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 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:942a6aabb2739dd624b0afd1e5c4245c5fb5230d51b294bbb363d549cc735b83
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca39d99a0ed094672c67fc987dd39ea57f9de75fac860d351618e7118df60653
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a2f2b93f8ea74be948a732eef86b4aff4d1e812615547d973b02c3c203a00f9
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5dbfe2f75425b62fb6a902946f58cd8151699f92ab0d768fb7835ecb58a449a
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -33,3 +33,39 @@
|
|
| 33 |
{"current_steps": 330, "total_steps": 1035, "loss": 0.7835, "lr": 5e-06, "epoch": 0.9558291093410572, "percentage": 31.88, "elapsed_time": "2:56:44", "remaining_time": "6:17:35"}
|
| 34 |
{"current_steps": 340, "total_steps": 1035, "loss": 0.785, "lr": 5e-06, "epoch": 0.9847936278059377, "percentage": 32.85, "elapsed_time": "3:02:08", "remaining_time": "6:12:18"}
|
| 35 |
{"current_steps": 345, "total_steps": 1035, "eval_loss": 0.7745929956436157, "epoch": 0.999275887038378, "percentage": 33.33, "elapsed_time": "3:09:00", "remaining_time": "6:18:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
{"current_steps": 330, "total_steps": 1035, "loss": 0.7835, "lr": 5e-06, "epoch": 0.9558291093410572, "percentage": 31.88, "elapsed_time": "2:56:44", "remaining_time": "6:17:35"}
|
| 34 |
{"current_steps": 340, "total_steps": 1035, "loss": 0.785, "lr": 5e-06, "epoch": 0.9847936278059377, "percentage": 32.85, "elapsed_time": "3:02:08", "remaining_time": "6:12:18"}
|
| 35 |
{"current_steps": 345, "total_steps": 1035, "eval_loss": 0.7745929956436157, "epoch": 0.999275887038378, "percentage": 33.33, "elapsed_time": "3:09:00", "remaining_time": "6:18:00"}
|
| 36 |
+
{"current_steps": 350, "total_steps": 1035, "loss": 0.8189, "lr": 5e-06, "epoch": 1.0137581462708183, "percentage": 33.82, "elapsed_time": "3:12:45", "remaining_time": "6:17:16"}
|
| 37 |
+
{"current_steps": 360, "total_steps": 1035, "loss": 0.7355, "lr": 5e-06, "epoch": 1.0427226647356989, "percentage": 34.78, "elapsed_time": "3:18:07", "remaining_time": "6:11:29"}
|
| 38 |
+
{"current_steps": 370, "total_steps": 1035, "loss": 0.734, "lr": 5e-06, "epoch": 1.0716871832005792, "percentage": 35.75, "elapsed_time": "3:23:29", "remaining_time": "6:05:43"}
|
| 39 |
+
{"current_steps": 380, "total_steps": 1035, "loss": 0.7328, "lr": 5e-06, "epoch": 1.1006517016654598, "percentage": 36.71, "elapsed_time": "3:28:52", "remaining_time": "6:00:01"}
|
| 40 |
+
{"current_steps": 390, "total_steps": 1035, "loss": 0.732, "lr": 5e-06, "epoch": 1.1296162201303404, "percentage": 37.68, "elapsed_time": "3:34:15", "remaining_time": "5:54:21"}
|
| 41 |
+
{"current_steps": 400, "total_steps": 1035, "loss": 0.7297, "lr": 5e-06, "epoch": 1.158580738595221, "percentage": 38.65, "elapsed_time": "3:39:38", "remaining_time": "5:48:41"}
|
| 42 |
+
{"current_steps": 410, "total_steps": 1035, "loss": 0.7341, "lr": 5e-06, "epoch": 1.1875452570601013, "percentage": 39.61, "elapsed_time": "3:45:02", "remaining_time": "5:43:02"}
|
| 43 |
+
{"current_steps": 420, "total_steps": 1035, "loss": 0.7323, "lr": 5e-06, "epoch": 1.2165097755249819, "percentage": 40.58, "elapsed_time": "3:50:25", "remaining_time": "5:37:24"}
|
| 44 |
+
{"current_steps": 430, "total_steps": 1035, "loss": 0.7306, "lr": 5e-06, "epoch": 1.2454742939898624, "percentage": 41.55, "elapsed_time": "3:55:47", "remaining_time": "5:31:45"}
|
| 45 |
+
{"current_steps": 440, "total_steps": 1035, "loss": 0.7319, "lr": 5e-06, "epoch": 1.274438812454743, "percentage": 42.51, "elapsed_time": "4:01:10", "remaining_time": "5:26:07"}
|
| 46 |
+
{"current_steps": 450, "total_steps": 1035, "loss": 0.7363, "lr": 5e-06, "epoch": 1.3034033309196236, "percentage": 43.48, "elapsed_time": "4:06:32", "remaining_time": "5:20:30"}
|
| 47 |
+
{"current_steps": 460, "total_steps": 1035, "loss": 0.7324, "lr": 5e-06, "epoch": 1.332367849384504, "percentage": 44.44, "elapsed_time": "4:11:54", "remaining_time": "5:14:53"}
|
| 48 |
+
{"current_steps": 470, "total_steps": 1035, "loss": 0.7305, "lr": 5e-06, "epoch": 1.3613323678493845, "percentage": 45.41, "elapsed_time": "4:17:17", "remaining_time": "5:09:17"}
|
| 49 |
+
