sedrickkeh commited on
Commit
acadfbb
·
verified ·
1 Parent(s): d72e42a

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 sha256:78c82be77c2f912d9a2f10f405ddaf2c3327fbc77600e501d81e5bd61baf9bef
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af955f154057eadbe15f95e17cb1e465a6317cda2d323f81005c38c2c77761c9
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1643b616abdda78e5a6f7d63d2a7adaa00b0fb2e065b624384f34cca8215f59d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d185e5e215a6583a87f182e86df92099125e498707f058dd277f1adcc164390
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:b3a43014ce6901f6e53441d268b9832eb34baa04d1287668cdb31cb8fab6e934
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e98de217bf49eea35b85d40cd7e4f11e18e4d79275953496f1b485ec89baf64
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:cea43ad41a833819cd88953897e82b5f1a7d0b263c2e248d68721d93023d3432
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d0148b78d67844a16091de7bd83e29932714767b72177d6086d789cdf16da5
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -41,3 +41,45 @@
41
  {"current_steps": 410, "total_steps": 844, "loss": 0.6489, "lr": 5e-06, "epoch": 0.9701271813073056, "percentage": 48.58, "elapsed_time": "6:35:38", "remaining_time": "6:58:47"}
42
  {"current_steps": 420, "total_steps": 844, "loss": 0.6478, "lr": 5e-06, "epoch": 0.9937888198757764, "percentage": 49.76, "elapsed_time": "6:45:17", "remaining_time": "6:49:08"}
43
  {"current_steps": 422, "total_steps": 844, "eval_loss": 0.6501929759979248, "epoch": 0.9985211475894705, "percentage": 50.0, "elapsed_time": "6:55:11", "remaining_time": "6:55:11"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  {"current_steps": 410, "total_steps": 844, "loss": 0.6489, "lr": 5e-06, "epoch": 0.9701271813073056, "percentage": 48.58, "elapsed_time": "6:35:38", "remaining_time": "6:58:47"}
42
  {"current_steps": 420, "total_steps": 844, "loss": 0.6478, "lr": 5e-06, "epoch": 0.9937888198757764, "percentage": 49.76, "elapsed_time": "6:45:17", "remaining_time": "6:49:08"}
43
  {"current_steps": 422, "total_steps": 844, "eval_loss": 0.6501929759979248, "epoch": 0.9985211475894705, "percentage": 50.0, "elapsed_time": "6:55:11", "remaining_time": "6:55:11"}
44
+ {"current_steps": 430, "total_steps": 844, "loss": 0.6515, "lr": 5e-06, "epoch": 1.0177462289263532, "percentage": 50.95, "elapsed_time": "7:03:39", "remaining_time": "6:47:53"}
45
+ {"current_steps": 440, "total_steps": 844, "loss": 0.605, "lr": 5e-06, "epoch": 1.041407867494824, "percentage": 52.13, "elapsed_time": "7:13:18", "remaining_time": "6:37:51"}
46
+ {"current_steps": 450, "total_steps": 844, "loss": 0.603, "lr": 5e-06, "epoch": 1.0650695060632949, "percentage": 53.32, "elapsed_time": "7:22:57", "remaining_time": "6:27:50"}
47
+ {"current_steps": 460, "total_steps": 844, "loss": 0.6134, "lr": 5e-06, "epoch": 1.0887311446317658, "percentage": 54.5, "elapsed_time": "7:32:37", "remaining_time": "6:17:50"}
48
+ {"current_steps": 470, "total_steps": 844, "loss": 0.6106, "lr": 5e-06, "epoch": 1.1123927832002367, "percentage": 55.69, "elapsed_time": "7:42:16", "remaining_time": "6:07:51"}
49
+ {"current_steps": 480, "total_steps": 844, "loss": 0.611, "lr": 5e-06, "epoch": 1.1360544217687074, "percentage": 56.87, "elapsed_time": "7:51:56", "remaining_time": "5:57:53"}
