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 sha256:98983d3a83ece3b84cce2058406ee62b018700858776d8fe32825a1a71052c4c
|
| 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 sha256:6ce2932fb69c71c0fb891edb4655a9dfd14299292e938a0c41b6eb9f7f6bae55
|
| 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 sha256:03040aa5cf3d4025ca0bc6fd6bbf2976d9bcf19a45647859206700d993be7821
|
| 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:e5c780508e2ce628c33dc2d04c504343c2f418dab8f10f5f69dec411832ae637
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -28,3 +28,33 @@
|
|
| 28 |
{"current_steps": 280, "total_steps": 864, "loss": 0.7583, "lr": 5e-06, "epoch": 0.9709579540528825, "percentage": 32.41, "elapsed_time": "2:30:01", "remaining_time": "5:12:55"}
|
| 29 |
{"current_steps": 288, "total_steps": 864, "eval_loss": 0.753886342048645, "epoch": 0.9986996098829649, "percentage": 33.33, "elapsed_time": "2:37:48", "remaining_time": "5:15:36"}
|
| 30 |
{"current_steps": 290, "total_steps": 864, "loss": 0.7976, "lr": 5e-06, "epoch": 1.0056350238404854, "percentage": 33.56, "elapsed_time": "2:39:53", "remaining_time": "5:16:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
{"current_steps": 280, "total_steps": 864, "loss": 0.7583, "lr": 5e-06, "epoch": 0.9709579540528825, "percentage": 32.41, "elapsed_time": "2:30:01", "remaining_time": "5:12:55"}
|
| 29 |
{"current_steps": 288, "total_steps": 864, "eval_loss": 0.753886342048645, "epoch": 0.9986996098829649, "percentage": 33.33, "elapsed_time": "2:37:48", "remaining_time": "5:15:36"}
|
| 30 |
{"current_steps": 290, "total_steps": 864, "loss": 0.7976, "lr": 5e-06, "epoch": 1.0056350238404854, "percentage": 33.56, "elapsed_time": "2:39:53", "remaining_time": "5:16:29"}
|
| 31 |
+
{"current_steps": 300, "total_steps": 864, "loss": 0.7106, "lr": 5e-06, "epoch": 1.0403120936280885, "percentage": 34.72, "elapsed_time": "2:45:15", "remaining_time": "5:10:40"}
|
| 32 |
+
{"current_steps": 310, "total_steps": 864, "loss": 0.7066, "lr": 5e-06, "epoch": 1.0749891634156914, "percentage": 35.88, "elapsed_time": "2:50:37", "remaining_time": "5:04:54"}
|
| 33 |
+
{"current_steps": 320, "total_steps": 864, "loss": 0.7058, "lr": 5e-06, "epoch": 1.1096662332032943, "percentage": 37.04, "elapsed_time": "2:55:58", "remaining_time": "4:59:09"}
|
| 34 |
+
{"current_steps": 330, "total_steps": 864, "loss": 0.7031, "lr": 5e-06, "epoch": 1.1443433029908974, "percentage": 38.19, "elapsed_time": "3:01:19", "remaining_time": "4:53:24"}
|
| 35 |
+
{"current_steps": 340, "total_steps": 864, "loss": 0.6997, "lr": 5e-06, "epoch": 1.1790203727785002, "percentage": 39.35, "elapsed_time": "3:06:39", "remaining_time": "4:47:40"}
|
| 36 |
+
{"current_steps": 350, "total_steps": 864, "loss": 0.7048, "lr": 5e-06, "epoch": 1.2136974425661031, "percentage": 40.51, "elapsed_time": "3:11:59", "remaining_time": "4:41:56"}
|
| 37 |
+
{"current_steps": 360, "total_steps": 864, "loss": 0.7049, "lr": 5e-06, "epoch": 1.2483745123537062, "percentage": 41.67, "elapsed_time": "3:17:19", "remaining_time": "4:36:15"}
|
| 38 |
+
{"current_steps": 370, "total_steps": 864, "loss": 0.7025, "lr": 5e-06, "epoch": 1.283051582141309, "percentage": 42.82, "elapsed_time": "3:22:41", "remaining_time": "4:30:36"}
|
| 39 |
+
{"current_steps": 380, "total_steps": 864, "loss": 0.7071, "lr": 5e-06, "epoch": 1.317728651928912, "percentage": 43.98, "elapsed_time": "3:28:01", "remaining_time": "4:24:57"}
|
| 40 |
+
{"current_steps": 390, "total_steps": 864, "loss": 0.7062, "lr": 5e-06, "epoch": 1.352405721716515, "percentage": 45.14, "elapsed_time": "3:33:22", "remaining_time": "4:19:19"}
|
| 41 |
+
