Hugging Face's logo

PKU-Alignment
/
ProgressGym-HistLlama3-8B-C019-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
64f5692
•
1 Parent(s): a541f1c

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": 0.9787, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.020833333333333332, "percentage": 0.52, "elapsed_time": "0:00:02", "remaining_time": "0:09:29"}
2
- {"current_steps": 5, "total_steps": 192, "loss": 0.9575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.10416666666666667, "percentage": 2.6, "elapsed_time": "0:00:08", "remaining_time": "0:05:16"}
3
- {"current_steps": 10, "total_steps": 192, "loss": 0.8647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.25e-06, "epoch": 0.20833333333333334, "percentage": 5.21, "elapsed_time": "0:00:15", "remaining_time": "0:04:36"}
4
- {"current_steps": 15, "total_steps": 192, "loss": 0.8335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9e-06, "epoch": 0.3125, "percentage": 7.81, "elapsed_time": "0:00:22", "remaining_time": "0:04:25"}
5
- {"current_steps": 20, "total_steps": 192, "loss": 0.8164, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.275e-05, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:00:30", "remaining_time": "0:04:22"}
6
- {"current_steps": 20, "total_steps": 192, "loss": null, "eval_loss": 0.8431240916252136, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:00:30", "remaining_time": "0:04:22"}
7
- {"current_steps": 25, "total_steps": 192, "loss": 0.8222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3195176200175283e-05, "epoch": 0.5208333333333334, "percentage": 13.02, "elapsed_time": "0:01:25", "remaining_time": "0:09:33"}
8
- {"current_steps": 30, "total_steps": 192, "loss": 0.8995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.515676612044427e-06, "epoch": 0.625, "percentage": 15.62, "elapsed_time": "0:01:32", "remaining_time": "0:08:20"}
9
- {"current_steps": 35, "total_steps": 192, "loss": 0.8188, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.797580677308734e-06, "epoch": 0.7291666666666666, "percentage": 18.23, "elapsed_time": "0:01:39", "remaining_time": "0:07:24"}
10
- {"current_steps": 40, "total_steps": 192, "loss": 0.7962, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.808575415542887e-06, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:01:45", "remaining_time": "0:06:40"}
11
- {"current_steps": 40, "total_steps": 192, "loss": null, "eval_loss": 0.8461718559265137, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:01:45", "remaining_time": "0:06:40"}
12
- {"current_steps": 45, "total_steps": 192, "loss": 0.8768, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3676619069852654e-06, "epoch": 0.9375, "percentage": 23.44, "elapsed_time": "0:03:29", "remaining_time": "0:11:24"}
13
- {"current_steps": 50, "total_steps": 192, "loss": 0.721, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.334947896124909e-06, "epoch": 1.0416666666666667, "percentage": 26.04, "elapsed_time": "0:03:36", "remaining_time": "0:10:15"}
14
- {"current_steps": 55, "total_steps": 192, "loss": 0.4634, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.603233215095547e-06, "epoch": 1.1458333333333333, "percentage": 28.65, "elapsed_time": "0:03:42", "remaining_time": "0:09:15"}
15
- {"current_steps": 60, "total_steps": 192, "loss": 0.4335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0911174606561334e-06, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:03:49", "remaining_time": "0:08:24"}
16
- {"current_steps": 60, "total_steps": 192, "loss": null, "eval_loss": 0.8650219440460205, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:03:49", "remaining_time": "0:08:24"}
17
- {"current_steps": 65, "total_steps": 192, "loss": 0.3981, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.373930741131784e-07, "epoch": 1.3541666666666667, "percentage": 33.85, "elapsed_time": "0:05:25", "remaining_time": "0:10:36"}
18
- {"current_steps": 70, "total_steps": 192, "loss": 0.4411, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.965174334325768e-07, "epoch": 1.4583333333333333, "percentage": 36.46, "elapsed_time": "0:05:32", "remaining_time": "0:09:39"}
19
- {"current_steps": 75, "total_steps": 192, "loss": 0.4387, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.349849877937343e-07, "epoch": 1.5625, "percentage": 39.06, "elapsed_time": "0:05:39", "remaining_time": "0:08:49"}
