sedrickkeh commited on
Commit
2c2263a
·
verified ·
1 Parent(s): 2910f76

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 sha256:4fbc9025a3c36aa92270726707bcb364b8974cac8eae9e9b8b7a4516efadccce
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b4bc1ce0e765e64ad79e4fcbd4e983ebd9ba061fab0d36c261b247a411016c
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:b83c4b96c07e6b1cf5c74b9b677d2843f7e477a95aff4a76df643e3c56577738
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465382e517332d108a535d86ee365128bff708b5d8ef83b1afc95be4b7e70b04
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63a0cbeb36c7832a9e5d62b9b719576e9d19cb0a9c70a319353ebca727df8d47
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb4d9346a9205144160b408e062fae197618a09b6b1d34d5439ebe6df1d9b8c
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:b2cbab2687c53cce2bfa947024e837002c8db0a0d57f85d9545e92e4c65da4b0
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12afde00a7bbdf0a32afab8654542b839ba9bd0bc86e25e78cf5ba9d3b7562b
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -80,3 +80,42 @@
80
  {"current_steps": 790, "total_steps": 1197, "loss": 0.7419, "lr": 5e-06, "epoch": 1.9780976220275344, "percentage": 66.0, "elapsed_time": "7:03:29", "remaining_time": "3:38:10"}
81
  {"current_steps": 798, "total_steps": 1197, "eval_loss": 0.7726743817329407, "epoch": 1.9981226533166458, "percentage": 66.67, "elapsed_time": "7:12:37", "remaining_time": "3:36:18"}
82
  {"current_steps": 800, "total_steps": 1197, "loss": 0.7865, "lr": 5e-06, "epoch": 2.0037546933667083, "percentage": 66.83, "elapsed_time": "7:14:45", "remaining_time": "3:35:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  {"current_steps": 790, "total_steps": 1197, "loss": 0.7419, "lr": 5e-06, "epoch": 1.9780976220275344, "percentage": 66.0, "elapsed_time": "7:03:29", "remaining_time": "3:38:10"}
81
  {"current_steps": 798, "total_steps": 1197, "eval_loss": 0.7726743817329407, "epoch": 1.9981226533166458, "percentage": 66.67, "elapsed_time": "7:12:37", "remaining_time": "3:36:18"}
82
  {"current_steps": 800, "total_steps": 1197, "loss": 0.7865, "lr": 5e-06, "epoch": 2.0037546933667083, "percentage": 66.83, "elapsed_time": "7:14:45", "remaining_time": "3:35:44"}
83
+ {"current_steps": 810, "total_steps": 1197, "loss": 0.699, "lr": 5e-06, "epoch": 2.0287859824780976, "percentage": 67.67, "elapsed_time": "7:20:01", "remaining_time": "3:30:14"}
84
+ {"current_steps": 820, "total_steps": 1197, "loss": 0.6925, "lr": 5e-06, "epoch": 2.053817271589487, "percentage": 68.5, "elapsed_time": "7:25:20", "remaining_time": "3:24:44"}
85
+ {"current_steps": 830, "total_steps": 1197, "loss": 0.6919, "lr": 5e-06, "epoch": 2.078848560700876, "percentage": 69.34, "elapsed_time": "7:30:38", "remaining_time": "3:19:15"}
86
+ {"current_steps": 840, "total_steps": 1197, "loss": 0.6934, "lr": 5e-06, "epoch": 2.1038798498122655, "percentage": 70.18, "elapsed_time": "7:35:56", "remaining_time": "3:13:46"}
87
+ {"current_steps": 850, "total_steps": 1197, "loss": 0.6927, "lr": 5e-06, "epoch": 2.1289111389236544, "percentage": 71.01, "elapsed_time": "7:41:14", "remaining_time": "3:08:17"}
