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:
|
| 3 |
size 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9944d901dbd5315569143db5ea6b585280919c0a3d4033ba02aa20b35742a137
|
| 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:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb897a225c4cf51ba5bc7b6b532f0576b057d63d4d53587132aaff1a2c0976fb
|
| 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:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ea08e26aae03284264c18afc0eb6f49aeef16d171044ebae6ab6815952db2ed
|
| 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:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99d131b3cc3cdb49bc64ecb7f02aba1f9c32c413b459e48af289ff0fc9bee007
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1084,3 +1084,43 @@
|
|
| 1084 |
{"current_steps": 5395, "total_steps": 6188, "loss": 0.0764, "lr": 1.972937167082014e-06, "epoch": 6.10413129598189, "percentage": 87.18, "elapsed_time": "17:27:42", "remaining_time": "2:33:59"}
|
| 1085 |
{"current_steps": 5400, "total_steps": 6188, "loss": 0.0868, "lr": 1.948577660105082e-06, "epoch": 6.109790605546124, "percentage": 87.27, "elapsed_time": "17:29:35", "remaining_time": "2:33:09"}
|
| 1086 |
{"current_steps": 5405, "total_steps": 6188, "loss": 0.0812, "lr": 1.924361767022038e-06, "epoch": 6.115449915110356, "percentage": 87.35, "elapsed_time": "17:32:35", "remaining_time": "2:32:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1084 |
{"current_steps": 5395, "total_steps": 6188, "loss": 0.0764, "lr": 1.972937167082014e-06, "epoch": 6.10413129598189, "percentage": 87.18, "elapsed_time": "17:27:42", "remaining_time": "2:33:59"}
|
| 1085 |
{"current_steps": 5400, "total_steps": 6188, "loss": 0.0868, "lr": 1.948577660105082e-06, "epoch": 6.109790605546124, "percentage": 87.27, "elapsed_time": "17:29:35", "remaining_time": "2:33:09"}
|
| 1086 |
{"current_steps": 5405, "total_steps": 6188, "loss": 0.0812, "lr": 1.924361767022038e-06, "epoch": 6.115449915110356, "percentage": 87.35, "elapsed_time": "17:32:35", "remaining_time": "2:32:29"}
|
| 1087 |
+
{"current_steps": 5410, "total_steps": 6188, "loss": 0.1063, "lr": 1.9002896804902039e-06, "epoch": 6.12110922467459, "percentage": 87.43, "elapsed_time": "17:34:32", "remaining_time": "2:31:39"}
|
| 1088 |
+
{"current_steps": 5415, "total_steps": 6188, "loss": 0.0877, "lr": 1.8763615920228084e-06, "epoch": 6.126768534238823, "percentage": 87.51, "elapsed_time": "17:36:07", "remaining_time": "2:30:45"}
|
| 1089 |
+
{"current_steps": 5420, "total_steps": 6188, "loss": 0.0709, "lr": 1.8525776919874472e-06, "epoch": 6.132427843803056, "percentage": 87.59, "elapsed_time": "17:37:38", "remaining_time": "2:29:51"}
|
| 1090 |
+
{"current_steps": 5425, "total_steps": 6188, "loss": 0.1019, "lr": 1.8289381696045817e-06, "epoch": 6.138087153367289, "percentage": 87.67, "elapsed_time": "17:39:14", "remaining_time": "2:28:58"}
|
| 1091 |
+
{"current_steps": 5430, "total_steps": 6188, "loss": 0.0875, "lr": 1.8054432129460386e-06, "epoch": 6.143746462931523, "percentage": 87.75, "elapsed_time": "17:41:11", "remaining_time": "2:28:08"}
|
| 1092 |
+
{"current_steps": 5435, "total_steps": 6188, "loss": 0.0781, "lr": 1.7820930089334965e-06, "epoch": 6.149405772495755, "percentage": 87.83, "elapsed_time": "17:42:44", "remaining_time": "2:27:14"}
|
| 1093 |
+
{"current_steps": 5440, "total_steps": 6188, "loss": 0.263, "lr": 1.7588877433370076e-06, "epoch": 6.155065082059989, "percentage": 87.91, "elapsed_time": "17:45:04", "remaining_time": "2:26:26"}
