Training in progress, epoch 1
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:cd6f495bb0dfa7968382eca1c2e515a27ad5ecb1b1b1b25bfadb91ba7df0386d
|
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:d6042aa198e435a9f490fa9a76ad1ca0e4fd7e6cdf85d7eea5b24b1f7b3a5561
|
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 sha256:266b84f0dce5c61a68e97f4b20f15d57a283377c0dc175994dda2373103749b2
|
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:be0cb6cc8dfe4334b387ea886a1965edd3de29012b64d9da648502dbcc5b365c
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -78,3 +78,81 @@
|
|
78 |
{"current_steps": 78, "total_steps": 390, "loss": 0.989, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "2:01:35", "remaining_time": "8:06:23"}
|
79 |
{"current_steps": 79, "total_steps": 390, "loss": 0.9824, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "2:03:49", "remaining_time": "8:07:26"}
|
80 |
{"current_steps": 80, "total_steps": 390, "loss": 0.9637, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "2:05:22", "remaining_time": "8:05:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
{"current_steps": 78, "total_steps": 390, "loss": 0.989, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "2:01:35", "remaining_time": "8:06:23"}
|
79 |
{"current_steps": 79, "total_steps": 390, "loss": 0.9824, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "2:03:49", "remaining_time": "8:07:26"}
|
80 |
{"current_steps": 80, "total_steps": 390, "loss": 0.9637, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "2:05:22", "remaining_time": "8:05:51"}
|
81 |
+
{"current_steps": 81, "total_steps": 390, "loss": 0.9629, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "2:06:52", "remaining_time": "8:03:59"}
|
82 |
+
{"current_steps": 82, "total_steps": 390, "loss": 0.9612, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "2:08:18", "remaining_time": "8:01:55"}
|
83 |
+
{"current_steps": 83, "total_steps": 390, "loss": 0.9808, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "2:09:53", "remaining_time": "8:00:25"}
|
84 |
+
{"current_steps": 84, "total_steps": 390, "loss": 0.9676, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "2:11:24", "remaining_time": "7:58:42"}
|
85 |
+
{"current_steps": 85, "total_steps": 390, "loss": 0.9899, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "2:12:50", "remaining_time": "7:56:40"}
|
86 |
+
{"current_steps": 86, "total_steps": 390, "loss": 0.9841, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "2:14:21", "remaining_time": "7:54:56"}
|
87 |
+
{"current_steps": 87, "total_steps": 390, "loss": 1.0057, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "2:15:53", "remaining_time": "7:53:17"}
|
88 |
+
{"current_steps": 88, "total_steps": 390, "loss": 1.0046, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "2:17:30", "remaining_time": "7:51:53"}
|
89 |
+
{"current_steps": 89, "total_steps": 390, "loss": 0.96, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "2:19:08", "remaining_time": "7:50:36"}
|
90 |
+
{"current_steps": 90, "total_steps": 390, "loss": 0.9694, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "2:20:49", "remaining_time": "7:49:26"}
|
91 |
+
{"current_steps": 91, "total_steps": 390, "loss": 0.9462, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "2:22:20", "remaining_time": "7:47:40"}
|
92 |
+
{"current_steps": 92, "total_steps": 390, "loss": 0.995, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "2:23:58", "remaining_time": "7:46:22"}
|
93 |
+
{"current_steps": 93, "total_steps": 390, "loss": 0.9653, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "2:25:28", "remaining_time": "7:44:34"}
|
94 |
+
{"current_steps": 94, "total_steps": 390, "loss": 0.9723, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "2:26:49", "remaining_time": "7:42:20"}
|
95 |
+
{"current_steps": 95, "total_steps": 390, "loss": 0.9558, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "2:28:18", "remaining_time": "7:40:33"}
|
96 |
+
{"current_steps": 96, "total_steps": 390, "loss": 0.9625, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "2:29:56", "remaining_time": "7:39:10"}
|
97 |
+
{"current_steps": 97, "total_steps": 390, "loss": 0.9642, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "2:31:21", "remaining_time": "7:37:13"}
|
98 |
+
{"current_steps": 98, "total_steps": 390, "loss": 0.9553, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "2:33:07", "remaining_time": "7:36:14"}
|
99 |
+
{"current_steps": 99, "total_steps": 390, "loss": 0.955, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "2:34:30", "remaining_time": "7:34:09"}
|
100 |
+
{"current_steps": 100, "total_steps": 390, "loss": 0.9468, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "2:36:02", "remaining_time": "7:32:31"}
