Training in progress, epoch 0
Browse files- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- trainer_log.jsonl +175 -175
- training_args.bin +1 -1
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:f5f6f53eda40e8f9f7d41b54d1e314ed8ca8323233e509f4e51b876bdad8f3f0
|
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 sha256:97b46fc65db3a146665553f60cffd6760c389fca0c278cefd044e2987277472d
|
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 sha256:460bb808bf272c8ac1ca7c2c6c879f2f08e14306e3e084d0135615c60572ca64
|
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:edbf49ac81206c76de63e48438e22ee10d89b0fa2ee10a59b67d98d7ab88d356
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -1,175 +1,175 @@
|
|
1 |
-
{"current_steps": 1, "total_steps": 519, "loss": 0.8904, "lr": 1.5384615384615387e-06, "epoch": 0.005772005772005772, "percentage": 0.19, "elapsed_time": "0:01:
|
2 |
-
{"current_steps": 2, "total_steps": 519, "loss": 0.9046, "lr": 3.0769230769230774e-06, "epoch": 0.011544011544011544, "percentage": 0.39, "elapsed_time": "0:02:
|
3 |
-
{"current_steps": 3, "total_steps": 519, "loss": 0.
|
4 |
-
{"current_steps": 4, "total_steps": 519, "loss": 0.8572, "lr": 6.153846153846155e-06, "epoch": 0.023088023088023088, "percentage": 0.77, "elapsed_time": "0:04:
|
5 |
-
{"current_steps": 5, "total_steps": 519, "loss": 0.793, "lr": 7.692307692307694e-06, "epoch": 0.02886002886002886, "percentage": 0.96, "elapsed_time": "0:05:
|
6 |
-
{"current_steps": 6, "total_steps": 519, "loss": 0.
|
7 |
-
{"current_steps": 7, "total_steps": 519, "loss": 0.
|
8 |
-
{"current_steps": 8, "total_steps": 519, "loss": 0.7438, "lr": 1.230769230769231e-05, "epoch": 0.046176046176046176, "percentage": 1.54, "elapsed_time": "0:07:
|
9 |
-
{"current_steps": 9, "total_steps": 519, "loss": 0.7438, "lr": 1.3846153846153847e-05, "epoch": 0.05194805194805195, "percentage": 1.73, "elapsed_time": "0:08:
|
10 |
-
{"current_steps": 10, "total_steps": 519, "loss": 0.7188, "lr": 1.5384615384615387e-05, "epoch": 0.05772005772005772, "percentage": 1.93, "elapsed_time": "0:09:
|
11 |
-
{"current_steps": 11, "total_steps": 519, "loss": 0.6873, "lr": 1.6923076923076924e-05, "epoch": 0.06349206349206349, "percentage": 2.12, "elapsed_time": "0:10:
|
12 |
-
{"current_steps": 12, "total_steps": 519, "loss": 0.
|
13 |
-
{"current_steps": 13, "total_steps": 519, "loss": 0.6549, "lr": 2e-05, "epoch": 0.07503607503607504, "percentage": 2.5, "elapsed_time": "0:
|
14 |
-
{"current_steps": 14, "total_steps": 519, "loss": 0.6572, "lr": 2.153846153846154e-05, "epoch": 0.08080808080808081, "percentage": 2.7, "elapsed_time": "0:
|
15 |
-
{"current_steps": 15, "total_steps": 519, "loss": 0.6267, "lr": 2.3076923076923076e-05, "epoch": 0.08658008658008658, "percentage": 2.89, "elapsed_time": "0:13:
|
16 |
-
{"current_steps": 16, "total_steps": 519, "loss": 0.6148, "lr": 2.461538461538462e-05, "epoch": 0.09235209235209235, "percentage": 3.08, "elapsed_time": "0:14:
|
17 |
-
{"current_steps": 17, "total_steps": 519, "loss": 0.6063, "lr": 2.6153846153846157e-05, "epoch": 0.09812409812409813, "percentage": 3.28, "elapsed_time": "0:15:
|
18 |
-
{"current_steps": 18, "total_steps": 519, "loss": 0.
|
19 |
-
{"current_steps": 19, "total_steps": 519, "loss": 0.
