Training in progress, epoch 2
Browse files
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4949453792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8789c2b1e3e8d971fb74db1988bb61183dcf1f2fb32ff725ebaa66c5ead1e6f2
|
3 |
size 4949453792
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e939d9ac55789736abaae102f0a564eaf53e83b03ba43f2bff99a3932bf1352d
|
3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4546807800
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ab53a643fd0d585141a60203ce0823f580735bf147bd39343e6b624a6d00ace
|
3 |
size 4546807800
|
trainer_log.jsonl
CHANGED
@@ -98,3 +98,52 @@
|
|
98 |
{"current_steps": 970, "total_steps": 1470, "loss": 0.174, "lr": 1.780283785735729e-06, "epoch": 1.9770700636942675, "percentage": 65.99, "elapsed_time": "8:33:50", "remaining_time": "4:24:52"}
|
99 |
{"current_steps": 980, "total_steps": 1470, "loss": 0.1749, "lr": 1.734842635131455e-06, "epoch": 1.997452229299363, "percentage": 66.67, "elapsed_time": "8:39:05", "remaining_time": "4:19:32"}
|
100 |
{"current_steps": 981, "total_steps": 1470, "eval_loss": 0.030678020790219307, "epoch": 1.9994904458598726, "percentage": 66.73, "elapsed_time": "8:45:18", "remaining_time": "4:21:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
{"current_steps": 970, "total_steps": 1470, "loss": 0.174, "lr": 1.780283785735729e-06, "epoch": 1.9770700636942675, "percentage": 65.99, "elapsed_time": "8:33:50", "remaining_time": "4:24:52"}
|
99 |
{"current_steps": 980, "total_steps": 1470, "loss": 0.1749, "lr": 1.734842635131455e-06, "epoch": 1.997452229299363, "percentage": 66.67, "elapsed_time": "8:39:05", "remaining_time": "4:19:32"}
|
100 |
{"current_steps": 981, "total_steps": 1470, "eval_loss": 0.030678020790219307, "epoch": 1.9994904458598726, "percentage": 66.73, "elapsed_time": "8:45:18", "remaining_time": "4:21:51"}
|
101 |
+
{"current_steps": 990, "total_steps": 1470, "loss": 0.1179, "lr": 1.689915580201614e-06, "epoch": 2.0178343949044586, "percentage": 67.35, "elapsed_time": "8:51:05", "remaining_time": "4:17:29"}
|
102 |
+
{"current_steps": 1000, "total_steps": 1470, "loss": 0.106, "lr": 1.6455253728912765e-06, "epoch": 2.038216560509554, "percentage": 68.03, "elapsed_time": "8:56:18", "remaining_time": "4:12:04"}
|
103 |
+
{"current_steps": 1010, "total_steps": 1470, "loss": 0.1055, "lr": 1.6016944932753123e-06, "epoch": 2.0585987261146497, "percentage": 68.71, "elapsed_time": "9:01:32", "remaining_time": "4:06:38"}
|
104 |
+
{"current_steps": 1020, "total_steps": 1470, "loss": 0.1068, "lr": 1.558445138174033e-06, "epoch": 2.078980891719745, "percentage": 69.39, "elapsed_time": "9:06:45", "remaining_time": "4:01:13"}
|
105 |
+
{"current_steps": 1030, "total_steps": 1470, "loss": 0.1061, "lr": 1.5157992099122896e-06, "epoch": 2.0993630573248407, "percentage": 70.07, "elapsed_time": "9:12:00", "remaining_time": "3:55:48"}
|
106 |
+