|
101 |
+
{"current_steps": 101, "total_steps": 390, "loss": 0.968, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "2:37:31", "remaining_time": "7:30:43"}
|
102 |
+
{"current_steps": 102, "total_steps": 390, "loss": 0.9662, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "2:38:59", "remaining_time": "7:28:55"}
|
103 |
+
{"current_steps": 103, "total_steps": 390, "loss": 0.97, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "2:40:36", "remaining_time": "7:27:32"}
|
104 |
+
{"current_steps": 104, "total_steps": 390, "loss": 0.9536, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "2:42:09", "remaining_time": "7:25:56"}
|
105 |
+
{"current_steps": 105, "total_steps": 390, "loss": 0.9558, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "2:43:50", "remaining_time": "7:24:43"}
|
106 |
+
{"current_steps": 106, "total_steps": 390, "loss": 0.9609, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "2:45:33", "remaining_time": "7:23:33"}
|
107 |
+
{"current_steps": 107, "total_steps": 390, "loss": 0.9596, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "2:47:15", "remaining_time": "7:22:22"}
|
108 |
+
{"current_steps": 108, "total_steps": 390, "loss": 0.988, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "2:48:51", "remaining_time": "7:20:54"}
|
109 |
+
{"current_steps": 109, "total_steps": 390, "loss": 0.9635, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "2:50:26", "remaining_time": "7:19:24"}
|
110 |
+
{"current_steps": 110, "total_steps": 390, "loss": 1.0002, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "2:52:06", "remaining_time": "7:18:06"}
|
111 |
+
{"current_steps": 111, "total_steps": 390, "loss": 0.9543, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "2:53:44", "remaining_time": "7:16:41"}
|
112 |
+
{"current_steps": 112, "total_steps": 390, "loss": 0.976, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "2:55:20", "remaining_time": "7:15:12"}
|
113 |
+
{"current_steps": 113, "total_steps": 390, "loss": 0.9568, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "2:56:47", "remaining_time": "7:13:23"}
|
114 |
+
{"current_steps": 114, "total_steps": 390, "loss": 0.9429, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "2:58:24", "remaining_time": "7:11:57"}
|
115 |
+
{"current_steps": 115, "total_steps": 390, "loss": 0.9811, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "2:59:55", "remaining_time": "7:10:15"}
|
116 |
+
{"current_steps": 116, "total_steps": 390, "loss": 0.9488, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "3:01:31", "remaining_time": "7:08:45"}
|
117 |
+
{"current_steps": 117, "total_steps": 390, "loss": 0.9774, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "3:03:05", "remaining_time": "7:07:11"}
|
118 |
+
{"current_steps": 118, "total_steps": 390, "loss": 0.9713, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "3:04:49", "remaining_time": "7:06:02"}
|
119 |
+
{"current_steps": 119, "total_steps": 390, "loss": 0.9523, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "3:06:30", "remaining_time": "7:04:43"}
|
120 |
+
{"current_steps": 120, "total_steps": 390, "loss": 0.9787, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "3:08:02", "remaining_time": "7:03:06"}
|
121 |
+
{"current_steps": 121, "total_steps": 390, "loss": 0.9652, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "3:09:30", "remaining_time": "7:01:17"}
|
122 |
+
{"current_steps": 122, "total_steps": 390, "loss": 0.985, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "3:11:10", "remaining_time": "6:59:56"}
|
123 |
+
{"current_steps": 123, "total_steps": 390, "loss": 0.9495, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "3:12:48", "remaining_time": "6:58:31"}
|
124 |
+
{"current_steps": 124, "total_steps": 390, "loss": 0.9416, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "3:14:21", "remaining_time": "6:56:56"}
|
125 |
+
{"current_steps": 125, "total_steps": 390, "loss": 0.9732, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "3:15:47", "remaining_time": "6:55:05"}
|
126 |
+
{"current_steps": 126, "total_steps": 390, "loss": 0.9546, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "3:17:20", "remaining_time": "6:53:28"}
|
127 |
+
{"current_steps": 127, "total_steps": 390, "loss": 0.9506, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "3:18:48", "remaining_time": "6:51:41"}
|
128 |
+
{"current_steps": 128, "total_steps": 390, "loss": 0.9704, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "3:20:24", "remaining_time": "6:50:13"}
|
129 |
+
{"current_steps": 129, "total_steps": 390, "loss": 0.9588, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "3:22:07", "remaining_time": "6:48:57"}
