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 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fc14ad1d8594a5f42a89a5498dcc79153ff5ac22e224ea6881e36b3ae6b71e4
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15fc54a2771dc75d5de6ccb1e8de307e35236f3fd6a6f3c8c7f6b736b0b778fc
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c4563f79859a977f2a22c953c4afd07e37a19c5af548ab225675552e6daf29
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29e20838c1c365c119dcf64394ec30dde536842adc19645f2d24d0b5058132af
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -52,3 +52,54 @@
|
|
| 52 |
{"current_steps": 52, "total_steps": 153, "loss": 1.4462, "lr": 8.390845161763756e-06, "epoch": 1.012965964343598, "percentage": 33.99, "elapsed_time": "0:42:19", "remaining_time": "1:22:12"}
|
| 53 |
{"current_steps": 53, "total_steps": 153, "loss": 0.9298, "lr": 8.305699187343586e-06, "epoch": 1.032414910858995, "percentage": 34.64, "elapsed_time": "0:43:19", "remaining_time": "1:21:45"}
|
| 54 |
{"current_steps": 54, "total_steps": 153, "loss": 0.7472, "lr": 8.218815000254233e-06, "epoch": 1.0518638573743921, "percentage": 35.29, "elapsed_time": "0:43:59", "remaining_time": "1:20:38"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
{"current_steps": 52, "total_steps": 153, "loss": 1.4462, "lr": 8.390845161763756e-06, "epoch": 1.012965964343598, "percentage": 33.99, "elapsed_time": "0:42:19", "remaining_time": "1:22:12"}
|
| 53 |
{"current_steps": 53, "total_steps": 153, "loss": 0.9298, "lr": 8.305699187343586e-06, "epoch": 1.032414910858995, "percentage": 34.64, "elapsed_time": "0:43:19", "remaining_time": "1:21:45"}
|
| 54 |
{"current_steps": 54, "total_steps": 153, "loss": 0.7472, "lr": 8.218815000254233e-06, "epoch": 1.0518638573743921, "percentage": 35.29, "elapsed_time": "0:43:59", "remaining_time": "1:20:38"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 153, "loss": 0.8235, "lr": 8.130238286199747e-06, "epoch": 1.0713128038897892, "percentage": 35.95, "elapsed_time": "0:44:49", "remaining_time": "1:19:52"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 153, "loss": 0.9211, "lr": 8.04001562085379e-06, "epoch": 1.0907617504051863, "percentage": 36.6, "elapsed_time": "0:45:45", "remaining_time": "1:19:15"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 153, "loss": 0.9178, "lr": 7.948194445369065e-06, "epoch": 1.1102106969205834, "percentage": 37.25, "elapsed_time": "0:46:43", "remaining_time": "1:18:41"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 153, "loss": 0.7913, "lr": 7.85482304143168e-06, "epoch": 1.1296596434359805, "percentage": 37.91, "elapsed_time": "0:47:23", "remaining_time": "1:17:37"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 153, "loss": 0.8701, "lr": 7.759950505873523e-06, "epoch": 1.1491085899513775, "percentage": 38.56, "elapsed_time": "0:48:07", "remaining_time": "1:16:40"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 153, "loss": 0.8091, "lr": 7.66362672485601e-06, "epoch": 1.1685575364667746, "percentage": 39.22, "elapsed_time": "0:48:57", "remaining_time": "1:15:53"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 153, "loss": 0.8805, "lr": 7.565902347638806e-06, "epoch": 1.1880064829821717, "percentage": 39.87, "elapsed_time": "0:49:50", "remaining_time": "1:15:10"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 153, "loss": 0.8076, "lr": 7.466828759947271e-06, "epoch": 1.2074554294975688, "percentage": 40.52, "elapsed_time": "0:50:40", "remaining_time": "1:14:22"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 153, "loss": 0.7676, "lr": 7.366458056952668e-06, "epoch": 1.2269043760129659, "percentage": 41.18, "elapsed_time": "0:51:21", "remaining_time": "1:13:22"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 153, "loss": 0.9008, "lr": 7.264843015879321e-06, "epoch": 1.246353322528363, "percentage": 41.83, "elapsed_time": "0:52:12", "remaining_time": "1:12:36"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 153, "loss": 0.7623, "lr": 7.162037068253141e-06, "epoch": 1.26580226904376, "percentage": 42.48, "elapsed_time": "0:52:55", "remaining_time": "1:11:38"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 