|
| 1094 |
+
{"current_steps": 5445, "total_steps": 6188, "loss": 0.0914, "lr": 1.7358276007735276e-06, "epoch": 6.160724391624222, "percentage": 87.99, "elapsed_time": "17:46:58", "remaining_time": "2:25:35"}
|
| 1095 |
+
{"current_steps": 5450, "total_steps": 6188, "loss": 0.0808, "lr": 1.71291276470543e-06, "epoch": 6.166383701188455, "percentage": 88.07, "elapsed_time": "17:48:36", "remaining_time": "2:24:42"}
|
| 1096 |
+
{"current_steps": 5455, "total_steps": 6188, "loss": 0.1721, "lr": 1.6901434174390652e-06, "epoch": 6.172043010752688, "percentage": 88.15, "elapsed_time": "17:50:54", "remaining_time": "2:23:54"}
|
| 1097 |
+
{"current_steps": 5460, "total_steps": 6188, "loss": 0.0699, "lr": 1.6675197401232869e-06, "epoch": 6.1777023203169215, "percentage": 88.24, "elapsed_time": "17:52:35", "remaining_time": "2:23:00"}
|
| 1098 |
+
{"current_steps": 5465, "total_steps": 6188, "loss": 0.0826, "lr": 1.6450419127480422e-06, "epoch": 6.183361629881155, "percentage": 88.32, "elapsed_time": "17:54:27", "remaining_time": "2:22:08"}
|
| 1099 |
+
{"current_steps": 5470, "total_steps": 6188, "loss": 0.0772, "lr": 1.6227101141429114e-06, "epoch": 6.1890209394453874, "percentage": 88.4, "elapsed_time": "17:56:08", "remaining_time": "2:21:15"}
|
| 1100 |
+
{"current_steps": 5475, "total_steps": 6188, "loss": 0.0711, "lr": 1.6005245219756927e-06, "epoch": 6.194680249009621, "percentage": 88.48, "elapsed_time": "17:57:48", "remaining_time": "2:20:21"}
|
| 1101 |
+
{"current_steps": 5480, "total_steps": 6188, "loss": 0.0698, "lr": 1.5784853127510058e-06, "epoch": 6.200339558573854, "percentage": 88.56, "elapsed_time": "17:59:31", "remaining_time": "2:19:28"}
|
| 1102 |
+
{"current_steps": 5485, "total_steps": 6188, "loss": 0.0681, "lr": 1.5565926618088578e-06, "epoch": 6.205998868138087, "percentage": 88.64, "elapsed_time": "18:01:03", "remaining_time": "2:18:33"}
|
| 1103 |
+
{"current_steps": 5490, "total_steps": 6188, "loss": 0.0668, "lr": 1.5348467433232728e-06, "epoch": 6.21165817770232, "percentage": 88.72, "elapsed_time": "18:02:34", "remaining_time": "2:17:38"}
|
| 1104 |
+
{"current_steps": 5495, "total_steps": 6188, "loss": 0.07, "lr": 1.5132477303009018e-06, "epoch": 6.217317487266554, "percentage": 88.8, "elapsed_time": "18:04:08", "remaining_time": "2:16:43"}
|
| 1105 |
+
{"current_steps": 5500, "total_steps": 6188, "loss": 0.1007, "lr": 1.4917957945796313e-06, "epoch": 6.222976796830786, "percentage": 88.88, "elapsed_time": "18:06:06", "remaining_time": "2:15:51"}
|
| 1106 |
+
{"current_steps": 5505, "total_steps": 6188, "loss": 0.056, "lr": 1.4704911068272366e-06, "epoch": 6.22863610639502, "percentage": 88.96, "elapsed_time": "18:07:39", "remaining_time": "2:14:56"}
|
| 1107 |
+
{"current_steps": 5510, "total_steps": 6188, "loss": 0.0697, "lr": 1.4493338365400034e-06, "epoch": 6.234295415959253, "percentage": 89.04, "elapsed_time": "18:09:13", "remaining_time": "2:14:01"}
|
| 1108 |
+
{"current_steps": 5515, "total_steps": 6188, "loss": 0.063, "lr": 1.428324152041407e-06, "epoch": 6.239954725523486, "percentage": 89.12, "elapsed_time": "18:10:51", "remaining_time": "2:13:07"}
|
| 1109 |
+
{"current_steps": 5520, "total_steps": 6188, "loss": 0.107, "lr": 1.407462220480742e-06, "epoch": 6.245614035087719, "percentage": 89.2, "elapsed_time": "18:13:09", "remaining_time": "2:12:17"}
|
| 1110 |
+
