Training in progress, epoch 2
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 sha256:461a934e522eaac55eef6cde09970886a89b5298d76a46600ad1e15ec5df90ec
|
| 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 sha256:4f485dcb0c5459882a49acf66e03bc7edc65bc0b0a5c8341c33bbf27d0f2cc59
|
| 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 sha256:922635d7a3d66e59423af285b9fd172a2cd0de35b8448de20f25e7bc894e0261
|
| 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:e6b9489bd53513e7a3676c66e3c6b29acc738e7ecdf9ecff10fa8b03fb20518a
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -26,3 +26,32 @@
|
|
| 26 |
{"current_steps": 260, "total_steps": 822, "loss": 0.7471, "lr": 5e-06, "epoch": 0.948905109489051, "percentage": 31.63, "elapsed_time": "2:19:49", "remaining_time": "5:02:13"}
|
| 27 |
{"current_steps": 270, "total_steps": 822, "loss": 0.7448, "lr": 5e-06, "epoch": 0.9854014598540146, "percentage": 32.85, "elapsed_time": "2:25:11", "remaining_time": "4:56:49"}
|
| 28 |
{"current_steps": 274, "total_steps": 822, "eval_loss": 0.7464940547943115, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "2:30:33", "remaining_time": "5:01:06"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
{"current_steps": 260, "total_steps": 822, "loss": 0.7471, "lr": 5e-06, "epoch": 0.948905109489051, "percentage": 31.63, "elapsed_time": "2:19:49", "remaining_time": "5:02:13"}
|
| 27 |
{"current_steps": 270, "total_steps": 822, "loss": 0.7448, "lr": 5e-06, "epoch": 0.9854014598540146, "percentage": 32.85, "elapsed_time": "2:25:11", "remaining_time": "4:56:49"}
|
| 28 |
{"current_steps": 274, "total_steps": 822, "eval_loss": 0.7464940547943115, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "2:30:33", "remaining_time": "5:01:06"}
|
| 29 |
+
{"current_steps": 280, "total_steps": 822, "loss": 0.7201, "lr": 5e-06, "epoch": 1.0218978102189782, "percentage": 34.06, "elapsed_time": "2:34:56", "remaining_time": "4:59:54"}
|
| 30 |
+
{"current_steps": 290, "total_steps": 822, "loss": 0.6987, "lr": 5e-06, "epoch": 1.0583941605839415, "percentage": 35.28, "elapsed_time": "2:40:18", "remaining_time": "4:54:04"}
|
| 31 |
+
{"current_steps": 300, "total_steps": 822, "loss": 0.695, "lr": 5e-06, "epoch": 1.094890510948905, "percentage": 36.5, "elapsed_time": "2:45:39", "remaining_time": "4:48:14"}
|
| 32 |
+
{"current_steps": 310, "total_steps": 822, "loss": 0.6922, "lr": 5e-06, "epoch": 1.1313868613138687, "percentage": 37.71, "elapsed_time": "2:51:01", "remaining_time": "4:42:28"}
|
| 33 |
+
{"current_steps": 320, "total_steps": 822, "loss": 0.7005, "lr": 5e-06, "epoch": 1.167883211678832, "percentage": 38.93, "elapsed_time": "2:56:23", "remaining_time": "4:36:43"}
|
| 34 |
+
{"current_steps": 330, "total_steps": 822, "loss": 0.696, "lr": 5e-06, "epoch": 1.2043795620437956, "percentage": 40.15, "elapsed_time": "3:01:46", "remaining_time": "4:31:00"}
|
| 35 |
+
{"current_steps": 340, "total_steps": 822, "loss": 0.6961, "lr": 5e-06, "epoch": 1.2408759124087592, "percentage": 41.36, "elapsed_time": "3:07:10", "remaining_time": "4:25:20"}
|
| 36 |
+
{"current_steps": 350, "total_steps": 822, "loss": 0.6955, "lr": 5e-06, "epoch": 1.2773722627737225, "percentage": 42.58, "elapsed_time": "3:12:32", "remaining_time": "4:19:38"}
|
| 37 |
+
{"current_steps": 360, "total_steps": 822, "loss": 0.6967, "lr": 5e-06, "epoch": 1.313868613138686, "percentage": 43.8, "elapsed_time": "3:17:53", "remaining_time": "4:13:57"}
|
| 38 |
+
{"current_steps": 370, "total_steps": 822, "loss": 0.702, "lr": 5e-06, "epoch": 1.3503649635036497, "percentage": 45.01, "elapsed_time": "3:23:15", "remaining_time": "4:08:18"}
