Hugging Face's logo

LeeSB
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
Model card Files Metrics Community
LeeSB commited on
Commit
6569e33
•
1 Parent(s): d9e622d

Model save

Browse files
Files changed (8) hide show
  1. README.md +46 -47
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. all_results.json +5 -5
  5. runs/Apr06_07-03-35_allennlp-cirrascale-68.reviz.ai2.in/events.out.tfevents.1712412243.allennlp-cirrascale-68.reviz.ai2.in.65868.0 +2 -2
  6. train_results.json +5 -5
  7. trainer_state.json +0 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5056
22
- - Rewards/chosen: -1.4058
23
- - Rewards/rejected: -2.2921
24
- - Rewards/accuracies: 0.7345
25
- - Rewards/margins: 0.8863
26
- - Logps/rejected: -492.4564
27
- - Logps/chosen: -425.7130
28
- - Logits/rejected: -1.8131
29
- - Logits/chosen: -1.9265
30
 
31
  ## Model description
32
 
@@ -61,44 +61,43 @@ 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
- | 0.6896 | 0.03 | 100 | 0.6884 | 0.0072 | -0.0023 | 0.6745 | 0.0096 | -263.4773 | -284.4093 | -2.5586 | -2.6909 |
65
- | 0.6699 | 0.05 | 200 | 0.6726 | 0.0082 | -0.0359 | 0.6895 | 0.0441 | -266.8299 | -284.3103 | -2.5495 | -2.6813 |
66
- | 0.636 | 0.08 | 300 | 0.6466 | -0.0002 | -0.1125 | 0.6780 | 0.1123 | -274.4987 | -285.1534 | -2.5520 | -2.6823 |
67
- | 0.6312 | 0.1 | 400 | 0.6191 | -0.2138 | -0.4222 | 0.6805 | 0.2084 | -305.4655 | -306.5131 | -2.5251 | -2.6530 |
68
- | 0.5918 | 0.13 | 500 | 0.6031 | -0.2627 | -0.5412 | 0.6880 | 0.2785 | -317.3649 | -311.4058 | -2.5298 | -2.6575 |
69
- | 0.6012 | 0.16 | 600 | 0.5928 | -0.5129 | -0.8554 | 0.6935 | 0.3424 | -348.7829 | -336.4283 | -2.5443 | -2.6737 |
70
- | 0.5823 | 0.18 | 700 | 0.5811 | -0.5775 | -1.0207 | 0.7000 | 0.4432 | -365.3115 | -342.8825 | -2.3446 | -2.4662 |
71
- | 0.5502 | 0.21 | 800 | 0.5688 | -0.5710 | -1.0329 | 0.7040 | 0.4619 | -366.5324 | -342.2334 | -2.3173 | -2.4395 |
72
- | 0.551 | 0.24 | 900 | 0.5723 | -0.5585 | -1.0146 | 0.7100 | 0.4561 | -364.7085 | -340.9870 | -2.2573 | -2.3767 |
73
- | 0.5684 | 0.26 | 1000 | 0.5602 | -0.7542 | -1.3111 | 0.7070 | 0.5569 | -394.3551 | -360.5555 | -2.2283 | -2.3464 |
74
- | 0.5722 | 0.29 | 1100 | 0.5429 | -0.7936 | -1.4574 | 0.7240 | 0.6638 | -408.9803 | -364.4904 | -2.0677 | -2.1820 |
75
- | 0.5866 | 0.31 | 1200 | 0.5338 | -1.0463 | -1.7337 | 0.7205 | 0.6874 | -436.6128 | -389.7662 | -2.0249 | -2.1388 |
76
- | 0.5659 | 0.34 | 1300 | 0.5310 | -0.8607 | -1.5398 | 0.7310 | 0.6792 | -417.2296 | -371.2006 | -1.9893 | -2.1049 |
77
- | 0.5625 | 0.37 | 1400 | 0.5295 | -0.7999 | -1.5056 | 0.7215 | 0.7058 | -413.8092 | -365.1206 | -1.9254 | -2.0391 |
78
- | 0.4575 | 0.39 | 1500 | 0.5266 | -1.1455 | -1.9646 | 0.7260 | 0.8191 | -459.7086 | -399.6889 | -1.9105 | -2.0252 |
79
