Training in progress, step 1000
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:bcfe4181fc7b759deeb934fd1ce7f0d05ed49aa95f26ddf5775be6cb73c50ecb
|
| 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 sha256:12e7a8575d2a9e7bba697a929be56f4e3991c354c8d7a7dc9a10bcc014333eea
|
| 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 sha256:1a6f68b339bf46be541e76ca3377d68ac5e841a508c9d87f5dcb51b114364676
|
| 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:c8e011e55455016c29dfa81be7772163b8ba53206178c3d01184d4bad298c8a3
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -159,3 +159,43 @@
|
|
| 159 |
{"current_steps": 795, "total_steps": 9128, "loss": 0.3673, "lr": 3.478641840087624e-05, "epoch": 0.6098964326812428, "percentage": 8.71, "elapsed_time": "5:06:37", "remaining_time": "2 days, 5:33:54"}
|
| 160 |
{"current_steps": 800, "total_steps": 9128, "loss": 0.3637, "lr": 3.500547645125959e-05, "epoch": 0.6137322593018796, "percentage": 8.76, "elapsed_time": "5:08:19", "remaining_time": "2 days, 5:29:43"}
|
| 161 |
{"current_steps": 805, "total_steps": 9128, "loss": 0.3748, "lr": 3.522453450164294e-05, "epoch": 0.6175680859225163, "percentage": 8.82, "elapsed_time": "5:11:03", "remaining_time": "2 days, 5:36:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
{"current_steps": 795, "total_steps": 9128, "loss": 0.3673, "lr": 3.478641840087624e-05, "epoch": 0.6098964326812428, "percentage": 8.71, "elapsed_time": "5:06:37", "remaining_time": "2 days, 5:33:54"}
|
| 160 |
{"current_steps": 800, "total_steps": 9128, "loss": 0.3637, "lr": 3.500547645125959e-05, "epoch": 0.6137322593018796, "percentage": 8.76, "elapsed_time": "5:08:19", "remaining_time": "2 days, 5:29:43"}
|
| 161 |
{"current_steps": 805, "total_steps": 9128, "loss": 0.3748, "lr": 3.522453450164294e-05, "epoch": 0.6175680859225163, "percentage": 8.82, "elapsed_time": "5:11:03", "remaining_time": "2 days, 5:36:05"}
|
| 162 |
+
{"current_steps": 810, "total_steps": 9128, "loss": 0.3802, "lr": 3.544359255202629e-05, "epoch": 0.6214039125431531, "percentage": 8.87, "elapsed_time": "5:12:40", "remaining_time": "2 days, 5:30:56"}
|
| 163 |
+
{"current_steps": 815, "total_steps": 9128, "loss": 0.3665, "lr": 3.566265060240964e-05, "epoch": 0.6252397391637898, "percentage": 8.93, "elapsed_time": "5:14:24", "remaining_time": "2 days, 5:26:54"}
|
| 164 |
+
{"current_steps": 820, "total_steps": 9128, "loss": 0.3711, "lr": 3.588170865279299e-05, "epoch": 0.6290755657844266, "percentage": 8.98, "elapsed_time": "5:16:06", "remaining_time": "2 days, 5:22:46"}
|
| 165 |
+
{"current_steps": 825, "total_steps": 9128, "loss": 0.3504, "lr": 3.6100766703176346e-05, "epoch": 0.6329113924050633, "percentage": 9.04, "elapsed_time": "5:17:48", "remaining_time": "2 days, 5:18:31"}
|
| 166 |
+
{"current_steps": 830, "total_steps": 9128, "loss": 0.3466, "lr": 3.63198247535597e-05, "epoch": 0.6367472190257001, "percentage": 9.09, "elapsed_time": "5:19:31", "remaining_time": "2 days, 5:14:29"}
|
| 167 |
+
{"current_steps": 835, "total_steps": 9128, "loss": 0.3495, "lr": 3.653888280394305e-05, "epoch": 0.6405830456463368, "percentage": 9.15, "elapsed_time": "5:21:07", "remaining_time": "2 days, 5:09:23"}
|
| 168 |
+
{"current_steps": 840, "total_steps": 9128, "loss": 0.3616, "lr": 3.67579408543264e-05, "epoch": 0.6444188722669736, "percentage": 9.2, "elapsed_time": "5:22:48", "remaining_time": "2 days, 5:04:57"}
|
| 169 |
+