|
20 |
-
{"current_steps": 20, "total_steps": 519, "loss": 0.
|
21 |
-
{"current_steps": 21, "total_steps": 519, "loss": 0.
|
22 |
-
{"current_steps": 22, "total_steps": 519, "loss": 0.
|
23 |
-
{"current_steps": 23, "total_steps": 519, "loss": 0.
|
24 |
-
{"current_steps": 24, "total_steps": 519, "loss": 0.
|
25 |
-
{"current_steps": 25, "total_steps": 519, "loss": 0.
|
26 |
-
{"current_steps": 26, "total_steps": 519, "loss": 0.
|
27 |
-
{"current_steps": 27, "total_steps": 519, "loss": 0.
|
28 |
-
{"current_steps": 28, "total_steps": 519, "loss": 0.
|
29 |
-
{"current_steps": 29, "total_steps": 519, "loss": 0.
|
30 |
-
{"current_steps": 30, "total_steps": 519, "loss": 0.
|
31 |
-
{"current_steps": 31, "total_steps": 519, "loss": 0.
|
32 |
-
{"current_steps": 32, "total_steps": 519, "loss": 0.
|
33 |
-
{"current_steps": 33, "total_steps": 519, "loss": 0.
|
34 |
-
{"current_steps": 34, "total_steps": 519, "loss": 0.
|
35 |
-
{"current_steps": 35, "total_steps": 519, "loss": 0.
|
36 |
-
{"current_steps": 36, "total_steps": 519, "loss": 0.
|
37 |
-
{"current_steps": 37, "total_steps": 519, "loss": 0.
|
38 |
-
{"current_steps": 38, "total_steps": 519, "loss": 0.
|
39 |
-
{"current_steps": 39, "total_steps": 519, "loss": 0.
|
40 |
-
{"current_steps": 40, "total_steps": 519, "loss": 0.
|
41 |
-
{"current_steps": 41, "total_steps": 519, "loss": 0.
|
42 |
-
{"current_steps": 42, "total_steps": 519, "loss": 0.
|
43 |
-
{"current_steps": 43, "total_steps": 519, "loss": 0.
|
44 |
-
{"current_steps": 44, "total_steps": 519, "loss": 0.
|
45 |
-
{"current_steps": 45, "total_steps": 519, "loss": 0.
|
46 |
-
{"current_steps": 46, "total_steps": 519, "loss": 0.
|
47 |
-
{"current_steps": 47, "total_steps": 519, "loss": 0.
|
48 |
-
{"current_steps": 48, "total_steps": 519, "loss": 0.
|
49 |
-
{"current_steps": 49, "total_steps": 519, "loss": 0.
|
50 |
-
{"current_steps": 50, "total_steps": 519, "loss": 0.
|
51 |
-
{"current_steps": 51, "total_steps": 519, "loss": 0.
|
52 |
-
{"current_steps": 52, "total_steps": 519, "loss": 0.
|
53 |
-
{"current_steps": 53, "total_steps": 519, "loss": 0.
|
54 |
-
{"current_steps": 54, "total_steps": 519, "loss": 0.
|
55 |
-
{"current_steps": 55, "total_steps": 519, "loss": 0.
|
56 |
-
{"current_steps": 56, "total_steps": 519, "loss": 0.
|
57 |
-
{"current_steps": 57, "total_steps": 519, "loss": 0.
|
58 |
-
{"current_steps": 58, "total_steps": 519, "loss": 0.
|
59 |
-
{"current_steps": 59, "total_steps": 519, "loss": 0.
|
60 |
-
{"current_steps": 60, "total_steps": 519, "loss": 0.
|
61 |
-
{"current_steps": 61, "total_steps": 519, "loss": 0.
|
62 |
-
{"current_steps": 62, "total_steps": 519, "loss": 0.
|
63 |
-
{"current_steps": 63, "total_steps": 519, "loss": 0.
|
64 |
-
{"current_steps": 64, "total_steps": 519, "loss": 0.
|
65 |
-
{"current_steps": 65, "total_steps": 519, "loss": 0.
|
66 |
-
{"current_steps": 66, "total_steps": 519, "loss": 0.
|
67 |
-
{"current_steps": 67, "total_steps": 519, "loss": 0.