20
- {"current_steps": 80, "total_steps": 192, "loss": 0.4578, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2844505627726646e-07, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:05:45", "remaining_time": "0:08:04"}
21
- {"current_steps": 80, "total_steps": 192, "loss": null, "eval_loss": 0.8532621264457703, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:05:45", "remaining_time": "0:08:04"}
22
- {"current_steps": 85, "total_steps": 192, "loss": 0.4262, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.594328760942437e-07, "epoch": 1.7708333333333335, "percentage": 44.27, "elapsed_time": "0:07:22", "remaining_time": "0:09:16"}
23
- {"current_steps": 90, "total_steps": 192, "loss": 0.4247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.156010161291434e-07, "epoch": 1.875, "percentage": 46.88, "elapsed_time": "0:07:29", "remaining_time": "0:08:28"}
24
- {"current_steps": 95, "total_steps": 192, "loss": 0.4835, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.835555547373544e-08, "epoch": 1.9791666666666665, "percentage": 49.48, "elapsed_time": "0:07:37", "remaining_time": "0:07:47"}
25
- {"current_steps": 100, "total_steps": 192, "loss": 0.3944, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.181664349277562e-08, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:07:46", "remaining_time": "0:07:08"}
26
- {"current_steps": 100, "total_steps": 192, "loss": null, "eval_loss": 0.848356306552887, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:07:46", "remaining_time": "0:07:08"}
27
- {"current_steps": 105, "total_steps": 192, "loss": 0.3698, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.203637972657601e-08, "epoch": 2.1875, "percentage": 54.69, "elapsed_time": "0:09:24", "remaining_time": "0:07:47"}
28
- {"current_steps": 110, "total_steps": 192, "loss": 0.3999, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.6418543066491835e-08, "epoch": 2.2916666666666665, "percentage": 57.29, "elapsed_time": "0:09:30", "remaining_time": "0:07:05"}
29
- {"current_steps": 115, "total_steps": 192, "loss": 0.3575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.329471712759216e-08, "epoch": 2.3958333333333335, "percentage": 59.9, "elapsed_time": "0:09:37", "remaining_time": "0:06:26"}
30
- {"current_steps": 120, "total_steps": 192, "loss": 0.3997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.161995210302015e-08, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:09:44", "remaining_time": "0:05:50"}
31
- {"current_steps": 120, "total_steps": 192, "loss": null, "eval_loss": 0.8528212904930115, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:09:44", "remaining_time": "0:05:50"}
32
- {"current_steps": 125, "total_steps": 192, "loss": 0.3796, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.075841465580837e-08, "epoch": 2.6041666666666665, "percentage": 65.1, "elapsed_time": "0:11:19", "remaining_time": "0:06:03"}
33
- {"current_steps": 130, "total_steps": 192, "loss": 0.3768, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.033564114946932e-08, "epoch": 2.7083333333333335, "percentage": 67.71, "elapsed_time": "0:11:25", "remaining_time": "0:05:26"}
34
- {"current_steps": 135, "total_steps": 192, "loss": 0.3762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.013915282607116e-08, "epoch": 2.8125, "percentage": 70.31, "elapsed_time": "0:11:32", "remaining_time": "0:04:52"}
35
- {"current_steps": 140, "total_steps": 192, "loss": 0.3752, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.005343402153039e-08, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:11:38", "remaining_time": "0:04:19"}
36
- {"current_steps": 140, "total_steps": 192, "loss": null, "eval_loss": 0.8572859764099121, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:11:38", "remaining_time": "0:04:19"}
37
- {"current_steps": 145, "total_steps": 192, "loss": 0.3768, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.001872829857116e-08, "epoch": 3.0208333333333335, "percentage": 75.52, "elapsed_time": "0:13:12", "remaining_time": "0:04:16"}
38
- {"current_steps": 150, "total_steps": 192, "loss": 0.3765, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000587713853837e-08, "epoch": 3.125, "percentage": 78.12, "elapsed_time": "0:13:21", "remaining_time": "0:03:44"}
