Training in progress, epoch 5
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:fc54557a0e0c714ea07d44c3afbe1261e59c4fa0d9f32dc6f0683636f3c8f204
|
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 sha256:97c95a5177b4dd52a0d19e8c4eee010215536cbd560eeb2893aeff110f3fedcb
|
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 sha256:78e0d6ea243b2b8c832fa02394b3bf47ec92e60bee82eb6ef2ee0eb290ee210e
|
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:ebc4f082cb415d8e1be5d8129743c907d97c19a158e67747f97eaeb848735a5f
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -139,3 +139,35 @@
|
|
139 |
{"current_steps": 139, "total_steps": 231, "loss": 0.1261, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "0:51:12", "remaining_time": "0:33:53"}
|
140 |
{"current_steps": 140, "total_steps": 231, "loss": 0.1255, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "0:51:29", "remaining_time": "0:33:28"}
|
141 |
{"current_steps": 141, "total_steps": 231, "loss": 0.1543, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "0:51:48", "remaining_time": "0:33:04"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
139 |
{"current_steps": 139, "total_steps": 231, "loss": 0.1261, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "0:51:12", "remaining_time": "0:33:53"}
|
140 |
{"current_steps": 140, "total_steps": 231, "loss": 0.1255, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "0:51:29", "remaining_time": "0:33:28"}
|
141 |
{"current_steps": 141, "total_steps": 231, "loss": 0.1543, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "0:51:48", "remaining_time": "0:33:04"}
|
142 |
+
{"current_steps": 142, "total_steps": 231, "loss": 0.139, "lr": 7.817086484143987e-06, "epoch": 4.303030303030303, "percentage": 61.47, "elapsed_time": "0:52:10", "remaining_time": "0:32:42"}
|
143 |
+
{"current_steps": 143, "total_steps": 231, "loss": 0.1257, "lr": 7.669235889528436e-06, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "0:52:35", "remaining_time": "0:32:21"}
|
144 |
+
{"current_steps": 144, "total_steps": 231, "loss": 0.1343, "lr": 7.521922140071003e-06, "epoch": 4.363636363636363, "percentage": 62.34, "elapsed_time": "0:52:58", "remaining_time": "0:32:00"}
|
145 |
+
{"current_steps": 145, "total_steps": 231, "loss": 0.1172, "lr": 7.375179166564062e-06, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "0:53:18", "remaining_time": "0:31:36"}
|
146 |
+
{"current_steps": 146, "total_steps": 231, "loss": 0.1321, "lr": 7.2290407683331154e-06, "epoch": 4.424242424242424, "percentage": 63.2, "elapsed_time": "0:53:37", "remaining_time": "0:31:13"}
|
147 |
+
{"current_steps": 147, "total_steps": 231, "loss": 0.1361, "lr": 7.0835406054517505e-06, "epoch": 4.454545454545454, "percentage": 63.64, "elapsed_time": "0:53:55", "remaining_time": "0:30:48"}
|
148 |
+
{"current_steps": 148, "total_steps": 231, "loss": 0.0898, "lr": 6.93871219098876e-06, "epoch": 4.484848484848484, "percentage": 64.07, "elapsed_time": "0:54:13", "remaining_time": "0:30:24"}
|
149 |
+
{"current_steps": 149, "total_steps": 231, "loss": 0.1315, "lr": 6.79458888328903e-06, "epoch": 4.515151515151516, "percentage": 64.5, "elapsed_time": "0:54:34", "remaining_time": "0:30:02"}
|
150 |
+
{"current_steps": 150, "total_steps": 231, "loss": 0.1323, "lr": 6.651203878290139e-06, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "0:54:49", "remaining_time": "0:29:36"}
|
151 |
+
{"current_steps": 151, "total_steps": 231, "loss": 0.1454, "lr": 6.508590201876317e-06, "epoch": 4.575757575757576, "percentage": 65.37, "elapsed_time": "0:55:05", "remaining_time": "0:29:11"}
|
152 |
+
{"current_steps": 152, "total_steps": 231, "loss": 0.1082, "lr": 6.366780702271589e-06, "epoch": 4.606060606060606, "percentage": 65.8, "elapsed_time": "0:55:18", "remaining_time": "0:28:44"}
|
153 |
+
