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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d889bde9824b885949fca79df5cc2c06dd92372d312bb8c2b73e0a8e5d8a7eb
|
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:b60c1c0aaeb6f9ddbde99fcb2d0e90856d435713398b1dc652e86b552bbbd44a
|
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:ad4c1d3c6a04b9e03b68ae4fe27514136d96afba921d74c3b1c1c6cb856a5436
|
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:a2f7ee762c2f99a9c8dd7d4fd1c82dbec258322c68c3edf75add10c7bebaac95
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -26,3 +26,32 @@
|
|
26 |
{"current_steps": 260, "total_steps": 816, "loss": 0.7457, "lr": 5e-06, "epoch": 0.9532538955087076, "percentage": 31.86, "elapsed_time": "1:13:02", "remaining_time": "2:36:12"}
|
27 |
{"current_steps": 270, "total_steps": 816, "loss": 0.7434, "lr": 5e-06, "epoch": 0.9899175068744271, "percentage": 33.09, "elapsed_time": "1:15:50", "remaining_time": "2:33:21"}
|
28 |
{"current_steps": 272, "total_steps": 816, "eval_loss": 0.743977963924408, "epoch": 0.997250229147571, "percentage": 33.33, "elapsed_time": "1:18:04", "remaining_time": "2:36:08"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
{"current_steps": 260, "total_steps": 816, "loss": 0.7457, "lr": 5e-06, "epoch": 0.9532538955087076, "percentage": 31.86, "elapsed_time": "1:13:02", "remaining_time": "2:36:12"}
|
27 |
{"current_steps": 270, "total_steps": 816, "loss": 0.7434, "lr": 5e-06, "epoch": 0.9899175068744271, "percentage": 33.09, "elapsed_time": "1:15:50", "remaining_time": "2:33:21"}
|
28 |
{"current_steps": 272, "total_steps": 816, "eval_loss": 0.743977963924408, "epoch": 0.997250229147571, "percentage": 33.33, "elapsed_time": "1:18:04", "remaining_time": "2:36:08"}
|
29 |
+
{"current_steps": 280, "total_steps": 816, "loss": 0.7593, "lr": 5e-06, "epoch": 1.0284142988084326, "percentage": 34.31, "elapsed_time": "1:21:12", "remaining_time": "2:35:26"}
|
30 |
+
{"current_steps": 290, "total_steps": 816, "loss": 0.6885, "lr": 5e-06, "epoch": 1.065077910174152, "percentage": 35.54, "elapsed_time": "1:23:58", "remaining_time": "2:32:18"}
|
31 |
+
{"current_steps": 300, "total_steps": 816, "loss": 0.6893, "lr": 5e-06, "epoch": 1.1017415215398716, "percentage": 36.76, "elapsed_time": "1:26:45", "remaining_time": "2:29:13"}
|
32 |
+
{"current_steps": 310, "total_steps": 816, "loss": 0.6868, "lr": 5e-06, "epoch": 1.138405132905591, "percentage": 37.99, "elapsed_time": "1:29:33", "remaining_time": "2:26:10"}
|
33 |
+
{"current_steps": 320, "total_steps": 816, "loss": 0.6885, "lr": 5e-06, "epoch": 1.1750687442713108, "percentage": 39.22, "elapsed_time": "1:32:21", "remaining_time": "2:23:09"}
|
34 |
+
{"current_steps": 330, "total_steps": 816, "loss": 0.6871, "lr": 5e-06, "epoch": 1.2117323556370303, "percentage": 40.44, "elapsed_time": "1:35:09", "remaining_time": "2:20:08"}
|
35 |
+
{"current_steps": 340, "total_steps": 816, "loss": 0.6935, "lr": 5e-06, "epoch": 1.2483959670027498, "percentage": 41.67, "elapsed_time": "1:37:58", "remaining_time": "2:17:09"}
|
36 |
+
{"current_steps": 350, "total_steps": 816, "loss": 0.6943, "lr": 5e-06, "epoch": 1.2850595783684693, "percentage": 42.89, "elapsed_time": "1:40:44", "remaining_time": "2:14:08"}
|
37 |
+
{"current_steps": 360, "total_steps": 816, "loss": 0.6938, "lr": 5e-06, "epoch": 1.3217231897341888, "percentage": 44.12, "elapsed_time": "1:43:31", "remaining_time": "2:11:07"}
|
38 |
+
{"current_steps": 370, "total_steps": 816, "loss": 0.6856, "lr": 5e-06, "epoch": 1.3583868010999083, "percentage": 45.34, "elapsed_time": "1:46:16", "remaining_time": "2:08:05"}
