Hugging Face's logo

PKU-Alignment
/
ProgressGym-HistLlama3-8B-C018-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
015c28d
•
1 Parent(s): fe856f2

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": 0.9378, "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": "0:09:20"}
2
- {"current_steps": 5, "total_steps": 192, "loss": 0.914, "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": "0:05:10"}
3
- {"current_steps": 10, "total_steps": 192, "loss": 0.9191, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.75e-06, "epoch": 0.20833333333333334, "percentage": 5.21, "elapsed_time": "0:00:14", "remaining_time": "0:04:31"}
4
- {"current_steps": 15, "total_steps": 192, "loss": 0.8384, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.5e-06, "epoch": 0.3125, "percentage": 7.81, "elapsed_time": "0:00:22", "remaining_time": "0:04:22"}
5
- {"current_steps": 20, "total_steps": 192, "loss": 0.8108, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.125e-05, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:00:30", "remaining_time": "0:04:20"}
6
- {"current_steps": 20, "total_steps": 192, "loss": null, "eval_loss": 0.8423399925231934, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:00:30", "remaining_time": "0:04:20"}
7
- {"current_steps": 25, "total_steps": 192, "loss": 0.8145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5e-05, "epoch": 0.5208333333333334, "percentage": 13.02, "elapsed_time": "0:01:32", "remaining_time": "0:10:15"}
8
- {"current_steps": 30, "total_steps": 192, "loss": 0.8903, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0857107196807194e-05, "epoch": 0.625, "percentage": 15.62, "elapsed_time": "0:01:38", "remaining_time": "0:08:54"}
9
- {"current_steps": 35, "total_steps": 192, "loss": 0.8187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.785589881369409e-06, "epoch": 0.7291666666666666, "percentage": 18.23, "elapsed_time": "0:01:45", "remaining_time": "0:07:52"}
10
- {"current_steps": 40, "total_steps": 192, "loss": 0.7995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.529292099652595e-06, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:01:51", "remaining_time": "0:07:04"}
11
- {"current_steps": 40, "total_steps": 192, "loss": null, "eval_loss": 0.8555145263671875, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:01:51", "remaining_time": "0:07:04"}
12
- {"current_steps": 45, "total_steps": 192, "loss": 0.882, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.888024511896068e-06, "epoch": 0.9375, "percentage": 23.44, "elapsed_time": "0:03:32", "remaining_time": "0:11:32"}
13
- {"current_steps": 50, "total_steps": 192, "loss": 0.736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.706555900111454e-06, "epoch": 1.0416666666666667, "percentage": 26.04, "elapsed_time": "0:03:39", "remaining_time": "0:10:22"}
14
- {"current_steps": 55, "total_steps": 192, "loss": 0.4778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.865515934042282e-06, "epoch": 1.1458333333333333, "percentage": 28.65, "elapsed_time": "0:03:45", "remaining_time": "0:09:21"}
15
- {"current_steps": 60, "total_steps": 192, "loss": 0.4526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2739241815556468e-06, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:03:51", "remaining_time": "0:08:30"}
16
- {"current_steps": 60, "total_steps": 192, "loss": null, "eval_loss": 0.8815763592720032, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:03:51", "remaining_time": "0:08:30"}
17
- {"current_steps": 65, "total_steps": 192, "loss": 0.4192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.630954296648578e-07, "epoch": 1.3541666666666667, "percentage": 33.85, "elapsed_time": "0:05:22", "remaining_time": "0:10:29"}
18
- {"current_steps": 70, "total_steps": 192, "loss": 0.4476, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.817031181133133e-07, "epoch": 1.4583333333333333, "percentage": 36.46, "elapsed_time": "0:05:28", "remaining_time": "0:09:33"}
19
- {"current_steps": 75, "total_steps": 192, "loss": 0.445, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.918112984729563e-07, "epoch": 1.5625, "percentage": 39.06, "elapsed_time": "0:05:35", "remaining_time": "0:08:43"}
20
- {"current_steps": 80, "total_steps": 192, "loss": 0.4663, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6571123033559406e-07, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:05:42", "remaining_time": "0:07:58"}
21
- {"current_steps": 80, "total_steps": 192, "loss": null, "eval_loss": 0.8521442413330078, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:05:42", "remaining_time": "0:07:58"}
22
- {"current_steps": 85, "total_steps": 192, "loss": 0.4356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8342171723792628e-07, "epoch": 1.7708333333333335, "percentage": 44.27, "elapsed_time": "0:07:16", "remaining_time": "0:09:08"}
23
- {"current_steps": 90, "total_steps": 192, "loss": 0.4398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3073276582043678e-07, "epoch": 1.875, "percentage": 46.88, "elapsed_time": "0:07:23", "remaining_time": "0:08:22"}
24
- {"current_steps": 95, "total_steps": 192, "loss": 0.4823, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.769031226024856e-08, "epoch": 1.9791666666666665, "percentage": 49.48, "elapsed_time": "0:07:31", "remaining_time": "0:07:40"}
