Training in progress, step 1000
Browse files- model.safetensors +1 -1
- trainer_log.jsonl +104 -104
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3554214752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:468bf692036f0c3cb6e76cca972ed38ceb470465ffc06e132ad2bd1e01d45b89
|
3 |
size 3554214752
|
trainer_log.jsonl
CHANGED
@@ -1,104 +1,104 @@
|
|
1 |
-
{"current_steps": 10, "total_steps": 37092, "loss": 0.
|
2 |
-
{"current_steps": 20, "total_steps": 37092, "loss": 0.6618, "lr": 5.3908355795148254e-08, "epoch": 0.0010783487784330244, "percentage": 0.05, "elapsed_time": "0:01:03", "remaining_time": "1 day, 8:
|
3 |
-
{"current_steps": 30, "total_steps": 37092, "loss": 0.659, "lr": 8.086253369272238e-08, "epoch": 0.0016175231676495367, "percentage": 0.08, "elapsed_time": "0:01:32", "remaining_time": "1 day, 7:
|
4 |
-
{"current_steps": 40, "total_steps": 37092, "loss": 0.663, "lr": 1.0781671159029651e-07, "epoch": 0.002156697556866049, "percentage": 0.11, "elapsed_time": "0:02:01", "remaining_time": "1 day, 7:
|
5 |
-
{"current_steps": 50, "total_steps": 37092, "loss": 0.
|
6 |
-
{"current_steps": 60, "total_steps": 37092, "loss": 0.
|
7 |
-
{"current_steps": 70, "total_steps": 37092, "loss": 0.6301, "lr": 1.886792452830189e-07, "epoch": 0.0037742207245155856, "percentage": 0.19, "elapsed_time": "0:03:29", "remaining_time": "1 day, 6:
|
8 |
-
{"current_steps": 80, "total_steps": 37092, "loss": 0.
|
9 |
-
{"current_steps": 90, "total_steps": 37092, "loss": 0.
|
10 |
-
{"current_steps": 100, "total_steps": 37092, "loss": 0.
|
11 |
-
{"current_steps": 110, "total_steps": 37092, "loss": 0.
|
12 |
-
{"current_steps": 120, "total_steps": 37092, "loss": 0.
|
13 |
-
{"current_steps": 130, "total_steps": 37092, "loss": 0.3684, "lr": 3.504043126684636e-07, "epoch": 0.007009267059814659, "percentage": 0.35, "elapsed_time": "0:06:
|
14 |
-
{"current_steps": 140, "total_steps": 37092, "loss": 0.
|
15 |
-
{"current_steps": 150, "total_steps": 37092, "loss": 0.
|
16 |
-
{"current_steps": 160, "total_steps": 37092, "loss": 0.29, "lr": 4.3126684636118604e-07, "epoch": 0.008626790227464196, "percentage": 0.43, "elapsed_time": "0:08:
|
17 |
-
{"current_steps": 170, "total_steps": 37092, "loss": 0.2575, "lr": 4.5822102425876014e-07, "epoch": 0.009165964616680707, "percentage": 0.46, "elapsed_time": "0:08:
|
18 |
-
{"current_steps": 180, "total_steps": 37092, "loss": 0.
|
19 |
-
{"current_steps": 190, "total_steps": 37092, "loss": 0.
|
20 |
-
{"current_steps": 200, "total_steps": 37092, "loss": 0.
|
21 |
-
{"current_steps": 210, "total_steps": 37092, "loss": 0.2396, "lr": 5.660377358490567e-07, "epoch": 0.011322662173546756, "percentage": 0.57, "elapsed_time": "0:10:
|
22 |
-
{"current_steps": 220, "total_steps": 37092, "loss": 0.2372, "lr": 5.929919137466308e-07, "epoch": 0.011861836562763269, "percentage": 0.59, "elapsed_time": "0:11:
|
23 |
-
{"current_steps": 230, "total_steps": 37092, "loss": 0.
|
24 |
-
{"current_steps": 240, "total_steps": 37092, "loss": 0.
|
25 |
-
{"current_steps": 250, "total_steps": 37092, "loss": 0.2042, "lr": 6.738544474393531e-07, "epoch": 0.013479359730412805, "percentage": 0.67, "elapsed_time": "0:12:
|
26 |
-
{"current_steps": 260, "total_steps": 37092, "loss": 0.2052, "lr": 7.008086253369272e-07, "epoch": 0.014018534119629318, "percentage": 0.7, "elapsed_time": "0:13:
|
27 |
-
{"current_steps": 270, "total_steps": 37092, "loss": 0.1883, "lr": 7.277628032345015e-07, "epoch": 0.014557708508845829, "percentage": 0.73, "elapsed_time": "0:13:
|
28 |
-
{"current_steps": 280, "total_steps": 37092, "loss": 0.
|
29 |
-
{"current_steps": 290, "total_steps": 37092, "loss": 0.
|
30 |
-
{"current_steps": 300, "total_steps": 37092, "loss": 0.
|
31 |
-
{"current_steps": 310, "total_steps": 37092, "loss": 0.171, "lr": 8.355795148247979e-07, "epoch": 0.016714406065711878, "percentage": 0.84, "elapsed_time": "0:15:
|
32 |
-
{"current_steps": 320, "total_steps": 37092, "loss": 0.
|
33 |
-
{"current_steps": 330, "total_steps": 37092, "loss": 0.1666, "lr": 8.894878706199461e-07, "epoch": 0.017792754844144904, "percentage": 0.89, "elapsed_time": "0:16:
|
34 |
-
{"current_steps": 340, "total_steps": 37092, "loss": 0.1576, "lr": 9.164420485175203e-07, "epoch": 0.018331929233361414, "percentage": 0.92, "elapsed_time": "0:17:
|
35 |
-
{"current_steps": 350, "total_steps": 37092, "loss": 0.