|
68 |
-
{"current_steps": 68, "total_steps": 519, "loss": 0.
|
69 |
-
{"current_steps": 69, "total_steps": 519, "loss": 0.
|
70 |
-
{"current_steps": 70, "total_steps": 519, "loss": 0.
|
71 |
-
{"current_steps": 71, "total_steps": 519, "loss": 0.
|
72 |
-
{"current_steps": 72, "total_steps": 519, "loss":
|
73 |
-
{"current_steps": 73, "total_steps": 519, "loss": 0.
|
74 |
-
{"current_steps": 74, "total_steps": 519, "loss": 0.
|
75 |
-
{"current_steps": 75, "total_steps": 519, "loss": 0.
|
76 |
-
{"current_steps": 76, "total_steps": 519, "loss": 0.
|
77 |
-
{"current_steps": 77, "total_steps": 519, "loss": 0.
|
78 |
-
{"current_steps": 78, "total_steps": 519, "loss": 0.
|
79 |
-
{"current_steps": 79, "total_steps": 519, "loss": 0.
|
80 |
-
{"current_steps": 80, "total_steps": 519, "loss": 0.
|
81 |
-
{"current_steps": 81, "total_steps": 519, "loss": 0.
|
82 |
-
{"current_steps": 82, "total_steps": 519, "loss": 0.
|
83 |
-
{"current_steps": 83, "total_steps": 519, "loss": 0.
|
84 |
-
{"current_steps": 84, "total_steps": 519, "loss": 0.
|
85 |
-
{"current_steps": 85, "total_steps": 519, "loss": 0.
|
86 |
-
{"current_steps": 86, "total_steps": 519, "loss": 0.
|
87 |
-
{"current_steps": 87, "total_steps": 519, "loss": 0.
|
88 |
-
{"current_steps": 88, "total_steps": 519, "loss": 0.
|
89 |
-
{"current_steps": 89, "total_steps": 519, "loss": 0.
|
90 |
-
{"current_steps": 90, "total_steps": 519, "loss": 0.
|
91 |
-
{"current_steps": 91, "total_steps": 519, "loss": 0.
|
92 |
-
{"current_steps": 92, "total_steps": 519, "loss": 0.
|
93 |
-
{"current_steps": 93, "total_steps": 519, "loss": 0.
|
94 |
-
{"current_steps": 94, "total_steps": 519, "loss": 0.
|
95 |
-
{"current_steps": 95, "total_steps": 519, "loss": 0.
|
96 |
-
{"current_steps": 96, "total_steps": 519, "loss": 0.
|
97 |
-
{"current_steps": 97, "total_steps": 519, "loss": 0.
|
98 |
-
{"current_steps": 98, "total_steps": 519, "loss": 0.
|
99 |
-
{"current_steps": 99, "total_steps": 519, "loss": 0.
|
100 |
-
{"current_steps": 100, "total_steps": 519, "loss": 0.
|
101 |
-
{"current_steps": 101, "total_steps": 519, "loss": 0.
|
102 |
-
{"current_steps": 102, "total_steps": 519, "loss": 0.
|
103 |
-
{"current_steps": 103, "total_steps": 519, "loss": 0.
|
104 |
-
{"current_steps": 104, "total_steps": 519, "loss": 0.
|
105 |
-
{"current_steps": 105, "total_steps": 519, "loss": 0.
|
106 |
-
{"current_steps": 106, "total_steps": 519, "loss": 0.
|
107 |
-
{"current_steps": 107, "total_steps": 519, "loss": 0.
|
108 |
-
{"current_steps": 108, "total_steps": 519, "loss": 0.
|
109 |
-
{"current_steps": 109, "total_steps": 519, "loss": 0.
|
110 |
-
{"current_steps": 110, "total_steps": 519, "loss": 0.
|
111 |
-
{"current_steps": 111, "total_steps": 519, "loss": 0.
|
112 |
-
{"current_steps": 112, "total_steps": 519, "loss": 0.
|
113 |
-
{"current_steps": 113, "total_steps": 519, "loss": 0.
|
114 |
-
{"current_steps": 114, "total_steps": 519, "loss": 0.
|
115 |
-
{"current_steps": 115, "total_steps": 519, "loss": 0.