{"current_steps": 1040, "total_steps": 1470, "loss": 0.1054, "lr": 1.4737783052277017e-06, "epoch": 2.1197452229299363, "percentage": 70.75, "elapsed_time": "9:17:14", "remaining_time": "3:50:23"}
|
107 |
+
{"current_steps": 1050, "total_steps": 1470, "loss": 0.1056, "lr": 1.432403704333643e-06, "epoch": 2.140127388535032, "percentage": 71.43, "elapsed_time": "9:22:28", "remaining_time": "3:44:59"}
|
108 |
+
{"current_steps": 1060, "total_steps": 1470, "loss": 0.1058, "lr": 1.3916963601425293e-06, "epoch": 2.1605095541401274, "percentage": 72.11, "elapsed_time": "9:27:42", "remaining_time": "3:39:35"}
|
109 |
+
{"current_steps": 1070, "total_steps": 1470, "loss": 0.1068, "lr": 1.3516768876548404e-06, "epoch": 2.180891719745223, "percentage": 72.79, "elapsed_time": "9:32:54", "remaining_time": "3:34:10"}
|
110 |
+
{"current_steps": 1080, "total_steps": 1470, "loss": 0.1059, "lr": 1.3123655535192873e-06, "epoch": 2.2012738853503184, "percentage": 73.47, "elapsed_time": "9:38:08", "remaining_time": "3:28:46"}
|
111 |
+
{"current_steps": 1090, "total_steps": 1470, "loss": 0.106, "lr": 1.2737822657693763e-06, "epoch": 2.221656050955414, "percentage": 74.15, "elapsed_time": "9:43:21", "remaining_time": "3:23:22"}
|
112 |
+
{"current_steps": 1100, "total_steps": 1470, "loss": 0.106, "lr": 1.235946563741594e-06, "epoch": 2.2420382165605095, "percentage": 74.83, "elapsed_time": "9:48:34", "remaining_time": "3:17:58"}
|
113 |
+
{"current_steps": 1110, "total_steps": 1470, "loss": 0.1049, "lr": 1.1988776081802975e-06, "epoch": 2.262420382165605, "percentage": 75.51, "elapsed_time": "9:53:45", "remaining_time": "3:12:34"}
|
114 |
+
{"current_steps": 1120, "total_steps": 1470, "loss": 0.1054, "lr": 1.1625941715343404e-06, "epoch": 2.2828025477707006, "percentage": 76.19, "elapsed_time": "9:58:58", "remaining_time": "3:07:10"}
|
115 |
+
{"current_steps": 1130, "total_steps": 1470, "loss": 0.1055, "lr": 1.1271146284503326e-06, "epoch": 2.303184713375796, "percentage": 76.87, "elapsed_time": "10:04:11", "remaining_time": "3:01:47"}
|
116 |
+
{"current_steps": 1140, "total_steps": 1470, "loss": 0.1055, "lr": 1.0924569464673593e-06, "epoch": 2.3235668789808916, "percentage": 77.55, "elapsed_time": "10:09:26", "remaining_time": "2:56:25"}
|
117 |
+
{"current_steps": 1150, "total_steps": 1470, "loss": 0.106, "lr": 1.0586386769178644e-06, "epoch": 2.343949044585987, "percentage": 78.23, "elapsed_time": "10:14:37", "remaining_time": "2:51:01"}
|
118 |
+
{"current_steps": 1160, "total_steps": 1470, "loss": 0.1056, "lr": 1.0256769460393087e-06, "epoch": 2.3643312101910827, "percentage": 78.91, "elapsed_time": "10:19:49", "remaining_time": "2:45:38"}
|
119 |
+
{"current_steps": 1170, "total_steps": 1470, "loss": 0.1045, "lr": 9.935884463011108e-07, "epoch": 2.3847133757961783, "percentage": 79.59, "elapsed_time": "10:25:02", "remaining_time": "2:40:16"}
|
120 |
+
{"current_steps": 1180, "total_steps": 1470, "loss": 0.1054, "lr": 9.623894279512455e-07, "epoch": 2.405095541401274, "percentage": 80.27, "elapsed_time": "10:30:13", "remaining_time": "2:34:53"}