{"current_steps": 845, "total_steps": 9128, "loss": 0.3628, "lr": 3.697699890470975e-05, "epoch": 0.6482546988876102, "percentage": 9.26, "elapsed_time": "5:24:25", "remaining_time": "2 days, 5:00:04"}
|
| 170 |
+
{"current_steps": 850, "total_steps": 9128, "loss": 0.3445, "lr": 3.71960569550931e-05, "epoch": 0.652090525508247, "percentage": 9.31, "elapsed_time": "5:26:09", "remaining_time": "2 days, 4:56:20"}
|
| 171 |
+
{"current_steps": 855, "total_steps": 9128, "loss": 0.3455, "lr": 3.7415115005476456e-05, "epoch": 0.6559263521288837, "percentage": 9.37, "elapsed_time": "5:27:46", "remaining_time": "2 days, 4:51:35"}
|
| 172 |
+
{"current_steps": 860, "total_steps": 9128, "loss": 0.3547, "lr": 3.76341730558598e-05, "epoch": 0.6597621787495205, "percentage": 9.42, "elapsed_time": "5:29:26", "remaining_time": "2 days, 4:47:12"}
|
| 173 |
+
{"current_steps": 865, "total_steps": 9128, "loss": 0.3526, "lr": 3.7853231106243156e-05, "epoch": 0.6635980053701572, "percentage": 9.48, "elapsed_time": "5:31:09", "remaining_time": "2 days, 4:43:21"}
|
| 174 |
+
{"current_steps": 870, "total_steps": 9128, "loss": 0.343, "lr": 3.807228915662651e-05, "epoch": 0.667433831990794, "percentage": 9.53, "elapsed_time": "5:32:46", "remaining_time": "2 days, 4:38:38"}
|
| 175 |
+
{"current_steps": 875, "total_steps": 9128, "loss": 0.3471, "lr": 3.8291347207009864e-05, "epoch": 0.6712696586114307, "percentage": 9.59, "elapsed_time": "5:34:26", "remaining_time": "2 days, 4:34:27"}
|
| 176 |
+
{"current_steps": 880, "total_steps": 9128, "loss": 0.3575, "lr": 3.851040525739321e-05, "epoch": 0.6751054852320675, "percentage": 9.64, "elapsed_time": "5:36:05", "remaining_time": "2 days, 4:30:03"}
|
| 177 |
+
{"current_steps": 885, "total_steps": 9128, "loss": 0.3371, "lr": 3.8729463307776565e-05, "epoch": 0.6789413118527042, "percentage": 9.7, "elapsed_time": "5:37:49", "remaining_time": "2 days, 4:26:34"}
|
| 178 |
+
{"current_steps": 890, "total_steps": 9128, "loss": 0.3624, "lr": 3.894852135815991e-05, "epoch": 0.682777138473341, "percentage": 9.75, "elapsed_time": "5:39:23", "remaining_time": "2 days, 4:21:28"}
|
| 179 |
+
{"current_steps": 895, "total_steps": 9128, "loss": 0.3535, "lr": 3.9167579408543266e-05, "epoch": 0.6866129650939777, "percentage": 9.8, "elapsed_time": "5:41:01", "remaining_time": "2 days, 4:16:58"}
|
| 180 |
+
{"current_steps": 900, "total_steps": 9128, "loss": 0.3473, "lr": 3.938663745892662e-05, "epoch": 0.6904487917146145, "percentage": 9.86, "elapsed_time": "5:42:40", "remaining_time": "2 days, 4:12:45"}
|
| 181 |
+
{"current_steps": 905, "total_steps": 9128, "loss": 0.3423, "lr": 3.960569550930997e-05, "epoch": 0.6942846183352512, "percentage": 9.91, "elapsed_time": "5:44:24", "remaining_time": "2 days, 4:09:18"}
|
| 182 |
+
{"current_steps": 910, "total_steps": 9128, "loss": 0.3426, "lr": 3.982475355969332e-05, "epoch": 0.698120444955888, "percentage": 9.97, "elapsed_time": "5:46:03", "remaining_time": "2 days, 4:05:13"}
|
| 183 |
+
{"current_steps": 915, "total_steps": 9128, "loss": 0.3394, "lr": 3.999999853753796e-05, "epoch": 0.7019562715765247, "percentage": 10.02, "elapsed_time": "5:47:47", "remaining_time": "2 days, 4:01:47"}
|
| 184 |
+
{"current_steps": 920, "total_steps": 9128, "loss": 0.3505, "lr": 3.999994735138874e-05, "epoch": 0.7057920981971615, "percentage": 10.08, "elapsed_time": "5:49:26", "remaining_time": "2 days, 3:57:36"}
|
| 185 |
+
{"current_steps": 925, "total_steps": 9128, "loss": 0.3478, "lr": 3.999982304235102e-05, "epoch": 0.7096279248177982, "percentage": 10.13, "elapsed_time": "5:51:03", "remaining_time": "2 days, 3:53:13"}
