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:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33e32679088b8c5cb2b84f0bbc403981e068f84c1dbd1a830a4743b855680c4c
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdb7a56088b423662a901c734366f5849348e9423c6613b8ccf8564d669e8699
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dc85600e81015ab03b4cd39bd6c49c82d6db7e8c2febfa8d9dccb78ba549a46
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5b95af599e5c0ad4d5a0806949ee1831f35a66cc911ea295b449c352ee4043d
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -114,3 +114,56 @@
|
|
114 |
{"current_steps": 114, "total_steps": 168, "loss": 0.7745, "lr": 2.8372782981874964e-06, "epoch": 2.026666666666667, "percentage": 67.86, "elapsed_time": "1:29:34", "remaining_time": "0:42:25"}
|
115 |
{"current_steps": 115, "total_steps": 168, "loss": 0.6196, "lr": 2.7439617423043146e-06, "epoch": 2.0444444444444443, "percentage": 68.45, "elapsed_time": "1:30:17", "remaining_time": "0:41:36"}
|
116 |
{"current_steps": 116, "total_steps": 168, "loss": 0.5975, "lr": 2.6516216963089698e-06, "epoch": 2.062222222222222, "percentage": 69.05, "elapsed_time": "1:30:58", "remaining_time": "0:40:46"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
{"current_steps": 114, "total_steps": 168, "loss": 0.7745, "lr": 2.8372782981874964e-06, "epoch": 2.026666666666667, "percentage": 67.86, "elapsed_time": "1:29:34", "remaining_time": "0:42:25"}
|
115 |
{"current_steps": 115, "total_steps": 168, "loss": 0.6196, "lr": 2.7439617423043146e-06, "epoch": 2.0444444444444443, "percentage": 68.45, "elapsed_time": "1:30:17", "remaining_time": "0:41:36"}
|
116 |
{"current_steps": 116, "total_steps": 168, "loss": 0.5975, "lr": 2.6516216963089698e-06, "epoch": 2.062222222222222, "percentage": 69.05, "elapsed_time": "1:30:58", "remaining_time": "0:40:46"}
|
117 |
+
{"current_steps": 117, "total_steps": 168, "loss": 0.7238, "lr": 2.560298128924358e-06, "epoch": 2.08, "percentage": 69.64, "elapsed_time": "1:31:44", "remaining_time": "0:39:59"}
|
118 |
+
{"current_steps": 118, "total_steps": 168, "loss": 0.7086, "lr": 2.470030568897938e-06, "epoch": 2.097777777777778, "percentage": 70.24, "elapsed_time": "1:32:31", "remaining_time": "0:39:12"}
|
119 |
+
{"current_steps": 119, "total_steps": 168, "loss": 0.7369, "lr": 2.3808580878919948e-06, "epoch": 2.1155555555555554, "percentage": 70.83, "elapsed_time": "1:33:18", "remaining_time": "0:38:25"}
|
120 |
+
{"current_steps": 120, "total_steps": 168, "loss": 0.6709, "lr": 2.2928192835717642e-06, "epoch": 2.1333333333333333, "percentage": 71.43, "elapsed_time": "1:34:07", "remaining_time": "0:37:38"}
|
121 |
+
{"current_steps": 121, "total_steps": 168, "loss": 0.6351, "lr": 2.205952262898704e-06, "epoch": 2.151111111111111, "percentage": 72.02, "elapsed_time": "1:34:54", "remaining_time": "0:36:52"}
|
122 |
+
{"current_steps": 122, "total_steps": 168, "loss": 0.6603, "lr": 2.120294625636171e-06, "epoch": 2.168888888888889, "percentage": 72.62, "elapsed_time": "1:35:38", "remaining_time": "0:36:03"}
|
123 |
+
