sedrickkeh commited on
Commit
3ab8d58
·
verified ·
1 Parent(s): 92c2454

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c1f5b61082a9e60bb79d4f6b43235f84b579290bd4d5d914ce7154b5b4f6799
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882fbc354c93cc6d2545c230e08d49544a6345f90a3cae9676b6d1d9a27f5c7f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aa05fd9f6c84a1af2d22745e023b9a12f2e497f66ab6bd2e64589fe309169bb
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c3ea15e5a737d9b96e657dcc96800fa88a91ee3c116b0a6d7242e7ba2b9284
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b0fdb04730f27c37fedfb7770a9a9aa93d8369b5827ad9582031040c064a647
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eead24df65cb4f657d37539f22bd814d064a4cb32d1e8b1db76a7f727a3a520f
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a2e2fe3d538e0fe85ff25546e510d9fccd34020754a7943fb3c348c1afd242a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916cfd550ce712604c09205a3b11f5ac6e3a026ead73678953fd66acd3247d60
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -41,3 +41,46 @@
41
  {"current_steps": 410, "total_steps": 1257, "loss": 0.4531, "lr": 5e-06, "epoch": 0.976481095564156, "percentage": 32.62, "elapsed_time": "3:38:35", "remaining_time": "7:31:34"}
42
  {"current_steps": 419, "total_steps": 1257, "eval_loss": 0.45424818992614746, "epoch": 0.9979160464423936, "percentage": 33.33, "elapsed_time": "3:48:12", "remaining_time": "7:36:25"}
43
  {"current_steps": 420, "total_steps": 1257, "loss": 0.4859, "lr": 5e-06, "epoch": 1.0020839535576065, "percentage": 33.41, "elapsed_time": "3:49:51", "remaining_time": "7:38:04"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  {"current_steps": 410, "total_steps": 1257, "loss": 0.4531, "lr": 5e-06, "epoch": 0.976481095564156, "percentage": 32.62, "elapsed_time": "3:38:35", "remaining_time": "7:31:34"}
42
  {"current_steps": 419, "total_steps": 1257, "eval_loss": 0.45424818992614746, "epoch": 0.9979160464423936, "percentage": 33.33, "elapsed_time": "3:48:12", "remaining_time": "7:36:25"}
43
  {"current_steps": 420, "total_steps": 1257, "loss": 0.4859, "lr": 5e-06, "epoch": 1.0020839535576065, "percentage": 33.41, "elapsed_time": "3:49:51", "remaining_time": "7:38:04"}
44
+ {"current_steps": 430, "total_steps": 1257, "loss": 0.4102, "lr": 5e-06, "epoch": 1.025900565644537, "percentage": 34.21, "elapsed_time": "3:55:08", "remaining_time": "7:32:14"}
45
+ {"current_steps": 440, "total_steps": 1257, "loss": 0.4092, "lr": 5e-06, "epoch": 1.0497171777314678, "percentage": 35.0, "elapsed_time": "4:00:26", "remaining_time": "7:26:26"}
46
+ {"current_steps": 450, "total_steps": 1257, "loss": 0.4052, "lr": 5e-06, "epoch": 1.0735337898183983, "percentage": 35.8, "elapsed_time": "4:05:47", "remaining_time": "7:20:46"}
47
+ {"current_steps": 460, "total_steps": 1257, "loss": 0.4105, "lr": 5e-06, "epoch": 1.097350401905329, "percentage": 36.6, "elapsed_time": "4:11:08", "remaining_time": "7:15:07"}
48
+ {"current_steps": 470, "total_steps": 1257, "loss": 0.4084, "lr": 5e-06, "epoch": 1.1211670139922596, "percentage": 37.39, "elapsed_time": "4:16:27", "remaining_time": "7:09:25"}
49
+ {"current_steps": 480, "total_steps": 1257, "loss": 0.411, "lr": 5e-06, "epoch": 1.1449836260791901, "percentage": 38.19, "elapsed_time": "4:21:47", "remaining_time": "7:03:47"}
50
