sedrickkeh commited on
Commit
63dc119
·
verified ·
1 Parent(s): fd86056

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 sha256:066b3a7a5cf27a05c66469227322ea54d585bd7dd867095f6609c2314a9aed6c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ab6bd4888fa3ad59fde35bae043002dcd0fc74c529b44a14e739b5b0c89b6e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ae10e4075b7357ae976c42cb7a4c966165b2b685a6bc0b7c2b71d8f642ed7c9
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17512d00a78e7d69bdae69de85d1de184df9b441868a329b310467184bc8468c
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08c1823d209ec9ea7c7004f85d603ae41fbe9d65e557568f49837598e1543756
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02482d851e4ce3e70350c56eb07e9e09bb2d8c196b546adbc4baeda77550edaf
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:a3609e213adee70875805ab34294ced85b87f699c57bfaa35e2fd2ae7582553b
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928961851868c825e9e085b1221cbe54937b3bd4d8cc5cf817c3f2b74f6c0e18
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -41,3 +41,46 @@
41
  {"current_steps": 410, "total_steps": 1266, "loss": 0.6491, "lr": 5e-06, "epoch": 0.9701271813073056, "percentage": 32.39, "elapsed_time": "3:39:39", "remaining_time": "7:38:35"}
42
  {"current_steps": 420, "total_steps": 1266, "loss": 0.648, "lr": 5e-06, "epoch": 0.9937888198757764, "percentage": 33.18, "elapsed_time": "3:44:59", "remaining_time": "7:33:11"}
43
  {"current_steps": 422, "total_steps": 1266, "eval_loss": 0.6503860950469971, "epoch": 0.9985211475894705, "percentage": 33.33, "elapsed_time": "3:51:15", "remaining_time": "7:42:30"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  {"current_steps": 410, "total_steps": 1266, "loss": 0.6491, "lr": 5e-06, "epoch": 0.9701271813073056, "percentage": 32.39, "elapsed_time": "3:39:39", "remaining_time": "7:38:35"}
42
  {"current_steps": 420, "total_steps": 1266, "loss": 0.648, "lr": 5e-06, "epoch": 0.9937888198757764, "percentage": 33.18, "elapsed_time": "3:44:59", "remaining_time": "7:33:11"}
43
  {"current_steps": 422, "total_steps": 1266, "eval_loss": 0.6503860950469971, "epoch": 0.9985211475894705, "percentage": 33.33, "elapsed_time": "3:51:15", "remaining_time": "7:42:30"}
44
+ {"current_steps": 430, "total_steps": 1266, "loss": 0.6519, "lr": 5e-06, "epoch": 1.0177462289263532, "percentage": 33.97, "elapsed_time": "3:56:30", "remaining_time": "7:39:48"}
45
+ {"current_steps": 440, "total_steps": 1266, "loss": 0.6054, "lr": 5e-06, "epoch": 1.041407867494824, "percentage": 34.76, "elapsed_time": "4:01:52", "remaining_time": "7:34:03"}
46
+ {"current_steps": 450, "total_steps": 1266, "loss": 0.6036, "lr": 5e-06, "epoch": 1.0650695060632949, "percentage": 35.55, "elapsed_time": "4:07:11", "remaining_time": "7:28:14"}
47
+ {"current_steps": 460, "total_steps": 1266, "loss": 0.6138, "lr": 5e-06, "epoch": 1.0887311446317658, "percentage": 36.33, "elapsed_time": "4:12:31", "remaining_time": "7:22:28"}
48
+ {"current_steps": 470, "total_steps": 1266, "loss": 0.611, "lr": 5e-06, "epoch": 1.1123927832002367, "percentage": 37.12, "elapsed_time": "4:17:53", "remaining_time": "7:16:45"}
49
+ {"current_steps": 480, "total_steps": 1266, "loss": 0.6114, "lr": 5e-06, "epoch": 1.1360544217687074, "percentage": 37.91, "elapsed_time": "4:23:13", "remaining_time": "7:11:02"}
50
