sedrickkeh commited on
Commit
3843e03
·
verified ·
1 Parent(s): eafc573

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd664d1802b5457934bb10e07fa511e0c96c9f576b4c886ff16f3629c79aa8f7
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4770c11a93fb53c5c7fb03dbf7e00dde651009c354770f44dd1f0d5be1dc9a4
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b4999be5e3837b447f2984076ffa80981aed7764d9ed63795e637505f7877b8
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0269164d6758b0b4f36e8c38ed085deea7e5f8a6079cc3bb307ee5308257fa6
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:b86bf01290ecc2bbe6a0dbc201001d783f4c94b570491857f37f2677a5ff6c96
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d331c41b3a32cdf3ec67078b954f4a1cddfae9be3ce180c28766a228db644a9
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:b022e1f4d171243316ae56316920a7ae289bd4ea9fc8fe5884bf96880ea95357
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b422a2aac3a98492ef1b9de23212158e9b38e081c238086a2c727d66384c77
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -50,3 +50,28 @@
50
  {"current_steps": 490, "total_steps": 756, "loss": 0.7817, "lr": 5e-06, "epoch": 1.9415552253590886, "percentage": 64.81, "elapsed_time": "7:58:04", "remaining_time": "4:19:31"}
51
  {"current_steps": 500, "total_steps": 756, "loss": 0.7778, "lr": 5e-06, "epoch": 1.9811788013868252, "percentage": 66.14, "elapsed_time": "8:07:42", "remaining_time": "4:09:42"}
52
  {"current_steps": 504, "total_steps": 756, "eval_loss": 0.8146935701370239, "epoch": 1.9970282317979198, "percentage": 66.67, "elapsed_time": "8:16:45", "remaining_time": "4:08:22"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  {"current_steps": 490, "total_steps": 756, "loss": 0.7817, "lr": 5e-06, "epoch": 1.9415552253590886, "percentage": 64.81, "elapsed_time": "7:58:04", "remaining_time": "4:19:31"}
51
  {"current_steps": 500, "total_steps": 756, "loss": 0.7778, "lr": 5e-06, "epoch": 1.9811788013868252, "percentage": 66.14, "elapsed_time": "8:07:42", "remaining_time": "4:09:42"}
52
  {"current_steps": 504, "total_steps": 756, "eval_loss": 0.8146935701370239, "epoch": 1.9970282317979198, "percentage": 66.67, "elapsed_time": "8:16:45", "remaining_time": "4:08:22"}
53
+ {"current_steps": 510, "total_steps": 756, "loss": 0.8016, "lr": 5e-06, "epoch": 2.0208023774145616, "percentage": 67.46, "elapsed_time": "8:23:05", "remaining_time": "4:02:39"}
54
+ {"current_steps": 520, "total_steps": 756, "loss": 0.7316, "lr": 5e-06, "epoch": 2.060425953442298, "percentage": 68.78, "elapsed_time": "8:32:44", "remaining_time": "3:52:42"}
55
+ {"current_steps": 530, "total_steps": 756, "loss": 0.7265, "lr": 5e-06, "epoch": 2.1000495294700348, "percentage": 70.11, "elapsed_time": "8:42:24", "remaining_time": "3:42:45"}
56
+ {"current_steps": 540, "total_steps": 756, "loss": 0.7311, "lr": 5e-06, "epoch": 2.139673105497771, "percentage": 71.43, "elapsed_time": "8:52:03", "remaining_time": "3:32:49"}
57
+ {"current_steps": 550, "total_steps": 756, "loss": 0.7294, "lr": 5e-06, "epoch": 2.1792966815255075, "percentage": 72.75, "elapsed_time": "9:01:42", "remaining_time": "3:22:53"}
58
+ {"current_steps": 560, "total_steps": 756, "loss": 0.7307, "lr": 5e-06, "epoch": 2.2189202575532443, "percentage": 74.07, "elapsed_time": "9:11:21", "remaining_time": "3:12:58"}
59
