Training in progress, step 4600
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 sha256:50626df635c3e1fe3291c719407a0d9f6dc371ebba916600955c7f45e4592184
|
| 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:f0c31306f1265ec6a6c0a10975c97322369700be1c4fbcdabb09ce135728d5d0
|
| 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 sha256:05d82091689e4e7ad4ea040fc7d2ed7a4b709e33edb0de679066649c1fb4ac43
|
| 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:f0d27e07ead2a81f1f2c589f232ea5a776d9e9e97665e8e148f85e228ddd5f8c
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -901,3 +901,43 @@
|
|
| 901 |
{"current_steps": 4390, "total_steps": 6713, "loss": 0.2102, "lr": 1.2913139082569434e-05, "epoch": 4.579029733959311, "percentage": 65.4, "elapsed_time": "10:54:56", "remaining_time": "5:46:34"}
|
| 902 |
{"current_steps": 4395, "total_steps": 6713, "loss": 0.209, "lr": 1.2864532868358799e-05, "epoch": 4.584246218049035, "percentage": 65.47, "elapsed_time": "10:56:41", "remaining_time": "5:46:20"}
|
| 903 |
{"current_steps": 4400, "total_steps": 6713, "loss": 0.2151, "lr": 1.2815974898252482e-05, "epoch": 4.589462702138759, "percentage": 65.54, "elapsed_time": "10:58:22", "remaining_time": "5:46:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 901 |
{"current_steps": 4390, "total_steps": 6713, "loss": 0.2102, "lr": 1.2913139082569434e-05, "epoch": 4.579029733959311, "percentage": 65.4, "elapsed_time": "10:54:56", "remaining_time": "5:46:34"}
|
| 902 |
{"current_steps": 4395, "total_steps": 6713, "loss": 0.209, "lr": 1.2864532868358799e-05, "epoch": 4.584246218049035, "percentage": 65.47, "elapsed_time": "10:56:41", "remaining_time": "5:46:20"}
|
| 903 |
{"current_steps": 4400, "total_steps": 6713, "loss": 0.2151, "lr": 1.2815974898252482e-05, "epoch": 4.589462702138759, "percentage": 65.54, "elapsed_time": "10:58:22", "remaining_time": "5:46:05"}
|
| 904 |
+
{"current_steps": 4405, "total_steps": 6713, "loss": 0.2081, "lr": 1.2767465500559162e-05, "epoch": 4.594679186228482, "percentage": 65.62, "elapsed_time": "11:01:30", "remaining_time": "5:46:35"}
|
| 905 |
+
{"current_steps": 4410, "total_steps": 6713, "loss": 0.2161, "lr": 1.271900500325911e-05, "epoch": 4.5998956703182055, "percentage": 65.69, "elapsed_time": "11:03:10", "remaining_time": "5:46:19"}
|
| 906 |
+
{"current_steps": 4415, "total_steps": 6713, "loss": 0.2121, "lr": 1.2670593734001972e-05, "epoch": 4.605112154407929, "percentage": 65.77, "elapsed_time": "11:04:48", "remaining_time": "5:46:02"}
|
| 907 |
+
{"current_steps": 4420, "total_steps": 6713, "loss": 0.2145, "lr": 1.2622232020104568e-05, "epoch": 4.610328638497653, "percentage": 65.84, "elapsed_time": "11:06:34", "remaining_time": "5:45:48"}
|
| 908 |
+
{"current_steps": 4425, "total_steps": 6713, "loss": 0.2111, "lr": 1.2573920188548634e-05, "epoch": 4.615545122587376, "percentage": 65.92, "elapsed_time": "11:08:19", "remaining_time": "5:45:33"}
|
| 909 |
+
{"current_steps": 4430, "total_steps": 6713, "loss": 0.2086, "lr": 1.2525658565978668e-05, "epoch": 4.6207616066771, "percentage": 65.99, "elapsed_time": "11:09:59", "remaining_time": "5:45:16"}
|
| 910 |
+
{"current_steps": 4435, "total_steps": 6713, "loss": 0.209, "lr": 1.2477447478699696e-05, "epoch": 4.625978090766823, "percentage": 66.07, "elapsed_time": "11:11:35", "remaining_time": "5:44:57"}
|
| 911 |
+