39
- {"current_steps": 155, "total_steps": 192, "loss": 0.3702, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0001608748597456e-08, "epoch": 3.2291666666666665, "percentage": 80.73, "elapsed_time": "0:13:28", "remaining_time": "0:03:13"}
40
- {"current_steps": 160, "total_steps": 192, "loss": 0.3697, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000370319656156e-08, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:13:35", "remaining_time": "0:02:43"}
41
- {"current_steps": 160, "total_steps": 192, "loss": null, "eval_loss": 0.8608274459838867, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:13:35", "remaining_time": "0:02:43"}
42
- {"current_steps": 165, "total_steps": 192, "loss": 0.3654, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000067945715855e-08, "epoch": 3.4375, "percentage": 85.94, "elapsed_time": "0:15:08", "remaining_time": "0:02:28"}
43
- {"current_steps": 170, "total_steps": 192, "loss": 0.3523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000009144677036e-08, "epoch": 3.5416666666666665, "percentage": 88.54, "elapsed_time": "0:15:15", "remaining_time": "0:01:58"}
44
- {"current_steps": 175, "total_steps": 192, "loss": 0.3668, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000785521776e-08, "epoch": 3.6458333333333335, "percentage": 91.15, "elapsed_time": "0:15:21", "remaining_time": "0:01:29"}
45
- {"current_steps": 180, "total_steps": 192, "loss": 0.3636, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000003317662e-08, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "0:15:28", "remaining_time": "0:01:01"}
46
- {"current_steps": 180, "total_steps": 192, "loss": null, "eval_loss": 0.8633963465690613, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "0:15:28", "remaining_time": "0:01:01"}
47
- {"current_steps": 185, "total_steps": 192, "loss": 0.3717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000038355e-08, "epoch": 3.8541666666666665, "percentage": 96.35, "elapsed_time": "0:17:03", "remaining_time": "0:00:38"}
48
- {"current_steps": 190, "total_steps": 192, "loss": 0.3687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000000018e-08, "epoch": 3.9583333333333335, "percentage": 98.96, "elapsed_time": "0:17:10", "remaining_time": "0:00:10"}
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": "0:17:12", "remaining_time": "0:00:00"}
50
- {"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.8431240916252136, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:17:45", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 48, "loss": 1.0289, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.020833333333333332, "percentage": 2.08, "elapsed_time": "0:00:06", "remaining_time": "0:04:54"}
2
+ {"current_steps": 3, "total_steps": 48, "loss": 0.9475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.5e-07, "epoch": 0.0625, "percentage": 6.25, "elapsed_time": "0:00:07", "remaining_time": "0:01:58"}
3
+ {"current_steps": 5, "total_steps": 48, "loss": null, "eval_loss": 0.9170231819152832, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.10416666666666667, "percentage": 10.42, "elapsed_time": "0:00:09", "remaining_time": "0:01:20"}
4
+ {"current_steps": 6, "total_steps": 48, "loss": 1.032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-06, "epoch": 0.125, "percentage": 12.5, "elapsed_time": "0:00:10", "remaining_time": "0:01:16"}
5
+ {"current_steps": 9, "total_steps": 48, "loss": 0.8569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7988636363636366e-06, "epoch": 0.1875, "percentage": 18.75, "elapsed_time": "0:00:13", "remaining_time": "0:00:56"}
6
+ {"current_steps": 10, "total_steps": 48, "loss": null, "eval_loss": 0.8191882967948914, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.20833333333333334, "percentage": 20.83, "elapsed_time": "0:00:13", "remaining_time": "0:00:51"}
7
+ {"current_steps": 12, "total_steps": 48, "loss": 0.7857, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6647727272727274e-06, "epoch": 0.25, "percentage": 25.0, "elapsed_time": "0:01:02", "remaining_time": "0:03:08"}
8