|
| 186 |
+
{"current_steps": 930, "total_steps": 9128, "loss": 0.3436, "lr": 3.9999625610879285e-05, "epoch": 0.713463751438435, "percentage": 10.19, "elapsed_time": "5:52:46", "remaining_time": "2 days, 3:49:46"}
|
| 187 |
+
{"current_steps": 935, "total_steps": 9128, "loss": 0.3405, "lr": 3.999935505769538e-05, "epoch": 0.7172995780590717, "percentage": 10.24, "elapsed_time": "5:54:29", "remaining_time": "2 days, 3:46:17"}
|
| 188 |
+
{"current_steps": 940, "total_steps": 9128, "loss": 0.337, "lr": 3.999901138378847e-05, "epoch": 0.7211354046797085, "percentage": 10.3, "elapsed_time": "5:56:08", "remaining_time": "2 days, 3:42:16"}
|
| 189 |
+
{"current_steps": 945, "total_steps": 9128, "loss": 0.3408, "lr": 3.99985945904151e-05, "epoch": 0.7249712313003452, "percentage": 10.35, "elapsed_time": "5:57:46", "remaining_time": "2 days, 3:38:02"}
|
| 190 |
+
{"current_steps": 950, "total_steps": 9128, "loss": 0.335, "lr": 3.999810467909913e-05, "epoch": 0.728807057920982, "percentage": 10.41, "elapsed_time": "5:59:30", "remaining_time": "2 days, 3:34:50"}
|
| 191 |
+
{"current_steps": 955, "total_steps": 9128, "loss": 0.352, "lr": 3.999754165163174e-05, "epoch": 0.7326428845416187, "percentage": 10.46, "elapsed_time": "6:01:07", "remaining_time": "2 days, 3:30:34"}
|
| 192 |
+
{"current_steps": 960, "total_steps": 9128, "loss": 0.3523, "lr": 3.9996905510071454e-05, "epoch": 0.7364787111622555, "percentage": 10.52, "elapsed_time": "6:02:46", "remaining_time": "2 days, 3:26:38"}
|
| 193 |
+
{"current_steps": 965, "total_steps": 9128, "loss": 0.3393, "lr": 3.99961962567441e-05, "epoch": 0.7403145377828922, "percentage": 10.57, "elapsed_time": "6:04:28", "remaining_time": "2 days, 3:23:03"}
|
| 194 |
+
{"current_steps": 970, "total_steps": 9128, "loss": 0.3412, "lr": 3.999541389424281e-05, "epoch": 0.744150364403529, "percentage": 10.63, "elapsed_time": "6:06:11", "remaining_time": "2 days, 3:19:50"}
|
| 195 |
+
{"current_steps": 975, "total_steps": 9128, "loss": 0.3438, "lr": 3.999455842542805e-05, "epoch": 0.7479861910241657, "percentage": 10.68, "elapsed_time": "6:07:45", "remaining_time": "2 days, 3:15:12"}
|
| 196 |
+
{"current_steps": 980, "total_steps": 9128, "loss": 0.3406, "lr": 3.9993629853427506e-05, "epoch": 0.7518220176448025, "percentage": 10.74, "elapsed_time": "6:09:28", "remaining_time": "2 days, 3:11:58"}
|
| 197 |
+
{"current_steps": 985, "total_steps": 9128, "loss": 0.3199, "lr": 3.9992628181636204e-05, "epoch": 0.7556578442654392, "percentage": 10.79, "elapsed_time": "6:11:10", "remaining_time": "2 days, 3:08:31"}
|
| 198 |
+
{"current_steps": 990, "total_steps": 9128, "loss": 0.3335, "lr": 3.9991553413716414e-05, "epoch": 0.759493670886076, "percentage": 10.85, "elapsed_time": "6:12:46", "remaining_time": "2 days, 3:04:19"}
|
| 199 |
+
{"current_steps": 995, "total_steps": 9128, "loss": 0.3149, "lr": 3.9990405553597644e-05, "epoch": 0.7633294975067128, "percentage": 10.9, "elapsed_time": "6:14:29", "remaining_time": "2 days, 3:01:06"}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 9128, "loss": 0.3559, "lr": 3.998918460547664e-05, "epoch": 0.7671653241273494, "percentage": 10.96, "elapsed_time": "6:16:10", "remaining_time": "2 days, 2:57:31"}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 9128, "loss": 0.3294, "lr": 3.998789057381739e-05, "epoch": 0.7710011507479861, "percentage": 11.01, "elapsed_time": "6:19:16", "remaining_time": "2 days, 3:05:32"}
|