- | 0.5855 | 0.42 | 1600 | 0.5227 | -1.0359 | -1.7628 | 0.7345 | 0.7269 | -439.5246 | -388.7278 | -1.9276 | -2.0403 |
80
- | 0.5333 | 0.44 | 1700 | 0.5155 | -1.1618 | -1.9731 | 0.7310 | 0.8113 | -460.5566 | -401.3148 | -1.9572 | -2.0732 |
81
- | 0.5055 | 0.47 | 1800 | 0.5181 | -1.1105 | -1.8968 | 0.7330 | 0.7863 | -452.9257 | -396.1870 | -1.9572 | -2.0727 |
82
- | 0.4687 | 0.5 | 1900 | 0.5198 | -1.4078 | -2.3064 | 0.7290 | 0.8986 | -493.8867 | -425.9163 | -1.8519 | -1.9678 |
83
- | 0.4936 | 0.52 | 2000 | 0.5123 | -1.4097 | -2.2536 | 0.7290 | 0.8438 | -488.6001 | -426.1056 | -1.8371 | -1.9508 |
84
- | 0.5058 | 0.55 | 2100 | 0.5121 | -1.4030 | -2.2804 | 0.7320 | 0.8773 | -491.2808 | -425.4353 | -1.8156 | -1.9302 |
85
- | 0.491 | 0.58 | 2200 | 0.5102 | -1.2883 | -2.1172 | 0.7300 | 0.8289 | -474.9657 | -413.9656 | -1.8893 | -2.0053 |
86
- | 0.4923 | 0.6 | 2300 | 0.5107 | -1.2460 | -2.0925 | 0.7320 | 0.8465 | -472.4916 | -409.7295 | -1.8949 | -2.0101 |
87
- | 0.4718 | 0.63 | 2400 | 0.5093 | -1.3443 | -2.1905 | 0.7265 | 0.8462 | -482.2936 | -419.5653 | -1.8618 | -1.9757 |
88
- | 0.5187 | 0.65 | 2500 | 0.5103 | -1.3233 | -2.2095 | 0.7285 | 0.8862 | -484.1988 | -417.4668 | -1.8641 | -1.9796 |
89
- | 0.5025 | 0.68 | 2600 | 0.5115 | -1.2910 | -2.1842 | 0.7315 | 0.8932 | -481.6620 | -414.2359 | -1.8388 | -1.9538 |
90
- | 0.4946 | 0.71 | 2700 | 0.5094 | -1.3454 | -2.2424 | 0.7300 | 0.8970 | -487.4804 | -419.6713 | -1.8200 | -1.9339 |
91
- | 0.5054 | 0.73 | 2800 | 0.5085 | -1.4083 | -2.3252 | 0.7320 | 0.9169 | -495.7629 | -425.9614 | -1.8042 | -1.9180 |
92
- | 0.5159 | 0.76 | 2900 | 0.5066 | -1.3467 | -2.2328 | 0.7320 | 0.8861 | -486.5227 | -419.8022 | -1.8193 | -1.9330 |
93
- | 0.4671 | 0.79 | 3000 | 0.5062 | -1.4194 | -2.3064 | 0.7325 | 0.8870 | -493.8865 | -427.0751 | -1.8140 | -1.9274 |
94
- | 0.4864 | 0.81 | 3100 | 0.5059 | -1.4248 | -2.3084 | 0.7330 | 0.8836 | -494.0863 | -427.6172 | -1.8158 | -1.9291 |
95
- | 0.5101 | 0.84 | 3200 | 0.5056 | -1.4159 | -2.2981 | 0.7340 | 0.8821 | -493.0526 | -426.7279 | -1.8167 | -1.9300 |
96
- | 0.5317 | 0.86 | 3300 | 0.5056 | -1.4029 | -2.2863 | 0.7355 | 0.8834 | -491.8742 | -425.4280 | -1.8139 | -1.9273 |
97
- | 0.4668 | 0.89 | 3400 | 0.5055 | -1.4064 | -2.2921 | 0.7350 | 0.8857 | -492.4527 | -425.7719 | -1.8132 | -1.9266 |
98
- | 0.5671 | 0.92 | 3500 | 0.5056 | -1.4036 | -2.2899 | 0.7345 | 0.8863 | -492.2395 | -425.4986 | -1.8158 | -1.9291 |
99
- | 0.4708 | 0.94 | 3600 | 0.5056 | -1.4050 | -2.2912 | 0.7345 | 0.8862 | -492.3603 | -425.6342 | -1.8127 | -1.9261 |
100
- | 0.4904 | 0.97 | 3700 | 0.5054 | -1.4047 | -2.2913 | 0.7355 | 0.8866 | -492.3736 | -425.6043 | -1.8155 | -1.9289 |
101
- | 0.5001 | 0.99 | 3800 | 0.5056 | -1.4058 | -2.2921 | 0.7345 | 0.8863 | -492.4564 | -425.7130 | -1.8131 | -1.9265 |
102
 