+ {"current_steps": 15, "total_steps": 48, "loss": 0.8358, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4636363636363635e-06, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:05", "remaining_time": "0:02:23"}
9
+ {"current_steps": 15, "total_steps": 48, "loss": null, "eval_loss": 0.8035795092582703, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:05", "remaining_time": "0:02:23"}
10
+ {"current_steps": 18, "total_steps": 48, "loss": 0.7692, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2625e-06, "epoch": 0.375, "percentage": 37.5, "elapsed_time": "0:01:08", "remaining_time": "0:01:53"}
11
+ {"current_steps": 20, "total_steps": 48, "loss": null, "eval_loss": 0.7883596420288086, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 41.67, "elapsed_time": "0:01:09", "remaining_time": "0:01:37"}
12
+ {"current_steps": 21, "total_steps": 48, "loss": 0.8029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0613636363636364e-06, "epoch": 0.4375, "percentage": 43.75, "elapsed_time": "0:01:59", "remaining_time": "0:02:33"}
13
+ {"current_steps": 24, "total_steps": 48, "loss": 0.7192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8602272727272725e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:02:01", "remaining_time": "0:02:01"}
14
+ {"current_steps": 25, "total_steps": 48, "loss": null, "eval_loss": 0.7828572392463684, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5208333333333334, "percentage": 52.08, "elapsed_time": "0:02:02", "remaining_time": "0:01:52"}
15
+ {"current_steps": 27, "total_steps": 48, "loss": 0.7906, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.659090909090909e-06, "epoch": 0.5625, "percentage": 56.25, "elapsed_time": "0:02:04", "remaining_time": "0:01:36"}
16
+ {"current_steps": 30, "total_steps": 48, "loss": 0.8181, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4579545454545454e-06, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:06", "remaining_time": "0:01:15"}
17
+ {"current_steps": 30, "total_steps": 48, "loss": null, "eval_loss": 0.7780725955963135, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:06", "remaining_time": "0:01:15"}
18
+ {"current_steps": 33, "total_steps": 48, "loss": 0.6879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2568181818181817e-06, "epoch": 0.6875, "percentage": 68.75, "elapsed_time": "0:02:57", "remaining_time": "0:01:20"}
19
+ {"current_steps": 35, "total_steps": 48, "loss": null, "eval_loss": 0.7747842669487, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7291666666666666, "percentage": 72.92, "elapsed_time": "0:02:58", "remaining_time": "0:01:06"}
20
+ {"current_steps": 36, "total_steps": 48, "loss": 0.7508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0556818181818182e-06, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:03:00", "remaining_time": "0:01:00"}
21
+ {"current_steps": 39, "total_steps": 48, "loss": 0.7032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.545454545454544e-07, "epoch": 0.8125, "percentage": 81.25, "elapsed_time": "0:03:02", "remaining_time": "0:00:42"}
22
+ {"current_steps": 40, "total_steps": 48, "loss": null, "eval_loss": 0.7724230289459229, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 83.33, "elapsed_time": "0:03:03", "remaining_time": "0:00:36"}
23
+ {"current_steps": 42, "total_steps": 48, "loss": 0.7755, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.534090909090911e-07, "epoch": 0.875, "percentage": 87.5, "elapsed_time": "0:03:54", "remaining_time": "0:00:33"}
24
+ {"current_steps": 45, "total_steps": 48, "loss": 0.8136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.522727272727273e-07, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:56", "remaining_time": "0:00:15"}
25
+ {"current_steps": 45, "total_steps": 48, "loss": null, "eval_loss": 0.7702701091766357, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:56", "remaining_time": "0:00:15"}
26
+ {"current_steps": 48, "total_steps": 48, "loss": 0.8008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.511363636363638e-07, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:59", "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": "0:03:59", "remaining_time": "0:00:00"}
28
+ {"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.7724230289459229, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:04:37", "remaining_time": "0:00:00"}