Hugging Face's logo

PKU-Alignment
/
ProgressGym-HistLlama3-8B-C021-instruct-v0.2

Text Generation
Transformers
Safetensors
llama
alignment
value alignment
AI safety
safety
LLM
history
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
TianyiQ commited on
Commit
582771b
•
1 Parent(s): 15b6cde

Upload ./trainer_log.jsonl with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_log.jsonl +28 -50
trainer_log.jsonl CHANGED
@@ -1,50 +1,28 @@
1
- {"current_steps": 1, "total_steps": 192, "loss": 0.9347, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.020833333333333332, "percentage": 0.52, "elapsed_time": "0:00:03", "remaining_time": "0:09:49"}
2
- {"current_steps": 5, "total_steps": 192, "loss": 0.9437, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5e-06, "epoch": 0.10416666666666667, "percentage": 2.6, "elapsed_time": "0:00:08", "remaining_time": "0:05:33"}
3
- {"current_steps": 10, "total_steps": 192, "loss": 0.8846, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5e-06, "epoch": 0.20833333333333334, "percentage": 5.21, "elapsed_time": "0:00:15", "remaining_time": "0:04:44"}
4
- {"current_steps": 15, "total_steps": 192, "loss": 0.8294, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.25e-06, "epoch": 0.3125, "percentage": 7.81, "elapsed_time": "0:00:22", "remaining_time": "0:04:30"}
5
- {"current_steps": 20, "total_steps": 192, "loss": 0.8056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2e-05, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:00:31", "remaining_time": "0:04:31"}
6
- {"current_steps": 20, "total_steps": 192, "loss": null, "eval_loss": 0.8397957682609558, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:00:31", "remaining_time": "0:04:31"}
7
- {"current_steps": 25, "total_steps": 192, "loss": 0.8125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4071209905461127e-05, "epoch": 0.5208333333333334, "percentage": 13.02, "elapsed_time": "0:01:27", "remaining_time": "0:09:41"}
8
- {"current_steps": 30, "total_steps": 192, "loss": 0.8944, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0166196232101288e-05, "epoch": 0.625, "percentage": 15.62, "elapsed_time": "0:01:33", "remaining_time": "0:08:26"}
9
- {"current_steps": 35, "total_steps": 192, "loss": 0.813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.276248845991498e-06, "epoch": 0.7291666666666666, "percentage": 18.23, "elapsed_time": "0:01:40", "remaining_time": "0:07:29"}
10
- {"current_steps": 40, "total_steps": 192, "loss": 0.7984, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.157388080190487e-06, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:01:46", "remaining_time": "0:06:45"}
11
- {"current_steps": 40, "total_steps": 192, "loss": null, "eval_loss": 0.8509224057197571, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:01:46", "remaining_time": "0:06:45"}
12
- {"current_steps": 45, "total_steps": 192, "loss": 0.8755, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6192313334626905e-06, "epoch": 0.9375, "percentage": 23.44, "elapsed_time": "0:03:38", "remaining_time": "0:11:54"}
13
- {"current_steps": 50, "total_steps": 192, "loss": 0.7267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.514391432582838e-06, "epoch": 1.0416666666666667, "percentage": 26.04, "elapsed_time": "0:03:45", "remaining_time": "0:10:41"}
14
- {"current_steps": 55, "total_steps": 192, "loss": 0.4663, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7297262757656213e-06, "epoch": 1.1458333333333333, "percentage": 28.65, "elapsed_time": "0:03:52", "remaining_time": "0:09:38"}
15
- {"current_steps": 60, "total_steps": 192, "loss": 0.439, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1791620375982074e-06, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:03:58", "remaining_time": "0:08:44"}
16
- {"current_steps": 60, "total_steps": 192, "loss": null, "eval_loss": 0.8703265190124512, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:03:58", "remaining_time": "0:08:44"}
17
- {"current_steps": 65, "total_steps": 192, "loss": 0.4085, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.978466092394693e-07, "epoch": 1.3541666666666667, "percentage": 33.85, "elapsed_time": "0:05:41", "remaining_time": "0:11:06"}
18
- {"current_steps": 70, "total_steps": 192, "loss": 0.445, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.374210410959207e-07, "epoch": 1.4583333333333333, "percentage": 36.46, "elapsed_time": "0:05:47", "remaining_time": "0:10:06"}
