 | 0.0367 | 0.6120 | -0.0207 | 0.0508 | -0.0714 |
77
+ | 0.0432 | 0.37 | 1400 | 0.9482 | 1.0463 | -279.0112 | -250.1082 | 0.0367 | 0.6260 | -0.0146 | 0.0483 | -0.0629 |
78
+ | 0.0304 | 0.39 | 1500 | 0.9496 | 1.0471 | -282.7773 | -254.4339 | 0.0359 | 0.6360 | -0.0523 | 0.0539 | -0.1062 |
79
+ | 0.0436 | 0.42 | 1600 | 0.9585 | 1.0586 | -280.7699 | -252.2616 | 0.0359 | 0.6340 | -0.0322 | 0.0522 | -0.0845 |
80
+ | 0.0405 | 0.44 | 1700 | 0.9322 | 1.0312 | -282.8529 | -254.8697 | 0.0355 | 0.6335 | -0.0531 | 0.0575 | -0.1105 |
81
+ | 0.0352 | 0.47 | 1800 | 0.9539 | 1.0533 | -281.2394 | -253.3721 | 0.0354 | 0.6220 | -0.0369 | 0.0586 | -0.0956 |
82
+ | 0.0392 | 0.5 | 1900 | 0.9508 | 1.0498 | -280.3594 | -252.4193 | 0.0355 | 0.6210 | -0.0281 | 0.0579 | -0.0860 |
83
+ | 0.0368 | 0.52 | 2000 | 0.9577 | 1.0563 | -279.8615 | -251.5159 | 0.0354 | 0.6300 | -0.0231 | 0.0539 | -0.0770 |
84
+ | 0.0326 | 0.55 | 2100 | 0.9760 | 1.0751 | -281.1432 | -252.9630 | 0.0352 | 0.6300 | -0.0360 | 0.0555 | -0.0915 |
85
+ | 0.0368 | 0.58 | 2200 | 0.9640 | 1.0642 | -281.4595 | -253.4691 | 0.0352 | 0.6345 | -0.0391 | 0.0574 | -0.0965 |
86
+ | 0.0315 | 0.6 | 2300 | 0.9676 | 1.0685 | -280.0628 | -251.8242 | 0.0351 | 0.6330 | -0.0252 | 0.0549 | -0.0801 |
87
+ | 0.0341 | 0.63 | 2400 | 0.9405 | 1.0420 | -279.9447 | -251.8426 | 0.0352 | 0.6320 | -0.0240 | 0.0563 | -0.0803 |
88
+ | 0.0488 | 0.65 | 2500 | 0.9378 | 1.0394 | -280.7594 | -252.9968 | 0.0350 | 0.6340 | -0.0321 | 0.0597 | -0.0918 |
89
+ | 0.0279 | 0.68 | 2600 | 0.9350 | 1.0361 | -281.3765 | -253.7721 | 0.0349 | 0.6315 | -0.0383 | 0.0613 | -0.0996 |
90
+ | 0.0427 | 0.71 | 2700 | 0.9319 | 1.0336 | -280.6644 | -252.9290 | 0.0348 | 0.6310 | -0.0312 | 0.0600 | -0.0911 |
91
+ | 0.0331 | 0.73 | 2800 | 0.9335 | 1.0354 | -280.4611 | -252.5369 | 0.0349 | 0.6290 | -0.0291 | 0.0581 | -0.0872 |
92
+ | 0.0415 | 0.76 | 2900 | 0.9228 | 1.0248 | -280.5276 | -252.6469 | 0.0349 | 0.6315 | -0.0298 | 0.0585 | -0.0883 |
93
+ | 0.0404 | 0.79 | 3000 | 0.9277 | 1.0305 | -280.2291 | -252.4009 | 0.0349 | 0.6295 | -0.0268 | 0.0590 | -0.0859 |
94
+ | 0.0362 | 0.81 | 3100 | 0.9270 | 1.0296 | -280.1861 | -252.3079 | 0.0348 | 0.6305 | -0.0264 | 0.0585 | -0.0849 |
95
+ | 0.0412 | 0.84 | 3200 | 0.9313 | 1.0338 | -280.2876 | -252.4237 | 0.0348 | 0.6260 | -0.0274 | 0.0587 | -0.0861 |
96
+ | 0.0485 | 0.86 | 3300 | 0.9336 | 1.0359 | -279.9648 | -252.0546 | 0.0347 | 0.6270 | -0.0242 | 0.0582 | -0.0824 |
97
+ | 0.0376 | 0.89 | 3400 | 0.9354 | 1.0377 | -280.1902 | -252.3589 | 0.0346 | 0.6310 | -0.0264 | 0.0590 | -0.0854 |
98
+ | 0.0352 | 0.92 | 3500 | 0.9392 | 1.0418 | -280.2037 | -252.3726 | 0.0346 | 0.6260 | -0.0266 | 0.0590 | -0.0856 |
99
+ | 0.0379 | 0.94 | 3600 | 0.9390 | 1.0414 | -280.1781 | -252.3377 | 0.0347 | 0.6315 | -0.0263 | 0.0589 | -0.0852 |
100
+ | 0.0361 | 0.97 | 3700 | 0.9377 | 1.0399 | -280.2047 | -252.3741 | 0.0346 | 0.6310 | -0.0266 | 0.0590 | -0.0856 |
101
+ | 0.0298 | 0.99 | 3800 | 0.9387 | 1.0412 | -280.1767 | -252.3201 | 0.0347 | 0.6275 | -0.0263 | 0.0587 | -0.0850 |
102
 
103
 
104
  ### Framework versions
adapter_config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
  "k_proj",
24
  "dense",
25
- "v_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "k_proj",
23
  "dense",
24
+ "v_proj",
25
+ "q_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e08781d9a0271a1068d57908b2717ee4698996351a0446a8c4605d7a05a1b447