25
- {"current_steps": 100, "total_steps": 192, "loss": 0.3927, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.74357826465857e-08, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:07:40", "remaining_time": "0:07:03"}
26
- {"current_steps": 100, "total_steps": 192, "loss": null, "eval_loss": 0.8507040143013, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:07:40", "remaining_time": "0:07:03"}
27
- {"current_steps": 105, "total_steps": 192, "loss": 0.3733, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.532831361687478e-08, "epoch": 2.1875, "percentage": 54.69, "elapsed_time": "0:09:15", "remaining_time": "0:07:40"}
28
- {"current_steps": 110, "total_steps": 192, "loss": 0.4061, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.828972369827512e-08, "epoch": 2.2916666666666665, "percentage": 57.29, "elapsed_time": "0:09:22", "remaining_time": "0:06:59"}
29
- {"current_steps": 115, "total_steps": 192, "loss": 0.3621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.4322954384342975e-08, "epoch": 2.3958333333333335, "percentage": 59.9, "elapsed_time": "0:09:29", "remaining_time": "0:06:21"}
30
- {"current_steps": 120, "total_steps": 192, "loss": 0.4017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.2163845524645534e-08, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:09:35", "remaining_time": "0:05:45"}
31
- {"current_steps": 120, "total_steps": 192, "loss": null, "eval_loss": 0.8561407923698425, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:09:35", "remaining_time": "0:05:45"}
32
- {"current_steps": 125, "total_steps": 192, "loss": 0.3944, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.1033917145757624e-08, "epoch": 2.6041666666666665, "percentage": 65.1, "elapsed_time": "0:11:06", "remaining_time": "0:05:57"}
33
- {"current_steps": 130, "total_steps": 192, "loss": 0.3947, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.046843690876512e-08, "epoch": 2.7083333333333335, "percentage": 67.71, "elapsed_time": "0:11:12", "remaining_time": "0:05:20"}
34
- {"current_steps": 135, "total_steps": 192, "loss": 0.381, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.019958911899713e-08, "epoch": 2.8125, "percentage": 70.31, "elapsed_time": "0:11:19", "remaining_time": "0:04:46"}
35
- {"current_steps": 140, "total_steps": 192, "loss": 0.368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0079150140309806e-08, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:11:26", "remaining_time": "0:04:14"}
36
- {"current_steps": 140, "total_steps": 192, "loss": null, "eval_loss": 0.8607857823371887, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:11:26", "remaining_time": "0:04:14"}
37
- {"current_steps": 145, "total_steps": 192, "loss": 0.3777, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0028831355203246e-08, "epoch": 3.0208333333333335, "percentage": 75.52, "elapsed_time": "0:12:50", "remaining_time": "0:04:09"}
38
- {"current_steps": 150, "total_steps": 192, "loss": 0.3817, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.00094821039914e-08, "epoch": 3.125, "percentage": 78.12, "elapsed_time": "0:12:59", "remaining_time": "0:03:38"}
39
- {"current_steps": 155, "total_steps": 192, "loss": 0.3773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000275150604354e-08, "epoch": 3.2291666666666665, "percentage": 80.73, "elapsed_time": "0:13:06", "remaining_time": "0:03:07"}
40
- {"current_steps": 160, "total_steps": 192, "loss": 0.3677, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000068241292119e-08, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:13:13", "remaining_time": "0:02:38"}
41
- {"current_steps": 160, "total_steps": 192, "loss": null, "eval_loss": 0.8646895885467529, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:13:13", "remaining_time": "0:02:38"}
42
- {"current_steps": 165, "total_steps": 192, "loss": 0.3656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000013819045227e-08, "epoch": 3.4375, "percentage": 85.94, "elapsed_time": "0:14:30", "remaining_time": "0:02:22"}
43
- {"current_steps": 170, "total_steps": 192, "loss": 0.3503, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000002132208559e-08, "epoch": 3.5416666666666665, "percentage": 88.54, "elapsed_time": "0:14:38", "remaining_time": "0:01:53"}
44
- {"current_steps": 175, "total_steps": 192, "loss": 0.3707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.00000022411853e-08, "epoch": 3.6458333333333335, "percentage": 91.15, "elapsed_time": "0:14:44", "remaining_time": "0:01:25"}
45
- {"current_steps": 180, "total_steps": 192, "loss": 0.3635, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000013145176e-08, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "0:14:51", "remaining_time": "0:00:59"}
46
- {"current_steps": 180, "total_steps": 192, "loss": null, "eval_loss": 0.8675721287727356, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "0:14:51", "remaining_time": "0:00:59"}
47
- {"current_steps": 185, "total_steps": 192, "loss": 0.3833, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000284985e-08, "epoch": 3.8541666666666665, "percentage": 96.35, "elapsed_time": "0:16:23", "remaining_time": "0:00:37"}
48