|
36 |
-
{"current_steps": 360, "total_steps": 37092, "loss": 0.
|
37 |
-
{"current_steps": 370, "total_steps": 37092, "loss": 0.1528, "lr": 9.973045822102428e-07, "epoch": 0.019949452401010953, "percentage": 1.0, "elapsed_time": "0:18:
|
38 |
-
{"current_steps": 380, "total_steps": 37092, "loss": 0.153, "lr": 1.0242587601078167e-06, "epoch": 0.020488626790227463, "percentage": 1.02, "elapsed_time": "0:19:
|
39 |
-
{"current_steps": 390, "total_steps": 37092, "loss": 0.
|
40 |
-
{"current_steps": 400, "total_steps": 37092, "loss": 0.1461, "lr": 1.078167115902965e-06, "epoch": 0.02156697556866049, "percentage": 1.08, "elapsed_time": "0:20:
|
41 |
-
{"current_steps": 410, "total_steps": 37092, "loss": 0.1487, "lr": 1.1051212938005392e-06, "epoch": 0.022106149957877002, "percentage": 1.11, "elapsed_time": "0:20:
|
42 |
-
{"current_steps": 420, "total_steps": 37092, "loss": 0.1468, "lr": 1.1320754716981133e-06, "epoch": 0.02264532434709351, "percentage": 1.13, "elapsed_time": "0:21:
|
43 |
-
{"current_steps": 430, "total_steps": 37092, "loss": 0.1579, "lr": 1.1590296495956873e-06, "epoch": 0.023184498736310025, "percentage": 1.16, "elapsed_time": "0:21:
|
44 |
-
{"current_steps": 440, "total_steps": 37092, "loss": 0.
|
45 |
-
{"current_steps": 450, "total_steps": 37092, "loss": 0.
|
46 |
-
{"current_steps": 460, "total_steps": 37092, "loss": 0.156, "lr": 1.2398921832884097e-06, "epoch": 0.02480202190395956, "percentage": 1.24, "elapsed_time": "0:23:
|
47 |
-
{"current_steps": 470, "total_steps": 37092, "loss": 0.
|
48 |
-
{"current_steps": 480, "total_steps": 37092, "loss": 0.
|
49 |
-
{"current_steps": 490, "total_steps": 37092, "loss": 0.1436, "lr": 1.3207547169811322e-06, "epoch": 0.0264195450716091, "percentage": 1.32, "elapsed_time": "0:24:
|
50 |
-
{"current_steps": 500, "total_steps": 37092, "loss": 0.1347, "lr": 1.3477088948787062e-06, "epoch": 0.02695871946082561, "percentage": 1.35, "elapsed_time": "0:25:
|
51 |
-
{"current_steps": 510, "total_steps": 37092, "loss": 0.1417, "lr": 1.3746630727762805e-06, "epoch": 0.027497893850042122, "percentage": 1.37, "elapsed_time": "0:25:
|
52 |
-
{"current_steps": 520, "total_steps": 37092, "loss": 0.
|
53 |
-
{"current_steps": 530, "total_steps": 37092, "loss": 0.1274, "lr": 1.4285714285714286e-06, "epoch": 0.02857624262847515, "percentage": 1.43, "elapsed_time": "0:26:
|
54 |
-
{"current_steps": 540, "total_steps": 37092, "loss": 0.
|
55 |
-
{"current_steps": 550, "total_steps": 37092, "loss": 0.125, "lr": 1.482479784366577e-06, "epoch": 0.02965459140690817, "percentage": 1.48, "elapsed_time": "0:27:
|
56 |
-
{"current_steps": 560, "total_steps": 37092, "loss": 0.1288, "lr": 1.509433962264151e-06, "epoch": 0.030193765796124684, "percentage": 1.51, "elapsed_time": "0:28:
|
57 |
-
{"current_steps": 570, "total_steps": 37092, "loss": 0.
|
58 |
-
{"current_steps": 580, "total_steps": 37092, "loss": 0.1317, "lr": 1.5633423180592994e-06, "epoch": 0.03127211457455771, "percentage": 1.56, "elapsed_time": "0:29:
|
59 |
-
{"current_steps": 590, "total_steps": 37092, "loss": 0.
|
60 |
-
{"current_steps": 600, "total_steps": 37092, "loss": 0.1239, "lr": 1.6172506738544475e-06, "epoch": 0.03235046335299073, "percentage": 1.62, "elapsed_time": "0:30:
|
61 |
-
{"current_steps": 610, "total_steps": 37092, "loss": 0.1349, "lr": 1.6442048517520217e-06, "epoch": 0.032889637742207246, "percentage": 1.64, "elapsed_time": "0:
|
62 |
-
{"current_steps": 620, "total_steps": 37092, "loss": 0.
|
63 |
-
{"current_steps": 630, "total_steps": 37092, "loss": 0.
|
64 |
-
{"current_steps": 640, "total_steps": 37092, "loss": 0.1306, "lr": 1.7250673854447441e-06, "epoch": 0.03450716090985678, "percentage": 1.73, "elapsed_time": "0:32:
|
65 |
-
{"current_steps": 650, "total_steps": 37092, "loss": 0.
|
66 |
-
{"current_steps": 660, "total_steps": 37092, "loss": 0.
|
67 |
-
{"current_steps": 670, "total_steps": 37092, "loss": 0.
|
68 |
-
{"current_steps": 680, "total_steps": 37092, "loss": 0.1151, "lr": 1.8328840970350406e-06, "epoch": 0.03666385846672283, "percentage": 1.83, "elapsed_time": "0:34:
|
69 |
-
{"current_steps": 690, "total_steps": 37092, "loss": 0.