50
+ {"current_steps": 490, "total_steps": 844, "loss": 0.6079, "lr": 5e-06, "epoch": 1.1597160603371783, "percentage": 58.06, "elapsed_time": "8:01:37", "remaining_time": "5:47:56"}
51
+ {"current_steps": 500, "total_steps": 844, "loss": 0.6036, "lr": 5e-06, "epoch": 1.1833776989056493, "percentage": 59.24, "elapsed_time": "8:11:17", "remaining_time": "5:38:00"}
52
+ {"current_steps": 510, "total_steps": 844, "loss": 0.6034, "lr": 5e-06, "epoch": 1.2070393374741202, "percentage": 60.43, "elapsed_time": "8:20:55", "remaining_time": "5:28:03"}
53
+ {"current_steps": 520, "total_steps": 844, "loss": 0.6099, "lr": 5e-06, "epoch": 1.2307009760425909, "percentage": 61.61, "elapsed_time": "8:30:36", "remaining_time": "5:18:08"}
54
+ {"current_steps": 530, "total_steps": 844, "loss": 0.6125, "lr": 5e-06, "epoch": 1.2543626146110618, "percentage": 62.8, "elapsed_time": "8:40:16", "remaining_time": "5:08:14"}
55
+ {"current_steps": 540, "total_steps": 844, "loss": 0.6121, "lr": 5e-06, "epoch": 1.2780242531795327, "percentage": 63.98, "elapsed_time": "8:49:56", "remaining_time": "4:58:20"}
56
+ {"current_steps": 550, "total_steps": 844, "loss": 0.6089, "lr": 5e-06, "epoch": 1.3016858917480034, "percentage": 65.17, "elapsed_time": "8:59:37", "remaining_time": "4:48:27"}
57
+ {"current_steps": 560, "total_steps": 844, "loss": 0.6073, "lr": 5e-06, "epoch": 1.3253475303164743, "percentage": 66.35, "elapsed_time": "9:09:16", "remaining_time": "4:38:33"}
58
+ {"current_steps": 570, "total_steps": 844, "loss": 0.6084, "lr": 5e-06, "epoch": 1.3490091688849453, "percentage": 67.54, "elapsed_time": "9:18:56", "remaining_time": "4:28:41"}
59
+ {"current_steps": 580, "total_steps": 844, "loss": 0.611, "lr": 5e-06, "epoch": 1.3726708074534162, "percentage": 68.72, "elapsed_time": "9:28:36", "remaining_time": "4:18:48"}
60
+ {"current_steps": 590, "total_steps": 844, "loss": 0.6115, "lr": 5e-06, "epoch": 1.396332446021887, "percentage": 69.91, "elapsed_time": "9:38:14", "remaining_time": "4:08:56"}
61
+ {"current_steps": 600, "total_steps": 844, "loss": 0.6008, "lr": 5e-06, "epoch": 1.4199940845903578, "percentage": 71.09, "elapsed_time": "9:47:54", "remaining_time": "3:59:05"}
62
+ {"current_steps": 610, "total_steps": 844, "loss": 0.6002, "lr": 5e-06, "epoch": 1.4436557231588287, "percentage": 72.27, "elapsed_time": "9:57:33", "remaining_time": "3:49:13"}
63
+ {"current_steps": 620, "total_steps": 844, "loss": 0.6037, "lr": 5e-06, "epoch": 1.4673173617272997, "percentage": 73.46, "elapsed_time": "10:07:13", "remaining_time": "3:39:23"}
64
+ {"current_steps": 630, "total_steps": 844, "loss": 0.6157, "lr": 5e-06, "epoch": 1.4909790002957704, "percentage": 74.64, "elapsed_time": "10:16:54", "remaining_time": "3:29:33"}
65
+ {"current_steps": 640, "total_steps": 844, "loss": 0.6101, "lr": 5e-06, "epoch": 1.5146406388642415, "percentage": 75.83, "elapsed_time": "10:26:33", "remaining_time": "3:19:42"}
66
+ {"current_steps": 650, "total_steps": 844, "loss": 0.6042, "lr": 5e-06, "epoch": 1.5383022774327122, "percentage": 77.01, "elapsed_time": "10:36:13", "remaining_time": "3:09:53"}
67
+ {"current_steps": 660, "total_steps": 844, "loss": 0.609, "lr": 5e-06, "epoch": 1.5619639160011831, "percentage": 78.2, "elapsed_time": "10:45:53", "remaining_time": "3:00:04"}