- {"current_steps": 190, "total_steps": 192, "loss": 0.3722, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000000758e-08, "epoch": 3.9583333333333335, "percentage": 98.96, "elapsed_time": "0:16:30", "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": "0:16:33", "remaining_time": "0:00:00"}
50
- {"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.8423399925231934, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:17:06", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 48, "loss": 0.8792, "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": "0:04:57"}
2
+ {"current_steps": 3, "total_steps": 48, "loss": 0.8254, "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": "0:01:56"}
3
+ {"current_steps": 5, "total_steps": 48, "loss": null, "eval_loss": 0.9155074954032898, "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": 0.9527, "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": "0:01:16"}
5
+ {"current_steps": 9, "total_steps": 48, "loss": 0.8488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.865909090909091e-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": 0.8055909276008606, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.20833333333333334, "percentage": 20.83, "elapsed_time": "0:00:13", "remaining_time": "0:00:52"}
7
+ {"current_steps": 12, "total_steps": 48, "loss": 0.7727, "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": "0:03:07"}
8
+ {"current_steps": 15, "total_steps": 48, "loss": 0.8256, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4636363636363635e-06, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:04", "remaining_time": "0:02:22"}
9
+ {"current_steps": 15, "total_steps": 48, "loss": null, "eval_loss": 0.7961261868476868, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:04", "remaining_time": "0:02:22"}
10
+ {"current_steps": 18, "total_steps": 48, "loss": 0.7613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2625e-06, "epoch": 0.375, "percentage": 37.5, "elapsed_time": "0:01:07", "remaining_time": "0:01:52"}
11
+ {"current_steps": 20, "total_steps": 48, "loss": null, "eval_loss": 0.7846309542655945, "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": 0.7927, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0613636363636364e-06, "epoch": 0.4375, "percentage": 43.75, "elapsed_time": "0:02:00", "remaining_time": "0:02:34"}
13
+ {"current_steps": 24, "total_steps": 48, "loss": 0.7126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8602272727272725e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:02:02", "remaining_time": "0:02:02"}
14
+ {"current_steps": 25, "total_steps": 48, "loss": null, "eval_loss": 0.7795621752738953, "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": 0.784, "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": "0:01:37"}
16
+ {"current_steps": 30, "total_steps": 48, "loss": 0.8101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4579545454545454e-06, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:07", "remaining_time": "0:01:16"}
17
+ {"current_steps": 30, "total_steps": 48, "loss": null, "eval_loss": 0.7749997973442078, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:07", "remaining_time": "0:01:16"}
18
+ {"current_steps": 33, "total_steps": 48, "loss": 0.6816, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2568181818181817e-06, "epoch": 0.6875, "percentage": 68.75, "elapsed_time": "0:02:58", "remaining_time": "0:01:21"}
19
+ {"current_steps": 35, "total_steps": 48, "loss": null, "eval_loss": 0.7707688212394714, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7291666666666666, "percentage": 72.92, "elapsed_time": "0:02:59", "remaining_time": "0:01:06"}
20
+ {"current_steps": 36, "total_steps": 48, "loss": 0.7442, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0556818181818182e-06, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:03:01", "remaining_time": "0:01:00"}
21
+ {"current_steps": 39, "total_steps": 48, "loss": 0.6972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.545454545454544e-07, "epoch": 0.8125, "percentage": 81.25, "elapsed_time": "0:03:03", "remaining_time": "0:00:42"}
22
+ {"current_steps": 40, "total_steps": 48, "loss": null, "eval_loss": 0.7688388824462891, "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": 0.7682, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.534090909090911e-07, "epoch": 0.875, "percentage": 87.5, "elapsed_time": "0:03:55", "remaining_time": "0:00:33"}
24
+ {"current_steps": 45, "total_steps": 48, "loss": 0.8067, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.522727272727273e-07, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:58", "remaining_time": "0:00:15"}
25
+ {"current_steps": 45, "total_steps": 48, "loss": null, "eval_loss": 0.7668374180793762, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:58", "remaining_time": "0:00:15"}
26
+ {"current_steps": 48, "total_steps": 48, "loss": 0.794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.511363636363638e-07, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:04:00", "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": "0:04:00", "remaining_time": "0:00:00"}
28
+ {"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.7688388824462891, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:04:39", "remaining_time": "0:00:00"}