|
39 |
+
{"current_steps": 380, "total_steps": 816, "loss": 0.69, "lr": 5e-06, "epoch": 1.3950504124656278, "percentage": 46.57, "elapsed_time": "1:49:04", "remaining_time": "2:05:08"}
|
40 |
+
{"current_steps": 390, "total_steps": 816, "loss": 0.682, "lr": 5e-06, "epoch": 1.4317140238313475, "percentage": 47.79, "elapsed_time": "1:51:52", "remaining_time": "2:02:11"}
|
41 |
+
{"current_steps": 400, "total_steps": 816, "loss": 0.6917, "lr": 5e-06, "epoch": 1.468377635197067, "percentage": 49.02, "elapsed_time": "1:54:39", "remaining_time": "1:59:14"}
|
42 |
+
{"current_steps": 410, "total_steps": 816, "loss": 0.6871, "lr": 5e-06, "epoch": 1.5050412465627865, "percentage": 50.25, "elapsed_time": "1:57:26", "remaining_time": "1:56:17"}
|
43 |
+
{"current_steps": 420, "total_steps": 816, "loss": 0.6829, "lr": 5e-06, "epoch": 1.541704857928506, "percentage": 51.47, "elapsed_time": "2:00:12", "remaining_time": "1:53:20"}
|
44 |
+
{"current_steps": 430, "total_steps": 816, "loss": 0.6824, "lr": 5e-06, "epoch": 1.5783684692942255, "percentage": 52.7, "elapsed_time": "2:03:00", "remaining_time": "1:50:24"}
|
45 |
+
{"current_steps": 440, "total_steps": 816, "loss": 0.6822, "lr": 5e-06, "epoch": 1.615032080659945, "percentage": 53.92, "elapsed_time": "2:05:47", "remaining_time": "1:47:30"}
|
46 |
+
{"current_steps": 450, "total_steps": 816, "loss": 0.6879, "lr": 5e-06, "epoch": 1.6516956920256645, "percentage": 55.15, "elapsed_time": "2:08:35", "remaining_time": "1:44:35"}
|
47 |
+
{"current_steps": 460, "total_steps": 816, "loss": 0.6804, "lr": 5e-06, "epoch": 1.6883593033913842, "percentage": 56.37, "elapsed_time": "2:11:22", "remaining_time": "1:41:40"}
|
48 |
+
{"current_steps": 470, "total_steps": 816, "loss": 0.686, "lr": 5e-06, "epoch": 1.7250229147571035, "percentage": 57.6, "elapsed_time": "2:14:08", "remaining_time": "1:38:45"}
|
49 |
+
{"current_steps": 480, "total_steps": 816, "loss": 0.6856, "lr": 5e-06, "epoch": 1.7616865261228232, "percentage": 58.82, "elapsed_time": "2:16:55", "remaining_time": "1:35:51"}
|
50 |
+
{"current_steps": 490, "total_steps": 816, "loss": 0.6814, "lr": 5e-06, "epoch": 1.7983501374885427, "percentage": 60.05, "elapsed_time": "2:19:42", "remaining_time": "1:32:57"}
|
51 |
+
{"current_steps": 500, "total_steps": 816, "loss": 0.6855, "lr": 5e-06, "epoch": 1.8350137488542622, "percentage": 61.27, "elapsed_time": "2:22:31", "remaining_time": "1:30:04"}
|
52 |
+
{"current_steps": 510, "total_steps": 816, "loss": 0.6875, "lr": 5e-06, "epoch": 1.8716773602199817, "percentage": 62.5, "elapsed_time": "2:25:17", "remaining_time": "1:27:10"}
|
53 |
+
{"current_steps": 520, "total_steps": 816, "loss": 0.6856, "lr": 5e-06, "epoch": 1.9083409715857012, "percentage": 63.73, "elapsed_time": "2:28:05", "remaining_time": "1:24:18"}
|
54 |
+
{"current_steps": 530, "total_steps": 816, "loss": 0.6841, "lr": 5e-06, "epoch": 1.9450045829514209, "percentage": 64.95, "elapsed_time": "2:30:54", "remaining_time": "1:21:26"}
|
55 |
+
{"current_steps": 540, "total_steps": 816, "loss": 0.6845, "lr": 5e-06, "epoch": 1.9816681943171401, "percentage": 66.18, "elapsed_time": "2:33:43", "remaining_time": "1:18:34"}
|
56 |
+
{"current_steps": 544, "total_steps": 816, "eval_loss": 0.7305116057395935, "epoch": 1.996333638863428, "percentage": 66.67, "elapsed_time": "2:36:33", "remaining_time": "1:18:16"}
|
57 |
+
{"current_steps": 550, "total_steps": 816, "loss": 0.707, "lr": 5e-06, "epoch": 2.020164986251146, "percentage": 67.4, "elapsed_time": "2:39:11", "remaining_time": "1:16:59"}
|