|
70 |
-
{"current_steps": 700, "total_steps": 37092, "loss": 0.1173, "lr": 1.8867924528301889e-06, "epoch": 0.037742207245155854, "percentage": 1.89, "elapsed_time": "0:35:
|
71 |
-
{"current_steps": 710, "total_steps": 37092, "loss": 0.104, "lr": 1.913746630727763e-06, "epoch": 0.03828138163437237, "percentage": 1.91, "elapsed_time": "0:36:
|
72 |
-
{"current_steps": 720, "total_steps": 37092, "loss": 0.1097, "lr": 1.940700808625337e-06, "epoch": 0.03882055602358888, "percentage": 1.94, "elapsed_time": "0:36:
|
73 |
-
{"current_steps": 730, "total_steps": 37092, "loss": 0.
|
74 |
-
{"current_steps": 740, "total_steps": 37092, "loss": 0.1295, "lr": 1.9946091644204855e-06, "epoch": 0.039898904802021906, "percentage": 2.0, "elapsed_time": "0:37:
|
75 |
-
{"current_steps": 750, "total_steps": 37092, "loss": 0.
|
76 |
-
{"current_steps": 760, "total_steps": 37092, "loss": 0.
|
77 |
-
{"current_steps": 770, "total_steps": 37092, "loss": 0.
|
78 |
-
{"current_steps": 780, "total_steps": 37092, "loss": 0.1131, "lr": 2.1024258760107817e-06, "epoch": 0.04205560235888795, "percentage": 2.1, "elapsed_time": "0:39:
|
79 |
-
{"current_steps": 790, "total_steps": 37092, "loss": 0.
|
80 |
-
{"current_steps": 800, "total_steps": 37092, "loss": 0.1015, "lr": 2.15633423180593e-06, "epoch": 0.04313395113732098, "percentage": 2.16, "elapsed_time": "0:40:
|
81 |
-
{"current_steps": 810, "total_steps": 37092, "loss": 0.
|
82 |
-
{"current_steps": 820, "total_steps": 37092, "loss": 0.1108, "lr": 2.2102425876010783e-06, "epoch": 0.044212299915754004, "percentage": 2.21, "elapsed_time": "0:41:
|
83 |
-
{"current_steps": 830, "total_steps": 37092, "loss": 0.
|
84 |
-
{"current_steps": 840, "total_steps": 37092, "loss": 0.
|
85 |
-
{"current_steps": 850, "total_steps": 37092, "loss": 0.
|
86 |
-
{"current_steps": 860, "total_steps": 37092, "loss": 0.
|
87 |
-
{"current_steps": 870, "total_steps": 37092, "loss": 0.
|
88 |
-
{"current_steps": 880, "total_steps": 37092, "loss": 0.
|
89 |
-
{"current_steps": 890, "total_steps": 37092, "loss": 0.
|
90 |
-
{"current_steps": 900, "total_steps": 37092, "loss": 0.0927, "lr": 2.4258760107816716e-06, "epoch": 0.0485256950294861, "percentage": 2.43, "elapsed_time": "0:45:
|
91 |
-
{"current_steps": 910, "total_steps": 37092, "loss": 0.
|
92 |
-
{"current_steps": 920, "total_steps": 37092, "loss": 0.
|
93 |
-
{"current_steps": 930, "total_steps": 37092, "loss": 0.
|
94 |
-
{"current_steps": 940, "total_steps": 37092, "loss": 0.
|
95 |
-
{"current_steps": 950, "total_steps": 37092, "loss": 0.0982, "lr": 2.5606469002695424e-06, "epoch": 0.051221566975568664, "percentage": 2.56, "elapsed_time": "0:48:
|
96 |
-
{"current_steps": 960, "total_steps": 37092, "loss": 0.099, "lr": 2.587601078167116e-06, "epoch": 0.05176074136478517, "percentage": 2.59, "elapsed_time": "0:48:
|
97 |
-
{"current_steps": 970, "total_steps": 37092, "loss": 0.
|
98 |
-
{"current_steps": 980, "total_steps": 37092, "loss": 0.
|
99 |
-
{"current_steps": 990, "total_steps": 37092, "loss": 0.
|
100 |
-
{"current_steps": 1000, "total_steps": 37092, "loss": 0.
|
101 |
-
{"current_steps": 1010, "total_steps": 37092, "loss": 0.1017, "lr": 2.722371967654987e-06, "epoch": 0.054456613310867735, "percentage": 2.72, "elapsed_time": "0:
|
102 |
-
{"current_steps": 1020, "total_steps": 37092, "loss": 0.
|
103 |
-
{"current_steps": 1030, "total_steps": 37092, "loss": 0.