|
116 |
-
{"current_steps": 116, "total_steps": 519, "loss": 0.
|
117 |
-
{"current_steps": 117, "total_steps": 519, "loss": 0.
|
118 |
-
{"current_steps": 118, "total_steps": 519, "loss": 0.
|
119 |
-
{"current_steps": 119, "total_steps": 519, "loss": 0.
|
120 |
-
{"current_steps": 120, "total_steps": 519, "loss": 0.
|
121 |
-
{"current_steps": 121, "total_steps": 519, "loss": 0.
|
122 |
-
{"current_steps": 122, "total_steps": 519, "loss": 0.
|
123 |
-
{"current_steps": 123, "total_steps": 519, "loss": 0.
|
124 |
-
{"current_steps": 124, "total_steps": 519, "loss": 0.
|
125 |
-
{"current_steps": 125, "total_steps": 519, "loss": 0.
|
126 |
-
{"current_steps": 126, "total_steps": 519, "loss": 0.
|
127 |
-
{"current_steps": 127, "total_steps": 519, "loss": 0.
|
128 |
-
{"current_steps": 128, "total_steps": 519, "loss": 0.
|
129 |
-
{"current_steps": 129, "total_steps": 519, "loss": 0.
|
130 |
-
{"current_steps": 130, "total_steps": 519, "loss": 0.
|
131 |
-
{"current_steps": 131, "total_steps": 519, "loss": 0.
|
132 |
-
{"current_steps": 132, "total_steps": 519, "loss": 0.
|
133 |
-
{"current_steps": 133, "total_steps": 519, "loss": 0.
|
134 |
-
{"current_steps": 134, "total_steps": 519, "loss": 0.
|
135 |
-
{"current_steps": 135, "total_steps": 519, "loss": 0.
|
136 |
-
{"current_steps": 136, "total_steps": 519, "loss": 0.
|
137 |
-
{"current_steps": 137, "total_steps": 519, "loss": 0.
|
138 |
-
{"current_steps": 138, "total_steps": 519, "loss": 0.
|
139 |
-
{"current_steps": 139, "total_steps": 519, "loss": 0.
|
140 |
-
{"current_steps": 140, "total_steps": 519, "loss": 0.
|
141 |
-
{"current_steps": 141, "total_steps": 519, "loss": 0.
|
142 |
-
{"current_steps": 142, "total_steps": 519, "loss": 0.
|
143 |
-
{"current_steps": 143, "total_steps": 519, "loss": 0.
|
144 |
-
{"current_steps": 144, "total_steps": 519, "loss": 0.
|
145 |
-
{"current_steps": 145, "total_steps": 519, "loss": 0.
|
146 |
-
{"current_steps": 146, "total_steps": 519, "loss": 0.
|
147 |
-
{"current_steps": 147, "total_steps": 519, "loss": 0.
|
148 |
-
{"current_steps": 148, "total_steps": 519, "loss": 0.
|
149 |
-
{"current_steps": 149, "total_steps": 519, "loss": 0.
|
150 |
-
{"current_steps": 150, "total_steps": 519, "loss": 0.
|
151 |
-
{"current_steps": 151, "total_steps": 519, "loss": 0.
|
152 |
-
{"current_steps": 152, "total_steps": 519, "loss": 0.
|
153 |
-
{"current_steps": 153, "total_steps": 519, "loss": 0.
|
154 |
-
{"current_steps": 154, "total_steps": 519, "loss": 0.
|
155 |
-
{"current_steps": 155, "total_steps": 519, "loss": 0.
|
156 |
-
{"current_steps": 156, "total_steps": 519, "loss": 0.
|
157 |
-
{"current_steps": 157, "total_steps": 519, "loss": 0.
|
158 |
-
{"current_steps": 158, "total_steps": 519, "loss": 0.
|
159 |
-
{"current_steps": 159, "total_steps": 519, "loss": 0.
|
160 |
-
{"current_steps": 160, "total_steps": 519, "loss": 0.
|
161 |
-
{"current_steps": 161, "total_steps": 519, "loss": 0.
|
162 |
-
{"current_steps": 162, "total_steps": 519, "loss": 0.
|
163 |
-
{"current_steps": 163, "total_steps": 519, "loss": 0.