88
+ {"current_steps": 860, "total_steps": 1197, "loss": 0.6937, "lr": 5e-06, "epoch": 2.1539424280350437, "percentage": 71.85, "elapsed_time": "7:46:31", "remaining_time": "3:02:48"}
89
+ {"current_steps": 870, "total_steps": 1197, "loss": 0.6945, "lr": 5e-06, "epoch": 2.178973717146433, "percentage": 72.68, "elapsed_time": "7:51:48", "remaining_time": "2:57:20"}
90
+ {"current_steps": 880, "total_steps": 1197, "loss": 0.6944, "lr": 5e-06, "epoch": 2.2040050062578223, "percentage": 73.52, "elapsed_time": "7:57:06", "remaining_time": "2:51:52"}
91
+ {"current_steps": 890, "total_steps": 1197, "loss": 0.6964, "lr": 5e-06, "epoch": 2.2290362953692116, "percentage": 74.35, "elapsed_time": "8:02:24", "remaining_time": "2:46:24"}
92
+ {"current_steps": 900, "total_steps": 1197, "loss": 0.6935, "lr": 5e-06, "epoch": 2.254067584480601, "percentage": 75.19, "elapsed_time": "8:07:43", "remaining_time": "2:40:56"}
93
+ {"current_steps": 910, "total_steps": 1197, "loss": 0.6993, "lr": 5e-06, "epoch": 2.27909887359199, "percentage": 76.02, "elapsed_time": "8:13:00", "remaining_time": "2:35:29"}
94
+ {"current_steps": 920, "total_steps": 1197, "loss": 0.6986, "lr": 5e-06, "epoch": 2.3041301627033794, "percentage": 76.86, "elapsed_time": "8:18:20", "remaining_time": "2:30:02"}
95
+ {"current_steps": 930, "total_steps": 1197, "loss": 0.6979, "lr": 5e-06, "epoch": 2.3291614518147683, "percentage": 77.69, "elapsed_time": "8:23:39", "remaining_time": "2:24:35"}
96
+ {"current_steps": 940, "total_steps": 1197, "loss": 0.6985, "lr": 5e-06, "epoch": 2.3541927409261576, "percentage": 78.53, "elapsed_time": "8:28:58", "remaining_time": "2:19:09"}
97
+ {"current_steps": 950, "total_steps": 1197, "loss": 0.6994, "lr": 5e-06, "epoch": 2.379224030037547, "percentage": 79.37, "elapsed_time": "8:34:17", "remaining_time": "2:13:42"}
98
+ {"current_steps": 960, "total_steps": 1197, "loss": 0.6953, "lr": 5e-06, "epoch": 2.404255319148936, "percentage": 80.2, "elapsed_time": "8:39:34", "remaining_time": "2:08:16"}
99
+ {"current_steps": 970, "total_steps": 1197, "loss": 0.6977, "lr": 5e-06, "epoch": 2.4292866082603255, "percentage": 81.04, "elapsed_time": "8:44:53", "remaining_time": "2:02:50"}
100
+ {"current_steps": 980, "total_steps": 1197, "loss": 0.6936, "lr": 5e-06, "epoch": 2.454317897371715, "percentage": 81.87, "elapsed_time": "8:50:12", "remaining_time": "1:57:24"}
101
+ {"current_steps": 990, "total_steps": 1197, "loss": 0.6966, "lr": 5e-06, "epoch": 2.4793491864831037, "percentage": 82.71, "elapsed_time": "8:55:30", "remaining_time": "1:51:58"}
102
+ {"current_steps": 1000, "total_steps": 1197, "loss": 0.6977, "lr": 5e-06, "epoch": 2.504380475594493, "percentage": 83.54, "elapsed_time": "9:00:48", "remaining_time": "1:46:32"}
103
+ {"current_steps": 1010, "total_steps": 1197, "loss": 0.7037, "lr": 5e-06, "epoch": 2.5294117647058822, "percentage": 84.38, "elapsed_time": "9:06:04", "remaining_time": "1:41:06"}
104
+ {"current_steps": 1020, "total_steps": 1197, "loss": 0.695, "lr": 5e-06, "epoch": 2.5544430538172715, "percentage": 85.21, "elapsed_time": "9:11:20", "remaining_time": "1:35:40"}
105
