Training in progress, step 60
Browse files- model-00001-of-00014.safetensors +1 -1
- model-00002-of-00014.safetensors +1 -1
- model-00003-of-00014.safetensors +1 -1
- model-00004-of-00014.safetensors +1 -1
- model-00005-of-00014.safetensors +1 -1
- model-00006-of-00014.safetensors +1 -1
- model-00007-of-00014.safetensors +1 -1
- model-00008-of-00014.safetensors +1 -1
- model-00009-of-00014.safetensors +1 -1
- model-00010-of-00014.safetensors +1 -1
- model-00011-of-00014.safetensors +1 -1
- model-00012-of-00014.safetensors +1 -1
- model-00013-of-00014.safetensors +1 -1
- model-00014-of-00014.safetensors +1 -1
- trainer_log.jsonl +40 -0
- training_args.bin +2 -2
model-00001-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932307584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06ff4d93753e553299d412f2cd771c9cb7ff01cfeb77b6ed2f0224717c1134e1
|
| 3 |
size 4932307584
|
model-00002-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b12e63b0cc06134a203f4aabc7d4587bae2e4a5f7c883ed270909c46ba006b86
|
| 3 |
size 4875989696
|
model-00003-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84b93b9ed3ad4b21da59385190684f3ecc8354b131b81e08367888eb45e7cef6
|
| 3 |
size 4875989720
|
model-00004-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:629ac9111591fcdc10d371fb375c6bc64651d834429098c6676326e225d481c8
|
| 3 |
size 4875989752
|
model-00005-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec3519cd941d2f6dc61c3b7fa602aaed9c211d4eb808fce8eab4f2f894f96f4e
|
| 3 |
size 4875989752
|
model-00006-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6e2d308b8b393de2ced610fede5d14149d0733f49e80aa1c0a4ea4fd19e5ba1
|
| 3 |
size 4875989752
|
model-00007-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e28be0a09aa768a680e074e529e8201b10f7a0192c911ce437458b0433bb7c3
|
| 3 |
size 4875989752
|
model-00008-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73d34349b87f5ff07bbcf4bd3c4cdcaa9951754381bc28fb142bded66d898f88
|
| 3 |
size 4875989752
|
model-00009-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:129e62af52ad83e41f425d638b57e62822c1eb315d5561b586a1bc0da2509164
|
| 3 |
size 4875989752
|
model-00010-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed56b7d068255f4e740257ca49e814fa2f168cd9ad52a195a802268b05815444
|
| 3 |
size 4875989752
|
model-00011-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05a4407f7c91457019ba317fa0918d30e4035106a835f8498c0690c9bb40a7d7
|
| 3 |
size 4875989752
|
model-00012-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67899789b0e0d2b69934c80395626a1945bbd541c790ade7ae2957af81826ceb
|
| 3 |
size 4875989752
|
model-00013-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4875989752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f6e1f2b80eb5675b06d9c942647ae9e9589377e62547d15c73b3e41ff6d900d
|
| 3 |
size 4875989752
|
model-00014-of-00014.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2080144040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88bffb2918ec67df05ef9184d95f68817e45ddfc2dee0fe0e18e8b3c8a4104b5
|
| 3 |
size 2080144040
|
trainer_log.jsonl
CHANGED
|
@@ -46,3 +46,43 @@
|
|
| 46 |