|
164 |
-
{"current_steps": 164, "total_steps": 519, "loss": 0.
|
165 |
-
{"current_steps": 165, "total_steps": 519, "loss": 0.
|
166 |
-
{"current_steps": 166, "total_steps": 519, "loss": 0.
|
167 |
-
{"current_steps": 167, "total_steps": 519, "loss": 0.
|
168 |
-
{"current_steps": 168, "total_steps": 519, "loss": 0.
|
169 |
-
{"current_steps": 169, "total_steps": 519, "loss": 0.
|
170 |
-
{"current_steps": 170, "total_steps": 519, "loss": 0.
|
171 |
-
{"current_steps": 171, "total_steps": 519, "loss": 0.
|
172 |
-
{"current_steps": 172, "total_steps": 519, "loss": 0.
|
173 |
-
{"current_steps": 173, "total_steps": 519, "loss": 0.
|
174 |
-
{"current_steps": 174, "total_steps": 519, "loss": 0.
|
175 |
-
{"current_steps": 175, "total_steps": 519, "loss": 0.
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 519, "loss": 0.8904, "lr": 1.5384615384615387e-06, "epoch": 0.005772005772005772, "percentage": 0.19, "elapsed_time": "0:01:39", "remaining_time": "14:21:58"}
|
2 |
+
{"current_steps": 2, "total_steps": 519, "loss": 0.9046, "lr": 3.0769230769230774e-06, "epoch": 0.011544011544011544, "percentage": 0.39, "elapsed_time": "0:02:32", "remaining_time": "10:55:20"}
|
3 |
+
{"current_steps": 3, "total_steps": 519, "loss": 0.8942, "lr": 4.615384615384616e-06, "epoch": 0.017316017316017316, "percentage": 0.58, "elapsed_time": "0:03:25", "remaining_time": "9:48:03"}
|
4 |
+
{"current_steps": 4, "total_steps": 519, "loss": 0.8572, "lr": 6.153846153846155e-06, "epoch": 0.023088023088023088, "percentage": 0.77, "elapsed_time": "0:04:17", "remaining_time": "9:12:42"}
|
5 |
+
{"current_steps": 5, "total_steps": 519, "loss": 0.793, "lr": 7.692307692307694e-06, "epoch": 0.02886002886002886, "percentage": 0.96, "elapsed_time": "0:05:09", "remaining_time": "8:50:38"}
|
6 |
+
{"current_steps": 6, "total_steps": 519, "loss": 0.7611, "lr": 9.230769230769232e-06, "epoch": 0.03463203463203463, "percentage": 1.16, "elapsed_time": "0:06:01", "remaining_time": "8:34:59"}
|
7 |
+
{"current_steps": 7, "total_steps": 519, "loss": 0.7895, "lr": 1.076923076923077e-05, "epoch": 0.04040404040404041, "percentage": 1.35, "elapsed_time": "0:06:53", "remaining_time": "8:24:38"}
|
8 |
+
{"current_steps": 8, "total_steps": 519, "loss": 0.7438, "lr": 1.230769230769231e-05, "epoch": 0.046176046176046176, "percentage": 1.54, "elapsed_time": "0:07:45", "remaining_time": "8:15:45"}
|
9 |
+
{"current_steps": 9, "total_steps": 519, "loss": 0.7438, "lr": 1.3846153846153847e-05, "epoch": 0.05194805194805195, "percentage": 1.73, "elapsed_time": "0:08:37", "remaining_time": "8:09:00"}
|
10 |
+
{"current_steps": 10, "total_steps": 519, "loss": 0.7188, "lr": 1.5384615384615387e-05, "epoch": 0.05772005772005772, "percentage": 1.93, "elapsed_time": "0:09:29", "remaining_time": "8:03:09"}
|
11 |
+
{"current_steps": 11, "total_steps": 519, "loss": 0.6873, "lr": 1.6923076923076924e-05, "epoch": 0.06349206349206349, "percentage": 2.12, "elapsed_time": "0:10:21", "remaining_time": "7:58:13"}
|
12 |
+