{"current_steps": 4440, "total_steps": 6713, "loss": 0.2117, "lr": 1.2429287252675062e-05, "epoch": 4.631194574856547, "percentage": 66.14, "elapsed_time": "11:13:20", "remaining_time": "5:44:42"}
|
| 912 |
+
{"current_steps": 4445, "total_steps": 6713, "loss": 0.2136, "lr": 1.2381178213524223e-05, "epoch": 4.63641105894627, "percentage": 66.21, "elapsed_time": "11:14:59", "remaining_time": "5:44:24"}
|
| 913 |
+
{"current_steps": 4450, "total_steps": 6713, "loss": 0.2134, "lr": 1.2333120686520568e-05, "epoch": 4.641627543035994, "percentage": 66.29, "elapsed_time": "11:16:39", "remaining_time": "5:44:06"}
|
| 914 |
+
{"current_steps": 4455, "total_steps": 6713, "loss": 0.209, "lr": 1.2285114996589181e-05, "epoch": 4.646844027125717, "percentage": 66.36, "elapsed_time": "11:18:20", "remaining_time": "5:43:49"}
|
| 915 |
+
{"current_steps": 4460, "total_steps": 6713, "loss": 0.2131, "lr": 1.2237161468304681e-05, "epoch": 4.652060511215441, "percentage": 66.44, "elapsed_time": "11:20:07", "remaining_time": "5:43:33"}
|
| 916 |
+
{"current_steps": 4465, "total_steps": 6713, "loss": 0.2118, "lr": 1.218926042588902e-05, "epoch": 4.657276995305164, "percentage": 66.51, "elapsed_time": "11:21:42", "remaining_time": "5:43:13"}
|
| 917 |
+
{"current_steps": 4470, "total_steps": 6713, "loss": 0.2095, "lr": 1.2141412193209274e-05, "epoch": 4.662493479394888, "percentage": 66.59, "elapsed_time": "11:23:25", "remaining_time": "5:42:56"}
|
| 918 |
+
{"current_steps": 4475, "total_steps": 6713, "loss": 0.1992, "lr": 1.2093617093775458e-05, "epoch": 4.6677099634846115, "percentage": 66.66, "elapsed_time": "11:25:08", "remaining_time": "5:42:38"}
|
| 919 |
+
{"current_steps": 4480, "total_steps": 6713, "loss": 0.2089, "lr": 1.2045875450738352e-05, "epoch": 4.672926447574335, "percentage": 66.74, "elapsed_time": "11:26:44", "remaining_time": "5:42:17"}
|
| 920 |
+
{"current_steps": 4485, "total_steps": 6713, "loss": 0.1894, "lr": 1.199818758688731e-05, "epoch": 4.678142931664058, "percentage": 66.81, "elapsed_time": "11:28:27", "remaining_time": "5:42:00"}
|
| 921 |
+
{"current_steps": 4490, "total_steps": 6713, "loss": 0.2235, "lr": 1.1950553824648077e-05, "epoch": 4.683359415753782, "percentage": 66.89, "elapsed_time": "11:30:06", "remaining_time": "5:41:40"}
|
| 922 |
+
{"current_steps": 4495, "total_steps": 6713, "loss": 0.2086, "lr": 1.1902974486080599e-05, "epoch": 4.688575899843506, "percentage": 66.96, "elapsed_time": "11:31:57", "remaining_time": "5:41:26"}
|
| 923 |
+
{"current_steps": 4500, "total_steps": 6713, "loss": 0.2108, "lr": 1.1855449892876858e-05, "epoch": 4.6937923839332285, "percentage": 67.03, "elapsed_time": "11:33:40", "remaining_time": "5:41:08"}
|
| 924 |
+
{"current_steps": 4505, "total_steps": 6713, "loss": 0.2147, "lr": 1.1807980366358699e-05, "epoch": 4.699008868022952, "percentage": 67.11, "elapsed_time": "11:35:24", "remaining_time": "5:40:50"}
|
| 925 |
+
{"current_steps": 4510, "total_steps": 6713, "loss": 0.2137, "lr": 1.1760566227475642e-05, "epoch": 4.704225352112676, "percentage": 67.18, "elapsed_time": "11:37:07", "remaining_time": "5:40:31"}
|
| 926 |
+
{"current_steps": 4515, "total_steps": 6713, "loss": 0.2104, "lr": 1.1713207796802739e-05, "epoch": 4.7094418362024, "percentage": 67.26, "elapsed_time": "11:38:50", "remaining_time": "5:40:12"}
|
| 927 |
+
{"current_steps": 4520, "total_steps": 6713, "loss": 0.2017, "lr": 1.166590539453837e-05, "epoch": 4.7146583202921235, "percentage": 67.33, "elapsed_time": "11:40:32", "remaining_time": "5:39:52"}