|
130 |
+
{"current_steps": 130, "total_steps": 390, "loss": 0.9664, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "3:23:33", "remaining_time": "6:47:07"}
|
131 |
+
{"current_steps": 131, "total_steps": 390, "loss": 0.9706, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "3:25:06", "remaining_time": "6:45:31"}
|
132 |
+
{"current_steps": 132, "total_steps": 390, "loss": 0.9635, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "3:26:33", "remaining_time": "6:43:44"}
|
133 |
+
{"current_steps": 133, "total_steps": 390, "loss": 0.9582, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "3:28:01", "remaining_time": "6:41:58"}
|
134 |
+
{"current_steps": 134, "total_steps": 390, "loss": 0.9466, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "3:29:32", "remaining_time": "6:40:19"}
|
135 |
+
{"current_steps": 135, "total_steps": 390, "loss": 0.9404, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "3:31:03", "remaining_time": "6:38:39"}
|
136 |
+
{"current_steps": 136, "total_steps": 390, "loss": 0.9293, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "3:32:33", "remaining_time": "6:36:58"}
|
137 |
+
{"current_steps": 137, "total_steps": 390, "loss": 0.9788, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "3:34:10", "remaining_time": "6:35:31"}
|
138 |
+
{"current_steps": 138, "total_steps": 390, "loss": 0.9905, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "3:35:38", "remaining_time": "6:33:47"}
|
139 |
+
{"current_steps": 139, "total_steps": 390, "loss": 0.9825, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "3:37:10", "remaining_time": "6:32:09"}
|
140 |
+
{"current_steps": 140, "total_steps": 390, "loss": 0.9652, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "3:38:44", "remaining_time": "6:30:36"}
|
141 |
+
{"current_steps": 141, "total_steps": 390, "loss": 1.0017, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "3:40:17", "remaining_time": "6:29:02"}
|
142 |
+
{"current_steps": 142, "total_steps": 390, "loss": 0.9528, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "3:42:01", "remaining_time": "6:27:44"}
|
143 |
+
{"current_steps": 143, "total_steps": 390, "loss": 0.9648, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "3:43:30", "remaining_time": "6:26:04"}
|
144 |
+
{"current_steps": 144, "total_steps": 390, "loss": 0.9602, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "3:45:03", "remaining_time": "6:24:29"}
|
145 |
+
{"current_steps": 145, "total_steps": 390, "loss": 0.9825, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "3:46:44", "remaining_time": "6:23:07"}
|
146 |
+
{"current_steps": 146, "total_steps": 390, "loss": 0.9643, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "3:48:18", "remaining_time": "6:21:33"}
|
147 |
+
{"current_steps": 147, "total_steps": 390, "loss": 0.9328, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "3:49:52", "remaining_time": "6:19:59"}
|
148 |
+
{"current_steps": 148, "total_steps": 390, "loss": 0.9528, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "3:51:23", "remaining_time": "6:18:21"}
|
149 |
+
{"current_steps": 149, "total_steps": 390, "loss": 0.9669, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "3:52:56", "remaining_time": "6:16:45"}
|
150 |
+
{"current_steps": 150, "total_steps": 390, "loss": 0.963, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "3:54:28", "remaining_time": "6:15:09"}
|
151 |
+
{"current_steps": 151, "total_steps": 390, "loss": 0.9441, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "3:56:08", "remaining_time": "6:13:45"}
|
152 |
+
{"current_steps": 152, "total_steps": 390, "loss": 0.9649, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "3:57:40", "remaining_time": "6:12:08"}
|
153 |
+
{"current_steps": 153, "total_steps": 390, "loss": 0.9622, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "3:59:13", "remaining_time": "6:10:33"}
|
154 |
+
{"current_steps": 154, "total_steps": 390, "loss": 0.9518, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "4:00:45", "remaining_time": "6:08:56"}
|
155 |
+
{"current_steps": 155, "total_steps": 390, "loss": 0.9643, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "4:02:12", "remaining_time": "6:07:12"}
|
156 |
+
{"current_steps": 156, "total_steps": 390, "loss": 0.9792, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "4:03:44", "remaining_time": "6:05:36"}
|
157 |
+
{"current_steps": 157, "total_steps": 390, "loss": 0.9135, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "4:05:59", "remaining_time": "6:05:04"}
|
158 |
+
{"current_steps": 158, "total_steps": 390, "loss": 0.9157, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "4:07:41", "remaining_time": "6:03:41"}
|