{"current_steps": 12, "total_steps": 519, "loss": 0.6738, "lr": 1.8461538461538465e-05, "epoch": 0.06926406926406926, "percentage": 2.31, "elapsed_time": "0:11:15", "remaining_time": "7:55:22"}
|
13 |
+
{"current_steps": 13, "total_steps": 519, "loss": 0.6549, "lr": 2e-05, "epoch": 0.07503607503607504, "percentage": 2.5, "elapsed_time": "0:12:09", "remaining_time": "7:53:21"}
|
14 |
+
{"current_steps": 14, "total_steps": 519, "loss": 0.6572, "lr": 2.153846153846154e-05, "epoch": 0.08080808080808081, "percentage": 2.7, "elapsed_time": "0:13:01", "remaining_time": "7:49:42"}
|
15 |
+
{"current_steps": 15, "total_steps": 519, "loss": 0.6267, "lr": 2.3076923076923076e-05, "epoch": 0.08658008658008658, "percentage": 2.89, "elapsed_time": "0:13:53", "remaining_time": "7:46:40"}
|
16 |
+
{"current_steps": 16, "total_steps": 519, "loss": 0.6148, "lr": 2.461538461538462e-05, "epoch": 0.09235209235209235, "percentage": 3.08, "elapsed_time": "0:14:45", "remaining_time": "7:43:43"}
|
17 |
+
{"current_steps": 17, "total_steps": 519, "loss": 0.6063, "lr": 2.6153846153846157e-05, "epoch": 0.09812409812409813, "percentage": 3.28, "elapsed_time": "0:15:36", "remaining_time": "7:41:07"}
|
18 |
+
{"current_steps": 18, "total_steps": 519, "loss": 0.6029, "lr": 2.7692307692307694e-05, "epoch": 0.1038961038961039, "percentage": 3.47, "elapsed_time": "0:16:28", "remaining_time": "7:38:36"}
|
19 |
+
{"current_steps": 19, "total_steps": 519, "loss": 0.6049, "lr": 2.923076923076923e-05, "epoch": 0.10966810966810966, "percentage": 3.66, "elapsed_time": "0:17:20", "remaining_time": "7:36:19"}
|
20 |
+
{"current_steps": 20, "total_steps": 519, "loss": 0.5893, "lr": 3.0769230769230774e-05, "epoch": 0.11544011544011544, "percentage": 3.85, "elapsed_time": "0:18:12", "remaining_time": "7:34:06"}
|
21 |
+
{"current_steps": 21, "total_steps": 519, "loss": 0.5789, "lr": 3.230769230769231e-05, "epoch": 0.12121212121212122, "percentage": 4.05, "elapsed_time": "0:19:03", "remaining_time": "7:32:01"}
|
22 |
+
{"current_steps": 22, "total_steps": 519, "loss": 0.5653, "lr": 3.384615384615385e-05, "epoch": 0.12698412698412698, "percentage": 4.24, "elapsed_time": "0:19:55", "remaining_time": "7:30:04"}
|
23 |
+
{"current_steps": 23, "total_steps": 519, "loss": 0.5784, "lr": 3.538461538461539e-05, "epoch": 0.13275613275613277, "percentage": 4.43, "elapsed_time": "0:20:47", "remaining_time": "7:28:13"}
|
24 |
+
{"current_steps": 24, "total_steps": 519, "loss": 0.5657, "lr": 3.692307692307693e-05, "epoch": 0.13852813852813853, "percentage": 4.62, "elapsed_time": "0:21:38", "remaining_time": "7:26:25"}
|
25 |
+
{"current_steps": 25, "total_steps": 519, "loss": 0.5628, "lr": 3.846153846153846e-05, "epoch": 0.1443001443001443, "percentage": 4.82, "elapsed_time": "0:22:30", "remaining_time": "7:24:43"}
|
26 |
+
{"current_steps": 26, "total_steps": 519, "loss": 0.5589, "lr": 4e-05, "epoch": 0.15007215007215008, "percentage": 5.01, "elapsed_time": "0:23:22", "remaining_time": "7:23:04"}
|
27 |
+
{"current_steps": 27, "total_steps": 519, "loss": 0.5587, "lr": 4.1538461538461544e-05, "epoch": 0.15584415584415584, "percentage": 5.2, "elapsed_time": "0:24:17", "remaining_time": "7:22:36"}
