penfever commited on
Commit
18350b7
·
verified ·
1 Parent(s): fa05f4b

Training in progress, step 5600

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b881435c9d9a6b4c747447c8b557c5676a251215b9b418f0bd6c9f5247d4f0c
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97913c267cc005ceb27c14ab9cd054dc23d35f07a1b06d9a6c4fa6ddaf0a123e
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a11dffc3d704a91298b3c978d546f8dc1aa54b11c9792f246d1ad2ddb3d62c08
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f765f289d2bff0fa1e32ae2e09b7338b02a37eb1cdba04efde32c1f07f9ddee7
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab8e147bc28636c023dcccfc47b836ad49e1702c32c1e66f943cd1edca800392
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d03a749070e0a5ae11e585936ca375b1b0cb48fd6bd6d05d6fc9e88d72124b
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8828a9a372b9d64fcf28199ee149a37128e4b35fe783e9cdcfa1a9abdc2e3e55
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc167935cf04c6a26b2f1ebeb3491bf5312b57fbafddc8c18633b02507ed7bf
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1078,3 +1078,43 @@
1078
  {"current_steps": 5390, "total_steps": 6713, "loss": 0.1809, "lr": 4.556506175491097e-06, "epoch": 5.621804903495044, "percentage": 80.29, "elapsed_time": "1 day, 1:44:33", "remaining_time": "6:19:07"}
1079
  {"current_steps": 5395, "total_steps": 6713, "loss": 0.1677, "lr": 4.523514217444918e-06, "epoch": 5.627021387584768, "percentage": 80.37, "elapsed_time": "1 day, 1:47:19", "remaining_time": "6:18:00"}
1080
  {"current_steps": 5400, "total_steps": 6713, "loss": 0.1753, "lr": 4.490626898545805e-06, "epoch": 5.632237871674492, "percentage": 80.44, "elapsed_time": "1 day, 1:49:57", "remaining_time": "6:16:52"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1078
  {"current_steps": 5390, "total_steps": 6713, "loss": 0.1809, "lr": 4.556506175491097e-06, "epoch": 5.621804903495044, "percentage": 80.29, "elapsed_time": "1 day, 1:44:33", "remaining_time": "6:19:07"}
1079
  {"current_steps": 5395, "total_steps": 6713, "loss": 0.1677, "lr": 4.523514217444918e-06, "epoch": 5.627021387584768, "percentage": 80.37, "elapsed_time": "1 day, 1:47:19", "remaining_time": "6:18:00"}
1080
  {"current_steps": 5400, "total_steps": 6713, "loss": 0.1753, "lr": 4.490626898545805e-06, "epoch": 5.632237871674492, "percentage": 80.44, "elapsed_time": "1 day, 1:49:57", "remaining_time": "6:16:52"}
1081
+ {"current_steps": 5405, "total_steps": 6713, "loss": 0.178, "lr": 4.4578444411505005e-06, "epoch": 5.6374543557642145, "percentage": 80.52, "elapsed_time": "1 day, 1:54:03", "remaining_time": "6:16:04"}
1082
+ {"current_steps": 5410, "total_steps": 6713, "loss": 0.167, "lr": 4.425167066906777e-06, "epoch": 5.642670839853938, "percentage": 80.59, "elapsed_time": "1 day, 1:56:51", "remaining_time": "6:14:58"}
1083
+ {"current_steps": 5415, "total_steps": 6713, "loss": 0.1768, "lr": 4.392594996751891e-06, "epoch": 5.647887323943662, "percentage": 80.66, "elapsed_time": "1 day, 1:59:36", "remaining_time": "6:13:50"}
1084
+ {"current_steps": 5420, "total_steps": 6713, "loss": 0.1806, "lr": 4.360128450911154e-06, "epoch": 5.653103808033386, "percentage": 80.74, "elapsed_time": "1 day, 2:02:12", "remaining_time": "6:12:40"}
1085
+ {"current_steps": 5425, "total_steps": 6713, "loss": 0.1741, "lr": 4.3277676488963775e-06, "epoch": 5.6583202921231095, "percentage": 80.81, "elapsed_time": "1 day, 2:04:59", "remaining_time": "6:11:33"}
1086
+ {"current_steps": 5430, "total_steps": 6713, "loss": 0.1737, "lr": 4.295512809504447e-06, "epoch": 5.663536776212832, "percentage": 80.89, "elapsed_time": "1 day, 2:07:54", "remaining_time": "6:10:27"}