19
- {"current_steps": 75, "total_steps": 192, "loss": 0.4392, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6222476698215175e-07, "epoch": 1.5625, "percentage": 39.06, "elapsed_time": "0:05:54", "remaining_time": "0:09:13"}
20
- {"current_steps": 80, "total_steps": 192, "loss": 0.4595, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.462755297384099e-07, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:06:01", "remaining_time": "0:08:25"}
21
- {"current_steps": 80, "total_steps": 192, "loss": null, "eval_loss": 0.8540446162223816, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:06:01", "remaining_time": "0:08:25"}
22
- {"current_steps": 85, "total_steps": 192, "loss": 0.431, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7088740175034947e-07, "epoch": 1.7708333333333335, "percentage": 44.27, "elapsed_time": "0:07:43", "remaining_time": "0:09:43"}
23
- {"current_steps": 90, "total_steps": 192, "loss": 0.4306, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.228102956599465e-07, "epoch": 1.875, "percentage": 46.88, "elapsed_time": "0:07:50", "remaining_time": "0:08:53"}
24
- {"current_steps": 95, "total_steps": 192, "loss": 0.4889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.279207916081227e-08, "epoch": 1.9791666666666665, "percentage": 49.48, "elapsed_time": "0:07:59", "remaining_time": "0:08:09"}
25
- {"current_steps": 100, "total_steps": 192, "loss": 0.3986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.448002404850094e-08, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:08:08", "remaining_time": "0:07:29"}
26
- {"current_steps": 100, "total_steps": 192, "loss": null, "eval_loss": 0.8511225581169128, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:08:08", "remaining_time": "0:07:29"}
27
- {"current_steps": 105, "total_steps": 192, "loss": 0.3708, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.35920070839697e-08, "epoch": 2.1875, "percentage": 54.69, "elapsed_time": "0:09:53", "remaining_time": "0:08:12"}
28
- {"current_steps": 110, "total_steps": 192, "loss": 0.4046, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.7299804687499997e-08, "epoch": 2.2916666666666665, "percentage": 57.29, "elapsed_time": "0:10:00", "remaining_time": "0:07:27"}
29
- {"current_steps": 115, "total_steps": 192, "loss": 0.3535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.37771434967624e-08, "epoch": 2.3958333333333335, "percentage": 59.9, "elapsed_time": "0:10:07", "remaining_time": "0:06:46"}
30
- {"current_steps": 120, "total_steps": 192, "loss": 0.3895, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.187403540619925e-08, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:10:13", "remaining_time": "0:06:08"}
31
- {"current_steps": 120, "total_steps": 192, "loss": null, "eval_loss": 0.8556583523750305, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:10:13", "remaining_time": "0:06:08"}
32
- {"current_steps": 125, "total_steps": 192, "loss": 0.3734, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.088648238966908e-08, "epoch": 2.6041666666666665, "percentage": 65.1, "elapsed_time": "0:11:57", "remaining_time": "0:06:24"}
33
- {"current_steps": 130, "total_steps": 192, "loss": 0.3789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.039701925276604e-08, "epoch": 2.7083333333333335, "percentage": 67.71, "elapsed_time": "0:12:03", "remaining_time": "0:05:45"}
34
- {"current_steps": 135, "total_steps": 192, "loss": 0.3885, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0166900048082497e-08, "epoch": 2.8125, "percentage": 70.31, "elapsed_time": "0:12:10", "remaining_time": "0:05:08"}
35
- {"current_steps": 140, "total_steps": 192, "loss": 0.3761, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0065147322870076e-08, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:12:16", "remaining_time": "0:04:33"}
36
- {"current_steps": 140, "total_steps": 192, "loss": null, "eval_loss": 0.86014723777771, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:12:16", "remaining_time": "0:04:33"}
37
- {"current_steps": 145, "total_steps": 192, "loss": 0.3827, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.002328628528332e-08, "epoch": 3.0208333333333335, "percentage": 75.52, "elapsed_time": "0:13:57", "remaining_time": "0:04:31"}
38
