sedrickkeh
commited on
Commit
•
57b2999
1
Parent(s):
753d753
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 sha256:148095ef68c8274c73d683bf79a6cb09db892bf600bf7624082408e1ff9789da
|
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 sha256:0bc23a8a1b35ba3ac6453a4a1e50c6a4531f5cf7bd9ccc2ac33cbdf3aa9b7a31
|
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:e3a5625495c997c43878198e85bbdff0690e29913ac1c0b00af4dae1f11acd41
|
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 sha256:232a9ad23db4319b2aeddd84edeefbf1490221e278b6ff268fe9c5a9fd18de70
|
3 |
size 3670322200
|
trainer_log.jsonl
CHANGED
@@ -32,3 +32,38 @@
|
|
32 |
{"current_steps": 320, "total_steps": 1002, "loss": 0.6153, "learning_rate": 5e-06, "epoch": 0.9579045837231057, "percentage": 31.94, "elapsed_time": "7:51:15", "remaining_time": "16:44:23"}
|
33 |
{"current_steps": 330, "total_steps": 1002, "loss": 0.6082, "learning_rate": 5e-06, "epoch": 0.9878391019644528, "percentage": 32.93, "elapsed_time": "8:06:00", "remaining_time": "16:29:40"}
|
34 |
{"current_steps": 334, "total_steps": 1002, "eval_loss": 0.6191971302032471, "epoch": 0.9998129092609915, "percentage": 33.33, "elapsed_time": "8:20:30", "remaining_time": "16:41:01"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
{"current_steps": 320, "total_steps": 1002, "loss": 0.6153, "learning_rate": 5e-06, "epoch": 0.9579045837231057, "percentage": 31.94, "elapsed_time": "7:51:15", "remaining_time": "16:44:23"}
|
33 |
{"current_steps": 330, "total_steps": 1002, "loss": 0.6082, "learning_rate": 5e-06, "epoch": 0.9878391019644528, "percentage": 32.93, "elapsed_time": "8:06:00", "remaining_time": "16:29:40"}
|
34 |
{"current_steps": 334, "total_steps": 1002, "eval_loss": 0.6191971302032471, "epoch": 0.9998129092609915, "percentage": 33.33, "elapsed_time": "8:20:30", "remaining_time": "16:41:01"}
|
35 |
+
{"current_steps": 340, "total_steps": 1002, "loss": 0.6383, "learning_rate": 5e-06, "epoch": 1.0177736202057999, "percentage": 33.93, "elapsed_time": "8:30:33", "remaining_time": "16:34:04"}
|
36 |
+
{"current_steps": 350, "total_steps": 1002, "loss": 0.5521, "learning_rate": 5e-06, "epoch": 1.047708138447147, "percentage": 34.93, "elapsed_time": "8:45:18", "remaining_time": "16:18:34"}
|
37 |
+
{"current_steps": 360, "total_steps": 1002, "loss": 0.5476, "learning_rate": 5e-06, "epoch": 1.077642656688494, "percentage": 35.93, "elapsed_time": "9:00:04", "remaining_time": "16:03:07"}
|
38 |
+
{"current_steps": 370, "total_steps": 1002, "loss": 0.5479, "learning_rate": 5e-06, "epoch": 1.1075771749298409, "percentage": 36.93, "elapsed_time": "9:14:51", "remaining_time": "15:47:44"}
|
39 |
+
{"current_steps": 380, "total_steps": 1002, "loss": 0.5482, "learning_rate": 5e-06, "epoch": 1.137511693171188, "percentage": 37.92, "elapsed_time": "9:29:36", "remaining_time": "15:32:20"}
|
40 |
+
{"current_steps": 390, "total_steps": 1002, "loss": 0.5497, "learning_rate": 5e-06, "epoch": 1.167446211412535, "percentage": 38.92, "elapsed_time": "9:44:19", "remaining_time": "15:16:55"}
|
41 |
+
{"current_steps": 400, "total_steps": 1002, "loss": 0.5498, "learning_rate": 5e-06, "epoch": 1.197380729653882, "percentage": 39.92, "elapsed_time": "9:59:02", "remaining_time": "15:01:33"}
|
42 |
+
{"current_steps": 410, "total_steps": 1002, "loss": 0.5522, "learning_rate": 5e-06, "epoch": 1.2273152478952292, "percentage": 40.92, "elapsed_time": "10:13:48", "remaining_time": "14:46:16"}
|
43 |
+
{"current_steps": 420, "total_steps": 1002, "loss": 0.5565, "learning_rate": 5e-06, "epoch": 1.2572497661365762, "percentage": 41.92, "elapsed_time": "10:28:33", "remaining_time": "14:31:00"}
|
44 |
+
{"current_steps": 430, "total_steps": 1002, "loss": 0.5512, "learning_rate": 5e-06, "epoch": 1.2871842843779233, "percentage": 42.91, "elapsed_time": "10:43:19", "remaining_time": "14:15:46"}
|
45 |
+
{"current_steps": 440, "total_steps": 1002, "loss": 0.5532, "learning_rate": 5e-06, "epoch": 1.3171188026192704, "percentage": 43.91, "elapsed_time": "10:58:05", "remaining_time": "14:00:33"}
|
46 |
+
{"current_steps": 450, "total_steps": 1002, "loss": 0.5472, "learning_rate": 5e-06, "epoch": 1.3470533208606175, "percentage": 44.91, "elapsed_time": "11:12:51", "remaining_time": "13:45:22"}
|
47 |
+
{"current_steps": 460, "total_steps": 1002, "loss": 0.5579, "learning_rate": 5e-06, "epoch": 1.3769878391019645, "percentage": 45.91, "elapsed_time": "11:27:36", "remaining_time": "13:30:10"}