{"current_steps": 153, "total_steps": 231, "loss": 0.1284, "lr": 6.225808042473857e-06, "epoch": 4.636363636363637, "percentage": 66.23, "elapsed_time": "0:55:36", "remaining_time": "0:28:20"}
|
154 |
+
{"current_steps": 154, "total_steps": 231, "loss": 0.139, "lr": 6.085704692731609e-06, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "0:55:58", "remaining_time": "0:27:59"}
|
155 |
+
{"current_steps": 155, "total_steps": 231, "loss": 0.1544, "lr": 5.946502923065054e-06, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "0:56:19", "remaining_time": "0:27:37"}
|
156 |
+
{"current_steps": 156, "total_steps": 231, "loss": 0.1275, "lr": 5.8082347958333625e-06, "epoch": 4.7272727272727275, "percentage": 67.53, "elapsed_time": "0:56:40", "remaining_time": "0:27:14"}
|
157 |
+
{"current_steps": 157, "total_steps": 231, "loss": 0.1117, "lr": 5.670932158349732e-06, "epoch": 4.757575757575758, "percentage": 67.97, "elapsed_time": "0:56:56", "remaining_time": "0:26:50"}
|
158 |
+
{"current_steps": 158, "total_steps": 231, "loss": 0.1312, "lr": 5.534626635546e-06, "epoch": 4.787878787878788, "percentage": 68.4, "elapsed_time": "0:57:16", "remaining_time": "0:26:27"}
|
159 |
+
{"current_steps": 159, "total_steps": 231, "loss": 0.1267, "lr": 5.399349622688479e-06, "epoch": 4.818181818181818, "percentage": 68.83, "elapsed_time": "0:57:34", "remaining_time": "0:26:04"}
|
160 |
+
{"current_steps": 160, "total_steps": 231, "loss": 0.146, "lr": 5.2651322781466606e-06, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "0:57:51", "remaining_time": "0:25:40"}
|
161 |
+
{"current_steps": 161, "total_steps": 231, "loss": 0.1607, "lr": 5.132005516216512e-06, "epoch": 4.878787878787879, "percentage": 69.7, "elapsed_time": "0:58:12", "remaining_time": "0:25:18"}
|
162 |
+
{"current_steps": 162, "total_steps": 231, "loss": 0.1361, "lr": 5.000000000000003e-06, "epoch": 4.909090909090909, "percentage": 70.13, "elapsed_time": "0:58:32", "remaining_time": "0:24:56"}
|
163 |
+
{"current_steps": 163, "total_steps": 231, "loss": 0.1266, "lr": 4.869146134342426e-06, "epoch": 4.9393939393939394, "percentage": 70.56, "elapsed_time": "0:58:48", "remaining_time": "0:24:32"}
|
164 |
+
{"current_steps": 164, "total_steps": 231, "loss": 0.1151, "lr": 4.739474058829288e-06, "epoch": 4.96969696969697, "percentage": 71.0, "elapsed_time": "0:59:05", "remaining_time": "0:24:08"}
|
165 |
+
{"current_steps": 165, "total_steps": 231, "loss": 0.1575, "lr": 4.611013640844245e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "0:59:24", "remaining_time": "0:23:45"}
|
166 |
+
{"current_steps": 166, "total_steps": 231, "loss": 0.0969, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:01:42", "remaining_time": "0:24:09"}
|
167 |
+
{"current_steps": 167, "total_steps": 231, "loss": 0.1062, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:02:05", "remaining_time": "0:23:47"}
|
168 |
+
{"current_steps": 168, "total_steps": 231, "loss": 0.0965, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:02:20", "remaining_time": "0:23:22"}
|
169 |
+
{"current_steps": 169, "total_steps": 231, "loss": 0.089, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:02:36", "remaining_time": "0:22:58"}
|
170 |
+
{"current_steps": 170, "total_steps": 231, "loss": 0.1036, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:02:53", "remaining_time": "0:22:33"}
|
171 |
+
{"current_steps": 171, "total_steps": 231, "loss": 0.1172, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:03:14", "remaining_time": "0:22:11"}
|
172 |
+
{"current_steps": 172, "total_steps": 231, "loss": 0.1003, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:03:29", "remaining_time": "0:21:46"}
|
173 |
+
{"current_steps": 173, "total_steps": 231, "loss": 0.0705, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:03:44", "remaining_time": "0:21:22"}
|