3
  size 167807296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8d2a67577d8b5fc349737e0b1ae736ba77981f537fc849ff62636023d219fd2
3
  size 167807296
all_results.json CHANGED
@@ -1,21 +1,21 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_logits/chosen": 0.937932550907135,
4
- "eval_logits/rejected": 1.0401638746261597,
5
- "eval_logps/chosen": -280.182861328125,
6
- "eval_logps/rejected": -252.35885620117188,
7
- "eval_loss": 0.034593481570482254,
8
- "eval_rewards/accuracies": 0.6290000081062317,
9
- "eval_rewards/chosen": -0.02636060118675232,
10
- "eval_rewards/margins": 0.059068720787763596,
11
- "eval_rewards/rejected": -0.08542931824922562,
12
- "eval_runtime": 538.4763,
13
  "eval_samples": 2000,
14
- "eval_samples_per_second": 3.714,
15
- "eval_steps_per_second": 0.929,
16
- "train_loss": 0.038748307645445686,
17
- "train_runtime": 55741.6245,
18
  "train_samples": 61135,
19
- "train_samples_per_second": 1.097,
20
- "train_steps_per_second": 0.069
21
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_logits/chosen": 0.9376290440559387,
4
+ "eval_logits/rejected": 1.0400481224060059,
5
+ "eval_logps/chosen": -280.18701171875,
6
+ "eval_logps/rejected": -252.3540496826172,
7
+ "eval_loss": 0.0390908420085907,
8
+ "eval_rewards/accuracies": 0.6330000162124634,
9
+ "eval_rewards/chosen": -0.013200990855693817,
10
+ "eval_rewards/margins": 0.029489602893590927,
11
+ "eval_rewards/rejected": -0.04269059747457504,
12
+ "eval_runtime": 539.3434,
13
  "eval_samples": 2000,
14
+ "eval_samples_per_second": 3.708,
15
+ "eval_steps_per_second": 0.927,
16
+ "train_loss": 0.0001892112643969555,
17
+ "train_runtime": 195.8108,
18
  "train_samples": 61135,
19
+ "train_samples_per_second": 312.215,
20
+ "train_steps_per_second": 19.514
21
  }
eval_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_logits/chosen": 0.937932550907135,
4
- "eval_logits/rejected": 1.0401638746261597,
5
- "eval_logps/chosen": -280.182861328125,
6
- "eval_logps/rejected": -252.35885620117188,
7
- "eval_loss": 0.034593481570482254,
8
- "eval_rewards/accuracies": 0.6290000081062317,
9
- "eval_rewards/chosen": -0.02636060118675232,
10
- "eval_rewards/margins": 0.059068720787763596,
11
- "eval_rewards/rejected": -0.08542931824922562,
12
- "eval_runtime": 538.4763,
13
  "eval_samples": 2000,
14
- "eval_samples_per_second": 3.714,
15
- "eval_steps_per_second": 0.929
16
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_logits/chosen": 0.9376290440559387,
4
+ "eval_logits/rejected": 1.0400481224060059,
5
+ "eval_logps/chosen": -280.18701171875,
6
+ "eval_logps/rejected": -252.3540496826172,
7
+ "eval_loss": 0.0390908420085907,
8
+ "eval_rewards/accuracies": 0.6330000162124634,
9
+ "eval_rewards/chosen": -0.013200990855693817,
10
+ "eval_rewards/margins": 0.029489602893590927,
11
+ "eval_rewards/rejected": -0.04269059747457504,
12
+ "eval_runtime": 539.3434,
13
  "eval_samples": 2000,
14
+ "eval_samples_per_second": 3.708,
15
+ "eval_steps_per_second": 0.927
16
  }
runs/Apr10_10-50-49_gpu4-119-5/events.out.tfevents.1712710486.gpu4-119-5.349569.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6ac0da0bf3604d909bd3b1c428183a26af6cbf45759b03d8c3e0b737feba762
3
+ size 6432
runs/Apr10_10-50-49_gpu4-119-5/events.out.tfevents.1712711221.gpu4-119-5.349569.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977c353b01fad3b5e96f9cda04d2580291ad5cfff53da7bec2ccc02bc08a6ba1