+ {"current_steps": 1030, "total_steps": 1197, "loss": 0.702, "lr": 5e-06, "epoch": 2.579474342928661, "percentage": 86.05, "elapsed_time": "9:16:37", "remaining_time": "1:30:14"}
106
+ {"current_steps": 1040, "total_steps": 1197, "loss": 0.6965, "lr": 5e-06, "epoch": 2.60450563204005, "percentage": 86.88, "elapsed_time": "9:21:54", "remaining_time": "1:24:49"}
107
+ {"current_steps": 1050, "total_steps": 1197, "loss": 0.6958, "lr": 5e-06, "epoch": 2.6295369211514394, "percentage": 87.72, "elapsed_time": "9:27:14", "remaining_time": "1:19:24"}
108
+ {"current_steps": 1060, "total_steps": 1197, "loss": 0.6977, "lr": 5e-06, "epoch": 2.6545682102628287, "percentage": 88.55, "elapsed_time": "9:32:32", "remaining_time": "1:13:59"}
109
+ {"current_steps": 1070, "total_steps": 1197, "loss": 0.6992, "lr": 5e-06, "epoch": 2.679599499374218, "percentage": 89.39, "elapsed_time": "9:37:51", "remaining_time": "1:08:35"}
110
+ {"current_steps": 1080, "total_steps": 1197, "loss": 0.6977, "lr": 5e-06, "epoch": 2.704630788485607, "percentage": 90.23, "elapsed_time": "9:43:10", "remaining_time": "1:03:10"}
111
+ {"current_steps": 1090, "total_steps": 1197, "loss": 0.6994, "lr": 5e-06, "epoch": 2.729662077596996, "percentage": 91.06, "elapsed_time": "9:48:29", "remaining_time": "0:57:46"}
112
+ {"current_steps": 1100, "total_steps": 1197, "loss": 0.698, "lr": 5e-06, "epoch": 2.7546933667083855, "percentage": 91.9, "elapsed_time": "9:53:48", "remaining_time": "0:52:21"}
113
+ {"current_steps": 1110, "total_steps": 1197, "loss": 0.699, "lr": 5e-06, "epoch": 2.779724655819775, "percentage": 92.73, "elapsed_time": "9:59:06", "remaining_time": "0:46:57"}
114
+ {"current_steps": 1120, "total_steps": 1197, "loss": 0.6979, "lr": 5e-06, "epoch": 2.804755944931164, "percentage": 93.57, "elapsed_time": "10:04:23", "remaining_time": "0:41:33"}
115
+ {"current_steps": 1130, "total_steps": 1197, "loss": 0.7011, "lr": 5e-06, "epoch": 2.829787234042553, "percentage": 94.4, "elapsed_time": "10:09:40", "remaining_time": "0:36:08"}
116
+ {"current_steps": 1140, "total_steps": 1197, "loss": 0.6988, "lr": 5e-06, "epoch": 2.8548185231539422, "percentage": 95.24, "elapsed_time": "10:14:58", "remaining_time": "0:30:44"}
117
+ {"current_steps": 1150, "total_steps": 1197, "loss": 0.6968, "lr": 5e-06, "epoch": 2.8798498122653315, "percentage": 96.07, "elapsed_time": "10:20:14", "remaining_time": "0:25:20"}
118
+ {"current_steps": 1160, "total_steps": 1197, "loss": 0.7005, "lr": 5e-06, "epoch": 2.904881101376721, "percentage": 96.91, "elapsed_time": "10:25:30", "remaining_time": "0:19:57"}
119
+ {"current_steps": 1170, "total_steps": 1197, "loss": 0.7034, "lr": 5e-06, "epoch": 2.92991239048811, "percentage": 97.74, "elapsed_time": "10:30:47", "remaining_time": "0:14:33"}
120
+ {"current_steps": 1180, "total_steps": 1197, "loss": 0.6951, "lr": 5e-06, "epoch": 2.9549436795994994, "percentage": 98.58, "elapsed_time": "10:36:04", "remaining_time": "0:09:09"}
121
+ {"current_steps": 1190, "total_steps": 1197, "loss": 0.6976, "lr": 5e-06, "epoch": 2.9799749687108887, "percentage": 99.42, "elapsed_time": "10:41:23", "remaining_time": "0:03:46"}