+ {"current_steps": 490, "total_steps": 1266, "loss": 0.6083, "lr": 5e-06, "epoch": 1.1597160603371783, "percentage": 38.7, "elapsed_time": "4:28:34", "remaining_time": "7:05:19"}
51
+ {"current_steps": 500, "total_steps": 1266, "loss": 0.6038, "lr": 5e-06, "epoch": 1.1833776989056493, "percentage": 39.49, "elapsed_time": "4:33:55", "remaining_time": "6:59:38"}
52
+ {"current_steps": 510, "total_steps": 1266, "loss": 0.6038, "lr": 5e-06, "epoch": 1.2070393374741202, "percentage": 40.28, "elapsed_time": "4:39:16", "remaining_time": "6:53:58"}
53
+ {"current_steps": 520, "total_steps": 1266, "loss": 0.6103, "lr": 5e-06, "epoch": 1.2307009760425909, "percentage": 41.07, "elapsed_time": "4:44:37", "remaining_time": "6:48:19"}
54
+ {"current_steps": 530, "total_steps": 1266, "loss": 0.6129, "lr": 5e-06, "epoch": 1.2543626146110618, "percentage": 41.86, "elapsed_time": "4:49:57", "remaining_time": "6:42:40"}
55
+ {"current_steps": 540, "total_steps": 1266, "loss": 0.6125, "lr": 5e-06, "epoch": 1.2780242531795327, "percentage": 42.65, "elapsed_time": "4:55:19", "remaining_time": "6:37:02"}
56
+ {"current_steps": 550, "total_steps": 1266, "loss": 0.6094, "lr": 5e-06, "epoch": 1.3016858917480034, "percentage": 43.44, "elapsed_time": "5:00:38", "remaining_time": "6:31:23"}
57
+ {"current_steps": 560, "total_steps": 1266, "loss": 0.6076, "lr": 5e-06, "epoch": 1.3253475303164743, "percentage": 44.23, "elapsed_time": "5:05:58", "remaining_time": "6:25:45"}
58
+ {"current_steps": 570, "total_steps": 1266, "loss": 0.6086, "lr": 5e-06, "epoch": 1.3490091688849453, "percentage": 45.02, "elapsed_time": "5:11:18", "remaining_time": "6:20:07"}
59
+ {"current_steps": 580, "total_steps": 1266, "loss": 0.6114, "lr": 5e-06, "epoch": 1.3726708074534162, "percentage": 45.81, "elapsed_time": "5:16:40", "remaining_time": "6:14:32"}
60
+ {"current_steps": 590, "total_steps": 1266, "loss": 0.6118, "lr": 5e-06, "epoch": 1.396332446021887, "percentage": 46.6, "elapsed_time": "5:22:02", "remaining_time": "6:08:58"}
61
+ {"current_steps": 600, "total_steps": 1266, "loss": 0.6012, "lr": 5e-06, "epoch": 1.4199940845903578, "percentage": 47.39, "elapsed_time": "5:27:23", "remaining_time": "6:03:24"}
62
+ {"current_steps": 610, "total_steps": 1266, "loss": 0.6006, "lr": 5e-06, "epoch": 1.4436557231588287, "percentage": 48.18, "elapsed_time": "5:32:43", "remaining_time": "5:57:49"}
63
+ {"current_steps": 620, "total_steps": 1266, "loss": 0.6041, "lr": 5e-06, "epoch": 1.4673173617272997, "percentage": 48.97, "elapsed_time": "5:38:03", "remaining_time": "5:52:13"}
64
+ {"current_steps": 630, "total_steps": 1266, "loss": 0.6161, "lr": 5e-06, "epoch": 1.4909790002957704, "percentage": 49.76, "elapsed_time": "5:43:23", "remaining_time": "5:46:39"}
65
+ {"current_steps": 640, "total_steps": 1266, "loss": 0.6104, "lr": 5e-06, "epoch": 1.5146406388642415, "percentage": 50.55, "elapsed_time": "5:48:45", "remaining_time": "5:41:07"}
66
+ {"current_steps": 650, "total_steps": 1266, "loss": 0.6044, "lr": 5e-06, "epoch": 1.5383022774327122, "percentage": 51.34, "elapsed_time": "5:54:03", "remaining_time": "5:35:32"}
67
+ {"current_steps": 660, "total_steps": 1266, "loss": 0.6093, "lr": 5e-06, "epoch": 1.5619639160011831, "percentage": 52.13, "elapsed_time": "5:59:23", "remaining_time": "5:29:59"}
68
+ {"current_steps": 670, "total_steps": 1266, "loss": 0.6018, "lr": 5e-06, "epoch": 1.585625554569654, "percentage": 52.92, "elapsed_time": "6:04:44", "remaining_time": "5:24:27"}