153, "loss": 0.8989, "lr": 7.058094271806091e-06, "epoch": 1.2852512155591573, "percentage": 43.14, "elapsed_time": "0:53:47", "remaining_time": "1:10:54"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 153, "loss": 0.8975, "lr": 6.953069282051397e-06, "epoch": 1.3047001620745542, "percentage": 43.79, "elapsed_time": "0:54:37", "remaining_time": "1:10:06"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 153, "loss": 0.744, "lr": 6.84701732354442e-06, "epoch": 1.3241491085899515, "percentage": 44.44, "elapsed_time": "0:55:30", "remaining_time": "1:09:23"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 153, "loss": 0.8693, "lr": 6.7399941608443096e-06, "epoch": 1.3435980551053484, "percentage": 45.1, "elapsed_time": "0:56:25", "remaining_time": "1:08:41"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 153, "loss": 0.8185, "lr": 6.632056069191723e-06, "epoch": 1.3630470016207457, "percentage": 45.75, "elapsed_time": "0:57:11", "remaining_time": "1:07:49"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 153, "loss": 0.8219, "lr": 6.523259804918001e-06, "epoch": 1.3824959481361425, "percentage": 46.41, "elapsed_time": "0:57:55", "remaining_time": "1:06:54"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 153, "loss": 0.8675, "lr": 6.413662575601391e-06, "epoch": 1.4019448946515398, "percentage": 47.06, "elapsed_time": "0:58:50", "remaining_time": "1:06:11"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 153, "loss": 0.8004, "lr": 6.303322009985984e-06, "epoch": 1.4213938411669367, "percentage": 47.71, "elapsed_time": "0:59:41", "remaining_time": "1:05:24"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 153, "loss": 0.8649, "lr": 6.1922961276791925e-06, "epoch": 1.440842787682334, "percentage": 48.37, "elapsed_time": "1:00:30", "remaining_time": "1:04:35"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 153, "loss": 0.7551, "lr": 6.08064330864371e-06, "epoch": 1.4602917341977308, "percentage": 49.02, "elapsed_time": "1:01:18", "remaining_time": "1:03:46"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 153, "loss": 0.798, "lr": 5.968422262499983e-06, "epoch": 1.4797406807131281, "percentage": 49.67, "elapsed_time": "1:02:09", "remaining_time": "1:02:58"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 153, "loss": 0.8498, "lr": 5.85569199765534e-06, "epoch": 1.499189627228525, "percentage": 50.33, "elapsed_time": "1:02:58", "remaining_time": "1:02:09"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 153, "loss": 0.7277, "lr": 5.7425117902760195e-06, "epoch": 1.5186385737439223, "percentage": 50.98, "elapsed_time": "1:03:41", "remaining_time": "1:01:14"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 153, "loss": 0.8525, "lr": 5.628941153118388e-06, "epoch": 1.5380875202593192, "percentage": 51.63, "elapsed_time": "1:04:23", "remaining_time": "1:00:19"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 153, "loss": 0.7927, "lr": 5.515039804235772e-06, "epoch": 1.5575364667747165, "percentage": 52.29, "elapsed_time": "1:05:07", "remaining_time": "0:59:25"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 153, "loss": 0.8495, "lr": 5.400867635577335e-06, "epoch": 1.5769854132901133, "percentage": 52.94, "elapsed_time": "1:06:00", "remaining_time": "0:58:40"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 153, "loss": 0.7973, "lr": 5.2864846814955e-06, "epoch": 1.5964343598055106, "percentage": 53.59, "elapsed_time": "1:06:47", "remaining_time": "0:57:50"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 153, "loss": 0.8542, "lr": 5.17195108717852e-06, "epoch": 1.6158833063209075, "percentage": 54.25, "elapsed_time": "1:07:35", "remaining_time": "0:57:00"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 153, "loss": 0.7751, "lr": 5.057327077024745e-06, "epoch": 1.6353322528363048, "percentage": 54.9, "elapsed_time": "1:08:24", "remaining_time": "0:56:11"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 153, "loss": 0.7718, "lr": 4.942672922975255e-06, "epoch": 1.6547811993517016, "percentage": 55.56, "elapsed_time": "1:09:10", "remaining_time": "0:55:20"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 