BraylonDash
commited on
Model save
Browse files- README.md +51 -54
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- all_results.json +16 -16
- eval_results.json +12 -12
- runs/Apr10_10-50-49_gpu4-119-5/events.out.tfevents.1712710486.gpu4-119-5.349569.0 +3 -0
- runs/Apr10_10-50-49_gpu4-119-5/events.out.tfevents.1712711221.gpu4-119-5.349569.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +21 -21
- 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 [
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 0.
|
25 |
-
- Rewards/chosen: -0.
|
26 |
-
- Rewards/rejected: -0.
|
27 |
-
- Rewards/accuracies: 0.
|
28 |
-
- Rewards/margins: 0.
|
29 |
-
- Logps/rejected: -252.
|
30 |
-
- Logps/chosen: -280.
|
31 |
-
- Logits/rejected: 1.
|
32 |
-
- Logits/chosen: 0.
|
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 |
|
66 |
-
|
67 |
-
| 0.0659 | 0.03 | 100 | 0.
|
68 |
-
| 0.0597 | 0.05 | 200 | 0.
|
69 |
-
| 0.0564 | 0.08 | 300 | 0.
|
70 |
-
| 0.0402 | 0.1 | 400 | 0.
|
71 |
-
| 0.0421 | 0.13 | 500 | 0.
|
72 |
-
| 0.0439 | 0.16 | 600 | 0.
|
73 |
-
| 0.0363 | 0.18 | 700 | 0.
|
74 |
-
| 0.0402 | 0.21 | 800 | 0.
|
75 |
-
| 0.0381 | 0.24 | 900 | 0.
|
76 |
-
| 0.0421 | 0.26 | 1000 | 0.
|
77 |
-
| 0.0393 | 0.29 | 1100 | 0.
|
78 |
-
| 0.0533 | 0.31 | 1200 | 0.
|
79 |
-
| 0.0392 | 0.34 | 1300 | 0.
|
80 |
-
| 0.0432 | 0.37 | 1400 | 0.
|
81 |
-
| 0.0304 | 0.39 | 1500 | 0.
|
82 |
-
| 0.0436 | 0.42 | 1600 | 0.
|
83 |
-
| 0.0405 | 0.44 | 1700 | 0.
|
84 |
-
| 0.0352 | 0.47 | 1800 | 0.
|
85 |
-
| 0.0392 | 0.5 | 1900 | 0.
|
86 |
-
| 0.0368 | 0.52 | 2000 | 0.
|
87 |
-
| 0.0326 | 0.55 | 2100 | 0.
|
88 |
-
| 0.0368 | 0.58 | 2200 | 0.
|
89 |
-
| 0.0315 | 0.6 | 2300 | 0.
|
90 |
-
| 0.0341 | 0.63 | 2400 | 0.
|
91 |
-
| 0.0488 | 0.65 | 2500 | 0.
|
92 |
-
| 0.0279 | 0.68 | 2600 | 0.
|
93 |
-
| 0.0427 | 0.71 | 2700 | 0.
|
94 |
-
| 0.0331 | 0.73 | 2800 | 0.
|
95 |
-
| 0.0415 | 0.76 | 2900 | 0.
|
96 |
-
| 0.0404 | 0.79 | 3000 | 0.
|
97 |
-
| 0.0362 | 0.81 | 3100 | 0.
|
98 |
-
| 0.0412 | 0.84 | 3200 | 0.
|
99 |
-
| 0.0485 | 0.86 | 3300 | 0.
|
100 |
-
| 0.0376 | 0.89 | 3400 | 0.
|
101 |
-
| 0.0352 | 0.92 | 3500 | 0.
|
102 |
-
| 0.0379 | 0.94 | 3600 | 0.
|
103 |
-
| 0.0361 | 0.97 | 3700 | 0.
|
104 |
-
| 0.0298 | 0.99 | 3800 | 0.
|
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:
|
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.
|
4 |
-
"eval_logits/rejected": 1.
|
5 |
-
"eval_logps/chosen": -280.
|
6 |
-
"eval_logps/rejected": -252.
|
7 |
-
"eval_loss": 0.
|
8 |
-
"eval_rewards/accuracies": 0.
|
9 |
-
"eval_rewards/chosen": -0.
|
10 |
-
"eval_rewards/margins": 0.
|
11 |
-
"eval_rewards/rejected": -0.
|
12 |
-
"eval_runtime":
|
13 |
"eval_samples": 2000,
|
14 |
-
"eval_samples_per_second": 3.
|
15 |
-
"eval_steps_per_second": 0.
|
16 |
-
"train_loss": 0.
|
17 |
-
"train_runtime":
|
18 |
"train_samples": 61135,
|
19 |
-
"train_samples_per_second":
|
20 |
-
"train_steps_per_second":
|
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.
|
4 |
-
"eval_logits/rejected": 1.
|
5 |
-
"eval_logps/chosen": -280.
|
6 |
-
"eval_logps/rejected": -252.
|
7 |
-
"eval_loss": 0.
|
8 |
-
"eval_rewards/accuracies": 0.
|
9 |
-
"eval_rewards/chosen": -0.
|
10 |
-
"eval_rewards/margins": 0.
|
11 |
-
"eval_rewards/rejected": -0.
|
12 |
-
"eval_runtime":
|
13 |
"eval_samples": 2000,
|
14 |
-
"eval_samples_per_second": 3.
|
15 |
-
"eval_steps_per_second": 0.
|
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.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 61135,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
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.
|
5957 |
-
"logits/rejected": 1.
|
5958 |
-
"logps/chosen": -302.
|
5959 |
-
"logps/rejected": -284.
|
5960 |
-
"loss": 0.
|
5961 |
"rewards/accuracies": 0.606249988079071,
|
5962 |
-
"rewards/chosen": -0.
|
5963 |
-
"rewards/margins": 0.
|
5964 |
-
"rewards/rejected": -0.
|
5965 |
"step": 3810
|
5966 |
},
|
5967 |
{
|
5968 |
"epoch": 1.0,
|
5969 |
"learning_rate": 1.0437535929996855e-12,
|
5970 |
-
"logits/chosen": 0.
|
5971 |
-
"logits/rejected": 0.
|
5972 |
-
"logps/chosen": -285.
|
5973 |
-
"logps/rejected": -266.
|
5974 |
-
"loss": 0.
|
5975 |
-
"rewards/accuracies": 0.
|
5976 |
-
"rewards/chosen": -0.
|
5977 |
-
"rewards/margins": 0.
|
5978 |
-
"rewards/rejected": -0.
|
5979 |
"step": 3820
|
5980 |
},
|
5981 |
{
|
5982 |
"epoch": 1.0,
|
5983 |
"step": 3821,
|
5984 |
"total_flos": 0.0,
|
5985 |
-
"train_loss": 0.
|
5986 |
-
"train_runtime":
|
5987 |
-
"train_samples_per_second":
|
5988 |
-
"train_steps_per_second":
|
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:
|
3 |
size 5816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c4c57ac1d47374eabe33b125281f2acbce106117a1ec6c669fdea34ec70d429
|
3 |
size 5816
|