{"current_steps": 39, "total_steps": 200, "loss": 0.9064, "lr": 2.9265847744427307e-06, "epoch": 1.9620253164556962, "percentage": 19.5, "elapsed_time": "7:55:05", "remaining_time": "1 day, 8:41:16"}
|
| 47 |
{"current_steps": 40, "total_steps": 200, "loss": 0.9201, "lr": 2.9182778633989753e-06, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "8:00:58", "remaining_time": "1 day, 8:03:53"}
|
| 48 |
{"current_steps": 40, "total_steps": 200, "eval_loss": 0.8951823115348816, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "8:05:34", "remaining_time": "1 day, 8:22:19"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
{"current_steps": 39, "total_steps": 200, "loss": 0.9064, "lr": 2.9265847744427307e-06, "epoch": 1.9620253164556962, "percentage": 19.5, "elapsed_time": "7:55:05", "remaining_time": "1 day, 8:41:16"}
|
| 47 |
{"current_steps": 40, "total_steps": 200, "loss": 0.9201, "lr": 2.9182778633989753e-06, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "8:00:58", "remaining_time": "1 day, 8:03:53"}
|
| 48 |
{"current_steps": 40, "total_steps": 200, "eval_loss": 0.8951823115348816, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "8:05:34", "remaining_time": "1 day, 8:22:19"}
|
| 49 |
+
{"current_steps": 41, "total_steps": 200, "loss": 0.9089, "lr": 2.9095389311788626e-06, "epoch": 2.050632911392405, "percentage": 20.5, "elapsed_time": "8:20:53", "remaining_time": "1 day, 8:22:30"}
|
| 50 |
+
{"current_steps": 42, "total_steps": 200, "loss": 0.9055, "lr": 2.9003706397458025e-06, "epoch": 2.1012658227848102, "percentage": 21.0, "elapsed_time": "8:32:27", "remaining_time": "1 day, 8:07:48"}
|
| 51 |
+
{"current_steps": 43, "total_steps": 200, "loss": 0.8989, "lr": 2.8907757818501814e-06, "epoch": 2.151898734177215, "percentage": 21.5, "elapsed_time": "8:42:39", "remaining_time": "1 day, 7:48:19"}
|
| 52 |
+
{"current_steps": 44, "total_steps": 200, "loss": 0.883, "lr": 2.880757280178661e-06, "epoch": 2.2025316455696204, "percentage": 22.0, "elapsed_time": "8:53:01", "remaining_time": "1 day, 7:29:47"}
|
| 53 |
+
{"current_steps": 45, "total_steps": 200, "loss": 0.9056, "lr": 2.8703181864639013e-06, "epoch": 2.2531645569620253, "percentage": 22.5, "elapsed_time": "9:03:55", "remaining_time": "1 day, 7:13:32"}
|
| 54 |
+
{"current_steps": 45, "total_steps": 200, "eval_loss": 0.8814523816108704, "epoch": 2.2531645569620253, "percentage": 22.5, "elapsed_time": "9:08:31", "remaining_time": "1 day, 7:29:20"}
|
| 55 |
+
{"current_steps": 46, "total_steps": 200, "loss": 0.8958, "lr": 2.859461680554975e-06, "epoch": 2.3037974683544302, "percentage": 23.0, "elapsed_time": "9:18:42", "remaining_time": "1 day, 7:10:26"}
|
| 56 |
+
{"current_steps": 47, "total_steps": 200, "loss": 0.8847, "lr": 2.8481910694487506e-06, "epoch": 2.3544303797468356, "percentage": 23.5, "elapsed_time": "9:29:18", "remaining_time": "1 day, 6:53:16"}
|
| 57 |
+
{"current_steps": 48, "total_steps": 200, "loss": 0.8917, "lr": 2.8365097862825516e-06, "epoch": 2.4050632911392404, "percentage": 24.0, "elapsed_time": "9:35:36", "remaining_time": "1 day, 6:22:44"}
|
| 58 |
+
