Training in progress, epoch 1
Browse files
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4938985352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a634cdfafc0be85869fdc4e4b1e1bdb28a04b2b37745d204ab6caeb38ab0007b
|
| 3 |
size 4938985352
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4947390880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ab59334d4f41e68e463df7b8d361ce73f976691cb759408580c21b84e766713
|
| 3 |
size 4947390880
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3590488816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:856d174537367591cdcc393c624feb7f7ea4a2a0e025675187000bd67942c42a
|
| 3 |
size 3590488816
|
trainer_log.jsonl
CHANGED
|
@@ -33,3 +33,38 @@
|
|
| 33 |
{"current_steps": 330, "total_steps": 1020, "loss": 0.6065, "lr": 5e-06, "epoch": 0.9684519442406456, "percentage": 32.35, "elapsed_time": "5:00:05", "remaining_time": "10:27:28"}
|
| 34 |
{"current_steps": 340, "total_steps": 1020, "loss": 0.6004, "lr": 5e-06, "epoch": 0.9977989728539985, "percentage": 33.33, "elapsed_time": "5:09:11", "remaining_time": "10:18:23"}
|
| 35 |
{"current_steps": 340, "total_steps": 1020, "eval_loss": 0.6064473986625671, "epoch": 0.9977989728539985, "percentage": 33.33, "elapsed_time": "5:15:13", "remaining_time": "10:30:26"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
{"current_steps": 330, "total_steps": 1020, "loss": 0.6065, "lr": 5e-06, "epoch": 0.9684519442406456, "percentage": 32.35, "elapsed_time": "5:00:05", "remaining_time": "10:27:28"}
|
| 34 |
{"current_steps": 340, "total_steps": 1020, "loss": 0.6004, "lr": 5e-06, "epoch": 0.9977989728539985, "percentage": 33.33, "elapsed_time": "5:09:11", "remaining_time": "10:18:23"}
|
| 35 |
{"current_steps": 340, "total_steps": 1020, "eval_loss": 0.6064473986625671, "epoch": 0.9977989728539985, "percentage": 33.33, "elapsed_time": "5:15:13", "remaining_time": "10:30:26"}
|
| 36 |
+
{"current_steps": 350, "total_steps": 1020, "loss": 0.6221, "lr": 5e-06, "epoch": 1.028613352898019, "percentage": 34.31, "elapsed_time": "5:25:07", "remaining_time": "10:22:23"}
|
| 37 |
+
{"current_steps": 360, "total_steps": 1020, "loss": 0.5821, "lr": 5e-06, "epoch": 1.057960381511372, "percentage": 35.29, "elapsed_time": "5:34:17", "remaining_time": "10:12:52"}
|
| 38 |
+
{"current_steps": 370, "total_steps": 1020, "loss": 0.5748, "lr": 5e-06, "epoch": 1.0873074101247249, "percentage": 36.27, "elapsed_time": "5:43:25", "remaining_time": "10:03:18"}
|
| 39 |
+
{"current_steps": 380, "total_steps": 1020, "loss": 0.571, "lr": 5e-06, "epoch": 1.1166544387380777, "percentage": 37.25, "elapsed_time": "5:52:34", "remaining_time": "9:53:48"}
|
| 40 |
+
{"current_steps": 390, "total_steps": 1020, "loss": 0.567, "lr": 5e-06, "epoch": 1.1460014673514307, "percentage": 38.24, "elapsed_time": "6:01:43", "remaining_time": "9:44:20"}
|
| 41 |
+
{"current_steps": 400, "total_steps": 1020, "loss": 0.573, "lr": 5e-06, "epoch": 1.1753484959647835, "percentage": 39.22, "elapsed_time": "6:10:52", "remaining_time": "9:34:51"}
|
| 42 |
+
{"current_steps": 410, "total_steps": 1020, "loss": 0.5762, "lr": 5e-06, "epoch": 1.2046955245781366, "percentage": 40.2, "elapsed_time": "6:20:01", "remaining_time": "9:25:24"}
|
| 43 |
+
{"current_steps": 420, "total_steps": 1020, "loss": 0.568, "lr": 5e-06, "epoch": 1.2340425531914894, "percentage": 41.18, "elapsed_time": "6:29:08", "remaining_time": "9:15:55"}
|
| 44 |
+
{"current_steps": 430, "total_steps": 1020, "loss": 0.5686, "lr": 5e-06, "epoch": 1.2633895818048422, "percentage": 42.16, "elapsed_time": "6:38:16", "remaining_time": "9:06:28"}
|
| 45 |
+
{"current_steps": 440, "total_steps": 1020, "loss": 0.5727, "lr": 5e-06, "epoch": 1.2927366104181952, "percentage": 43.14, "elapsed_time": "6:47:25", "remaining_time": "8:57:03"}
|
| 46 |
+
{"current_steps": 450, "total_steps": 1020, "loss": 0.5726, "lr": 5e-06, "epoch": 1.322083639031548, "percentage": 44.12, "elapsed_time": "6:56:34", "remaining_time": "8:47:40"}
|
| 47 |
+
{"current_steps": 460, "total_steps": 1020, "loss": 0.5662, "lr": 5e-06, "epoch": 1.3514306676449008, "percentage": 45.1, "elapsed_time": "7:05:43", "remaining_time": "8:38:16"}
|
| 48 |
+
