Training in progress, step 400
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 sha256:3579b269fefb144f523a4ecdfc6ba53b0fdc4f633bde6ddded73a2ec9ef0760b
|
| 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:d7f6ae0c00afd6dcf6d11bcb1d63826c2d6c1d484725c34cf15c1c6c28152c9b
|
| 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 sha256:4b84cf5e9e632b246267d665778d3806876fd4aaf39b2fbbaab6f18eb83af55b
|
| 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 sha256:28e3939e4b8011e4ac9e22df28126a8f58ee52a855e4695a9fb8717698160636
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -50,3 +50,34 @@
|
|
| 50 |
{"current_steps": 250, "total_steps": 1652, "loss": 0.2454, "lr": 3.969288312798693e-05, "epoch": 1.059447983014862, "percentage": 15.13, "elapsed_time": "2:38:34", "remaining_time": "14:49:16"}
|
| 51 |
{"current_steps": 255, "total_steps": 1652, "loss": 0.2257, "lr": 3.965487655963647e-05, "epoch": 1.0806794055201698, "percentage": 15.44, "elapsed_time": "2:41:43", "remaining_time": "14:45:58"}
|
| 52 |
{"current_steps": 260, "total_steps": 1652, "loss": 0.2189, "lr": 3.961467380886042e-05, "epoch": 1.1019108280254777, "percentage": 15.74, "elapsed_time": "2:44:51", "remaining_time": "14:42:40"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
{"current_steps": 250, "total_steps": 1652, "loss": 0.2454, "lr": 3.969288312798693e-05, "epoch": 1.059447983014862, "percentage": 15.13, "elapsed_time": "2:38:34", "remaining_time": "14:49:16"}
|
| 51 |
{"current_steps": 255, "total_steps": 1652, "loss": 0.2257, "lr": 3.965487655963647e-05, "epoch": 1.0806794055201698, "percentage": 15.44, "elapsed_time": "2:41:43", "remaining_time": "14:45:58"}
|
| 52 |
{"current_steps": 260, "total_steps": 1652, "loss": 0.2189, "lr": 3.961467380886042e-05, "epoch": 1.1019108280254777, "percentage": 15.74, "elapsed_time": "2:44:51", "remaining_time": "14:42:40"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 1652, "loss": 0.2266, "lr": 3.957227936780476e-05, "epoch": 1.1231422505307855, "percentage": 16.04, "elapsed_time": "2:48:02", "remaining_time": "14:39:30"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 1652, "loss": 0.2161, "lr": 3.952769797350899e-05, "epoch": 1.1443736730360934, "percentage": 16.34, "elapsed_time": "2:51:11", "remaining_time": "14:36:12"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 1652, "loss": 0.1904, "lr": 3.948093460737679e-05, "epoch": 1.1656050955414012, "percentage": 16.65, "elapsed_time": "2:54:20", "remaining_time": "14:32:57"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 1652, "loss": 0.2426, "lr": 3.943199449461944e-05, "epoch": 1.186836518046709, "percentage": 16.95, "elapsed_time": "2:57:28", "remaining_time": "14:29:37"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 1652, "loss": 0.2234, "lr": 3.938088310367199e-05, "epoch": 1.208067940552017, "percentage": 17.25, "elapsed_time": "3:00:35", "remaining_time": "14:26:12"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 1652, "loss": 0.2209, "lr": 3.932760614558218e-05, "epoch": 1.2292993630573248, "percentage": 17.55, "elapsed_time": "3:03:44", "remaining_time": "14:22:57"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 1652, "loss": 0.23, "lr": 3.9272169573372345e-05, "epoch": 1.2505307855626326, "percentage": 17.86, "elapsed_time": "3:06:54", "remaining_time": "14:19:45"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 1652, "loss": 0.2649, "lr": 3.921457958137421e-05, "epoch": 1.2717622080679405, "percentage": 18.16, "elapsed_time": "3:10:02", "remaining_time": "14:16:28"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 1652, "loss": 0.238, "lr": 3.915484260453679e-05, "epoch": 1.2929936305732483, "percentage": 18.46, "elapsed_time": "3:13:11", "remaining_time": "14:13:14"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 1652, "loss": 0.2319, "lr": 3.909296531770732e-05, "epoch": 1.3142250530785562, "percentage": 18.77, "elapsed_time": "3:16:21", "remaining_time": "14:10:00"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 1652, "loss": 0.2209, "lr": 3.902895463488547e-05, "epoch": 1.335456475583864, "percentage": 19.07, "elapsed_time": "3:19:29", "remaining_time": "14:06:42"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 