{"current_steps": 49, "total_steps": 200, "loss": 0.868, "lr": 2.8244213892883906e-06, "epoch": 2.4556962025316453, "percentage": 24.5, "elapsed_time": "9:47:54", "remaining_time": "1 day, 6:11:41"}
|
| 59 |
+
{"current_steps": 50, "total_steps": 200, "loss": 0.8865, "lr": 2.811929560709094e-06, "epoch": 2.5063291139240507, "percentage": 25.0, "elapsed_time": "9:59:55", "remaining_time": "1 day, 5:59:46"}
|
| 60 |
+
{"current_steps": 50, "total_steps": 200, "eval_loss": 0.8708593249320984, "epoch": 2.5063291139240507, "percentage": 25.0, "elapsed_time": "10:04:30", "remaining_time": "1 day, 6:13:32"}
|
| 61 |
+
{"current_steps": 51, "total_steps": 200, "loss": 0.8842, "lr": 2.7990381056766585e-06, "epoch": 2.5569620253164556, "percentage": 25.5, "elapsed_time": "10:12:19", "remaining_time": "1 day, 5:48:57"}
|
| 62 |
+
{"current_steps": 52, "total_steps": 200, "loss": 0.8991, "lr": 2.7857509510531684e-06, "epoch": 2.607594936708861, "percentage": 26.0, "elapsed_time": "10:20:00", "remaining_time": "1 day, 5:24:38"}
|
| 63 |
+
{"current_steps": 53, "total_steps": 200, "loss": 0.8594, "lr": 2.772072144234639e-06, "epoch": 2.6582278481012658, "percentage": 26.5, "elapsed_time": "10:30:50", "remaining_time": "1 day, 5:09:41"}
|
| 64 |
+
{"current_steps": 54, "total_steps": 200, "loss": 0.8863, "lr": 2.758005851918136e-06, "epoch": 2.708860759493671, "percentage": 27.0, "elapsed_time": "10:44:05", "remaining_time": "1 day, 5:01:25"}
|
| 65 |
+
{"current_steps": 41, "total_steps": 200, "loss": 0.9089, "lr": 2.9095389311788626e-06, "epoch": 2.050632911392405, "percentage": 20.5, "elapsed_time": "0:10:40", "remaining_time": "0:41:24"}
|
| 66 |
+
{"current_steps": 42, "total_steps": 200, "loss": 0.9054, "lr": 2.9003706397458025e-06, "epoch": 2.1012658227848102, "percentage": 21.0, "elapsed_time": "0:22:12", "remaining_time": "1:23:31"}
|
| 67 |
+
{"current_steps": 43, "total_steps": 200, "loss": 0.8988, "lr": 2.8907757818501814e-06, "epoch": 2.151898734177215, "percentage": 21.5, "elapsed_time": "0:32:21", "remaining_time": "1:58:10"}
|
| 68 |
+
{"current_steps": 44, "total_steps": 200, "loss": 0.883, "lr": 2.880757280178661e-06, "epoch": 2.2025316455696204, "percentage": 22.0, "elapsed_time": "0:42:46", "remaining_time": "2:31:39"}
|
| 69 |
+
{"current_steps": 45, "total_steps": 200, "loss": 0.9055, "lr": 2.8703181864639013e-06, "epoch": 2.2531645569620253, "percentage": 22.5, "elapsed_time": "0:53:40", "remaining_time": "3:04:52"}
|
| 70 |
+
{"current_steps": 45, "total_steps": 200, "eval_loss": 0.8943431973457336, "epoch": 2.2531645569620253, "percentage": 22.5, "elapsed_time": "1:01:08", "remaining_time": "3:30:36"}
|
| 71 |
+
{"current_steps": 46, "total_steps": 200, "loss": 0.8959, "lr": 2.859461680554975e-06, "epoch": 2.3037974683544302, "percentage": 23.0, "elapsed_time": "1:11:22", "remaining_time": "3:58:57"}
|
| 72 |
+
{"current_steps": 47, "total_steps": 200, "loss": 0.8848, "lr": 2.8481910694487506e-06, "epoch": 2.3544303797468356, "percentage": 23.5, "elapsed_time": "1:21:58", "remaining_time": "4:26:52"}
|
| 73 |
+
{"current_steps": 48, "total_steps": 200, "loss": 0.8915, "lr": 2.8365097862825516e-06, "epoch": 2.4050632911392404, "percentage": 24.0, "elapsed_time": "1:28:19", "remaining_time": "4:39:41"}