68
+ {"current_steps": 670, "total_steps": 844, "loss": 0.6015, "lr": 5e-06, "epoch": 1.585625554569654, "percentage": 79.38, "elapsed_time": "10:55:34", "remaining_time": "2:50:15"}
69
+ {"current_steps": 680, "total_steps": 844, "loss": 0.6098, "lr": 5e-06, "epoch": 1.6092871931381247, "percentage": 80.57, "elapsed_time": "11:05:14", "remaining_time": "2:40:26"}
70
+ {"current_steps": 690, "total_steps": 844, "loss": 0.601, "lr": 5e-06, "epoch": 1.6329488317065957, "percentage": 81.75, "elapsed_time": "11:14:54", "remaining_time": "2:30:37"}
71
+ {"current_steps": 700, "total_steps": 844, "loss": 0.6107, "lr": 5e-06, "epoch": 1.6566104702750666, "percentage": 82.94, "elapsed_time": "11:24:33", "remaining_time": "2:20:49"}
72
+ {"current_steps": 710, "total_steps": 844, "loss": 0.609, "lr": 5e-06, "epoch": 1.6802721088435373, "percentage": 84.12, "elapsed_time": "11:34:12", "remaining_time": "2:11:01"}
73
+ {"current_steps": 720, "total_steps": 844, "loss": 0.6118, "lr": 5e-06, "epoch": 1.7039337474120084, "percentage": 85.31, "elapsed_time": "11:43:52", "remaining_time": "2:01:13"}
74
+ {"current_steps": 730, "total_steps": 844, "loss": 0.6116, "lr": 5e-06, "epoch": 1.7275953859804791, "percentage": 86.49, "elapsed_time": "11:53:32", "remaining_time": "1:51:25"}
75
+ {"current_steps": 740, "total_steps": 844, "loss": 0.6039, "lr": 5e-06, "epoch": 1.75125702454895, "percentage": 87.68, "elapsed_time": "12:03:12", "remaining_time": "1:41:38"}
76
+ {"current_steps": 750, "total_steps": 844, "loss": 0.6101, "lr": 5e-06, "epoch": 1.774918663117421, "percentage": 88.86, "elapsed_time": "12:12:53", "remaining_time": "1:31:51"}
77
+ {"current_steps": 760, "total_steps": 844, "loss": 0.614, "lr": 5e-06, "epoch": 1.7985803016858917, "percentage": 90.05, "elapsed_time": "12:22:34", "remaining_time": "1:22:04"}
78
+ {"current_steps": 770, "total_steps": 844, "loss": 0.6158, "lr": 5e-06, "epoch": 1.8222419402543626, "percentage": 91.23, "elapsed_time": "12:32:13", "remaining_time": "1:12:17"}
79
+ {"current_steps": 780, "total_steps": 844, "loss": 0.6067, "lr": 5e-06, "epoch": 1.8459035788228335, "percentage": 92.42, "elapsed_time": "12:41:54", "remaining_time": "1:02:30"}
80
+ {"current_steps": 790, "total_steps": 844, "loss": 0.6054, "lr": 5e-06, "epoch": 1.8695652173913042, "percentage": 93.6, "elapsed_time": "12:51:34", "remaining_time": "0:52:44"}
81
+ {"current_steps": 800, "total_steps": 844, "loss": 0.6137, "lr": 5e-06, "epoch": 1.8932268559597754, "percentage": 94.79, "elapsed_time": "13:01:13", "remaining_time": "0:42:58"}
82
+ {"current_steps": 810, "total_steps": 844, "loss": 0.6114, "lr": 5e-06, "epoch": 1.916888494528246, "percentage": 95.97, "elapsed_time": "13:10:53", "remaining_time": "0:33:11"}
83
+ {"current_steps": 820, "total_steps": 844, "loss": 0.5996, "lr": 5e-06, "epoch": 1.940550133096717, "percentage": 97.16, "elapsed_time": "13:20:33", "remaining_time": "0:23:25"}
84
+ {"current_steps": 830, "total_steps": 844, "loss": 0.6108, "lr": 5e-06, "epoch": 1.964211771665188, "percentage": 98.34, "elapsed_time": "13:30:14", "remaining_time": "0:13:40"}
85
+ {"current_steps": 840, "total_steps": 844, "loss": 0.5981, "lr": 5e-06, "epoch": 1.9878734102336586, "percentage": 99.53, "elapsed_time": "13:39:54", "remaining_time": "0:03:54"}