|
| 928 |
+
{"current_steps": 4525, "total_steps": 6713, "loss": 0.2008, "lr": 1.1618659340502104e-05, "epoch": 4.719874804381846, "percentage": 67.41, "elapsed_time": "11:42:07", "remaining_time": "5:39:30"}
|
| 929 |
+
{"current_steps": 4530, "total_steps": 6713, "loss": 0.1985, "lr": 1.157146995413252e-05, "epoch": 4.72509128847157, "percentage": 67.48, "elapsed_time": "11:43:47", "remaining_time": "5:39:09"}
|
| 930 |
+
{"current_steps": 4535, "total_steps": 6713, "loss": 0.196, "lr": 1.152433755448509e-05, "epoch": 4.730307772561294, "percentage": 67.56, "elapsed_time": "11:45:29", "remaining_time": "5:38:49"}
|
| 931 |
+
{"current_steps": 4540, "total_steps": 6713, "loss": 0.1914, "lr": 1.1477262460229945e-05, "epoch": 4.735524256651017, "percentage": 67.63, "elapsed_time": "11:47:10", "remaining_time": "5:38:28"}
|
| 932 |
+
{"current_steps": 4545, "total_steps": 6713, "loss": 0.1895, "lr": 1.143024498964981e-05, "epoch": 4.7407407407407405, "percentage": 67.7, "elapsed_time": "11:48:47", "remaining_time": "5:38:05"}
|
| 933 |
+
{"current_steps": 4550, "total_steps": 6713, "loss": 0.2056, "lr": 1.1383285460637766e-05, "epoch": 4.745957224830464, "percentage": 67.78, "elapsed_time": "11:50:26", "remaining_time": "5:37:43"}
|
| 934 |
+
{"current_steps": 4555, "total_steps": 6713, "loss": 0.2222, "lr": 1.1336384190695172e-05, "epoch": 4.751173708920188, "percentage": 67.85, "elapsed_time": "11:52:07", "remaining_time": "5:37:22"}
|
| 935 |
+
{"current_steps": 4560, "total_steps": 6713, "loss": 0.1971, "lr": 1.1289541496929466e-05, "epoch": 4.756390193009912, "percentage": 67.93, "elapsed_time": "11:53:45", "remaining_time": "5:37:00"}
|
| 936 |
+
{"current_steps": 4565, "total_steps": 6713, "loss": 0.2162, "lr": 1.1242757696052044e-05, "epoch": 4.761606677099635, "percentage": 68.0, "elapsed_time": "11:55:25", "remaining_time": "5:36:37"}
|
| 937 |
+
{"current_steps": 4570, "total_steps": 6713, "loss": 0.2005, "lr": 1.1196033104376141e-05, "epoch": 4.766823161189358, "percentage": 68.08, "elapsed_time": "11:57:07", "remaining_time": "5:36:16"}
|
| 938 |
+
{"current_steps": 4575, "total_steps": 6713, "loss": 0.207, "lr": 1.1149368037814644e-05, "epoch": 4.772039645279082, "percentage": 68.15, "elapsed_time": "11:58:51", "remaining_time": "5:35:56"}
|
| 939 |
+
{"current_steps": 4580, "total_steps": 6713, "loss": 0.2005, "lr": 1.1102762811877974e-05, "epoch": 4.777256129368805, "percentage": 68.23, "elapsed_time": "12:00:37", "remaining_time": "5:35:36"}
|
| 940 |
+
{"current_steps": 4585, "total_steps": 6713, "loss": 0.195, "lr": 1.1056217741672e-05, "epoch": 4.782472613458529, "percentage": 68.3, "elapsed_time": "12:02:23", "remaining_time": "5:35:16"}
|
| 941 |
+
{"current_steps": 4590, "total_steps": 6713, "loss": 0.2089, "lr": 1.1009733141895823e-05, "epoch": 4.7876890975482524, "percentage": 68.37, "elapsed_time": "12:03:58", "remaining_time": "5:34:51"}
|
| 942 |
+
{"current_steps": 4595, "total_steps": 6713, "loss": 0.199, "lr": 1.0963309326839708e-05, "epoch": 4.792905581637976, "percentage": 68.45, "elapsed_time": "12:05:40", "remaining_time": "5:34:29"}
|
| 943 |
+
{"current_steps": 4600, "total_steps": 6713, "loss": 0.2058, "lr": 1.0916946610382966e-05, "epoch": 4.7981220657277, "percentage": 68.52, "elapsed_time": "12:07:19", "remaining_time": "5:34:05"}
|