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 sha256:583c055c7a98333c5a749b5f74453f81189ef98b2d058cc7b331e16cb8b5580e
|
| 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 sha256:392e2bf51e3970863e201e3e2a5221eaabb1ef7071364878c97da05702a3377c
|
| 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:c750421bcd52221e6b5f7875c0e15ffe0071569ea74e364f630a38a72de4bc45
|
| 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:e6ff650fbe3411b59b1bf6f72fdb29c3095fef516fb1010ba1f65dae799a3817
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -71,3 +71,38 @@
|
|
| 71 |
{"current_steps": 700, "total_steps": 1065, "loss": 0.604, "lr": 5e-06, "epoch": 1.969409282700422, "percentage": 65.73, "elapsed_time": "11:24:36", "remaining_time": "5:56:58"}
|
| 72 |
{"current_steps": 710, "total_steps": 1065, "loss": 0.6037, "lr": 5e-06, "epoch": 1.9975386779184248, "percentage": 66.67, "elapsed_time": "11:34:16", "remaining_time": "5:47:08"}
|
| 73 |
{"current_steps": 710, "total_steps": 1065, "eval_loss": 0.6334141492843628, "epoch": 1.9975386779184248, "percentage": 66.67, "elapsed_time": "11:41:16", "remaining_time": "5:50:38"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
{"current_steps": 700, "total_steps": 1065, "loss": 0.604, "lr": 5e-06, "epoch": 1.969409282700422, "percentage": 65.73, "elapsed_time": "11:24:36", "remaining_time": "5:56:58"}
|
| 72 |
{"current_steps": 710, "total_steps": 1065, "loss": 0.6037, "lr": 5e-06, "epoch": 1.9975386779184248, "percentage": 66.67, "elapsed_time": "11:34:16", "remaining_time": "5:47:08"}
|
| 73 |
{"current_steps": 710, "total_steps": 1065, "eval_loss": 0.6334141492843628, "epoch": 1.9975386779184248, "percentage": 66.67, "elapsed_time": "11:41:16", "remaining_time": "5:50:38"}
|
| 74 |
+
{"current_steps": 720, "total_steps": 1065, "loss": 0.6057, "lr": 5e-06, "epoch": 2.0260196905766525, "percentage": 67.61, "elapsed_time": "11:51:32", "remaining_time": "5:40:57"}
|
| 75 |
+
{"current_steps": 730, "total_steps": 1065, "loss": 0.5629, "lr": 5e-06, "epoch": 2.0541490857946556, "percentage": 68.54, "elapsed_time": "12:01:15", "remaining_time": "5:30:59"}
|
| 76 |
+
{"current_steps": 740, "total_steps": 1065, "loss": 0.5666, "lr": 5e-06, "epoch": 2.0822784810126582, "percentage": 69.48, "elapsed_time": "12:10:56", "remaining_time": "5:21:01"}
|
| 77 |
+
{"current_steps": 750, "total_steps": 1065, "loss": 0.5663, "lr": 5e-06, "epoch": 2.110407876230661, "percentage": 70.42, "elapsed_time": "12:20:36", "remaining_time": "5:11:03"}
|
| 78 |
+
{"current_steps": 760, "total_steps": 1065, "loss": 0.5621, "lr": 5e-06, "epoch": 2.138537271448664, "percentage": 71.36, "elapsed_time": "12:30:18", "remaining_time": "5:01:06"}
|
| 79 |
+
{"current_steps": 770, "total_steps": 1065, "loss": 0.5642, "lr": 5e-06, "epoch": 2.1666666666666665, "percentage": 72.3, "elapsed_time": "12:39:59", "remaining_time": "4:51:10"}
|
| 80 |
+
{"current_steps": 780, "total_steps": 1065, "loss": 0.562, "lr": 5e-06, "epoch": 2.1947960618846696, "percentage": 73.24, "elapsed_time": "12:49:40", "remaining_time": "4:41:13"}
|
| 81 |
+
{"current_steps": 790, "total_steps": 1065, "loss": 0.5624, "lr": 5e-06, "epoch": 2.222925457102672, "percentage": 74.18, "elapsed_time": "12:59:22", "remaining_time": "4:31:18"}
|
| 82 |
+
{"current_steps": 800, "total_steps": 1065, "loss": 0.5669, "lr": 5e-06, "epoch": 2.2510548523206753, "percentage": 75.12, "elapsed_time": "13:09:04", "remaining_time": "4:21:22"}
|
| 83 |
+
{"current_steps": 810, "total_steps": 1065, "loss": 0.5635, "lr": 5e-06, "epoch": 2.279184247538678, "percentage": 76.06, "elapsed_time": "13:18:44", "remaining_time": "4:11:27"}
|
| 84 |
+
{"current_steps": 820, "total_steps": 1065, "loss": 0.5665, "lr": 5e-06, "epoch": 2.3073136427566805, "percentage": 77.0, "elapsed_time": "13:28:26", "remaining_time": "4:01:32"}
|
| 85 |
+
{"current_steps": 830, "total_steps": 1065, "loss": 0.5582, "lr": 5e-06, "epoch": 2.3354430379746836, "percentage": 77.93, "elapsed_time": "13:38:07", "remaining_time": "3:51:38"}
|
| 86 |
+
{"current_steps": 840, "total_steps": 1065, "loss": 0.5679, "lr": 5e-06, "epoch": 2.363572433192686, "percentage": 78.87, "elapsed_time": "13:47:48", "remaining_time": "3:41:44"}