103
 
104
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.9740
22
+ - Rewards/chosen: -5.1257
23
+ - Rewards/rejected: -6.0686
24
+ - Rewards/accuracies: 0.5950
25
+ - Rewards/margins: 0.9430
26
+ - Logps/rejected: -870.1065
27
+ - Logps/chosen: -797.7003
28
+ - Logits/rejected: -1.8366
29
+ - Logits/chosen: -1.9539
30
 
31
  ## Model description
32
 
 
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
+ | 0.6698 | 0.03 | 100 | 0.6901 | -0.0365 | -0.0430 | 0.5625 | 0.0065 | -267.5472 | -288.7829 | -2.5622 | -2.6958 |
65
+ | 0.5864 | 0.05 | 200 | 0.6712 | -0.1514 | -0.2064 | 0.5915 | 0.0551 | -283.8881 | -300.2703 | -2.5837 | -2.7210 |
66
+ | 0.4604 | 0.08 | 300 | 0.6635 | -0.3454 | -0.4581 | 0.5755 | 0.1127 | -309.0577 | -319.6734 | -2.6465 | -2.7867 |
67
+ | 0.3274 | 0.11 | 400 | 0.6736 | -1.4021 | -1.7630 | 0.5865 | 0.3609 | -439.5495 | -425.3439 | -2.3318 | -2.4653 |
68
+ | 0.2403 | 0.13 | 500 | 0.6997 | -2.2874 | -2.7446 | 0.5985 | 0.4573 | -537.7081 | -513.8699 | -2.0456 | -2.1684 |
69
+ | 0.2586 | 0.16 | 600 | 0.7062 | -2.3888 | -2.8539 | 0.5840 | 0.4651 | -548.6315 | -524.0146 | -1.9324 | -2.0492 |
70
+ | 0.2338 | 0.19 | 700 | 0.7076 | -2.4279 | -2.8802 | 0.5865 | 0.4523 | -551.2661 | -527.9254 | -1.9258 | -2.0429 |
71
+ | 0.2163 | 0.21 | 800 | 0.7139 | -3.2505 | -3.7850 | 0.6030 | 0.5345 | -641.7469 | -610.1845 | -1.8626 | -1.9782 |
72
+ | 0.2297 | 0.24 | 900 | 0.7277 | -3.6449 | -4.1924 | 0.6015 | 0.5475 | -682.4832 | -649.6269 | -1.9512 | -2.0713 |
73
+ | 0.1739 | 0.27 | 1000 | 0.7613 | -3.7042 | -4.3355 | 0.6010 | 0.6313 | -696.7919 | -655.5536 | -1.9477 | -2.0703 |
74
+ | 0.1868 | 0.29 | 1100 | 0.9361 | -5.1247 | -5.8779 | 0.5725 | 0.7532 | -851.0316 | -797.6036 | -1.7606 | -1.8779 |
75
+ | 0.191 | 0.32 | 1200 | 0.8650 | -4.3479 | -5.0050 | 0.5785 | 0.6570 | -763.7404 | -719.9283 | -1.8935 | -2.0135 |
76
+ | 0.1594 | 0.35 | 1300 | 0.9262 | -5.0384 | -5.8517 | 0.5940 | 0.8132 | -848.4104 | -788.9777 | -1.8286 | -1.9478 |
77
+ | 0.1899 | 0.37 | 1400 | 0.7746 | -3.7073 | -4.4417 | 0.6080 | 0.7344 | -707.4120 | -655.8643 | -1.9178 | -2.0372 |
78
+ | 0.1972 | 0.4 | 1500 | 0.9740 | -5.8928 | -6.9457 | 0.6130 | 1.0529 | -957.8102 | -874.4113 | -1.7423 | -1.8571 |
79
+ | 0.1712 | 0.43 | 1600 | 0.8206 | -3.9552 | -4.6548 | 0.5935 | 0.6996 | -728.7280 | -680.6552 | -1.8792 | -1.9979 |
80
+ | 0.2211 | 0.45 | 1700 | 0.8185 | -4.3265 | -5.1186 | 0.6120 | 0.7921 | -775.1051 | -717.7828 | -1.8551 | -1.9732 |