|
48 |
+
{"current_steps": 470, "total_steps": 1002, "loss": 0.5572, "learning_rate": 5e-06, "epoch": 1.4069223573433116, "percentage": 46.91, "elapsed_time": "11:42:19", "remaining_time": "13:14:58"}
|
49 |
+
{"current_steps": 480, "total_steps": 1002, "loss": 0.5592, "learning_rate": 5e-06, "epoch": 1.4368568755846587, "percentage": 47.9, "elapsed_time": "11:57:04", "remaining_time": "12:59:49"}
|
50 |
+
{"current_steps": 490, "total_steps": 1002, "loss": 0.5585, "learning_rate": 5e-06, "epoch": 1.4667913938260055, "percentage": 48.9, "elapsed_time": "12:11:49", "remaining_time": "12:44:40"}
|
51 |
+
{"current_steps": 500, "total_steps": 1002, "loss": 0.5548, "learning_rate": 5e-06, "epoch": 1.4967259120673526, "percentage": 49.9, "elapsed_time": "12:26:32", "remaining_time": "12:29:31"}
|
52 |
+
{"current_steps": 510, "total_steps": 1002, "loss": 0.5576, "learning_rate": 5e-06, "epoch": 1.5266604303086997, "percentage": 50.9, "elapsed_time": "12:41:15", "remaining_time": "12:14:23"}
|
53 |
+
{"current_steps": 520, "total_steps": 1002, "loss": 0.5555, "learning_rate": 5e-06, "epoch": 1.5565949485500468, "percentage": 51.9, "elapsed_time": "12:56:00", "remaining_time": "11:59:17"}
|
54 |
+
{"current_steps": 530, "total_steps": 1002, "loss": 0.556, "learning_rate": 5e-06, "epoch": 1.5865294667913938, "percentage": 52.89, "elapsed_time": "13:10:45", "remaining_time": "11:44:13"}
|
55 |
+
{"current_steps": 540, "total_steps": 1002, "loss": 0.5597, "learning_rate": 5e-06, "epoch": 1.616463985032741, "percentage": 53.89, "elapsed_time": "13:25:31", "remaining_time": "11:29:10"}
|
56 |
+
{"current_steps": 550, "total_steps": 1002, "loss": 0.559, "learning_rate": 5e-06, "epoch": 1.646398503274088, "percentage": 54.89, "elapsed_time": "13:40:14", "remaining_time": "11:14:05"}
|
57 |
+
{"current_steps": 560, "total_steps": 1002, "loss": 0.5497, "learning_rate": 5e-06, "epoch": 1.6763330215154348, "percentage": 55.89, "elapsed_time": "13:55:00", "remaining_time": "10:59:03"}
|
58 |
+
{"current_steps": 570, "total_steps": 1002, "loss": 0.5515, "learning_rate": 5e-06, "epoch": 1.706267539756782, "percentage": 56.89, "elapsed_time": "14:09:44", "remaining_time": "10:44:00"}
|
59 |
+
{"current_steps": 580, "total_steps": 1002, "loss": 0.5528, "learning_rate": 5e-06, "epoch": 1.736202057998129, "percentage": 57.88, "elapsed_time": "14:24:30", "remaining_time": "10:29:00"}
|
60 |
+
{"current_steps": 590, "total_steps": 1002, "loss": 0.5557, "learning_rate": 5e-06, "epoch": 1.766136576239476, "percentage": 58.88, "elapsed_time": "14:39:15", "remaining_time": "10:13:59"}
|
61 |
+
{"current_steps": 600, "total_steps": 1002, "loss": 0.5563, "learning_rate": 5e-06, "epoch": 1.7960710944808231, "percentage": 59.88, "elapsed_time": "14:54:00", "remaining_time": "9:58:59"}
|
62 |
+
{"current_steps": 610, "total_steps": 1002, "loss": 0.5542, "learning_rate": 5e-06, "epoch": 1.8260056127221702, "percentage": 60.88, "elapsed_time": "15:08:43", "remaining_time": "9:43:58"}
|
63 |
+
{"current_steps": 620, "total_steps": 1002, "loss": 0.5522, "learning_rate": 5e-06, "epoch": 1.8559401309635173, "percentage": 61.88, "elapsed_time": "15:23:28", "remaining_time": "9:28:58"}
|
64 |
+
{"current_steps": 630, "total_steps": 1002, "loss": 0.5541, "learning_rate": 5e-06, "epoch": 1.8858746492048644, "percentage": 62.87, "elapsed_time": "15:38:14", "remaining_time": "9:14:00"}
|
65 |
+
{"current_steps": 640, "total_steps": 1002, "loss": 0.5555, "learning_rate": 5e-06, "epoch": 1.9158091674462114, "percentage": 63.87, "elapsed_time": "15:53:00", "remaining_time": "8:59:02"}
|
66 |
+
{"current_steps": 650, "total_steps": 1002, "loss": 0.5538, "learning_rate": 5e-06, "epoch": 1.9457436856875585, "percentage": 64.87, "elapsed_time": "16:07:46", "remaining_time": "8:44:05"}
|
67 |
+
{"current_steps": 660, "total_steps": 1002, "loss": 0.5586, "learning_rate": 5e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:22:31", "remaining_time": "8:29:07"}
|
68 |
+
{"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6157492399215698, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:43:01", "remaining_time": "8:21:30"}
|
69 |
+
{"current_steps": 670, "total_steps": 1002, "loss": 0.6006, "learning_rate": 5e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:47:10", "remaining_time": "8:19:04"}
|