|
28 |
+
{"current_steps": 28, "total_steps": 519, "loss": 0.5533, "lr": 4.307692307692308e-05, "epoch": 0.16161616161616163, "percentage": 5.39, "elapsed_time": "0:25:08", "remaining_time": "7:20:59"}
|
29 |
+
{"current_steps": 29, "total_steps": 519, "loss": 0.5532, "lr": 4.461538461538462e-05, "epoch": 0.1673881673881674, "percentage": 5.59, "elapsed_time": "0:26:00", "remaining_time": "7:19:31"}
|
30 |
+
{"current_steps": 30, "total_steps": 519, "loss": 0.5516, "lr": 4.615384615384615e-05, "epoch": 0.17316017316017315, "percentage": 5.78, "elapsed_time": "0:26:52", "remaining_time": "7:18:03"}
|
31 |
+
{"current_steps": 31, "total_steps": 519, "loss": 0.5443, "lr": 4.76923076923077e-05, "epoch": 0.17893217893217894, "percentage": 5.97, "elapsed_time": "0:27:44", "remaining_time": "7:16:39"}
|
32 |
+
{"current_steps": 32, "total_steps": 519, "loss": 0.5457, "lr": 4.923076923076924e-05, "epoch": 0.1847041847041847, "percentage": 6.17, "elapsed_time": "0:28:35", "remaining_time": "7:15:13"}
|
33 |
+
{"current_steps": 33, "total_steps": 519, "loss": 0.5452, "lr": 5.076923076923077e-05, "epoch": 0.19047619047619047, "percentage": 6.36, "elapsed_time": "0:29:27", "remaining_time": "7:13:51"}
|
34 |
+
{"current_steps": 34, "total_steps": 519, "loss": 0.5386, "lr": 5.230769230769231e-05, "epoch": 0.19624819624819625, "percentage": 6.55, "elapsed_time": "0:30:19", "remaining_time": "7:12:32"}
|
35 |
+
{"current_steps": 35, "total_steps": 519, "loss": 0.5326, "lr": 5.3846153846153853e-05, "epoch": 0.20202020202020202, "percentage": 6.74, "elapsed_time": "0:31:11", "remaining_time": "7:11:14"}
|
36 |
+
{"current_steps": 36, "total_steps": 519, "loss": 0.5445, "lr": 5.538461538461539e-05, "epoch": 0.2077922077922078, "percentage": 6.94, "elapsed_time": "0:32:02", "remaining_time": "7:09:58"}
|
37 |
+
{"current_steps": 37, "total_steps": 519, "loss": 0.5395, "lr": 5.692307692307693e-05, "epoch": 0.21356421356421357, "percentage": 7.13, "elapsed_time": "0:32:54", "remaining_time": "7:08:43"}
|
38 |
+
{"current_steps": 38, "total_steps": 519, "loss": 0.5288, "lr": 5.846153846153846e-05, "epoch": 0.21933621933621933, "percentage": 7.32, "elapsed_time": "0:33:46", "remaining_time": "7:07:28"}
|
39 |
+
{"current_steps": 39, "total_steps": 519, "loss": 0.5204, "lr": 6.000000000000001e-05, "epoch": 0.22510822510822512, "percentage": 7.51, "elapsed_time": "0:34:37", "remaining_time": "7:06:15"}
|
40 |
+
{"current_steps": 40, "total_steps": 519, "loss": 0.5261, "lr": 6.153846153846155e-05, "epoch": 0.23088023088023088, "percentage": 7.71, "elapsed_time": "0:35:29", "remaining_time": "7:05:03"}
|
41 |
+
{"current_steps": 41, "total_steps": 519, "loss": 0.5316, "lr": 6.307692307692308e-05, "epoch": 0.23665223665223664, "percentage": 7.9, "elapsed_time": "0:36:21", "remaining_time": "7:03:54"}
|
42 |
+
{"current_steps": 42, "total_steps": 519, "loss": 0.5298, "lr": 6.461538461538462e-05, "epoch": 0.24242424242424243, "percentage": 8.09, "elapsed_time": "0:37:19", "remaining_time": "7:03:59"}
|
43 |
+