+ {"current_steps": 490, "total_steps": 1257, "loss": 0.4035, "lr": 5e-06, "epoch": 1.1688002381661209, "percentage": 38.98, "elapsed_time": "4:27:08", "remaining_time": "6:58:09"}
51
+ {"current_steps": 500, "total_steps": 1257, "loss": 0.4128, "lr": 5e-06, "epoch": 1.1926168502530514, "percentage": 39.78, "elapsed_time": "4:32:29", "remaining_time": "6:52:33"}
52
+ {"current_steps": 510, "total_steps": 1257, "loss": 0.409, "lr": 5e-06, "epoch": 1.2164334623399822, "percentage": 40.57, "elapsed_time": "4:37:48", "remaining_time": "6:46:54"}
53
+ {"current_steps": 520, "total_steps": 1257, "loss": 0.4069, "lr": 5e-06, "epoch": 1.2402500744269127, "percentage": 41.37, "elapsed_time": "4:43:09", "remaining_time": "6:41:19"}
54
+ {"current_steps": 530, "total_steps": 1257, "loss": 0.403, "lr": 5e-06, "epoch": 1.2640666865138435, "percentage": 42.16, "elapsed_time": "4:48:30", "remaining_time": "6:35:44"}
55
+ {"current_steps": 540, "total_steps": 1257, "loss": 0.4043, "lr": 5e-06, "epoch": 1.287883298600774, "percentage": 42.96, "elapsed_time": "4:53:50", "remaining_time": "6:30:09"}
56
+ {"current_steps": 550, "total_steps": 1257, "loss": 0.4063, "lr": 5e-06, "epoch": 1.3116999106877048, "percentage": 43.75, "elapsed_time": "4:59:10", "remaining_time": "6:24:34"}
57
+ {"current_steps": 560, "total_steps": 1257, "loss": 0.4054, "lr": 5e-06, "epoch": 1.3355165227746353, "percentage": 44.55, "elapsed_time": "5:04:29", "remaining_time": "6:18:58"}
58
+ {"current_steps": 570, "total_steps": 1257, "loss": 0.4038, "lr": 5e-06, "epoch": 1.3593331348615658, "percentage": 45.35, "elapsed_time": "5:09:48", "remaining_time": "6:13:23"}
59
+ {"current_steps": 580, "total_steps": 1257, "loss": 0.4041, "lr": 5e-06, "epoch": 1.3831497469484966, "percentage": 46.14, "elapsed_time": "5:15:07", "remaining_time": "6:07:49"}
60
+ {"current_steps": 590, "total_steps": 1257, "loss": 0.4064, "lr": 5e-06, "epoch": 1.4069663590354273, "percentage": 46.94, "elapsed_time": "5:20:27", "remaining_time": "6:02:17"}
61
+ {"current_steps": 600, "total_steps": 1257, "loss": 0.3998, "lr": 5e-06, "epoch": 1.4307829711223579, "percentage": 47.73, "elapsed_time": "5:25:46", "remaining_time": "5:56:43"}
62
+ {"current_steps": 610, "total_steps": 1257, "loss": 0.4024, "lr": 5e-06, "epoch": 1.4545995832092884, "percentage": 48.53, "elapsed_time": "5:31:06", "remaining_time": "5:51:12"}
63
+ {"current_steps": 620, "total_steps": 1257, "loss": 0.4026, "lr": 5e-06, "epoch": 1.4784161952962191, "percentage": 49.32, "elapsed_time": "5:36:26", "remaining_time": "5:45:40"}
64
+ {"current_steps": 630, "total_steps": 1257, "loss": 0.4027, "lr": 5e-06, "epoch": 1.50223280738315, "percentage": 50.12, "elapsed_time": "5:41:47", "remaining_time": "5:40:09"}
65
+ {"current_steps": 640, "total_steps": 1257, "loss": 0.4054, "lr": 5e-06, "epoch": 1.5260494194700804, "percentage": 50.91, "elapsed_time": "5:47:07", "remaining_time": "5:34:38"}
66
+ {"current_steps": 650, "total_steps": 1257, "loss": 0.402, "lr": 5e-06, "epoch": 1.549866031557011, "percentage": 51.71, "elapsed_time": "5:52:25", "remaining_time": "5:29:06"}
67
+ {"current_steps": 660, "total_steps": 1257, "loss": 0.3977, "lr": 5e-06, "epoch": 1.5736826436439415, "percentage": 52.51, "elapsed_time": "5:57:42", "remaining_time": "5:23:34"}
68
+ {"current_steps": 670, "total_steps": 1257, "loss": 0.3986, "lr": 5e-06, "epoch": 1.5974992557308723, "percentage": 53.3, "elapsed_time": "6:03:03", "remaining_time": "5:18:04"}