|
104 |
-
{"current_steps": 1040, "total_steps": 37092, "loss": 0.0897, "lr": 2.803234501347709e-06, "epoch": 0.05607413647851727, "percentage": 2.8, "elapsed_time": "0:53:
|
|
|
1 |
+
{"current_steps": 10, "total_steps": 37092, "loss": 0.6542, "lr": 2.6954177897574127e-08, "epoch": 0.0005391743892165122, "percentage": 0.03, "elapsed_time": "0:00:28", "remaining_time": "1 day, 5:51:37"}
|
2 |
+
{"current_steps": 20, "total_steps": 37092, "loss": 0.6618, "lr": 5.3908355795148254e-08, "epoch": 0.0010783487784330244, "percentage": 0.05, "elapsed_time": "0:01:03", "remaining_time": "1 day, 8:32:55"}
|
3 |
+
{"current_steps": 30, "total_steps": 37092, "loss": 0.659, "lr": 8.086253369272238e-08, "epoch": 0.0016175231676495367, "percentage": 0.08, "elapsed_time": "0:01:32", "remaining_time": "1 day, 7:54:36"}
|
4 |
+
{"current_steps": 40, "total_steps": 37092, "loss": 0.663, "lr": 1.0781671159029651e-07, "epoch": 0.002156697556866049, "percentage": 0.11, "elapsed_time": "0:02:01", "remaining_time": "1 day, 7:16:32"}
|
5 |
+
{"current_steps": 50, "total_steps": 37092, "loss": 0.6438, "lr": 1.3477088948787063e-07, "epoch": 0.002695871946082561, "percentage": 0.13, "elapsed_time": "0:02:31", "remaining_time": "1 day, 7:08:01"}
|
6 |
+
{"current_steps": 60, "total_steps": 37092, "loss": 0.6421, "lr": 1.6172506738544476e-07, "epoch": 0.0032350463352990733, "percentage": 0.16, "elapsed_time": "0:03:00", "remaining_time": "1 day, 6:56:09"}
|
7 |
+
{"current_steps": 70, "total_steps": 37092, "loss": 0.6301, "lr": 1.886792452830189e-07, "epoch": 0.0037742207245155856, "percentage": 0.19, "elapsed_time": "0:03:29", "remaining_time": "1 day, 6:48:45"}
|
8 |
+
{"current_steps": 80, "total_steps": 37092, "loss": 0.5942, "lr": 2.1563342318059302e-07, "epoch": 0.004313395113732098, "percentage": 0.22, "elapsed_time": "0:03:56", "remaining_time": "1 day, 6:27:19"}
|
9 |
+
{"current_steps": 90, "total_steps": 37092, "loss": 0.5372, "lr": 2.4258760107816715e-07, "epoch": 0.00485256950294861, "percentage": 0.24, "elapsed_time": "0:04:26", "remaining_time": "1 day, 6:28:23"}
|
10 |
+
{"current_steps": 100, "total_steps": 37092, "loss": 0.5219, "lr": 2.6954177897574125e-07, "epoch": 0.005391743892165122, "percentage": 0.27, "elapsed_time": "0:04:54", "remaining_time": "1 day, 6:16:31"}
|
11 |
+
{"current_steps": 110, "total_steps": 37092, "loss": 0.4799, "lr": 2.964959568733154e-07, "epoch": 0.0059309182813816344, "percentage": 0.3, "elapsed_time": "0:05:23", "remaining_time": "1 day, 6:12:56"}
|
12 |
+
{"current_steps": 120, "total_steps": 37092, "loss": 0.4013, "lr": 3.234501347708895e-07, "epoch": 0.006470092670598147, "percentage": 0.32, "elapsed_time": "0:05:55", "remaining_time": "1 day, 6:25:25"}
|
13 |
+
{"current_steps": 130, "total_steps": 37092, "loss": 0.3684, "lr": 3.504043126684636e-07, "epoch": 0.007009267059814659, "percentage": 0.35, "elapsed_time": "0:06:28", "remaining_time": "1 day, 6:38:50"}
|
14 |
+
{"current_steps": 140, "total_steps": 37092, "loss": 0.3393, "lr": 3.773584905660378e-07, "epoch": 0.007548441449031171, "percentage": 0.38, "elapsed_time": "0:07:02", "remaining_time": "1 day, 6:57:40"}
|
15 |
+
{"current_steps": 150, "total_steps": 37092, "loss": 0.3167, "lr": 4.043126684636119e-07, "epoch": 0.008087615838247682, "percentage": 0.4, "elapsed_time": "0:07:35", "remaining_time": "1 day, 7:07:58"}
|
16 |
+
{"current_steps": 160, "total_steps": 37092, "loss": 0.29, "lr": 4.3126684636118604e-07, "epoch": 0.008626790227464196, "percentage": 0.43, "elapsed_time": "0:08:03", "remaining_time": "1 day, 7:00:58"}
|
17 |
+
{"current_steps": 170, "total_steps": 37092, "loss": 0.2575, "lr": 4.5822102425876014e-07, "epoch": 0.009165964616680707, "percentage": 0.46, "elapsed_time": "0:08:31", "remaining_time": "1 day, 6:52:21"}
|
18 |
+
{"current_steps": 180, "total_steps": 37092, "loss": 0.2597, "lr": 4.851752021563343e-07, "epoch": 0.00970513900589722, "percentage": 0.49, "elapsed_time": "0:09:05", "remaining_time": "1 day, 7:05:26"}
|
19 |
+
{"current_steps": 190, "total_steps": 37092, "loss": 0.2364, "lr": 5.121293800539083e-07, "epoch": 0.010244313395113731, "percentage": 0.51, "elapsed_time": "0:09:33", "remaining_time": "1 day, 6:56:15"}
|
20 |
+
{"current_steps": 200, "total_steps": 37092, "loss": 0.2361, "lr": 5.390835579514825e-07, "epoch": 0.010783487784330244, "percentage": 0.54, "elapsed_time": "0:10:03", "remaining_time": "1 day, 6:54:29"}
|
21 |
+
