sedrickkeh
commited on
Commit
•
3ac7cb6
1
Parent(s):
77ea1b2
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 4903351912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4508df679f2bae3ee713b795a553032606d1456f4c11d871fcfde692e295a43
|
3 |
size 4903351912
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4947570872
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c429dfd792b957d1228cb5ecd4bca53c5e669c3f7cd24516e7fb31ea36985af3
|
3 |
size 4947570872
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4962221464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:563898317b02918feb3c31d32779c8b1b1da9dbf8e81d2403f4ab0ce1715711a
|
3 |
size 4962221464
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3670322200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4ca06f425fda4ddcc679a813dd716ce64635958df958d24fcfd7367c3b96686
|
3 |
size 3670322200
|
trainer_log.jsonl
CHANGED
@@ -32,3 +32,38 @@
|
|
32 |
{"current_steps": 320, "total_steps": 1002, "loss": 0.6155, "learning_rate": 5e-06, "epoch": 0.9579045837231057, "percentage": 31.94, "elapsed_time": "7:52:14", "remaining_time": "16:46:28"}
|
33 |
{"current_steps": 330, "total_steps": 1002, "loss": 0.6084, "learning_rate": 5e-06, "epoch": 0.9878391019644528, "percentage": 32.93, "elapsed_time": "8:06:59", "remaining_time": "16:31:42"}
|
34 |
{"current_steps": 334, "total_steps": 1002, "eval_loss": 0.6195828914642334, "epoch": 0.9998129092609915, "percentage": 33.33, "elapsed_time": "8:21:33", "remaining_time": "16:43:07"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
{"current_steps": 320, "total_steps": 1002, "loss": 0.6155, "learning_rate": 5e-06, "epoch": 0.9579045837231057, "percentage": 31.94, "elapsed_time": "7:52:14", "remaining_time": "16:46:28"}
|
33 |
{"current_steps": 330, "total_steps": 1002, "loss": 0.6084, "learning_rate": 5e-06, "epoch": 0.9878391019644528, "percentage": 32.93, "elapsed_time": "8:06:59", "remaining_time": "16:31:42"}
|
34 |
{"current_steps": 334, "total_steps": 1002, "eval_loss": 0.6195828914642334, "epoch": 0.9998129092609915, "percentage": 33.33, "elapsed_time": "8:21:33", "remaining_time": "16:43:07"}
|
35 |
+
{"current_steps": 340, "total_steps": 1002, "loss": 0.6386, "learning_rate": 5e-06, "epoch": 1.0177736202057999, "percentage": 33.93, "elapsed_time": "8:31:34", "remaining_time": "16:36:04"}
|
36 |
+
{"current_steps": 350, "total_steps": 1002, "loss": 0.5525, "learning_rate": 5e-06, "epoch": 1.047708138447147, "percentage": 34.93, "elapsed_time": "8:46:19", "remaining_time": "16:20:27"}
|
37 |
+
{"current_steps": 360, "total_steps": 1002, "loss": 0.5481, "learning_rate": 5e-06, "epoch": 1.077642656688494, "percentage": 35.93, "elapsed_time": "9:01:04", "remaining_time": "16:04:55"}
|
38 |
+
{"current_steps": 370, "total_steps": 1002, "loss": 0.5481, "learning_rate": 5e-06, "epoch": 1.1075771749298409, "percentage": 36.93, "elapsed_time": "9:15:50", "remaining_time": "15:49:26"}
|
39 |
+
{"current_steps": 380, "total_steps": 1002, "loss": 0.5483, "learning_rate": 5e-06, "epoch": 1.137511693171188, "percentage": 37.92, "elapsed_time": "9:30:34", "remaining_time": "15:33:55"}
|
40 |
+
{"current_steps": 390, "total_steps": 1002, "loss": 0.55, "learning_rate": 5e-06, "epoch": 1.167446211412535, "percentage": 38.92, "elapsed_time": "9:45:17", "remaining_time": "15:18:27"}
|
41 |
+
{"current_steps": 400, "total_steps": 1002, "loss": 0.55, "learning_rate": 5e-06, "epoch": 1.197380729653882, "percentage": 39.92, "elapsed_time": "10:00:04", "remaining_time": "15:03:06"}
|
42 |
+
{"current_steps": 410, "total_steps": 1002, "loss": 0.5524, "learning_rate": 5e-06, "epoch": 1.2273152478952292, "percentage": 40.92, "elapsed_time": "10:14:51", "remaining_time": "14:47:47"}
|
43 |
+
{"current_steps": 420, "total_steps": 1002, "loss": 0.5567, "learning_rate": 5e-06, "epoch": 1.2572497661365762, "percentage": 41.92, "elapsed_time": "10:29:34", "remaining_time": "14:32:24"}
|
44 |
+
{"current_steps": 430, "total_steps": 1002, "loss": 0.5513, "learning_rate": 5e-06, "epoch": 1.2871842843779233, "percentage": 42.91, "elapsed_time": "10:44:18", "remaining_time": "14:17:04"}
|
45 |
+
{"current_steps": 440, "total_steps": 1002, "loss": 0.5533, "learning_rate": 5e-06, "epoch": 1.3171188026192704, "percentage": 43.91, "elapsed_time": "10:59:01", "remaining_time": "14:01:45"}
|
46 |
+
{"current_steps": 450, "total_steps": 1002, "loss": 0.5474, "learning_rate": 5e-06, "epoch": 1.3470533208606175, "percentage": 44.91, "elapsed_time": "11:13:47", "remaining_time": "13:46:31"}