81
+ | 0.1773 | 0.48 | 1800 | 0.9661 | -5.2583 | -6.2006 | 0.5950 | 0.9423 | -883.3090 | -810.9665 | -1.8040 | -1.9210 |
82
+ | 0.2611 | 0.51 | 1900 | 0.8358 | -3.9291 | -4.7135 | 0.6035 | 0.7844 | -734.5935 | -678.0472 | -1.8683 | -1.9849 |
83
+ | 0.1584 | 0.53 | 2000 | 0.9012 | -4.5759 | -5.4125 | 0.6010 | 0.8366 | -804.4951 | -742.7199 | -1.8457 | -1.9624 |
84
+ | 0.173 | 0.56 | 2100 | 0.9585 | -5.3270 | -6.2039 | 0.5905 | 0.8769 | -883.6325 | -817.8319 | -1.8311 | -1.9477 |
85
+ | 0.1348 | 0.59 | 2200 | 1.0276 | -5.6514 | -6.6786 | 0.6010 | 1.0272 | -931.1091 | -850.2776 | -1.8167 | -1.9336 |
86
+ | 0.1724 | 0.61 | 2300 | 0.9419 | -5.1420 | -6.0555 | 0.6030 | 0.9135 | -868.7937 | -799.3293 | -1.8558 | -1.9729 |
87
+ | 0.1652 | 0.64 | 2400 | 0.9893 | -5.2806 | -6.2527 | 0.5960 | 0.9721 | -888.5103 | -813.1928 | -1.8445 | -1.9630 |
88
+ | 0.1393 | 0.67 | 2500 | 1.0265 | -5.6807 | -6.7469 | 0.5985 | 1.0662 | -937.9327 | -853.2055 | -1.8254 | -1.9432 |
89
+ | 0.2064 | 0.69 | 2600 | 0.9616 | -4.9490 | -5.8748 | 0.5960 | 0.9259 | -850.7297 | -780.0315 | -1.8539 | -1.9722 |
90
+ | 0.1235 | 0.72 | 2700 | 1.0443 | -5.6025 | -6.6246 | 0.5925 | 1.0222 | -925.7085 | -845.3807 | -1.8262 | -1.9443 |
91
+ | 0.1229 | 0.75 | 2800 | 1.0563 | -5.7201 | -6.7637 | 0.5915 | 1.0437 | -939.6196 | -857.1437 | -1.8211 | -1.9388 |
92
+ | 0.1734 | 0.77 | 2900 | 1.0244 | -5.4916 | -6.5069 | 0.5940 | 1.0154 | -913.9391 | -834.2927 | -1.8266 | -1.9443 |
93
+ | 0.2791 | 0.8 | 3000 | 0.9939 | -5.2451 | -6.2104 | 0.5940 | 0.9654 | -884.2896 | -809.6420 | -1.8336 | -1.9511 |
94
+ | 0.2041 | 0.83 | 3100 | 0.9621 | -4.9990 | -5.9242 | 0.5955 | 0.9253 | -855.6674 | -785.0303 | -1.8434 | -1.9610 |
95
+ | 0.1699 | 0.85 | 3200 | 0.9698 | -5.0798 | -6.0155 | 0.5950 | 0.9357 | -864.7924 | -793.1119 | -1.8420 | -1.9592 |
96
+ | 0.1894 | 0.88 | 3300 | 0.9731 | -5.1171 | -6.0599 | 0.5975 | 0.9428 | -869.2389 | -796.8451 | -1.8393 | -1.9565 |
97
+ | 0.1929 | 0.91 | 3400 | 0.9734 | -5.1189 | -6.0616 | 0.5945 | 0.9427 | -869.4042 | -797.0283 | -1.8394 | -1.9565 |
98
+ | 0.1222 | 0.94 | 3500 | 0.9742 | -5.1242 | -6.0674 | 0.5955 | 0.9432 | -869.9834 | -797.5565 | -1.8377 | -1.9550 |
99
+ | 0.1486 | 0.96 | 3600 | 0.9741 | -5.1260 | -6.0694 | 0.5955 | 0.9434 | -870.1893 | -797.7342 | -1.8378 | -1.9550 |
100
+ | 0.1384 | 0.99 | 3700 | 0.9740 | -5.1257 | -6.0686 | 0.5950 | 0.9430 | -870.1065 | -797.7003 | -1.8366 | -1.9539 |
 