69
+ {"current_steps": 680, "total_steps": 1257, "loss": 0.4037, "lr": 5e-06, "epoch": 1.621315867817803, "percentage": 54.1, "elapsed_time": "6:08:23", "remaining_time": "5:12:35"}
70
+ {"current_steps": 690, "total_steps": 1257, "loss": 0.4022, "lr": 5e-06, "epoch": 1.6451324799047335, "percentage": 54.89, "elapsed_time": "6:13:42", "remaining_time": "5:07:05"}
71
+ {"current_steps": 700, "total_steps": 1257, "loss": 0.4068, "lr": 5e-06, "epoch": 1.668949091991664, "percentage": 55.69, "elapsed_time": "6:19:00", "remaining_time": "5:01:35"}
72
+ {"current_steps": 710, "total_steps": 1257, "loss": 0.4003, "lr": 5e-06, "epoch": 1.6927657040785948, "percentage": 56.48, "elapsed_time": "6:24:20", "remaining_time": "4:56:06"}
73
+ {"current_steps": 720, "total_steps": 1257, "loss": 0.3978, "lr": 5e-06, "epoch": 1.7165823161655256, "percentage": 57.28, "elapsed_time": "6:29:40", "remaining_time": "4:50:37"}
74
+ {"current_steps": 730, "total_steps": 1257, "loss": 0.4004, "lr": 5e-06, "epoch": 1.7403989282524561, "percentage": 58.07, "elapsed_time": "6:34:59", "remaining_time": "4:45:08"}
75
+ {"current_steps": 740, "total_steps": 1257, "loss": 0.4007, "lr": 5e-06, "epoch": 1.7642155403393867, "percentage": 58.87, "elapsed_time": "6:40:18", "remaining_time": "4:39:40"}
76
+ {"current_steps": 750, "total_steps": 1257, "loss": 0.4011, "lr": 5e-06, "epoch": 1.7880321524263174, "percentage": 59.67, "elapsed_time": "6:45:37", "remaining_time": "4:34:12"}
77
+ {"current_steps": 760, "total_steps": 1257, "loss": 0.3941, "lr": 5e-06, "epoch": 1.811848764513248, "percentage": 60.46, "elapsed_time": "6:50:57", "remaining_time": "4:28:44"}
78
+ {"current_steps": 770, "total_steps": 1257, "loss": 0.4042, "lr": 5e-06, "epoch": 1.8356653766001787, "percentage": 61.26, "elapsed_time": "6:56:15", "remaining_time": "4:23:16"}
79
+ {"current_steps": 780, "total_steps": 1257, "loss": 0.4029, "lr": 5e-06, "epoch": 1.8594819886871092, "percentage": 62.05, "elapsed_time": "7:01:34", "remaining_time": "4:17:48"}
80
+ {"current_steps": 790, "total_steps": 1257, "loss": 0.3992, "lr": 5e-06, "epoch": 1.8832986007740398, "percentage": 62.85, "elapsed_time": "7:06:54", "remaining_time": "4:12:21"}
81
+ {"current_steps": 800, "total_steps": 1257, "loss": 0.3969, "lr": 5e-06, "epoch": 1.9071152128609705, "percentage": 63.64, "elapsed_time": "7:12:13", "remaining_time": "4:06:54"}
82
+ {"current_steps": 810, "total_steps": 1257, "loss": 0.3995, "lr": 5e-06, "epoch": 1.9309318249479013, "percentage": 64.44, "elapsed_time": "7:17:33", "remaining_time": "4:01:28"}
83
+ {"current_steps": 820, "total_steps": 1257, "loss": 0.402, "lr": 5e-06, "epoch": 1.9547484370348318, "percentage": 65.23, "elapsed_time": "7:22:52", "remaining_time": "3:56:01"}
84
+ {"current_steps": 830, "total_steps": 1257, "loss": 0.3953, "lr": 5e-06, "epoch": 1.9785650491217623, "percentage": 66.03, "elapsed_time": "7:28:12", "remaining_time": "3:50:35"}
85
+ {"current_steps": 838, "total_steps": 1257, "eval_loss": 0.43693724274635315, "epoch": 1.997618338791307, "percentage": 66.67, "elapsed_time": "7:37:21", "remaining_time": "3:48:40"}
86
+ {"current_steps": 840, "total_steps": 1257, "loss": 0.4321, "lr": 5e-06, "epoch": 2.004167907115213, "percentage": 66.83, "elapsed_time": "7:39:36", "remaining_time": "3:48:09"}