|
| 74 |
+
{"current_steps": 49, "total_steps": 200, "loss": 0.868, "lr": 2.8244213892883906e-06, "epoch": 2.4556962025316453, "percentage": 24.5, "elapsed_time": "1:40:38", "remaining_time": "5:10:08"}
|
| 75 |
+
{"current_steps": 50, "total_steps": 200, "loss": 0.8863, "lr": 2.811929560709094e-06, "epoch": 2.5063291139240507, "percentage": 25.0, "elapsed_time": "1:52:41", "remaining_time": "5:38:03"}
|
| 76 |
+
{"current_steps": 50, "total_steps": 200, "eval_loss": 0.8839963674545288, "epoch": 2.5063291139240507, "percentage": 25.0, "elapsed_time": "2:00:08", "remaining_time": "6:00:25"}
|
| 77 |
+
{"current_steps": 51, "total_steps": 200, "loss": 0.8841, "lr": 2.7990381056766585e-06, "epoch": 2.5569620253164556, "percentage": 25.5, "elapsed_time": "2:07:58", "remaining_time": "6:13:53"}
|
| 78 |
+
{"current_steps": 52, "total_steps": 200, "loss": 0.899, "lr": 2.7857509510531684e-06, "epoch": 2.607594936708861, "percentage": 26.0, "elapsed_time": "2:15:39", "remaining_time": "6:26:07"}
|
| 79 |
+
{"current_steps": 53, "total_steps": 200, "loss": 0.8594, "lr": 2.772072144234639e-06, "epoch": 2.6582278481012658, "percentage": 26.5, "elapsed_time": "2:26:29", "remaining_time": "6:46:18"}
|
| 80 |
+
{"current_steps": 54, "total_steps": 200, "loss": 0.8865, "lr": 2.758005851918136e-06, "epoch": 2.708860759493671, "percentage": 27.0, "elapsed_time": "2:39:41", "remaining_time": "7:11:46"}
|
| 81 |
+
{"current_steps": 55, "total_steps": 200, "loss": 0.8689, "lr": 2.7435563588325624e-06, "epoch": 2.759493670886076, "percentage": 27.5, "elapsed_time": "2:46:29", "remaining_time": "7:18:55"}
|
| 82 |
+
{"current_steps": 55, "total_steps": 200, "eval_loss": 0.8752490878105164, "epoch": 2.759493670886076, "percentage": 27.5, "elapsed_time": "2:53:50", "remaining_time": "7:38:17"}
|
| 83 |
+
{"current_steps": 56, "total_steps": 200, "loss": 0.85, "lr": 2.728728066433488e-06, "epoch": 2.810126582278481, "percentage": 28.0, "elapsed_time": "3:04:10", "remaining_time": "7:53:34"}
|
| 84 |
+
{"current_steps": 57, "total_steps": 200, "loss": 0.822, "lr": 2.713525491562421e-06, "epoch": 2.8607594936708862, "percentage": 28.5, "elapsed_time": "3:21:23", "remaining_time": "8:25:15"}
|
| 85 |
+
{"current_steps": 58, "total_steps": 200, "loss": 0.8535, "lr": 2.6979532650709395e-06, "epoch": 2.911392405063291, "percentage": 29.0, "elapsed_time": "3:32:27", "remaining_time": "8:40:10"}
|
| 86 |
+
{"current_steps": 59, "total_steps": 200, "loss": 0.8765, "lr": 2.6820161304100827e-06, "epoch": 2.962025316455696, "percentage": 29.5, "elapsed_time": "3:47:46", "remaining_time": "9:04:20"}
|
| 87 |
+
{"current_steps": 60, "total_steps": 200, "loss": 0.86, "lr": 2.6657189421854562e-06, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "3:56:28", "remaining_time": "9:11:46"}
|
| 88 |
+
{"current_steps": 60, "total_steps": 200, "eval_loss": 0.8680967092514038, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "4:03:48", "remaining_time": "9:28:53"}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fb941336113ae945b1033dc7e4d1af368b2d723229876120191ed656a540f31
|
| 3 |
+
size 8273
|