1087
+ {"current_steps": 5435, "total_steps": 6713, "loss": 0.1782, "lr": 4.263364150815803e-06, "epoch": 5.668753260302556, "percentage": 80.96, "elapsed_time": "1 day, 2:10:39", "remaining_time": "6:09:19"}
1088
+ {"current_steps": 5440, "total_steps": 6713, "loss": 0.1753, "lr": 4.231321890192981e-06, "epoch": 5.67396974439228, "percentage": 81.04, "elapsed_time": "1 day, 2:13:39", "remaining_time": "6:08:14"}
1089
+ {"current_steps": 5445, "total_steps": 6713, "loss": 0.1665, "lr": 4.19938624427914e-06, "epoch": 5.679186228482003, "percentage": 81.11, "elapsed_time": "1 day, 2:16:26", "remaining_time": "6:07:06"}
1090
+ {"current_steps": 5450, "total_steps": 6713, "loss": 0.1697, "lr": 4.167557428996611e-06, "epoch": 5.6844027125717265, "percentage": 81.19, "elapsed_time": "1 day, 2:19:14", "remaining_time": "6:05:58"}
1091
+ {"current_steps": 5455, "total_steps": 6713, "loss": 0.1688, "lr": 4.135835659545406e-06, "epoch": 5.68961919666145, "percentage": 81.26, "elapsed_time": "1 day, 2:22:14", "remaining_time": "6:04:53"}
1092
+ {"current_steps": 5460, "total_steps": 6713, "loss": 0.1738, "lr": 4.104221150401806e-06, "epoch": 5.694835680751174, "percentage": 81.33, "elapsed_time": "1 day, 2:25:07", "remaining_time": "6:03:45"}
1093
+ {"current_steps": 5465, "total_steps": 6713, "loss": 0.1643, "lr": 4.072714115316863e-06, "epoch": 5.700052164840898, "percentage": 81.41, "elapsed_time": "1 day, 2:28:05", "remaining_time": "6:02:39"}
1094
+ {"current_steps": 5470, "total_steps": 6713, "loss": 0.1689, "lr": 4.041314767314983e-06, "epoch": 5.705268648930621, "percentage": 81.48, "elapsed_time": "1 day, 2:30:45", "remaining_time": "6:01:29"}
1095
+ {"current_steps": 5475, "total_steps": 6713, "loss": 0.181, "lr": 4.010023318692502e-06, "epoch": 5.710485133020344, "percentage": 81.56, "elapsed_time": "1 day, 2:33:31", "remaining_time": "6:00:19"}
1096
+ {"current_steps": 5480, "total_steps": 6713, "loss": 0.1805, "lr": 3.978839981016203e-06, "epoch": 5.715701617110068, "percentage": 81.63, "elapsed_time": "1 day, 2:36:12", "remaining_time": "5:59:08"}
1097
+ {"current_steps": 5485, "total_steps": 6713, "loss": 0.1753, "lr": 3.947764965121934e-06, "epoch": 5.720918101199791, "percentage": 81.71, "elapsed_time": "1 day, 2:39:04", "remaining_time": "5:58:00"}
1098
+ {"current_steps": 5490, "total_steps": 6713, "loss": 0.1778, "lr": 3.916798481113144e-06, "epoch": 5.726134585289515, "percentage": 81.78, "elapsed_time": "1 day, 2:41:49", "remaining_time": "5:56:50"}
1099
+ {"current_steps": 5495, "total_steps": 6713, "loss": 0.1785, "lr": 3.885940738359492e-06, "epoch": 5.731351069379238, "percentage": 81.86, "elapsed_time": "1 day, 2:44:38", "remaining_time": "5:55:40"}
1100
+ {"current_steps": 5500, "total_steps": 6713, "loss": 0.1721, "lr": 3.855191945495405e-06, "epoch": 5.736567553468962, "percentage": 81.93, "elapsed_time": "1 day, 2:47:23", "remaining_time": "5:54:30"}
1101
+ {"current_steps": 5505, "total_steps": 6713, "loss": 0.1748, "lr": 3.824552310418703e-06, "epoch": 5.741784037558686, "percentage": 82.01, "elapsed_time": "1 day, 2:50:19", "remaining_time": "5:53:21"}
1102
+ {"current_steps": 5510, "total_steps": 6713, "loss": 0.1751, "lr": 3.794022040289147e-06, "epoch": 5.747000521648409, "percentage": 82.08, "elapsed_time": "1 day, 2:52:56", "remaining_time": "5:52:09"}
1103
+ {"current_steps": 5515, "total_steps": 6713, "loss": 0.1784, "lr": 3.763601341527088e-06, "epoch": 5.7522170057381325, "percentage": 82.15, "elapsed_time": "1 day, 2:55:33", "remaining_time": "5:50:56"}