{"current_steps": 5525, "total_steps": 6188, "loss": 0.0832, "lr": 1.3867482078318095e-06, "epoch": 6.251273344651953, "percentage": 89.29, "elapsed_time": "18:14:57", "remaining_time": "2:11:23"}
|
| 1111 |
+
{"current_steps": 5530, "total_steps": 6188, "loss": 0.0866, "lr": 1.3661822788916013e-06, "epoch": 6.256932654216186, "percentage": 89.37, "elapsed_time": "18:16:34", "remaining_time": "2:10:28"}
|
| 1112 |
+
{"current_steps": 5535, "total_steps": 6188, "loss": 0.0727, "lr": 1.3457645972789778e-06, "epoch": 6.262591963780419, "percentage": 89.45, "elapsed_time": "18:18:09", "remaining_time": "2:09:33"}
|
| 1113 |
+
{"current_steps": 5540, "total_steps": 6188, "loss": 0.1142, "lr": 1.3254953254333613e-06, "epoch": 6.268251273344652, "percentage": 89.53, "elapsed_time": "18:20:08", "remaining_time": "2:08:40"}
|
| 1114 |
+
{"current_steps": 5545, "total_steps": 6188, "loss": 0.0819, "lr": 1.305374624613469e-06, "epoch": 6.2739105829088855, "percentage": 89.61, "elapsed_time": "18:21:46", "remaining_time": "2:07:45"}
|
| 1115 |
+
{"current_steps": 5550, "total_steps": 6188, "loss": 0.0996, "lr": 1.285402654896004e-06, "epoch": 6.279569892473118, "percentage": 89.69, "elapsed_time": "18:23:23", "remaining_time": "2:06:50"}
|
| 1116 |
+
{"current_steps": 5555, "total_steps": 6188, "loss": 0.0679, "lr": 1.265579575174387e-06, "epoch": 6.2852292020373515, "percentage": 89.77, "elapsed_time": "18:24:54", "remaining_time": "2:05:54"}
|
| 1117 |
+
{"current_steps": 5560, "total_steps": 6188, "loss": 0.0766, "lr": 1.245905543157504e-06, "epoch": 6.290888511601585, "percentage": 89.85, "elapsed_time": "18:26:42", "remaining_time": "2:05:00"}
|
| 1118 |
+
{"current_steps": 5565, "total_steps": 6188, "loss": 0.0802, "lr": 1.2263807153684448e-06, "epoch": 6.2965478211658175, "percentage": 89.93, "elapsed_time": "18:28:47", "remaining_time": "2:04:07"}
|
| 1119 |
+
{"current_steps": 5570, "total_steps": 6188, "loss": 0.0646, "lr": 1.2070052471432535e-06, "epoch": 6.302207130730051, "percentage": 90.01, "elapsed_time": "18:30:52", "remaining_time": "2:03:15"}
|
| 1120 |
+
{"current_steps": 5575, "total_steps": 6188, "loss": 0.063, "lr": 1.1877792926296893e-06, "epoch": 6.307866440294284, "percentage": 90.09, "elapsed_time": "18:32:29", "remaining_time": "2:02:19"}
|
| 1121 |
+
{"current_steps": 5580, "total_steps": 6188, "loss": 0.0708, "lr": 1.1687030047860248e-06, "epoch": 6.313525749858517, "percentage": 90.17, "elapsed_time": "18:34:10", "remaining_time": "2:01:24"}
|
| 1122 |
+
{"current_steps": 5585, "total_steps": 6188, "loss": 0.0863, "lr": 1.1497765353797963e-06, "epoch": 6.31918505942275, "percentage": 90.26, "elapsed_time": "18:36:33", "remaining_time": "2:00:33"}
|
| 1123 |
+
{"current_steps": 5590, "total_steps": 6188, "loss": 0.0832, "lr": 1.1310000349866136e-06, "epoch": 6.324844368986984, "percentage": 90.34, "elapsed_time": "18:38:08", "remaining_time": "1:59:36"}
|
| 1124 |
+
{"current_steps": 5595, "total_steps": 6188, "loss": 0.0709, "lr": 1.1123736529889674e-06, "epoch": 6.330503678551217, "percentage": 90.42, "elapsed_time": "18:39:41", "remaining_time": "1:58:40"}
|
| 1125 |
+
{"current_steps": 5600, "total_steps": 6188, "loss": 0.0671, "lr": 1.093897537575026e-06, "epoch": 6.33616298811545, "percentage": 90.5, "elapsed_time": "18:41:19", "remaining_time": "1:57:44"}
|
| 1126 |
+
{"current_steps": 5605, "total_steps": 6188, "loss": 0.0826, "lr": 1.075571835737459e-06, "epoch": 6.341822297679683, "percentage": 90.58, "elapsed_time": "18:44:35", "remaining_time": "1:56:58"}
|