{"current_steps": 210, "total_steps": 37092, "loss": 0.2396, "lr": 5.660377358490567e-07, "epoch": 0.011322662173546756, "percentage": 0.57, "elapsed_time": "0:10:36", "remaining_time": "1 day, 7:02:07"}
|
22 |
+
{"current_steps": 220, "total_steps": 37092, "loss": 0.2372, "lr": 5.929919137466308e-07, "epoch": 0.011861836562763269, "percentage": 0.59, "elapsed_time": "0:11:07", "remaining_time": "1 day, 7:03:58"}
|
23 |
+
{"current_steps": 230, "total_steps": 37092, "loss": 0.2108, "lr": 6.199460916442049e-07, "epoch": 0.01240101095197978, "percentage": 0.62, "elapsed_time": "0:11:40", "remaining_time": "1 day, 7:10:07"}
|
24 |
+
{"current_steps": 240, "total_steps": 37092, "loss": 0.2125, "lr": 6.46900269541779e-07, "epoch": 0.012940185341196293, "percentage": 0.65, "elapsed_time": "0:12:12", "remaining_time": "1 day, 7:15:16"}
|
25 |
+
{"current_steps": 250, "total_steps": 37092, "loss": 0.2042, "lr": 6.738544474393531e-07, "epoch": 0.013479359730412805, "percentage": 0.67, "elapsed_time": "0:12:40", "remaining_time": "1 day, 7:07:24"}
|
26 |
+
{"current_steps": 260, "total_steps": 37092, "loss": 0.2052, "lr": 7.008086253369272e-07, "epoch": 0.014018534119629318, "percentage": 0.7, "elapsed_time": "0:13:10", "remaining_time": "1 day, 7:05:42"}
|
27 |
+
{"current_steps": 270, "total_steps": 37092, "loss": 0.1883, "lr": 7.277628032345015e-07, "epoch": 0.014557708508845829, "percentage": 0.73, "elapsed_time": "0:13:39", "remaining_time": "1 day, 7:02:20"}
|
28 |
+
{"current_steps": 280, "total_steps": 37092, "loss": 0.1896, "lr": 7.547169811320755e-07, "epoch": 0.015096882898062342, "percentage": 0.75, "elapsed_time": "0:14:11", "remaining_time": "1 day, 7:05:55"}
|
29 |
+
{"current_steps": 290, "total_steps": 37092, "loss": 0.1993, "lr": 7.816711590296497e-07, "epoch": 0.015636057287278855, "percentage": 0.78, "elapsed_time": "0:14:43", "remaining_time": "1 day, 7:08:53"}
|
30 |
+
{"current_steps": 300, "total_steps": 37092, "loss": 0.1796, "lr": 8.086253369272238e-07, "epoch": 0.016175231676495365, "percentage": 0.81, "elapsed_time": "0:15:16", "remaining_time": "1 day, 7:12:38"}
|
31 |
+
{"current_steps": 310, "total_steps": 37092, "loss": 0.171, "lr": 8.355795148247979e-07, "epoch": 0.016714406065711878, "percentage": 0.84, "elapsed_time": "0:15:44", "remaining_time": "1 day, 7:08:19"}
|
32 |
+
{"current_steps": 320, "total_steps": 37092, "loss": 0.1772, "lr": 8.625336927223721e-07, "epoch": 0.01725358045492839, "percentage": 0.86, "elapsed_time": "0:16:15", "remaining_time": "1 day, 7:07:53"}
|
33 |
+
{"current_steps": 330, "total_steps": 37092, "loss": 0.1666, "lr": 8.894878706199461e-07, "epoch": 0.017792754844144904, "percentage": 0.89, "elapsed_time": "0:16:42", "remaining_time": "1 day, 7:00:39"}
|
34 |
+
{"current_steps": 340, "total_steps": 37092, "loss": 0.1576, "lr": 9.164420485175203e-07, "epoch": 0.018331929233361414, "percentage": 0.92, "elapsed_time": "0:17:11", "remaining_time": "1 day, 6:58:05"}
|
35 |
+
{"current_steps": 350, "total_steps": 37092, "loss": 0.1637, "lr": 9.433962264150944e-07, "epoch": 0.018871103622577927, "percentage": 0.94, "elapsed_time": "0:17:42", "remaining_time": "1 day, 6:58:43"}
|
36 |
+
{"current_steps": 360, "total_steps": 37092, "loss": 0.1568, "lr": 9.703504043126686e-07, "epoch": 0.01941027801179444, "percentage": 0.97, "elapsed_time": "0:18:12", "remaining_time": "1 day, 6:57:59"}
|
37 |
+
{"current_steps": 370, "total_steps": 37092, "loss": 0.1528, "lr": 9.973045822102428e-07, "epoch": 0.019949452401010953, "percentage": 1.0, "elapsed_time": "0:18:42", "remaining_time": "1 day, 6:56:15"}
|
38 |
+
{"current_steps": 380, "total_steps": 37092, "loss": 0.153, "lr": 1.0242587601078167e-06, "epoch": 0.020488626790227463, "percentage": 1.02, "elapsed_time": "0:19:13", "remaining_time": "1 day, 6:56:55"}
|
39 |
+
{"current_steps": 390, "total_steps": 37092, "loss": 0.1417, "lr": 1.0512129380053909e-06, "epoch": 0.021027801179443976, "percentage": 1.05, "elapsed_time": "0:19:40", "remaining_time": "1 day, 6:51:19"}
|
40 |
+
{"current_steps": 400, "total_steps": 37092, "loss": 0.1461, "lr": 1.078167115902965e-06, "epoch": 0.02156697556866049, "percentage": 1.08, "elapsed_time": "0:20:13", "remaining_time": "1 day, 6:55:41"}
|
41 |
+
{"current_steps": 410, "total_steps": 37092, "loss": 0.1487, "lr": 1.1051212938005392e-06, "epoch": 0.022106149957877002, "percentage": 1.11, "elapsed_time": "0:20:42", "remaining_time": "1 day, 6:52:05"}
|
42 |
+