{"current_steps": 480, "total_steps": 1035, "loss": 0.7335, "lr": 5e-06, "epoch": 1.390296886314265, "percentage": 46.38, "elapsed_time": "4:22:38", "remaining_time": "5:03:40"}
|
| 50 |
+
{"current_steps": 490, "total_steps": 1035, "loss": 0.7331, "lr": 5e-06, "epoch": 1.4192614047791454, "percentage": 47.34, "elapsed_time": "4:28:00", "remaining_time": "4:58:05"}
|
| 51 |
+
{"current_steps": 500, "total_steps": 1035, "loss": 0.7316, "lr": 5e-06, "epoch": 1.448225923244026, "percentage": 48.31, "elapsed_time": "4:33:23", "remaining_time": "4:52:31"}
|
| 52 |
+
{"current_steps": 510, "total_steps": 1035, "loss": 0.7325, "lr": 5e-06, "epoch": 1.4771904417089066, "percentage": 49.28, "elapsed_time": "4:38:45", "remaining_time": "4:46:57"}
|
| 53 |
+
{"current_steps": 520, "total_steps": 1035, "loss": 0.7322, "lr": 5e-06, "epoch": 1.5061549601737871, "percentage": 50.24, "elapsed_time": "4:44:08", "remaining_time": "4:41:24"}
|
| 54 |
+
{"current_steps": 530, "total_steps": 1035, "loss": 0.7267, "lr": 5e-06, "epoch": 1.5351194786386677, "percentage": 51.21, "elapsed_time": "4:49:29", "remaining_time": "4:35:50"}
|
| 55 |
+
{"current_steps": 540, "total_steps": 1035, "loss": 0.7278, "lr": 5e-06, "epoch": 1.5640839971035483, "percentage": 52.17, "elapsed_time": "4:54:48", "remaining_time": "4:30:14"}
|
| 56 |
+
{"current_steps": 550, "total_steps": 1035, "loss": 0.7282, "lr": 5e-06, "epoch": 1.5930485155684286, "percentage": 53.14, "elapsed_time": "5:00:10", "remaining_time": "4:24:42"}
|
| 57 |
+
{"current_steps": 560, "total_steps": 1035, "loss": 0.7322, "lr": 5e-06, "epoch": 1.6220130340333092, "percentage": 54.11, "elapsed_time": "5:05:33", "remaining_time": "4:19:10"}
|
| 58 |
+
{"current_steps": 570, "total_steps": 1035, "loss": 0.7272, "lr": 5e-06, "epoch": 1.6509775524981896, "percentage": 55.07, "elapsed_time": "5:10:55", "remaining_time": "4:13:39"}
|
| 59 |
+
{"current_steps": 580, "total_steps": 1035, "loss": 0.7256, "lr": 5e-06, "epoch": 1.6799420709630701, "percentage": 56.04, "elapsed_time": "5:16:16", "remaining_time": "4:08:07"}
|
| 60 |
+
{"current_steps": 590, "total_steps": 1035, "loss": 0.7222, "lr": 5e-06, "epoch": 1.7089065894279507, "percentage": 57.0, "elapsed_time": "5:21:38", "remaining_time": "4:02:35"}
|
| 61 |
+
{"current_steps": 600, "total_steps": 1035, "loss": 0.7297, "lr": 5e-06, "epoch": 1.7378711078928313, "percentage": 57.97, "elapsed_time": "5:27:00", "remaining_time": "3:57:05"}
|
| 62 |
+
{"current_steps": 610, "total_steps": 1035, "loss": 0.7262, "lr": 5e-06, "epoch": 1.7668356263577119, "percentage": 58.94, "elapsed_time": "5:32:23", "remaining_time": "3:51:35"}
|
| 63 |
+
{"current_steps": 620, "total_steps": 1035, "loss": 0.7303, "lr": 5e-06, "epoch": 1.7958001448225924, "percentage": 59.9, "elapsed_time": "5:37:44", "remaining_time": "3:46:04"}
|
| 64 |
+
{"current_steps": 630, "total_steps": 1035, "loss": 0.7287, "lr": 5e-06, "epoch": 1.824764663287473, "percentage": 60.87, "elapsed_time": "5:43:05", "remaining_time": "3:40:33"}
|
| 65 |
+
{"current_steps": 640, "total_steps": 1035, "loss": 0.7247, "lr": 5e-06, "epoch": 1.8537291817523533, "percentage": 61.84, "elapsed_time": "5:48:25", "remaining_time": "3:35:02"}
|
| 66 |
+
{"current_steps": 650, "total_steps": 1035, "loss": 0.7294, "lr": 5e-06, "epoch": 1.882693700217234, "percentage": 62.8, "elapsed_time": "5:53:46", "remaining_time": "3:29:32"}
|
| 67 |
+
{"current_steps": 660, "total_steps": 1035, "loss": 0.7289, "lr": 5e-06, "epoch": 1.9116582186821143, "percentage": 63.77, "elapsed_time": "5:59:06", "remaining_time": "3:24:02"}
|
| 68 |
+
{"current_steps": 670, "total_steps": 1035, "loss": 0.7296, "lr": 5e-06, "epoch": 1.9406227371469948, "percentage": 64.73, "elapsed_time": "6:04:28", "remaining_time": "3:18:33"}
|
| 69 |
+
{"current_steps": 680, "total_steps": 1035, "loss": 0.7277, "lr": 5e-06, "epoch": 1.9695872556118754, "percentage": 65.7, "elapsed_time": "6:09:51", "remaining_time": "3:13:05"}
|
| 70 |
+
{"current_steps": 690, "total_steps": 1035, "loss": 0.72, "lr": 5e-06, "epoch": 1.998551774076756, "percentage": 66.67, "elapsed_time": "6:15:14", "remaining_time": "3:07:37"}
|
| 71 |
+
{"current_steps": 690, "total_steps": 1035, "eval_loss": 0.7591201663017273, "epoch": 1.998551774076756, "percentage": 66.67, "elapsed_time": "6:19:27", "remaining_time": "3:09:43"}
|