|
| 39 |
+
{"current_steps": 380, "total_steps": 822, "loss": 0.7, "lr": 5e-06, "epoch": 1.3868613138686132, "percentage": 46.23, "elapsed_time": "3:28:36", "remaining_time": "4:02:38"}
|
| 40 |
+
{"current_steps": 390, "total_steps": 822, "loss": 0.6935, "lr": 5e-06, "epoch": 1.4233576642335766, "percentage": 47.45, "elapsed_time": "3:33:57", "remaining_time": "3:56:59"}
|
| 41 |
+
{"current_steps": 400, "total_steps": 822, "loss": 0.6925, "lr": 5e-06, "epoch": 1.4598540145985401, "percentage": 48.66, "elapsed_time": "3:39:17", "remaining_time": "3:51:21"}
|
| 42 |
+
{"current_steps": 410, "total_steps": 822, "loss": 0.6987, "lr": 5e-06, "epoch": 1.4963503649635037, "percentage": 49.88, "elapsed_time": "3:44:40", "remaining_time": "3:45:46"}
|
| 43 |
+
{"current_steps": 420, "total_steps": 822, "loss": 0.6975, "lr": 5e-06, "epoch": 1.5328467153284673, "percentage": 51.09, "elapsed_time": "3:50:04", "remaining_time": "3:40:12"}
|
| 44 |
+
{"current_steps": 430, "total_steps": 822, "loss": 0.6955, "lr": 5e-06, "epoch": 1.5693430656934306, "percentage": 52.31, "elapsed_time": "3:55:26", "remaining_time": "3:34:38"}
|
| 45 |
+
{"current_steps": 440, "total_steps": 822, "loss": 0.6947, "lr": 5e-06, "epoch": 1.6058394160583942, "percentage": 53.53, "elapsed_time": "4:00:46", "remaining_time": "3:29:02"}
|
| 46 |
+
{"current_steps": 450, "total_steps": 822, "loss": 0.6979, "lr": 5e-06, "epoch": 1.6423357664233578, "percentage": 54.74, "elapsed_time": "4:06:07", "remaining_time": "3:23:27"}
|
| 47 |
+
{"current_steps": 460, "total_steps": 822, "loss": 0.6887, "lr": 5e-06, "epoch": 1.6788321167883211, "percentage": 55.96, "elapsed_time": "4:11:29", "remaining_time": "3:17:54"}
|
| 48 |
+
{"current_steps": 470, "total_steps": 822, "loss": 0.6925, "lr": 5e-06, "epoch": 1.7153284671532847, "percentage": 57.18, "elapsed_time": "4:16:48", "remaining_time": "3:12:20"}
|
| 49 |
+
{"current_steps": 480, "total_steps": 822, "loss": 0.6939, "lr": 5e-06, "epoch": 1.7518248175182483, "percentage": 58.39, "elapsed_time": "4:22:11", "remaining_time": "3:06:48"}
|
| 50 |
+
{"current_steps": 490, "total_steps": 822, "loss": 0.6968, "lr": 5e-06, "epoch": 1.7883211678832116, "percentage": 59.61, "elapsed_time": "4:27:34", "remaining_time": "3:01:17"}
|
| 51 |
+
{"current_steps": 500, "total_steps": 822, "loss": 0.6903, "lr": 5e-06, "epoch": 1.8248175182481752, "percentage": 60.83, "elapsed_time": "4:32:57", "remaining_time": "2:55:47"}
|
| 52 |
+
{"current_steps": 510, "total_steps": 822, "loss": 0.6919, "lr": 5e-06, "epoch": 1.8613138686131387, "percentage": 62.04, "elapsed_time": "4:38:19", "remaining_time": "2:50:16"}
|
| 53 |
+
{"current_steps": 520, "total_steps": 822, "loss": 0.6917, "lr": 5e-06, "epoch": 1.897810218978102, "percentage": 63.26, "elapsed_time": "4:43:40", "remaining_time": "2:44:44"}
|
| 54 |
+
{"current_steps": 530, "total_steps": 822, "loss": 0.6947, "lr": 5e-06, "epoch": 1.9343065693430657, "percentage": 64.48, "elapsed_time": "4:49:00", "remaining_time": "2:39:13"}
|
| 55 |
+
{"current_steps": 540, "total_steps": 822, "loss": 0.6909, "lr": 5e-06, "epoch": 1.9708029197080292, "percentage": 65.69, "elapsed_time": "4:54:22", "remaining_time": "2:33:43"}
|
| 56 |
+
{"current_steps": 548, "total_steps": 822, "eval_loss": 0.7327279448509216, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "5:01:42", "remaining_time": "2:30:51"}
|
| 57 |
+
{"current_steps": 550, "total_steps": 822, "loss": 0.6891, "lr": 5e-06, "epoch": 2.0072992700729926, "percentage": 66.91, "elapsed_time": "5:04:02", "remaining_time": "2:30:21"}
|