|
121 |
+
{"current_steps": 1190, "total_steps": 1470, "loss": 0.1056, "lr": 9.320956907868051e-07, "epoch": 2.4254777070063693, "percentage": 80.95, "elapsed_time": "10:35:24", "remaining_time": "2:29:30"}
|
122 |
+
{"current_steps": 1200, "total_steps": 1470, "loss": 0.1043, "lr": 9.027225761526653e-07, "epoch": 2.445859872611465, "percentage": 81.63, "elapsed_time": "10:40:36", "remaining_time": "2:24:08"}
|
123 |
+
{"current_steps": 1210, "total_steps": 1470, "loss": 0.1065, "lr": 8.742849591723315e-07, "epoch": 2.4662420382165604, "percentage": 82.31, "elapsed_time": "10:45:50", "remaining_time": "2:18:46"}
|
124 |
+
{"current_steps": 1220, "total_steps": 1470, "loss": 0.1049, "lr": 8.467972412148767e-07, "epoch": 2.486624203821656, "percentage": 82.99, "elapsed_time": "10:51:04", "remaining_time": "2:13:24"}
|
125 |
+
{"current_steps": 1230, "total_steps": 1470, "loss": 0.1039, "lr": 8.202733426018117e-07, "epoch": 2.5070063694267515, "percentage": 83.67, "elapsed_time": "10:56:17", "remaining_time": "2:08:03"}
|
126 |
+
{"current_steps": 1240, "total_steps": 1470, "loss": 0.1061, "lr": 7.947266955575562e-07, "epoch": 2.527388535031847, "percentage": 84.35, "elapsed_time": "11:01:31", "remaining_time": "2:02:42"}
|
127 |
+
{"current_steps": 1250, "total_steps": 1470, "loss": 0.1054, "lr": 7.701702374070962e-07, "epoch": 2.5477707006369426, "percentage": 85.03, "elapsed_time": "11:06:42", "remaining_time": "1:57:20"}
|
128 |
+
{"current_steps": 1260, "total_steps": 1470, "loss": 0.104, "lr": 7.466164040242694e-07, "epoch": 2.568152866242038, "percentage": 85.71, "elapsed_time": "11:11:53", "remaining_time": "1:51:58"}
|
129 |
+
{"current_steps": 1270, "total_steps": 1470, "loss": 0.1048, "lr": 7.24077123533992e-07, "epoch": 2.5885350318471336, "percentage": 86.39, "elapsed_time": "11:17:06", "remaining_time": "1:46:37"}
|
130 |
+
{"current_steps": 1280, "total_steps": 1470, "loss": 0.1046, "lr": 7.025638102716238e-07, "epoch": 2.608917197452229, "percentage": 87.07, "elapsed_time": "11:22:21", "remaining_time": "1:41:17"}
|
131 |
+
{"current_steps": 1290, "total_steps": 1470, "loss": 0.1042, "lr": 6.820873590025216e-07, "epoch": 2.6292993630573247, "percentage": 87.76, "elapsed_time": "11:27:34", "remaining_time": "1:35:56"}
|
132 |
+
{"current_steps": 1300, "total_steps": 1470, "loss": 0.1043, "lr": 6.626581394047174e-07, "epoch": 2.6496815286624202, "percentage": 88.44, "elapsed_time": "11:32:48", "remaining_time": "1:30:35"}
|
133 |
+
{"current_steps": 1310, "total_steps": 1470, "loss": 0.1053, "lr": 6.442859908175084e-07, "epoch": 2.6700636942675158, "percentage": 89.12, "elapsed_time": "11:38:02", "remaining_time": "1:25:15"}
|
134 |
+
{"current_steps": 1320, "total_steps": 1470, "loss": 0.1055, "lr": 6.269802172586215e-07, "epoch": 2.6904458598726113, "percentage": 89.8, "elapsed_time": "11:43:15", "remaining_time": "1:19:54"}
|
135 |
+