- {"current_steps": 150, "total_steps": 192, "loss": 0.3756, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0007484528133236e-08, "epoch": 3.125, "percentage": 78.12, "elapsed_time": "0:14:06", "remaining_time": "0:03:57"}
39
- {"current_steps": 155, "total_steps": 192, "loss": 0.3767, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0002110817570477e-08, "epoch": 3.2291666666666665, "percentage": 80.73, "elapsed_time": "0:14:14", "remaining_time": "0:03:23"}
40
- {"current_steps": 160, "total_steps": 192, "loss": 0.3652, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000504842356326e-08, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:14:20", "remaining_time": "0:02:52"}
41
- {"current_steps": 160, "total_steps": 192, "loss": null, "eval_loss": 0.8633076548576355, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:14:20", "remaining_time": "0:02:52"}
42
- {"current_steps": 165, "total_steps": 192, "loss": 0.363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000009745562451e-08, "epoch": 3.4375, "percentage": 85.94, "elapsed_time": "0:15:58", "remaining_time": "0:02:36"}
43
- {"current_steps": 170, "total_steps": 192, "loss": 0.3413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000014077810156e-08, "epoch": 3.5416666666666665, "percentage": 88.54, "elapsed_time": "0:16:05", "remaining_time": "0:02:04"}
44
- {"current_steps": 175, "total_steps": 192, "loss": 0.3642, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000001343508807e-08, "epoch": 3.6458333333333335, "percentage": 91.15, "elapsed_time": "0:16:11", "remaining_time": "0:01:34"}
45
- {"current_steps": 180, "total_steps": 192, "loss": 0.3712, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000006747581e-08, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "0:16:19", "remaining_time": "0:01:05"}
46
- {"current_steps": 180, "total_steps": 192, "loss": null, "eval_loss": 0.866676390171051, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "0:16:19", "remaining_time": "0:01:05"}
47
- {"current_steps": 185, "total_steps": 192, "loss": 0.3705, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000001094325e-08, "epoch": 3.8541666666666665, "percentage": 96.35, "elapsed_time": "0:17:58", "remaining_time": "0:00:40"}
48
- {"current_steps": 190, "total_steps": 192, "loss": 0.3576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000000139e-08, "epoch": 3.9583333333333335, "percentage": 98.96, "elapsed_time": "0:18:05", "remaining_time": "0:00:11"}
49
- {"current_steps": 192, "total_steps": 192, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:18:08", "remaining_time": "0:00:00"}
50
- {"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.8397957682609558, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:18:42", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 48, "loss": 0.9812, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.020833333333333332, "percentage": 2.08, "elapsed_time": "0:00:05", "remaining_time": "0:04:29"}
2
+ {"current_steps": 3, "total_steps": 48, "loss": 0.9339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.0625, "percentage": 6.25, "elapsed_time": "0:00:07", "remaining_time": "0:01:47"}
3
+ {"current_steps": 5, "total_steps": 48, "loss": null, "eval_loss": 1.004961609840393, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.10416666666666667, "percentage": 10.42, "elapsed_time": "0:00:08", "remaining_time": "0:01:14"}
4
+ {"current_steps": 6, "total_steps": 48, "loss": 1.0561, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.125, "percentage": 12.5, "elapsed_time": "0:00:10", "remaining_time": "0:01:11"}
5
+ {"current_steps": 9, "total_steps": 48, "loss": 0.8863, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.865909090909091e-06, "epoch": 0.1875, "percentage": 18.75, "elapsed_time": "0:00:12", "remaining_time": "0:00:53"}
6
+ {"current_steps": 10, "total_steps": 48, "loss": null, "eval_loss": 0.8208221793174744, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.20833333333333334, "percentage": 20.83, "elapsed_time": "0:00:12", "remaining_time": "0:00:49"}
7
+ {"current_steps": 12, "total_steps": 48, "loss": 0.7908, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7318181818181818e-06, "epoch": 0.25, "percentage": 25.0, "elapsed_time": "0:00:59", "remaining_time": "0:02:59"}
8