69
+ {"current_steps": 680, "total_steps": 1266, "loss": 0.6103, "lr": 5e-06, "epoch": 1.6092871931381247, "percentage": 53.71, "elapsed_time": "6:10:02", "remaining_time": "5:18:53"}
70
+ {"current_steps": 690, "total_steps": 1266, "loss": 0.6013, "lr": 5e-06, "epoch": 1.6329488317065957, "percentage": 54.5, "elapsed_time": "6:15:21", "remaining_time": "5:13:20"}
71
+ {"current_steps": 700, "total_steps": 1266, "loss": 0.6109, "lr": 5e-06, "epoch": 1.6566104702750666, "percentage": 55.29, "elapsed_time": "6:20:39", "remaining_time": "5:07:47"}
72
+ {"current_steps": 710, "total_steps": 1266, "loss": 0.6094, "lr": 5e-06, "epoch": 1.6802721088435373, "percentage": 56.08, "elapsed_time": "6:26:00", "remaining_time": "5:02:17"}
73
+ {"current_steps": 720, "total_steps": 1266, "loss": 0.6122, "lr": 5e-06, "epoch": 1.7039337474120084, "percentage": 56.87, "elapsed_time": "6:31:23", "remaining_time": "4:56:48"}
74
+ {"current_steps": 730, "total_steps": 1266, "loss": 0.612, "lr": 5e-06, "epoch": 1.7275953859804791, "percentage": 57.66, "elapsed_time": "6:36:41", "remaining_time": "4:51:16"}
75
+ {"current_steps": 740, "total_steps": 1266, "loss": 0.6042, "lr": 5e-06, "epoch": 1.75125702454895, "percentage": 58.45, "elapsed_time": "6:42:02", "remaining_time": "4:45:46"}
76
+ {"current_steps": 750, "total_steps": 1266, "loss": 0.6105, "lr": 5e-06, "epoch": 1.774918663117421, "percentage": 59.24, "elapsed_time": "6:47:23", "remaining_time": "4:40:17"}
77
+ {"current_steps": 760, "total_steps": 1266, "loss": 0.6146, "lr": 5e-06, "epoch": 1.7985803016858917, "percentage": 60.03, "elapsed_time": "6:52:46", "remaining_time": "4:34:48"}
78
+ {"current_steps": 770, "total_steps": 1266, "loss": 0.6161, "lr": 5e-06, "epoch": 1.8222419402543626, "percentage": 60.82, "elapsed_time": "6:58:07", "remaining_time": "4:29:20"}
79
+ {"current_steps": 780, "total_steps": 1266, "loss": 0.607, "lr": 5e-06, "epoch": 1.8459035788228335, "percentage": 61.61, "elapsed_time": "7:03:27", "remaining_time": "4:23:50"}
80
+ {"current_steps": 790, "total_steps": 1266, "loss": 0.6057, "lr": 5e-06, "epoch": 1.8695652173913042, "percentage": 62.4, "elapsed_time": "7:08:48", "remaining_time": "4:18:21"}
81
+ {"current_steps": 800, "total_steps": 1266, "loss": 0.614, "lr": 5e-06, "epoch": 1.8932268559597754, "percentage": 63.19, "elapsed_time": "7:14:08", "remaining_time": "4:12:53"}
82
+ {"current_steps": 810, "total_steps": 1266, "loss": 0.6118, "lr": 5e-06, "epoch": 1.916888494528246, "percentage": 63.98, "elapsed_time": "7:19:29", "remaining_time": "4:07:25"}
83
+ {"current_steps": 820, "total_steps": 1266, "loss": 0.6, "lr": 5e-06, "epoch": 1.940550133096717, "percentage": 64.77, "elapsed_time": "7:24:50", "remaining_time": "4:01:57"}
84
+ {"current_steps": 830, "total_steps": 1266, "loss": 0.6112, "lr": 5e-06, "epoch": 1.964211771665188, "percentage": 65.56, "elapsed_time": "7:30:10", "remaining_time": "3:56:28"}
85
+ {"current_steps": 840, "total_steps": 1266, "loss": 0.5984, "lr": 5e-06, "epoch": 1.9878734102336586, "percentage": 66.35, "elapsed_time": "7:35:29", "remaining_time": "3:50:59"}
86
+ {"current_steps": 845, "total_steps": 1266, "eval_loss": 0.640017032623291, "epoch": 1.999704229517894, "percentage": 66.75, "elapsed_time": "7:42:57", "remaining_time": "3:50:39"}