{"current_steps": 123, "total_steps": 168, "loss": 0.7047, "lr": 2.0358834480746363e-06, "epoch": 2.1866666666666665, "percentage": 73.21, "elapsed_time": "1:36:35", "remaining_time": "0:35:20"}
|
124 |
+
{"current_steps": 124, "total_steps": 168, "loss": 0.6574, "lr": 1.9527552669834797e-06, "epoch": 2.2044444444444444, "percentage": 73.81, "elapsed_time": "1:37:21", "remaining_time": "0:34:32"}
|
125 |
+
{"current_steps": 125, "total_steps": 168, "loss": 0.7172, "lr": 1.8709460637963123e-06, "epoch": 2.2222222222222223, "percentage": 74.4, "elapsed_time": "1:38:13", "remaining_time": "0:33:47"}
|
126 |
+
{"current_steps": 126, "total_steps": 168, "loss": 0.6212, "lr": 1.7904912490366723e-06, "epoch": 2.24, "percentage": 75.0, "elapsed_time": "1:39:02", "remaining_time": "0:33:00"}
|
127 |
+
{"current_steps": 127, "total_steps": 168, "loss": 0.7009, "lr": 1.711425646990838e-06, "epoch": 2.2577777777777777, "percentage": 75.6, "elapsed_time": "1:39:49", "remaining_time": "0:32:13"}
|
128 |
+
{"current_steps": 128, "total_steps": 168, "loss": 0.6447, "lr": 1.6337834806343783e-06, "epoch": 2.2755555555555556, "percentage": 76.19, "elapsed_time": "1:40:30", "remaining_time": "0:31:24"}
|
129 |
+
{"current_steps": 129, "total_steps": 168, "loss": 0.6013, "lr": 1.557598356819e-06, "epoch": 2.2933333333333334, "percentage": 76.79, "elapsed_time": "1:41:09", "remaining_time": "0:30:35"}
|
130 |
+
{"current_steps": 130, "total_steps": 168, "loss": 0.6542, "lr": 1.482903251726049e-06, "epoch": 2.311111111111111, "percentage": 77.38, "elapsed_time": "1:41:49", "remaining_time": "0:29:45"}
|
131 |
+
{"current_steps": 131, "total_steps": 168, "loss": 0.6156, "lr": 1.409730496593016e-06, "epoch": 2.328888888888889, "percentage": 77.98, "elapsed_time": "1:42:27", "remaining_time": "0:28:56"}
|
132 |
+
{"current_steps": 132, "total_steps": 168, "loss": 0.8226, "lr": 1.3381117637191887e-06, "epoch": 2.3466666666666667, "percentage": 78.57, "elapsed_time": "1:43:22", "remaining_time": "0:28:11"}
|
133 |
+
{"current_steps": 133, "total_steps": 168, "loss": 0.6674, "lr": 1.2680780527565313e-06, "epoch": 2.3644444444444446, "percentage": 79.17, "elapsed_time": "1:44:11", "remaining_time": "0:27:25"}
|
134 |
+
{"current_steps": 134, "total_steps": 168, "loss": 0.7292, "lr": 1.1996596772917091e-06, "epoch": 2.3822222222222225, "percentage": 79.76, "elapsed_time": "1:45:02", "remaining_time": "0:26:39"}
|
135 |
+
{"current_steps": 135, "total_steps": 168, "loss": 0.6922, "lr": 1.132886251725061e-06, "epoch": 2.4, "percentage": 80.36, "elapsed_time": "1:45:50", "remaining_time": "0:25:52"}
|
136 |
+
{"current_steps": 136, "total_steps": 168, "loss": 0.7064, "lr": 1.0677866784522317e-06, "epoch": 2.417777777777778, "percentage": 80.95, "elapsed_time": "1:46:37", "remaining_time": "0:25:05"}
|
137 |
+
{"current_steps": 137, "total_steps": 168, "loss": 0.6197, "lr": 1.004389135353972e-06, "epoch": 2.4355555555555557, "percentage": 81.55, "elapsed_time": "1:47:13", "remaining_time": "0:24:15"}
|
138 |
+
{"current_steps": 138, "total_steps": 168, "loss": 0.6535, "lr": 9.427210635995482e-07, "epoch": 2.453333333333333, "percentage": 82.14, "elapsed_time": "1:48:00", "remaining_time": "0:23:28"}