+ {"current_steps": 570, "total_steps": 756, "loss": 0.7325, "lr": 5e-06, "epoch": 2.2585438335809807, "percentage": 75.4, "elapsed_time": "9:21:01", "remaining_time": "3:03:04"}
60
+ {"current_steps": 580, "total_steps": 756, "loss": 0.7352, "lr": 5e-06, "epoch": 2.298167409608717, "percentage": 76.72, "elapsed_time": "9:30:40", "remaining_time": "2:53:10"}
61
+ {"current_steps": 590, "total_steps": 756, "loss": 0.7317, "lr": 5e-06, "epoch": 2.337790985636454, "percentage": 78.04, "elapsed_time": "9:40:18", "remaining_time": "2:43:16"}
62
+ {"current_steps": 600, "total_steps": 756, "loss": 0.7274, "lr": 5e-06, "epoch": 2.37741456166419, "percentage": 79.37, "elapsed_time": "9:49:58", "remaining_time": "2:33:23"}
63
+ {"current_steps": 610, "total_steps": 756, "loss": 0.7301, "lr": 5e-06, "epoch": 2.4170381376919265, "percentage": 80.69, "elapsed_time": "9:59:38", "remaining_time": "2:23:31"}
64
+ {"current_steps": 620, "total_steps": 756, "loss": 0.734, "lr": 5e-06, "epoch": 2.4566617137196634, "percentage": 82.01, "elapsed_time": "10:09:17", "remaining_time": "2:13:38"}
65
+ {"current_steps": 630, "total_steps": 756, "loss": 0.7361, "lr": 5e-06, "epoch": 2.4962852897473997, "percentage": 83.33, "elapsed_time": "10:18:56", "remaining_time": "2:03:47"}
66
+ {"current_steps": 640, "total_steps": 756, "loss": 0.7327, "lr": 5e-06, "epoch": 2.535908865775136, "percentage": 84.66, "elapsed_time": "10:28:34", "remaining_time": "1:53:55"}
67
+ {"current_steps": 650, "total_steps": 756, "loss": 0.7346, "lr": 5e-06, "epoch": 2.5755324418028724, "percentage": 85.98, "elapsed_time": "10:38:12", "remaining_time": "1:44:04"}
68
+ {"current_steps": 660, "total_steps": 756, "loss": 0.7314, "lr": 5e-06, "epoch": 2.6151560178306092, "percentage": 87.3, "elapsed_time": "10:47:51", "remaining_time": "1:34:14"}
69
+ {"current_steps": 670, "total_steps": 756, "loss": 0.7352, "lr": 5e-06, "epoch": 2.6547795938583456, "percentage": 88.62, "elapsed_time": "10:57:29", "remaining_time": "1:24:23"}
70
+ {"current_steps": 680, "total_steps": 756, "loss": 0.7328, "lr": 5e-06, "epoch": 2.6944031698860824, "percentage": 89.95, "elapsed_time": "11:07:08", "remaining_time": "1:14:33"}
71
+ {"current_steps": 690, "total_steps": 756, "loss": 0.7353, "lr": 5e-06, "epoch": 2.734026745913819, "percentage": 91.27, "elapsed_time": "11:16:47", "remaining_time": "1:04:44"}
72
+ {"current_steps": 700, "total_steps": 756, "loss": 0.7359, "lr": 5e-06, "epoch": 2.773650321941555, "percentage": 92.59, "elapsed_time": "11:26:27", "remaining_time": "0:54:54"}
73
+ {"current_steps": 710, "total_steps": 756, "loss": 0.7289, "lr": 5e-06, "epoch": 2.8132738979692915, "percentage": 93.92, "elapsed_time": "11:36:06", "remaining_time": "0:45:05"}
74
+ {"current_steps": 720, "total_steps": 756, "loss": 0.7321, "lr": 5e-06, "epoch": 2.8528974739970283, "percentage": 95.24, "elapsed_time": "11:45:44", "remaining_time": "0:35:17"}
75
+ {"current_steps": 730, "total_steps": 756, "loss": 0.7363, "lr": 5e-06, "epoch": 2.8925210500247647, "percentage": 96.56, "elapsed_time": "11:55:23", "remaining_time": "0:25:28"}
76
+ {"current_steps": 740, "total_steps": 756, "loss": 0.7317, "lr": 5e-06, "epoch": 2.9321446260525015, "percentage": 97.88, "elapsed_time": "12:05:02", "remaining_time": "0:15:40"}
77
+ {"current_steps": 750, "total_steps": 756, "loss": 0.7327, "lr": 5e-06, "epoch": 2.971768202080238, "percentage": 99.21, "elapsed_time": "12:14:41", "remaining_time": "0:05:52"}