+ {"current_steps": 15, "total_steps": 48, "loss": 0.8415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5306818181818182e-06, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:02", "remaining_time": "0:02:16"}
9
+ {"current_steps": 15, "total_steps": 48, "loss": null, "eval_loss": 0.8036231398582458, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:02", "remaining_time": "0:02:16"}
10
+ {"current_steps": 18, "total_steps": 48, "loss": 0.7685, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3295454545454547e-06, "epoch": 0.375, "percentage": 37.5, "elapsed_time": "0:01:04", "remaining_time": "0:01:48"}
11
+ {"current_steps": 20, "total_steps": 48, "loss": null, "eval_loss": 0.7909483909606934, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 41.67, "elapsed_time": "0:01:06", "remaining_time": "0:01:33"}
12
+ {"current_steps": 21, "total_steps": 48, "loss": 0.7973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.128409090909091e-06, "epoch": 0.4375, "percentage": 43.75, "elapsed_time": "0:01:54", "remaining_time": "0:02:26"}
13
+ {"current_steps": 24, "total_steps": 48, "loss": 0.7194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9272727272727273e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:01:55", "remaining_time": "0:01:55"}
14
+ {"current_steps": 25, "total_steps": 48, "loss": null, "eval_loss": 0.7860968708992004, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5208333333333334, "percentage": 52.08, "elapsed_time": "0:01:56", "remaining_time": "0:01:47"}
15
+ {"current_steps": 27, "total_steps": 48, "loss": 0.7893, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7261363636363635e-06, "epoch": 0.5625, "percentage": 56.25, "elapsed_time": "0:01:58", "remaining_time": "0:01:32"}
16
+ {"current_steps": 30, "total_steps": 48, "loss": 0.8176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.525e-06, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:00", "remaining_time": "0:01:12"}
17
+ {"current_steps": 30, "total_steps": 48, "loss": null, "eval_loss": 0.7812687754631042, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:00", "remaining_time": "0:01:12"}
18
+ {"current_steps": 33, "total_steps": 48, "loss": 0.6869, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3238636363636363e-06, "epoch": 0.6875, "percentage": 68.75, "elapsed_time": "0:02:49", "remaining_time": "0:01:16"}
19
+ {"current_steps": 35, "total_steps": 48, "loss": null, "eval_loss": 0.7764313817024231, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7291666666666666, "percentage": 72.92, "elapsed_time": "0:02:50", "remaining_time": "0:01:03"}
20
+ {"current_steps": 36, "total_steps": 48, "loss": 0.7511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1227272727272728e-06, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:02:52", "remaining_time": "0:00:57"}
21
+ {"current_steps": 39, "total_steps": 48, "loss": 0.7031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.215909090909091e-07, "epoch": 0.8125, "percentage": 81.25, "elapsed_time": "0:02:54", "remaining_time": "0:00:40"}
22
+ {"current_steps": 40, "total_steps": 48, "loss": null, "eval_loss": 0.7741241455078125, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 83.33, "elapsed_time": "0:02:54", "remaining_time": "0:00:34"}
23
+ {"current_steps": 42, "total_steps": 48, "loss": 0.7758, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.204545454545455e-07, "epoch": 0.875, "percentage": 87.5, "elapsed_time": "0:03:45", "remaining_time": "0:00:32"}
24
+ {"current_steps": 45, "total_steps": 48, "loss": 0.8116, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.193181818181818e-07, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:48", "remaining_time": "0:00:15"}
25
+ {"current_steps": 45, "total_steps": 48, "loss": null, "eval_loss": 0.771578311920166, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:48", "remaining_time": "0:00:15"}
26
+ {"current_steps": 48, "total_steps": 48, "loss": 0.7987, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.181818181818183e-07, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:50", "remaining_time": "0:00:00"}
27
+ {"current_steps": 48, "total_steps": 48, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:50", "remaining_time": "0:00:00"}
28
+ {"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.7741241455078125, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:04:29", "remaining_time": "0:00:00"}