1104
+ {"current_steps": 5520, "total_steps": 6713, "loss": 0.1657, "lr": 3.733290419812019e-06, "epoch": 5.757433489827856, "percentage": 82.23, "elapsed_time": "1 day, 2:58:27", "remaining_time": "5:49:47"}
1105
+ {"current_steps": 5525, "total_steps": 6713, "loss": 0.1828, "lr": 3.7030894800812365e-06, "epoch": 5.762649973917579, "percentage": 82.3, "elapsed_time": "1 day, 3:01:01", "remaining_time": "5:48:33"}
1106
+ {"current_steps": 5530, "total_steps": 6713, "loss": 0.1801, "lr": 3.672998726528414e-06, "epoch": 5.767866458007303, "percentage": 82.38, "elapsed_time": "1 day, 3:03:36", "remaining_time": "5:47:19"}
1107
+ {"current_steps": 5535, "total_steps": 6713, "loss": 0.1656, "lr": 3.6430183626022574e-06, "epoch": 5.773082942097027, "percentage": 82.45, "elapsed_time": "1 day, 3:06:10", "remaining_time": "5:46:05"}
1108
+ {"current_steps": 5540, "total_steps": 6713, "loss": 0.1693, "lr": 3.613148591005071e-06, "epoch": 5.77829942618675, "percentage": 82.53, "elapsed_time": "1 day, 3:08:56", "remaining_time": "5:44:54"}
1109
+ {"current_steps": 5545, "total_steps": 6713, "loss": 0.1772, "lr": 3.5833896136914705e-06, "epoch": 5.783515910276473, "percentage": 82.6, "elapsed_time": "1 day, 3:11:40", "remaining_time": "5:43:41"}
1110
+ {"current_steps": 5550, "total_steps": 6713, "loss": 0.1841, "lr": 3.553741631866938e-06, "epoch": 5.788732394366197, "percentage": 82.68, "elapsed_time": "1 day, 3:14:24", "remaining_time": "5:42:29"}
1111
+ {"current_steps": 5555, "total_steps": 6713, "loss": 0.1792, "lr": 3.524204845986523e-06, "epoch": 5.793948878455921, "percentage": 82.75, "elapsed_time": "1 day, 3:16:57", "remaining_time": "5:41:14"}
1112
+ {"current_steps": 5560, "total_steps": 6713, "loss": 0.1675, "lr": 3.494779455753443e-06, "epoch": 5.7991653625456445, "percentage": 82.82, "elapsed_time": "1 day, 3:19:41", "remaining_time": "5:40:01"}
1113
+ {"current_steps": 5565, "total_steps": 6713, "loss": 0.1844, "lr": 3.4654656601177482e-06, "epoch": 5.804381846635367, "percentage": 82.9, "elapsed_time": "1 day, 3:22:27", "remaining_time": "5:38:49"}
1114
+ {"current_steps": 5570, "total_steps": 6713, "loss": 0.177, "lr": 3.4362636572749984e-06, "epoch": 5.809598330725091, "percentage": 82.97, "elapsed_time": "1 day, 3:25:23", "remaining_time": "5:37:38"}
1115
+ {"current_steps": 5575, "total_steps": 6713, "loss": 0.1672, "lr": 3.4071736446648805e-06, "epoch": 5.814814814814815, "percentage": 83.05, "elapsed_time": "1 day, 3:28:20", "remaining_time": "5:36:28"}
1116
+ {"current_steps": 5580, "total_steps": 6713, "loss": 0.1839, "lr": 3.3781958189699183e-06, "epoch": 5.820031298904539, "percentage": 83.12, "elapsed_time": "1 day, 3:30:58", "remaining_time": "5:35:13"}
1117
+ {"current_steps": 5585, "total_steps": 6713, "loss": 0.1862, "lr": 3.3493303761141016e-06, "epoch": 5.8252477829942615, "percentage": 83.2, "elapsed_time": "1 day, 3:33:38", "remaining_time": "5:33:59"}
1118
+ {"current_steps": 5590, "total_steps": 6713, "loss": 0.1866, "lr": 3.320577511261589e-06, "epoch": 5.830464267083985, "percentage": 83.27, "elapsed_time": "1 day, 3:36:22", "remaining_time": "5:32:45"}
1119
+ {"current_steps": 5595, "total_steps": 6713, "loss": 0.1743, "lr": 3.291937418815376e-06, "epoch": 5.835680751173709, "percentage": 83.35, "elapsed_time": "1 day, 3:39:14", "remaining_time": "5:31:33"}
1120
+ {"current_steps": 5600, "total_steps": 6713, "loss": 0.1674, "lr": 3.2634102924159982e-06, "epoch": 5.840897235263433, "percentage": 83.42, "elapsed_time": "1 day, 3:41:58", "remaining_time": "5:30:19"}