|
| 87 |
+
{"current_steps": 850, "total_steps": 1065, "loss": 0.566, "lr": 5e-06, "epoch": 2.3917018284106892, "percentage": 79.81, "elapsed_time": "13:57:30", "remaining_time": "3:31:50"}
|
| 88 |
+
{"current_steps": 860, "total_steps": 1065, "loss": 0.5689, "lr": 5e-06, "epoch": 2.419831223628692, "percentage": 80.75, "elapsed_time": "14:07:12", "remaining_time": "3:21:56"}
|
| 89 |
+
{"current_steps": 870, "total_steps": 1065, "loss": 0.565, "lr": 5e-06, "epoch": 2.447960618846695, "percentage": 81.69, "elapsed_time": "14:16:50", "remaining_time": "3:12:03"}
|
| 90 |
+
{"current_steps": 880, "total_steps": 1065, "loss": 0.5669, "lr": 5e-06, "epoch": 2.4760900140646975, "percentage": 82.63, "elapsed_time": "14:26:32", "remaining_time": "3:02:10"}
|
| 91 |
+
{"current_steps": 890, "total_steps": 1065, "loss": 0.5662, "lr": 5e-06, "epoch": 2.5042194092827, "percentage": 83.57, "elapsed_time": "14:36:12", "remaining_time": "2:52:17"}
|
| 92 |
+
{"current_steps": 900, "total_steps": 1065, "loss": 0.5694, "lr": 5e-06, "epoch": 2.532348804500703, "percentage": 84.51, "elapsed_time": "14:45:51", "remaining_time": "2:42:24"}
|
| 93 |
+
{"current_steps": 910, "total_steps": 1065, "loss": 0.5644, "lr": 5e-06, "epoch": 2.5604781997187063, "percentage": 85.45, "elapsed_time": "14:55:32", "remaining_time": "2:32:32"}
|
| 94 |
+
{"current_steps": 920, "total_steps": 1065, "loss": 0.5668, "lr": 5e-06, "epoch": 2.588607594936709, "percentage": 86.38, "elapsed_time": "15:05:12", "remaining_time": "2:22:40"}
|
| 95 |
+
{"current_steps": 930, "total_steps": 1065, "loss": 0.5724, "lr": 5e-06, "epoch": 2.6167369901547115, "percentage": 87.32, "elapsed_time": "15:14:52", "remaining_time": "2:12:48"}
|
| 96 |
+
{"current_steps": 940, "total_steps": 1065, "loss": 0.5719, "lr": 5e-06, "epoch": 2.6448663853727146, "percentage": 88.26, "elapsed_time": "15:24:32", "remaining_time": "2:02:56"}
|
| 97 |
+
{"current_steps": 950, "total_steps": 1065, "loss": 0.5613, "lr": 5e-06, "epoch": 2.672995780590717, "percentage": 89.2, "elapsed_time": "15:34:12", "remaining_time": "1:53:05"}
|
| 98 |
+
{"current_steps": 960, "total_steps": 1065, "loss": 0.5639, "lr": 5e-06, "epoch": 2.7011251758087202, "percentage": 90.14, "elapsed_time": "15:43:53", "remaining_time": "1:43:14"}
|
| 99 |
+
{"current_steps": 970, "total_steps": 1065, "loss": 0.5673, "lr": 5e-06, "epoch": 2.729254571026723, "percentage": 91.08, "elapsed_time": "15:53:35", "remaining_time": "1:33:23"}
|
| 100 |
+
{"current_steps": 980, "total_steps": 1065, "loss": 0.5677, "lr": 5e-06, "epoch": 2.757383966244726, "percentage": 92.02, "elapsed_time": "16:03:16", "remaining_time": "1:23:32"}
|
| 101 |
+
{"current_steps": 990, "total_steps": 1065, "loss": 0.5705, "lr": 5e-06, "epoch": 2.7855133614627285, "percentage": 92.96, "elapsed_time": "16:12:55", "remaining_time": "1:13:42"}
|
| 102 |
+
{"current_steps": 1000, "total_steps": 1065, "loss": 0.5662, "lr": 5e-06, "epoch": 2.813642756680731, "percentage": 93.9, "elapsed_time": "16:22:36", "remaining_time": "1:03:52"}
|
| 103 |
+
{"current_steps": 1010, "total_steps": 1065, "loss": 0.5719, "lr": 5e-06, "epoch": 2.8417721518987342, "percentage": 94.84, "elapsed_time": "16:32:17", "remaining_time": "0:54:02"}
|
| 104 |
+
{"current_steps": 1020, "total_steps": 1065, "loss": 0.5699, "lr": 5e-06, "epoch": 2.869901547116737, "percentage": 95.77, "elapsed_time": "16:41:59", "remaining_time": "0:44:12"}
|
| 105 |
+
{"current_steps": 1030, "total_steps": 1065, "loss": 0.5678, "lr": 5e-06, "epoch": 2.89803094233474, "percentage": 96.71, "elapsed_time": "16:51:39", "remaining_time": "0:34:22"}
|
| 106 |
+
{"current_steps": 1040, "total_steps": 1065, "loss": 0.5668, "lr": 5e-06, "epoch": 2.9261603375527425, "percentage": 97.65, "elapsed_time": "17:01:20", "remaining_time": "0:24:33"}
|
| 107 |
+
{"current_steps": 1050, "total_steps": 1065, "loss": 0.5712, "lr": 5e-06, "epoch": 2.9542897327707456, "percentage": 98.59, "elapsed_time": "17:11:01", "remaining_time": "0:14:43"}
|
| 108 |
+
{"current_steps": 1060, "total_steps": 1065, "loss": 0.5749, "lr": 5e-06, "epoch": 2.982419127988748, "percentage": 99.53, "elapsed_time": "17:20:42", "remaining_time": "0:04:54"}
|