{"current_steps": 420, "total_steps": 37092, "loss": 0.1468, "lr": 1.1320754716981133e-06, "epoch": 0.02264532434709351, "percentage": 1.13, "elapsed_time": "0:21:10", "remaining_time": "1 day, 6:48:42"}
|
43 |
+
{"current_steps": 430, "total_steps": 37092, "loss": 0.1579, "lr": 1.1590296495956873e-06, "epoch": 0.023184498736310025, "percentage": 1.16, "elapsed_time": "0:21:43", "remaining_time": "1 day, 6:51:38"}
|
44 |
+
{"current_steps": 440, "total_steps": 37092, "loss": 0.1451, "lr": 1.1859838274932616e-06, "epoch": 0.023723673125526538, "percentage": 1.19, "elapsed_time": "0:22:17", "remaining_time": "1 day, 6:56:18"}
|
45 |
+
{"current_steps": 450, "total_steps": 37092, "loss": 0.1581, "lr": 1.2129380053908358e-06, "epoch": 0.02426284751474305, "percentage": 1.21, "elapsed_time": "0:22:49", "remaining_time": "1 day, 6:58:35"}
|
46 |
+
{"current_steps": 460, "total_steps": 37092, "loss": 0.156, "lr": 1.2398921832884097e-06, "epoch": 0.02480202190395956, "percentage": 1.24, "elapsed_time": "0:23:23", "remaining_time": "1 day, 7:03:00"}
|
47 |
+
{"current_steps": 470, "total_steps": 37092, "loss": 0.1349, "lr": 1.266846361185984e-06, "epoch": 0.025341196293176074, "percentage": 1.27, "elapsed_time": "0:23:52", "remaining_time": "1 day, 6:59:47"}
|
48 |
+
{"current_steps": 480, "total_steps": 37092, "loss": 0.1364, "lr": 1.293800539083558e-06, "epoch": 0.025880370682392587, "percentage": 1.29, "elapsed_time": "0:24:20", "remaining_time": "1 day, 6:57:12"}
|
49 |
+
{"current_steps": 490, "total_steps": 37092, "loss": 0.1436, "lr": 1.3207547169811322e-06, "epoch": 0.0264195450716091, "percentage": 1.32, "elapsed_time": "0:24:56", "remaining_time": "1 day, 7:03:18"}
|
50 |
+
{"current_steps": 500, "total_steps": 37092, "loss": 0.1347, "lr": 1.3477088948787062e-06, "epoch": 0.02695871946082561, "percentage": 1.35, "elapsed_time": "0:25:27", "remaining_time": "1 day, 7:03:04"}
|
51 |
+
{"current_steps": 510, "total_steps": 37092, "loss": 0.1417, "lr": 1.3746630727762805e-06, "epoch": 0.027497893850042122, "percentage": 1.37, "elapsed_time": "0:25:59", "remaining_time": "1 day, 7:04:17"}
|
52 |
+
{"current_steps": 520, "total_steps": 37092, "loss": 0.1422, "lr": 1.4016172506738545e-06, "epoch": 0.028037068239258636, "percentage": 1.4, "elapsed_time": "0:26:30", "remaining_time": "1 day, 7:04:27"}
|
53 |
+
{"current_steps": 530, "total_steps": 37092, "loss": 0.1274, "lr": 1.4285714285714286e-06, "epoch": 0.02857624262847515, "percentage": 1.43, "elapsed_time": "0:26:58", "remaining_time": "1 day, 7:00:44"}
|
54 |
+
{"current_steps": 540, "total_steps": 37092, "loss": 0.1318, "lr": 1.455525606469003e-06, "epoch": 0.029115417017691658, "percentage": 1.46, "elapsed_time": "0:27:28", "remaining_time": "1 day, 6:59:37"}
|
55 |
+
{"current_steps": 550, "total_steps": 37092, "loss": 0.125, "lr": 1.482479784366577e-06, "epoch": 0.02965459140690817, "percentage": 1.48, "elapsed_time": "0:27:58", "remaining_time": "1 day, 6:58:09"}
|
56 |
+
{"current_steps": 560, "total_steps": 37092, "loss": 0.1288, "lr": 1.509433962264151e-06, "epoch": 0.030193765796124684, "percentage": 1.51, "elapsed_time": "0:28:30", "remaining_time": "1 day, 6:59:38"}
|
57 |
+
{"current_steps": 570, "total_steps": 37092, "loss": 0.143, "lr": 1.5363881401617253e-06, "epoch": 0.030732940185341198, "percentage": 1.54, "elapsed_time": "0:29:00", "remaining_time": "1 day, 6:58:30"}
|
58 |
+
{"current_steps": 580, "total_steps": 37092, "loss": 0.1317, "lr": 1.5633423180592994e-06, "epoch": 0.03127211457455771, "percentage": 1.56, "elapsed_time": "0:29:29", "remaining_time": "1 day, 6:57:04"}
|
59 |
+
{"current_steps": 590, "total_steps": 37092, "loss": 0.1248, "lr": 1.5902964959568734e-06, "epoch": 0.03181128896377422, "percentage": 1.59, "elapsed_time": "0:29:58", "remaining_time": "1 day, 6:54:35"}
|
60 |
+
{"current_steps": 600, "total_steps": 37092, "loss": 0.1239, "lr": 1.6172506738544475e-06, "epoch": 0.03235046335299073, "percentage": 1.62, "elapsed_time": "0:30:30", "remaining_time": "1 day, 6:55:44"}
|
61 |
+
{"current_steps": 610, "total_steps": 37092, "loss": 0.1349, "lr": 1.6442048517520217e-06, "epoch": 0.032889637742207246, "percentage": 1.64, "elapsed_time": "0:31:00", "remaining_time": "1 day, 6:54:46"}
|
62 |
+
{"current_steps": 620, "total_steps": 37092, "loss": 0.1239, "lr": 1.6711590296495958e-06, "epoch": 0.033428812131423756, "percentage": 1.67, "elapsed_time": "0:31:29", "remaining_time": "1 day, 6:52:52"}
|
63 |
+