{"current_steps": 400, "total_steps": 864, "loss": 0.7013, "lr": 5e-06, "epoch": 1.387082791504118, "percentage": 46.3, "elapsed_time": "3:38:44", "remaining_time": "4:13:44"}
|
| 42 |
+
{"current_steps": 410, "total_steps": 864, "loss": 0.7043, "lr": 5e-06, "epoch": 1.4217598612917208, "percentage": 47.45, "elapsed_time": "3:44:06", "remaining_time": "4:08:09"}
|
| 43 |
+
{"current_steps": 420, "total_steps": 864, "loss": 0.705, "lr": 5e-06, "epoch": 1.456436931079324, "percentage": 48.61, "elapsed_time": "3:49:27", "remaining_time": "4:02:34"}
|
| 44 |
+
{"current_steps": 430, "total_steps": 864, "loss": 0.7035, "lr": 5e-06, "epoch": 1.4911140008669268, "percentage": 49.77, "elapsed_time": "3:54:48", "remaining_time": "3:56:59"}
|
| 45 |
+
{"current_steps": 440, "total_steps": 864, "loss": 0.7062, "lr": 5e-06, "epoch": 1.5257910706545297, "percentage": 50.93, "elapsed_time": "4:00:09", "remaining_time": "3:51:25"}
|
| 46 |
+
{"current_steps": 450, "total_steps": 864, "loss": 0.7056, "lr": 5e-06, "epoch": 1.5604681404421328, "percentage": 52.08, "elapsed_time": "4:05:31", "remaining_time": "3:45:52"}
|
| 47 |
+
{"current_steps": 460, "total_steps": 864, "loss": 0.7019, "lr": 5e-06, "epoch": 1.5951452102297354, "percentage": 53.24, "elapsed_time": "4:10:52", "remaining_time": "3:40:20"}
|
| 48 |
+
{"current_steps": 470, "total_steps": 864, "loss": 0.7019, "lr": 5e-06, "epoch": 1.6298222800173385, "percentage": 54.4, "elapsed_time": "4:16:13", "remaining_time": "3:34:47"}
|
| 49 |
+
{"current_steps": 480, "total_steps": 864, "loss": 0.7057, "lr": 5e-06, "epoch": 1.6644993498049416, "percentage": 55.56, "elapsed_time": "4:21:34", "remaining_time": "3:29:15"}
|
| 50 |
+
{"current_steps": 490, "total_steps": 864, "loss": 0.7043, "lr": 5e-06, "epoch": 1.6991764195925443, "percentage": 56.71, "elapsed_time": "4:26:55", "remaining_time": "3:23:43"}
|
| 51 |
+
{"current_steps": 500, "total_steps": 864, "loss": 0.704, "lr": 5e-06, "epoch": 1.7338534893801474, "percentage": 57.87, "elapsed_time": "4:32:16", "remaining_time": "3:18:12"}
|
| 52 |
+
{"current_steps": 510, "total_steps": 864, "loss": 0.7046, "lr": 5e-06, "epoch": 1.7685305591677505, "percentage": 59.03, "elapsed_time": "4:37:37", "remaining_time": "3:12:42"}
|
| 53 |
+
{"current_steps": 520, "total_steps": 864, "loss": 0.7031, "lr": 5e-06, "epoch": 1.8032076289553531, "percentage": 60.19, "elapsed_time": "4:43:00", "remaining_time": "3:07:13"}
|
| 54 |
+
{"current_steps": 530, "total_steps": 864, "loss": 0.7026, "lr": 5e-06, "epoch": 1.8378846987429562, "percentage": 61.34, "elapsed_time": "4:48:22", "remaining_time": "3:01:43"}
|
| 55 |
+
{"current_steps": 540, "total_steps": 864, "loss": 0.7006, "lr": 5e-06, "epoch": 1.8725617685305593, "percentage": 62.5, "elapsed_time": "4:53:42", "remaining_time": "2:56:13"}
|
| 56 |
+
{"current_steps": 550, "total_steps": 864, "loss": 0.7033, "lr": 5e-06, "epoch": 1.907238838318162, "percentage": 63.66, "elapsed_time": "4:59:03", "remaining_time": "2:50:43"}
|
| 57 |
+
{"current_steps": 560, "total_steps": 864, "loss": 0.6992, "lr": 5e-06, "epoch": 1.941915908105765, "percentage": 64.81, "elapsed_time": "5:04:23", "remaining_time": "2:45:14"}
|
| 58 |
+
{"current_steps": 570, "total_steps": 864, "loss": 0.6958, "lr": 5e-06, "epoch": 1.976592977893368, "percentage": 65.97, "elapsed_time": "5:09:43", "remaining_time": "2:39:45"}
|
| 59 |
+
{"current_steps": 576, "total_steps": 864, "eval_loss": 0.7401416897773743, "epoch": 1.9973992197659298, "percentage": 66.67, "elapsed_time": "5:16:31", "remaining_time": "2:38:15"}
|
| 60 |
+
{"current_steps": 580, "total_steps": 864, "loss": 0.7266, "lr": 5e-06, "epoch": 2.011270047680971, "percentage": 67.13, "elapsed_time": "5:19:40", "remaining_time": "2:36:31"}
|