|
139 |
+
{"current_steps": 139, "total_steps": 168, "loss": 0.7117, "lr": 8.828091557690288e-07, "epoch": 2.471111111111111, "percentage": 82.74, "elapsed_time": "1:48:51", "remaining_time": "0:22:42"}
|
140 |
+
{"current_steps": 140, "total_steps": 168, "loss": 0.7144, "lr": 8.246793442995954e-07, "epoch": 2.488888888888889, "percentage": 83.33, "elapsed_time": "1:49:42", "remaining_time": "0:21:56"}
|
141 |
+
{"current_steps": 141, "total_steps": 168, "loss": 0.6957, "lr": 7.68356790260873e-07, "epoch": 2.506666666666667, "percentage": 83.93, "elapsed_time": "1:50:25", "remaining_time": "0:21:08"}
|
142 |
+
{"current_steps": 142, "total_steps": 168, "loss": 0.7647, "lr": 7.138658724641417e-07, "epoch": 2.5244444444444447, "percentage": 84.52, "elapsed_time": "1:51:18", "remaining_time": "0:20:22"}
|
143 |
+
{"current_steps": 143, "total_steps": 168, "loss": 0.7211, "lr": 6.612301769101464e-07, "epoch": 2.542222222222222, "percentage": 85.12, "elapsed_time": "1:52:09", "remaining_time": "0:19:36"}
|
144 |
+
{"current_steps": 144, "total_steps": 168, "loss": 0.635, "lr": 6.104724865800665e-07, "epoch": 2.56, "percentage": 85.71, "elapsed_time": "1:52:52", "remaining_time": "0:18:48"}
|
145 |
+
{"current_steps": 145, "total_steps": 168, "loss": 0.5809, "lr": 5.616147715740611e-07, "epoch": 2.5777777777777775, "percentage": 86.31, "elapsed_time": "1:53:30", "remaining_time": "0:18:00"}
|
146 |
+
{"current_steps": 146, "total_steps": 168, "loss": 0.8847, "lr": 5.146781796016798e-07, "epoch": 2.5955555555555554, "percentage": 86.9, "elapsed_time": "1:54:24", "remaining_time": "0:17:14"}
|
147 |
+
{"current_steps": 147, "total_steps": 168, "loss": 0.6341, "lr": 4.696830268282204e-07, "epoch": 2.6133333333333333, "percentage": 87.5, "elapsed_time": "1:55:04", "remaining_time": "0:16:26"}
|
148 |
+
{"current_steps": 148, "total_steps": 168, "loss": 0.7013, "lr": 4.2664878908102556e-07, "epoch": 2.631111111111111, "percentage": 88.1, "elapsed_time": "1:55:49", "remaining_time": "0:15:39"}
|
149 |
+
{"current_steps": 149, "total_steps": 168, "loss": 0.7076, "lr": 3.855940934195146e-07, "epoch": 2.648888888888889, "percentage": 88.69, "elapsed_time": "1:56:41", "remaining_time": "0:14:52"}
|
150 |
+
{"current_steps": 150, "total_steps": 168, "loss": 0.7147, "lr": 3.4653671007259084e-07, "epoch": 2.6666666666666665, "percentage": 89.29, "elapsed_time": "1:57:31", "remaining_time": "0:14:06"}
|
151 |
+
{"current_steps": 151, "total_steps": 168, "loss": 0.6029, "lr": 3.0949354474692937e-07, "epoch": 2.6844444444444444, "percentage": 89.88, "elapsed_time": "1:58:18", "remaining_time": "0:13:19"}
|
152 |
+
{"current_steps": 152, "total_steps": 168, "loss": 0.7018, "lr": 2.7448063130946224e-07, "epoch": 2.7022222222222223, "percentage": 90.48, "elapsed_time": "1:58:59", "remaining_time": "0:12:31"}
|
153 |
+
{"current_steps": 153, "total_steps": 168, "loss": 0.7996, "lr": 2.4151312484723465e-07, "epoch": 2.7199999999999998, "percentage": 91.07, "elapsed_time": "1:59:44", "remaining_time": "0:11:44"}
|
154 |
+