1652, "loss": 0.2109, "lr": 3.896281770845076e-05, "epoch": 1.356687898089172, "percentage": 19.37, "elapsed_time": "3:22:37", "remaining_time": "14:03:25"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 1652, "loss": 0.2003, "lr": 3.8894561928363396e-05, "epoch": 1.3779193205944797, "percentage": 19.67, "elapsed_time": "3:25:46", "remaining_time": "14:00:10"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 1652, "loss": 0.2091, "lr": 3.8824194921338516e-05, "epoch": 1.3991507430997876, "percentage": 19.98, "elapsed_time": "3:28:54", "remaining_time": "13:56:54"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 1652, "loss": 0.2081, "lr": 3.875172454999402e-05, "epoch": 1.4203821656050954, "percentage": 20.28, "elapsed_time": "3:32:03", "remaining_time": "13:53:38"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 1652, "loss": 0.2073, "lr": 3.8677158911972e-05, "epoch": 1.4416135881104033, "percentage": 20.58, "elapsed_time": "3:35:12", "remaining_time": "13:50:26"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 1652, "loss": 0.2098, "lr": 3.860050633903395e-05, "epoch": 1.4628450106157111, "percentage": 20.88, "elapsed_time": "3:38:21", "remaining_time": "13:47:13"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 1652, "loss": 0.2233, "lr": 3.8521775396129824e-05, "epoch": 1.484076433121019, "percentage": 21.19, "elapsed_time": "3:41:30", "remaining_time": "13:43:59"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 1652, "loss": 0.2165, "lr": 3.8440974880440925e-05, "epoch": 1.5053078556263269, "percentage": 21.49, "elapsed_time": "3:44:39", "remaining_time": "13:40:47"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 1652, "loss": 0.2098, "lr": 3.835811382039703e-05, "epoch": 1.5265392781316347, "percentage": 21.79, "elapsed_time": "3:47:48", "remaining_time": "13:37:34"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 1652, "loss": 0.2201, "lr": 3.827320147466752e-05, "epoch": 1.5477707006369426, "percentage": 22.09, "elapsed_time": "3:50:57", "remaining_time": "13:34:21"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 1652, "loss": 0.2437, "lr": 3.818624733112687e-05, "epoch": 1.5690021231422504, "percentage": 22.4, "elapsed_time": "3:54:05", "remaining_time": "13:31:05"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 1652, "loss": 0.1932, "lr": 3.809726110579446e-05, "epoch": 1.5902335456475583, "percentage": 22.7, "elapsed_time": "3:57:14", "remaining_time": "13:27:52"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 1652, "loss": 0.227, "lr": 3.8006252741748986e-05, "epoch": 1.611464968152866, "percentage": 23.0, "elapsed_time": "4:00:22", "remaining_time": "13:24:36"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 1652, "loss": 0.2166, "lr": 3.79132324080174e-05, "epoch": 1.632696390658174, "percentage": 23.31, "elapsed_time": "4:03:30", "remaining_time": "13:21:22"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 1652, "loss": 0.1943, "lr": 3.781821049843869e-05, "epoch": 1.6539278131634818, "percentage": 23.61, "elapsed_time": "4:06:39", "remaining_time": "13:18:10"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 1652, "loss": 0.2147, "lr": 3.7721197630502485e-05, "epoch": 1.6751592356687897, "percentage": 23.91, "elapsed_time": "4:09:48", "remaining_time": "13:14:58"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 1652, "loss": 0.2095, "lr": 3.762220464416266e-05, "epoch": 1.6963906581740975, "percentage": 24.21, "elapsed_time": "4:12:58", "remaining_time": "13:11:47"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 1652, "loss": 0.1993, "lr": 3.7521242600626154e-05, "epoch": 1.7176220806794054, "percentage": 24.52, "elapsed_time": "4:17:20", "remaining_time": "13:12:20"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 1652, "loss": 0.2471, "lr": 3.7418322781117e-05, "epoch": 1.7388535031847132, "percentage": 24.82, "elapsed_time": "4:20:28", "remaining_time": "13:09:03"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 1652, "loss": 0.2065, "lr": 3.731345668561577e-05, "epoch": 1.7600849256900213, "percentage": 25.12, "elapsed_time": "4:23:38", "remaining_time": "13:05:49"}
|