|
47 |
+
{"current_steps": 460, "total_steps": 1002, "loss": 0.5579, "learning_rate": 5e-06, "epoch": 1.3769878391019645, "percentage": 45.91, "elapsed_time": "11:28:31", "remaining_time": "13:31:15"}
|
48 |
+
{"current_steps": 470, "total_steps": 1002, "loss": 0.5571, "learning_rate": 5e-06, "epoch": 1.4069223573433116, "percentage": 46.91, "elapsed_time": "11:43:16", "remaining_time": "13:16:02"}
|
49 |
+
{"current_steps": 480, "total_steps": 1002, "loss": 0.5591, "learning_rate": 5e-06, "epoch": 1.4368568755846587, "percentage": 47.9, "elapsed_time": "11:57:59", "remaining_time": "13:00:49"}
|
50 |
+
{"current_steps": 490, "total_steps": 1002, "loss": 0.5585, "learning_rate": 5e-06, "epoch": 1.4667913938260055, "percentage": 48.9, "elapsed_time": "12:12:45", "remaining_time": "12:45:39"}
|
51 |
+
{"current_steps": 500, "total_steps": 1002, "loss": 0.5546, "learning_rate": 5e-06, "epoch": 1.4967259120673526, "percentage": 49.9, "elapsed_time": "12:27:32", "remaining_time": "12:30:32"}
|
52 |
+
{"current_steps": 510, "total_steps": 1002, "loss": 0.5577, "learning_rate": 5e-06, "epoch": 1.5266604303086997, "percentage": 50.9, "elapsed_time": "12:42:15", "remaining_time": "12:15:21"}
|
53 |
+
{"current_steps": 520, "total_steps": 1002, "loss": 0.5555, "learning_rate": 5e-06, "epoch": 1.5565949485500468, "percentage": 51.9, "elapsed_time": "12:56:58", "remaining_time": "12:00:11"}
|
54 |
+
{"current_steps": 530, "total_steps": 1002, "loss": 0.5561, "learning_rate": 5e-06, "epoch": 1.5865294667913938, "percentage": 52.89, "elapsed_time": "13:11:45", "remaining_time": "11:45:06"}
|
55 |
+
{"current_steps": 540, "total_steps": 1002, "loss": 0.5599, "learning_rate": 5e-06, "epoch": 1.616463985032741, "percentage": 53.89, "elapsed_time": "13:26:31", "remaining_time": "11:30:01"}
|
56 |
+
{"current_steps": 550, "total_steps": 1002, "loss": 0.5592, "learning_rate": 5e-06, "epoch": 1.646398503274088, "percentage": 54.89, "elapsed_time": "13:41:18", "remaining_time": "11:14:57"}
|
57 |
+
{"current_steps": 560, "total_steps": 1002, "loss": 0.5498, "learning_rate": 5e-06, "epoch": 1.6763330215154348, "percentage": 55.89, "elapsed_time": "13:56:04", "remaining_time": "10:59:53"}
|
58 |
+
{"current_steps": 570, "total_steps": 1002, "loss": 0.5518, "learning_rate": 5e-06, "epoch": 1.706267539756782, "percentage": 56.89, "elapsed_time": "14:10:50", "remaining_time": "10:44:50"}
|
59 |
+
{"current_steps": 580, "total_steps": 1002, "loss": 0.5529, "learning_rate": 5e-06, "epoch": 1.736202057998129, "percentage": 57.88, "elapsed_time": "14:25:35", "remaining_time": "10:29:47"}
|
60 |
+
{"current_steps": 590, "total_steps": 1002, "loss": 0.5558, "learning_rate": 5e-06, "epoch": 1.766136576239476, "percentage": 58.88, "elapsed_time": "14:40:21", "remaining_time": "10:14:45"}
|
61 |
+
{"current_steps": 600, "total_steps": 1002, "loss": 0.5564, "learning_rate": 5e-06, "epoch": 1.7960710944808231, "percentage": 59.88, "elapsed_time": "14:55:06", "remaining_time": "9:59:43"}
|
62 |
+
{"current_steps": 610, "total_steps": 1002, "loss": 0.5543, "learning_rate": 5e-06, "epoch": 1.8260056127221702, "percentage": 60.88, "elapsed_time": "15:09:52", "remaining_time": "9:44:42"}
|
63 |
+
{"current_steps": 620, "total_steps": 1002, "loss": 0.5524, "learning_rate": 5e-06, "epoch": 1.8559401309635173, "percentage": 61.88, "elapsed_time": "15:24:39", "remaining_time": "9:29:42"}
|
64 |
+
{"current_steps": 630, "total_steps": 1002, "loss": 0.5543, "learning_rate": 5e-06, "epoch": 1.8858746492048644, "percentage": 62.87, "elapsed_time": "15:39:26", "remaining_time": "9:14:42"}
|
65 |
+
{"current_steps": 640, "total_steps": 1002, "loss": 0.556, "learning_rate": 5e-06, "epoch": 1.9158091674462114, "percentage": 63.87, "elapsed_time": "15:54:12", "remaining_time": "8:59:43"}
|
66 |
+
{"current_steps": 650, "total_steps": 1002, "loss": 0.5541, "learning_rate": 5e-06, "epoch": 1.9457436856875585, "percentage": 64.87, "elapsed_time": "16:08:55", "remaining_time": "8:44:42"}
|
67 |
+
{"current_steps": 660, "total_steps": 1002, "loss": 0.559, "learning_rate": 5e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:23:42", "remaining_time": "8:29:44"}
|
68 |
+
{"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6155872941017151, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:44:15", "remaining_time": "8:22:07"}
|
69 |
+
{"current_steps": 670, "total_steps": 1002, "loss": 0.6011, "learning_rate": 5e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:48:25", "remaining_time": "8:19:41"}
|