101
 
102
 
103
  ### Framework versions
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
  "down_proj",
24
- "k_proj",
25
- "up_proj",
26
- "o_proj",
27
  "gate_proj",
28
- "v_proj"
 
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "down_proj",
23
+ "v_proj",
24
+ "q_proj",
 
25
  "gate_proj",
26
+ "up_proj",
27
+ "k_proj",
28
+ "o_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6812d9f2ada063c38ac58daf7f2c9e2b7eb29c45e0b087cdd7b19647c7dd2e4a
3
  size 671150064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:272bb0c7d3a719d09545af46544a92fd509823ff48f70bb6bbf287b5a5178b5e
3
  size 671150064
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.5390157630246398,
4
- "train_runtime": 82744.187,
5
- "train_samples": 61134,
6
- "train_samples_per_second": 0.739,
7
- "train_steps_per_second": 0.046
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.23287739991377154,
4
+ "train_runtime": 68266.2327,
5
+ "train_samples": 59881,
6
+ "train_samples_per_second": 0.877,
7
+ "train_steps_per_second": 0.055
8
  }
runs/Apr06_07-03-35_allennlp-cirrascale-68.reviz.ai2.in/events.out.tfevents.1712412243.allennlp-cirrascale-68.reviz.ai2.in.65868.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3776dbc205268dc2e5cbfbfd0288d3c5a4bd746e619810607c07b745338212c0
3
- size 287741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b591b275b3ba1a5e9018f1d41df9a3eecbbd0fc8c5c41caf1fb434d1966743
3
+ size 290847
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.5390157630246398,
4
- "train_runtime": 82744.187,
5
- "train_samples": 61134,
6
- "train_samples_per_second": 0.739,
7
- "train_steps_per_second": 0.046
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.23287739991377154,
4
+ "train_runtime": 68266.2327,
5
+ "train_samples": 59881,
6
+ "train_samples_per_second": 0.877,
7
+ "train_steps_per_second": 0.055
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 sha256:8d87109cf5805bc8513ffd6453a88857167118e3603131054fd6d1ba53818559
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6ac409f4b3f1037a3decebc9bf5e468413437c66fffc5560e39e03505b104e
3
  size 5112