{"current_steps": 154, "total_steps": 168, "loss": 0.5584, "lr": 2.106052951076365e-07, "epoch": 2.7377777777777776, "percentage": 91.67, "elapsed_time": "2:00:21", "remaining_time": "0:10:56"}
|
155 |
+
{"current_steps": 155, "total_steps": 168, "loss": 0.626, "lr": 1.8177052032184285e-07, "epoch": 2.7555555555555555, "percentage": 92.26, "elapsed_time": "2:01:01", "remaining_time": "0:10:09"}
|
156 |
+
{"current_steps": 156, "total_steps": 168, "loss": 0.6039, "lr": 1.5502128141414496e-07, "epoch": 2.7733333333333334, "percentage": 92.86, "elapsed_time": "2:01:39", "remaining_time": "0:09:21"}
|
157 |
+
{"current_steps": 157, "total_steps": 168, "loss": 0.7568, "lr": 1.303691565996712e-07, "epoch": 2.7911111111111113, "percentage": 93.45, "elapsed_time": "2:02:30", "remaining_time": "0:08:34"}
|
158 |
+
{"current_steps": 158, "total_steps": 168, "loss": 0.7259, "lr": 1.0782481637284014e-07, "epoch": 2.8088888888888888, "percentage": 94.05, "elapsed_time": "2:03:21", "remaining_time": "0:07:48"}
|
159 |
+
{"current_steps": 159, "total_steps": 168, "loss": 0.5574, "lr": 8.739801888871468e-08, "epoch": 2.8266666666666667, "percentage": 94.64, "elapsed_time": "2:03:57", "remaining_time": "0:07:01"}
|
160 |
+
{"current_steps": 160, "total_steps": 168, "loss": 0.7079, "lr": 6.909760573925561e-08, "epoch": 2.8444444444444446, "percentage": 95.24, "elapsed_time": "2:04:39", "remaining_time": "0:06:13"}
|
161 |
+
{"current_steps": 161, "total_steps": 168, "loss": 0.6241, "lr": 5.2931498126298495e-08, "epoch": 2.862222222222222, "percentage": 95.83, "elapsed_time": "2:05:21", "remaining_time": "0:05:27"}
|
162 |
+
{"current_steps": 162, "total_steps": 168, "loss": 0.7255, "lr": 3.890669343292464e-08, "epoch": 2.88, "percentage": 96.43, "elapsed_time": "2:06:12", "remaining_time": "0:04:40"}
|
163 |
+
{"current_steps": 163, "total_steps": 168, "loss": 0.6244, "lr": 2.702926219468882e-08, "epoch": 2.897777777777778, "percentage": 97.02, "elapsed_time": "2:06:51", "remaining_time": "0:03:53"}
|
164 |
+
{"current_steps": 164, "total_steps": 168, "loss": 0.7233, "lr": 1.7304345472035634e-08, "epoch": 2.9155555555555557, "percentage": 97.62, "elapsed_time": "2:07:31", "remaining_time": "0:03:06"}
|
165 |
+
{"current_steps": 165, "total_steps": 168, "loss": 0.5895, "lr": 9.73615262502503e-09, "epoch": 2.9333333333333336, "percentage": 98.21, "elapsed_time": "2:08:07", "remaining_time": "0:02:19"}
|
166 |
+
{"current_steps": 166, "total_steps": 168, "loss": 0.7434, "lr": 4.327959491344791e-09, "epoch": 2.951111111111111, "percentage": 98.81, "elapsed_time": "2:08:47", "remaining_time": "0:01:33"}
|
167 |
+
{"current_steps": 167, "total_steps": 168, "loss": 0.6239, "lr": 1.082106968385288e-09, "epoch": 2.968888888888889, "percentage": 99.4, "elapsed_time": "2:09:36", "remaining_time": "0:00:46"}
|
168 |
+
{"current_steps": 168, "total_steps": 168, "loss": 0.6308, "lr": 0.0, "epoch": 2.986666666666667, "percentage": 100.0, "elapsed_time": "2:10:14", "remaining_time": "0:00:00"}
|
169 |
+
{"current_steps": 168, "total_steps": 168, "epoch": 2.986666666666667, "percentage": 100.0, "elapsed_time": "2:12:23", "remaining_time": "0:00:00"}
|