{"current_steps": 1330, "total_steps": 1470, "loss": 0.1041, "lr": 6.107495827124764e-07, "epoch": 2.710828025477707, "percentage": 90.48, "elapsed_time": "11:48:28", "remaining_time": "1:14:34"}
|
136 |
+
{"current_steps": 1340, "total_steps": 1470, "loss": 0.1026, "lr": 5.956023066919313e-07, "epoch": 2.7312101910828024, "percentage": 91.16, "elapsed_time": "11:53:41", "remaining_time": "1:09:14"}
|
137 |
+
{"current_steps": 1350, "total_steps": 1470, "loss": 0.1037, "lr": 5.815460600757599e-07, "epoch": 2.7515923566878984, "percentage": 91.84, "elapsed_time": "11:58:53", "remaining_time": "1:03:54"}
|
138 |
+
{"current_steps": 1360, "total_steps": 1470, "loss": 0.1057, "lr": 5.685879612239649e-07, "epoch": 2.771974522292994, "percentage": 92.52, "elapsed_time": "12:04:07", "remaining_time": "0:58:34"}
|
139 |
+
{"current_steps": 1370, "total_steps": 1470, "loss": 0.1047, "lr": 5.567345723729062e-07, "epoch": 2.7923566878980894, "percentage": 93.2, "elapsed_time": "12:09:20", "remaining_time": "0:53:14"}
|
140 |
+
{"current_steps": 1380, "total_steps": 1470, "loss": 0.1042, "lr": 5.459918963120477e-07, "epoch": 2.812738853503185, "percentage": 93.88, "elapsed_time": "12:14:32", "remaining_time": "0:47:54"}
|
141 |
+
{"current_steps": 1390, "total_steps": 1470, "loss": 0.1057, "lr": 5.363653733440328e-07, "epoch": 2.8331210191082805, "percentage": 94.56, "elapsed_time": "12:19:45", "remaining_time": "0:42:34"}
|
142 |
+
{"current_steps": 1400, "total_steps": 1470, "loss": 0.105, "lr": 5.278598785296044e-07, "epoch": 2.853503184713376, "percentage": 95.24, "elapsed_time": "12:24:57", "remaining_time": "0:37:14"}
|
143 |
+
{"current_steps": 1410, "total_steps": 1470, "loss": 0.1039, "lr": 5.2047971921878e-07, "epoch": 2.8738853503184716, "percentage": 95.92, "elapsed_time": "12:30:12", "remaining_time": "0:31:55"}
|
144 |
+
{"current_steps": 1420, "total_steps": 1470, "loss": 0.105, "lr": 5.142286328695235e-07, "epoch": 2.894267515923567, "percentage": 96.6, "elapsed_time": "12:35:26", "remaining_time": "0:26:35"}
|
145 |
+
{"current_steps": 1430, "total_steps": 1470, "loss": 0.1032, "lr": 5.091097851550239e-07, "epoch": 2.9146496815286627, "percentage": 97.28, "elapsed_time": "12:40:40", "remaining_time": "0:21:16"}
|
146 |
+
{"current_steps": 1440, "total_steps": 1470, "loss": 0.1036, "lr": 5.051257683605363e-07, "epoch": 2.935031847133758, "percentage": 97.96, "elapsed_time": "12:45:55", "remaining_time": "0:15:57"}
|
147 |
+
{"current_steps": 1450, "total_steps": 1470, "loss": 0.1027, "lr": 5.022786000705963e-07, "epoch": 2.9554140127388537, "percentage": 98.64, "elapsed_time": "12:51:09", "remaining_time": "0:10:38"}
|
148 |
+
{"current_steps": 1460, "total_steps": 1470, "loss": 0.1029, "lr": 5.005697221472769e-07, "epoch": 2.9757961783439493, "percentage": 99.32, "elapsed_time": "12:56:22", "remaining_time": "0:05:19"}
|
149 |
+
{"current_steps": 1470, "total_steps": 1470, "loss": 0.1027, "lr": 5e-07, "epoch": 2.996178343949045, "percentage": 100.0, "elapsed_time": "13:01:36", "remaining_time": "0:00:00"}
|