{"current_steps": 470, "total_steps": 1020, "loss": 0.57, "lr": 5e-06, "epoch": 1.3807776962582539, "percentage": 46.08, "elapsed_time": "7:14:54", "remaining_time": "8:28:55"}
|
| 49 |
+
{"current_steps": 480, "total_steps": 1020, "loss": 0.5664, "lr": 5e-06, "epoch": 1.4101247248716067, "percentage": 47.06, "elapsed_time": "7:24:01", "remaining_time": "8:19:31"}
|
| 50 |
+
{"current_steps": 490, "total_steps": 1020, "loss": 0.5669, "lr": 5e-06, "epoch": 1.4394717534849597, "percentage": 48.04, "elapsed_time": "7:33:10", "remaining_time": "8:10:09"}
|
| 51 |
+
{"current_steps": 500, "total_steps": 1020, "loss": 0.5651, "lr": 5e-06, "epoch": 1.4688187820983125, "percentage": 49.02, "elapsed_time": "7:42:19", "remaining_time": "8:00:48"}
|
| 52 |
+
{"current_steps": 510, "total_steps": 1020, "loss": 0.5647, "lr": 5e-06, "epoch": 1.4981658107116655, "percentage": 50.0, "elapsed_time": "7:51:26", "remaining_time": "7:51:26"}
|
| 53 |
+
{"current_steps": 520, "total_steps": 1020, "loss": 0.5649, "lr": 5e-06, "epoch": 1.5275128393250184, "percentage": 50.98, "elapsed_time": "8:00:31", "remaining_time": "7:42:02"}
|
| 54 |
+
{"current_steps": 530, "total_steps": 1020, "loss": 0.5599, "lr": 5e-06, "epoch": 1.5568598679383712, "percentage": 51.96, "elapsed_time": "8:09:38", "remaining_time": "7:32:41"}
|
| 55 |
+
{"current_steps": 540, "total_steps": 1020, "loss": 0.5639, "lr": 5e-06, "epoch": 1.5862068965517242, "percentage": 52.94, "elapsed_time": "8:18:44", "remaining_time": "7:23:19"}
|
| 56 |
+
{"current_steps": 550, "total_steps": 1020, "loss": 0.5712, "lr": 5e-06, "epoch": 1.615553925165077, "percentage": 53.92, "elapsed_time": "8:27:51", "remaining_time": "7:13:59"}
|
| 57 |
+
{"current_steps": 560, "total_steps": 1020, "loss": 0.5662, "lr": 5e-06, "epoch": 1.6449009537784298, "percentage": 54.9, "elapsed_time": "8:36:57", "remaining_time": "7:04:38"}
|
| 58 |
+
{"current_steps": 570, "total_steps": 1020, "loss": 0.569, "lr": 5e-06, "epoch": 1.6742479823917829, "percentage": 55.88, "elapsed_time": "8:46:02", "remaining_time": "6:55:18"}
|
| 59 |
+
{"current_steps": 580, "total_steps": 1020, "loss": 0.56, "lr": 5e-06, "epoch": 1.7035950110051359, "percentage": 56.86, "elapsed_time": "8:55:09", "remaining_time": "6:45:59"}
|
| 60 |
+
{"current_steps": 590, "total_steps": 1020, "loss": 0.5591, "lr": 5e-06, "epoch": 1.7329420396184885, "percentage": 57.84, "elapsed_time": "9:04:16", "remaining_time": "6:36:40"}
|
| 61 |
+
{"current_steps": 600, "total_steps": 1020, "loss": 0.5604, "lr": 5e-06, "epoch": 1.7622890682318415, "percentage": 58.82, "elapsed_time": "9:13:21", "remaining_time": "6:27:21"}
|
| 62 |
+
{"current_steps": 610, "total_steps": 1020, "loss": 0.5593, "lr": 5e-06, "epoch": 1.7916360968451945, "percentage": 59.8, "elapsed_time": "9:22:28", "remaining_time": "6:18:03"}
|
| 63 |
+
{"current_steps": 620, "total_steps": 1020, "loss": 0.5645, "lr": 5e-06, "epoch": 1.8209831254585473, "percentage": 60.78, "elapsed_time": "9:31:34", "remaining_time": "6:08:45"}
|
| 64 |
+
{"current_steps": 630, "total_steps": 1020, "loss": 0.5623, "lr": 5e-06, "epoch": 1.8503301540719002, "percentage": 61.76, "elapsed_time": "9:40:40", "remaining_time": "5:59:28"}
|
| 65 |
+
{"current_steps": 640, "total_steps": 1020, "loss": 0.5582, "lr": 5e-06, "epoch": 1.8796771826852532, "percentage": 62.75, "elapsed_time": "9:49:46", "remaining_time": "5:50:10"}
|
| 66 |
+
{"current_steps": 650, "total_steps": 1020, "loss": 0.564, "lr": 5e-06, "epoch": 1.909024211298606, "percentage": 63.73, "elapsed_time": "9:58:51", "remaining_time": "5:40:53"}
|
| 67 |
+
{"current_steps": 660, "total_steps": 1020, "loss": 0.5701, "lr": 5e-06, "epoch": 1.9383712399119588, "percentage": 64.71, "elapsed_time": "10:07:56", "remaining_time": "5:31:36"}
|
| 68 |
+
{"current_steps": 670, "total_steps": 1020, "loss": 0.566, "lr": 5e-06, "epoch": 1.9677182685253118, "percentage": 65.69, "elapsed_time": "10:17:03", "remaining_time": "5:22:20"}
|
| 69 |
+
{"current_steps": 680, "total_steps": 1020, "loss": 0.5587, "lr": 5e-06, "epoch": 1.9970652971386649, "percentage": 66.67, "elapsed_time": "10:26:07", "remaining_time": "5:13:03"}
|
| 70 |
+
{"current_steps": 680, "total_steps": 1020, "eval_loss": 0.5877389907836914, "epoch": 1.9970652971386649, "percentage": 66.67, "elapsed_time": "10:32:18", "remaining_time": "5:16:09"}
|