{"current_steps": 630, "total_steps": 37092, "loss": 0.1239, "lr": 1.6981132075471698e-06, "epoch": 0.03396798652064027, "percentage": 1.7, "elapsed_time": "0:32:02", "remaining_time": "1 day, 6:53:58"}
|
64 |
+
{"current_steps": 640, "total_steps": 37092, "loss": 0.1306, "lr": 1.7250673854447441e-06, "epoch": 0.03450716090985678, "percentage": 1.73, "elapsed_time": "0:32:35", "remaining_time": "1 day, 6:56:03"}
|
65 |
+
{"current_steps": 650, "total_steps": 37092, "loss": 0.1033, "lr": 1.7520215633423183e-06, "epoch": 0.03504633529907329, "percentage": 1.75, "elapsed_time": "0:33:00", "remaining_time": "1 day, 6:50:55"}
|
66 |
+
{"current_steps": 660, "total_steps": 37092, "loss": 0.1291, "lr": 1.7789757412398922e-06, "epoch": 0.03558550968828981, "percentage": 1.78, "elapsed_time": "0:33:32", "remaining_time": "1 day, 6:51:11"}
|
67 |
+
{"current_steps": 670, "total_steps": 37092, "loss": 0.1245, "lr": 1.8059299191374666e-06, "epoch": 0.03612468407750632, "percentage": 1.81, "elapsed_time": "0:34:05", "remaining_time": "1 day, 6:53:27"}
|
68 |
+
{"current_steps": 680, "total_steps": 37092, "loss": 0.1151, "lr": 1.8328840970350406e-06, "epoch": 0.03666385846672283, "percentage": 1.83, "elapsed_time": "0:34:37", "remaining_time": "1 day, 6:54:25"}
|
69 |
+
{"current_steps": 690, "total_steps": 37092, "loss": 0.1121, "lr": 1.8598382749326147e-06, "epoch": 0.037203032855939344, "percentage": 1.86, "elapsed_time": "0:35:06", "remaining_time": "1 day, 6:52:28"}
|
70 |
+
{"current_steps": 700, "total_steps": 37092, "loss": 0.1173, "lr": 1.8867924528301889e-06, "epoch": 0.037742207245155854, "percentage": 1.89, "elapsed_time": "0:35:38", "remaining_time": "1 day, 6:53:00"}
|
71 |
+
{"current_steps": 710, "total_steps": 37092, "loss": 0.104, "lr": 1.913746630727763e-06, "epoch": 0.03828138163437237, "percentage": 1.91, "elapsed_time": "0:36:07", "remaining_time": "1 day, 6:51:02"}
|
72 |
+
{"current_steps": 720, "total_steps": 37092, "loss": 0.1097, "lr": 1.940700808625337e-06, "epoch": 0.03882055602358888, "percentage": 1.94, "elapsed_time": "0:36:36", "remaining_time": "1 day, 6:48:55"}
|
73 |
+
{"current_steps": 730, "total_steps": 37092, "loss": 0.1042, "lr": 1.967654986522911e-06, "epoch": 0.03935973041280539, "percentage": 1.97, "elapsed_time": "0:37:06", "remaining_time": "1 day, 6:48:32"}
|
74 |
+
{"current_steps": 740, "total_steps": 37092, "loss": 0.1295, "lr": 1.9946091644204855e-06, "epoch": 0.039898904802021906, "percentage": 2.0, "elapsed_time": "0:37:39", "remaining_time": "1 day, 6:50:02"}
|
75 |
+
{"current_steps": 750, "total_steps": 37092, "loss": 0.1213, "lr": 2.0215633423180597e-06, "epoch": 0.040438079191238416, "percentage": 2.02, "elapsed_time": "0:38:12", "remaining_time": "1 day, 6:51:41"}
|
76 |
+
{"current_steps": 760, "total_steps": 37092, "loss": 0.1082, "lr": 2.0485175202156334e-06, "epoch": 0.040977253580454925, "percentage": 2.05, "elapsed_time": "0:38:42", "remaining_time": "1 day, 6:50:19"}
|
77 |
+
{"current_steps": 770, "total_steps": 37092, "loss": 0.1159, "lr": 2.075471698113208e-06, "epoch": 0.04151642796967144, "percentage": 2.08, "elapsed_time": "0:39:13", "remaining_time": "1 day, 6:50:32"}
|
78 |
+
{"current_steps": 780, "total_steps": 37092, "loss": 0.1131, "lr": 2.1024258760107817e-06, "epoch": 0.04205560235888795, "percentage": 2.1, "elapsed_time": "0:39:45", "remaining_time": "1 day, 6:51:14"}
|
79 |
+
{"current_steps": 790, "total_steps": 37092, "loss": 0.1129, "lr": 2.129380053908356e-06, "epoch": 0.04259477674810447, "percentage": 2.13, "elapsed_time": "0:40:20", "remaining_time": "1 day, 6:54:08"}
|
80 |
+
{"current_steps": 800, "total_steps": 37092, "loss": 0.1015, "lr": 2.15633423180593e-06, "epoch": 0.04313395113732098, "percentage": 2.16, "elapsed_time": "0:40:50", "remaining_time": "1 day, 6:52:26"}
|
81 |
+
{"current_steps": 810, "total_steps": 37092, "loss": 0.1204, "lr": 2.183288409703504e-06, "epoch": 0.04367312552653749, "percentage": 2.18, "elapsed_time": "0:41:22", "remaining_time": "1 day, 6:52:57"}
|
82 |
+
{"current_steps": 820, "total_steps": 37092, "loss": 0.1108, "lr": 2.2102425876010783e-06, "epoch": 0.044212299915754004, "percentage": 2.21, "elapsed_time": "0:41:50", "remaining_time": "1 day, 6:51:08"}
|
83 |
+
{"current_steps": 830, "total_steps": 37092, "loss": 0.118, "lr": 2.2371967654986525e-06, "epoch": 0.044751474304970514, "percentage": 2.24, "elapsed_time": "0:42:22", "remaining_time": "1 day, 6:51:37"}
|
84 |
+
{"current_steps": 840, "total_steps": 37092, "loss": 0.111, "lr": 2.2641509433962266e-06, "epoch": 0.04529064869418702, "percentage": 2.26, "elapsed_time": "0:42:51", "remaining_time": "1 day, 6:49:47"}