153, "loss": 0.7642, "lr": 4.82804891282148e-06, "epoch": 1.674230145867099, "percentage": 56.21, "elapsed_time": "1:09:52", "remaining_time": "0:54:25"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 153, "loss": 0.9642, "lr": 4.713515318504501e-06, "epoch": 1.6936790923824958, "percentage": 56.86, "elapsed_time": "1:10:44", "remaining_time": "0:53:39"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 153, "loss": 0.7228, "lr": 4.599132364422666e-06, "epoch": 1.7131280388978931, "percentage": 57.52, "elapsed_time": "1:11:28", "remaining_time": "0:52:47"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 153, "loss": 0.8748, "lr": 4.4849601957642295e-06, "epoch": 1.73257698541329, "percentage": 58.17, "elapsed_time": "1:12:22", "remaining_time": "0:52:02"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 153, "loss": 0.8228, "lr": 4.371058846881614e-06, "epoch": 1.7520259319286873, "percentage": 58.82, "elapsed_time": "1:13:07", "remaining_time": "0:51:11"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 153, "loss": 0.7398, "lr": 4.257488209723981e-06, "epoch": 1.7714748784440841, "percentage": 59.48, "elapsed_time": "1:13:48", "remaining_time": "0:50:16"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 153, "loss": 0.8464, "lr": 4.1443080023446605e-06, "epoch": 1.7909238249594814, "percentage": 60.13, "elapsed_time": "1:14:34", "remaining_time": "0:49:26"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 153, "loss": 0.8294, "lr": 4.0315777375000185e-06, "epoch": 1.8103727714748783, "percentage": 60.78, "elapsed_time": "1:15:19", "remaining_time": "0:48:35"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 153, "loss": 0.7465, "lr": 3.9193566913562915e-06, "epoch": 1.8298217179902756, "percentage": 61.44, "elapsed_time": "1:15:59", "remaining_time": "0:47:41"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 153, "loss": 0.8468, "lr": 3.807703872320809e-06, "epoch": 1.8492706645056725, "percentage": 62.09, "elapsed_time": "1:16:51", "remaining_time": "0:46:55"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 153, "loss": 0.83, "lr": 3.6966779900140193e-06, "epoch": 1.8687196110210698, "percentage": 62.75, "elapsed_time": "1:17:46", "remaining_time": "0:46:10"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 153, "loss": 0.8286, "lr": 3.586337424398609e-06, "epoch": 1.8881685575364666, "percentage": 63.4, "elapsed_time": "1:18:36", "remaining_time": "0:45:23"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 153, "loss": 0.7724, "lr": 3.4767401950820003e-06, "epoch": 1.907617504051864, "percentage": 64.05, "elapsed_time": "1:19:18", "remaining_time": "0:44:30"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 153, "loss": 0.8476, "lr": 3.3679439308082777e-06, "epoch": 1.9270664505672608, "percentage": 64.71, "elapsed_time": "1:20:12", "remaining_time": "0:43:45"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 153, "loss": 0.7916, "lr": 3.260005839155691e-06, "epoch": 1.946515397082658, "percentage": 65.36, "elapsed_time": "1:20:52", "remaining_time": "0:42:51"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 153, "loss": 0.7754, "lr": 3.152982676455581e-06, "epoch": 1.965964343598055, "percentage": 66.01, "elapsed_time": "1:21:37", "remaining_time": "0:42:01"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 153, "loss": 0.8918, "lr": 3.046930717948604e-06, "epoch": 1.9854132901134522, "percentage": 66.67, "elapsed_time": "1:22:28", "remaining_time": "0:41:14"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 153, "loss": 1.2974, "lr": 2.9419057281939106e-06, "epoch": 2.006482982171799, "percentage": 67.32, "elapsed_time": "1:24:22", "remaining_time": "0:40:57"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 153, "loss": 0.7535, "lr": 2.8379629317468604e-06, "epoch": 2.025931928687196, "percentage": 67.97, "elapsed_time": "1:25:17", "remaining_time": "0:40:11"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 153, "loss": 0.7966, "lr": 2.7351569841206792e-06, "epoch": 2.0453808752025933, "percentage": 68.63, "elapsed_time": "1:26:02", "remaining_time": "0:39:20"}
|