3
+ size 828
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.038748307645445686,
4
- "train_runtime": 55741.6245,
5
  "train_samples": 61135,
6
- "train_samples_per_second": 1.097,
7
- "train_steps_per_second": 0.069
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.0001892112643969555,
4
+ "train_runtime": 195.8108,
5
  "train_samples": 61135,
6
+ "train_samples_per_second": 312.215,
7
+ "train_steps_per_second": 19.514
8
  }
trainer_state.json CHANGED
@@ -5953,39 +5953,39 @@
5953
  {
5954
  "epoch": 1.0,
5955
  "learning_rate": 1.2629313018819312e-10,
5956
- "logits/chosen": 0.9093559980392456,
5957
- "logits/rejected": 1.0155284404754639,
5958
- "logps/chosen": -302.20904541015625,
5959
- "logps/rejected": -284.8764953613281,
5960
- "loss": 0.0297,
5961
  "rewards/accuracies": 0.606249988079071,
5962
- "rewards/chosen": -0.014634281396865845,
5963
- "rewards/margins": 0.05110809952020645,
5964
- "rewards/rejected": -0.0657423883676529,
5965
  "step": 3810
5966
  },
5967
  {
5968
  "epoch": 1.0,
5969
  "learning_rate": 1.0437535929996855e-12,
5970
- "logits/chosen": 0.9967252612113953,
5971
- "logits/rejected": 0.9475840330123901,
5972
- "logps/chosen": -285.2461242675781,
5973
- "logps/rejected": -266.7107238769531,
5974
- "loss": 0.0281,
5975
- "rewards/accuracies": 0.6187499761581421,
5976
- "rewards/chosen": -0.02502075769007206,
5977
- "rewards/margins": 0.06247056648135185,
5978
- "rewards/rejected": -0.08749131858348846,
5979
  "step": 3820
5980
  },
5981
  {
5982
  "epoch": 1.0,
5983
  "step": 3821,
5984
  "total_flos": 0.0,
5985
- "train_loss": 0.038748307645445686,
5986
- "train_runtime": 55741.6245,
5987
- "train_samples_per_second": 1.097,
5988
- "train_steps_per_second": 0.069
5989
  }
5990
  ],
5991
  "logging_steps": 10,
 
5953
  {
5954
  "epoch": 1.0,
5955
  "learning_rate": 1.2629313018819312e-10,
5956
+ "logits/chosen": 0.9089424014091492,
5957
+ "logits/rejected": 1.0153186321258545,
5958
+ "logps/chosen": -302.22296142578125,
5959
+ "logps/rejected": -284.89483642578125,
5960
+ "loss": 0.0326,
5961
  "rewards/accuracies": 0.606249988079071,
5962
+ "rewards/chosen": -0.007386692799627781,
5963
+ "rewards/margins": 0.025576096028089523,
5964
+ "rewards/rejected": -0.03296279162168503,
5965
  "step": 3810
5966
  },
5967
  {
5968
  "epoch": 1.0,
5969
  "learning_rate": 1.0437535929996855e-12,
5970
+ "logits/chosen": 0.9965023994445801,
5971
+ "logits/rejected": 0.9472867250442505,
5972
+ "logps/chosen": -285.3251037597656,
5973
+ "logps/rejected": -266.6712341308594,
5974
+ "loss": 0.035,
5975
+ "rewards/accuracies": 0.6312500238418579,
5976
+ "rewards/chosen": -0.012905353680253029,
5977
+ "rewards/margins": 0.030642932280898094,
5978
+ "rewards/rejected": -0.04354828968644142,
5979
  "step": 3820
5980
  },
5981
  {
5982
  "epoch": 1.0,
5983
  "step": 3821,
5984
  "total_flos": 0.0,
5985
+ "train_loss": 0.0001892112643969555,
5986
+ "train_runtime": 195.8108,
5987
+ "train_samples_per_second": 312.215,
5988
+ "train_steps_per_second": 19.514
5989
  }
5990
  ],
5991
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:414133517de32292e7d20c88f77226c5914371163a57f401036ee58e664e628f
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c4c57ac1d47374eabe33b125281f2acbce106117a1ec6c669fdea34ec70d429
3
  size 5816