|
85 |
+
{"current_steps": 850, "total_steps": 37092, "loss": 0.1137, "lr": 2.291105121293801e-06, "epoch": 0.04582982308340354, "percentage": 2.29, "elapsed_time": "0:43:19", "remaining_time": "1 day, 6:47:09"}
|
86 |
+
{"current_steps": 860, "total_steps": 37092, "loss": 0.1114, "lr": 2.3180592991913745e-06, "epoch": 0.04636899747262005, "percentage": 2.32, "elapsed_time": "0:43:49", "remaining_time": "1 day, 6:46:04"}
|
87 |
+
{"current_steps": 870, "total_steps": 37092, "loss": 0.1127, "lr": 2.345013477088949e-06, "epoch": 0.046908171861836566, "percentage": 2.35, "elapsed_time": "0:44:20", "remaining_time": "1 day, 6:46:11"}
|
88 |
+
{"current_steps": 880, "total_steps": 37092, "loss": 0.105, "lr": 2.3719676549865233e-06, "epoch": 0.047447346251053076, "percentage": 2.37, "elapsed_time": "0:44:50", "remaining_time": "1 day, 6:45:14"}
|
89 |
+
{"current_steps": 890, "total_steps": 37092, "loss": 0.0953, "lr": 2.398921832884097e-06, "epoch": 0.047986520640269585, "percentage": 2.4, "elapsed_time": "0:45:20", "remaining_time": "1 day, 6:44:00"}
|
90 |
+
{"current_steps": 900, "total_steps": 37092, "loss": 0.0927, "lr": 2.4258760107816716e-06, "epoch": 0.0485256950294861, "percentage": 2.43, "elapsed_time": "0:45:50", "remaining_time": "1 day, 6:43:40"}
|
91 |
+
{"current_steps": 910, "total_steps": 37092, "loss": 0.1017, "lr": 2.4528301886792453e-06, "epoch": 0.04906486941870261, "percentage": 2.45, "elapsed_time": "0:46:23", "remaining_time": "1 day, 6:44:17"}
|
92 |
+
{"current_steps": 920, "total_steps": 37092, "loss": 0.0879, "lr": 2.4797843665768195e-06, "epoch": 0.04960404380791912, "percentage": 2.48, "elapsed_time": "0:46:53", "remaining_time": "1 day, 6:43:20"}
|
93 |
+
{"current_steps": 930, "total_steps": 37092, "loss": 0.0941, "lr": 2.5067385444743936e-06, "epoch": 0.05014321819713564, "percentage": 2.51, "elapsed_time": "0:47:21", "remaining_time": "1 day, 6:41:38"}
|
94 |
+
{"current_steps": 940, "total_steps": 37092, "loss": 0.1024, "lr": 2.533692722371968e-06, "epoch": 0.05068239258635215, "percentage": 2.53, "elapsed_time": "0:47:55", "remaining_time": "1 day, 6:43:17"}
|
95 |
+
{"current_steps": 950, "total_steps": 37092, "loss": 0.0982, "lr": 2.5606469002695424e-06, "epoch": 0.051221566975568664, "percentage": 2.56, "elapsed_time": "0:48:27", "remaining_time": "1 day, 6:43:44"}
|
96 |
+
{"current_steps": 960, "total_steps": 37092, "loss": 0.099, "lr": 2.587601078167116e-06, "epoch": 0.05176074136478517, "percentage": 2.59, "elapsed_time": "0:48:58", "remaining_time": "1 day, 6:43:34"}
|
97 |
+
{"current_steps": 970, "total_steps": 37092, "loss": 0.113, "lr": 2.6145552560646903e-06, "epoch": 0.05229991575400168, "percentage": 2.62, "elapsed_time": "0:49:34", "remaining_time": "1 day, 6:46:21"}
|
98 |
+
{"current_steps": 980, "total_steps": 37092, "loss": 0.1012, "lr": 2.6415094339622644e-06, "epoch": 0.0528390901432182, "percentage": 2.64, "elapsed_time": "0:50:08", "remaining_time": "1 day, 6:47:52"}
|
99 |
+
{"current_steps": 990, "total_steps": 37092, "loss": 0.1099, "lr": 2.6684636118598386e-06, "epoch": 0.05337826453243471, "percentage": 2.67, "elapsed_time": "0:50:40", "remaining_time": "1 day, 6:47:38"}
|
100 |
+
{"current_steps": 1000, "total_steps": 37092, "loss": 0.104, "lr": 2.6954177897574123e-06, "epoch": 0.05391743892165122, "percentage": 2.7, "elapsed_time": "0:51:12", "remaining_time": "1 day, 6:48:02"}
|
101 |
+
{"current_steps": 1010, "total_steps": 37092, "loss": 0.1017, "lr": 2.722371967654987e-06, "epoch": 0.054456613310867735, "percentage": 2.72, "elapsed_time": "0:52:04", "remaining_time": "1 day, 7:00:14"}
|
102 |
+
{"current_steps": 1020, "total_steps": 37092, "loss": 0.0934, "lr": 2.749326145552561e-06, "epoch": 0.054995787700084245, "percentage": 2.75, "elapsed_time": "0:52:32", "remaining_time": "1 day, 6:58:05"}
|
103 |
+
{"current_steps": 1030, "total_steps": 37092, "loss": 0.0953, "lr": 2.776280323450135e-06, "epoch": 0.05553496208930076, "percentage": 2.78, "elapsed_time": "0:53:03", "remaining_time": "1 day, 6:57:23"}
|
104 |
+
{"current_steps": 1040, "total_steps": 37092, "loss": 0.0897, "lr": 2.803234501347709e-06, "epoch": 0.05607413647851727, "percentage": 2.8, "elapsed_time": "0:53:29", "remaining_time": "1 day, 6:54:35"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a13e24daa9e76827e282453a2b60ead928a74755911a9c4dfd6434b61eb0dce6
|
3 |
size 7416
|