{"current_steps": 43, "total_steps": 519, "loss": 0.5289, "lr": 6.615384615384616e-05, "epoch": 0.2481962481962482, "percentage": 8.29, "elapsed_time": "0:38:12", "remaining_time": "7:02:57"}
|
44 |
+
{"current_steps": 44, "total_steps": 519, "loss": 0.5155, "lr": 6.76923076923077e-05, "epoch": 0.25396825396825395, "percentage": 8.48, "elapsed_time": "0:39:04", "remaining_time": "7:01:46"}
|
45 |
+
{"current_steps": 45, "total_steps": 519, "loss": 0.5311, "lr": 6.923076923076924e-05, "epoch": 0.2597402597402597, "percentage": 8.67, "elapsed_time": "0:39:55", "remaining_time": "7:00:36"}
|
46 |
+
{"current_steps": 46, "total_steps": 519, "loss": 0.5244, "lr": 7.076923076923078e-05, "epoch": 0.26551226551226553, "percentage": 8.86, "elapsed_time": "0:40:47", "remaining_time": "6:59:27"}
|
47 |
+
{"current_steps": 47, "total_steps": 519, "loss": 0.5229, "lr": 7.230769230769232e-05, "epoch": 0.2712842712842713, "percentage": 9.06, "elapsed_time": "0:41:39", "remaining_time": "6:58:19"}
|
48 |
+
{"current_steps": 48, "total_steps": 519, "loss": 0.5222, "lr": 7.384615384615386e-05, "epoch": 0.27705627705627706, "percentage": 9.25, "elapsed_time": "0:42:31", "remaining_time": "6:57:11"}
|
49 |
+
{"current_steps": 49, "total_steps": 519, "loss": 0.5127, "lr": 7.538461538461539e-05, "epoch": 0.2828282828282828, "percentage": 9.44, "elapsed_time": "0:43:22", "remaining_time": "6:56:06"}
|
50 |
+
{"current_steps": 50, "total_steps": 519, "loss": 0.5358, "lr": 7.692307692307693e-05, "epoch": 0.2886002886002886, "percentage": 9.63, "elapsed_time": "0:44:14", "remaining_time": "6:55:00"}
|
51 |
+
{"current_steps": 51, "total_steps": 519, "loss": 0.5202, "lr": 7.846153846153847e-05, "epoch": 0.2943722943722944, "percentage": 9.83, "elapsed_time": "0:45:06", "remaining_time": "6:53:55"}
|
52 |
+
{"current_steps": 52, "total_steps": 519, "loss": 0.5231, "lr": 8e-05, "epoch": 0.30014430014430016, "percentage": 10.02, "elapsed_time": "0:45:58", "remaining_time": "6:52:49"}
|
53 |
+
{"current_steps": 53, "total_steps": 519, "loss": 0.5266, "lr": 7.999909490463248e-05, "epoch": 0.3059163059163059, "percentage": 10.21, "elapsed_time": "0:46:49", "remaining_time": "6:51:45"}
|
54 |
+
{"current_steps": 54, "total_steps": 519, "loss": 0.5092, "lr": 7.999637965948977e-05, "epoch": 0.3116883116883117, "percentage": 10.4, "elapsed_time": "0:47:41", "remaining_time": "6:50:41"}
|
55 |
+
{"current_steps": 55, "total_steps": 519, "loss": 0.5095, "lr": 7.999185438744968e-05, "epoch": 0.31746031746031744, "percentage": 10.6, "elapsed_time": "0:48:33", "remaining_time": "6:49:38"}
|
56 |
+
{"current_steps": 56, "total_steps": 519, "loss": 0.5114, "lr": 7.998551929330234e-05, "epoch": 0.32323232323232326, "percentage": 10.79, "elapsed_time": "0:49:25", "remaining_time": "6:48:38"}
|
57 |
+
{"current_steps": 57, "total_steps": 519, "loss": 0.5091, "lr": 7.997737466374096e-05, "epoch": 0.329004329004329, "percentage": 10.98, "elapsed_time": "0:50:24", "remaining_time": "6:48:31"}
|
58 |
+
{"current_steps": 58, "total_steps": 519, "loss": 0.502, "lr": 7.99674208673489e-05, "epoch": 0.3347763347763348, "percentage": 11.18, "elapsed_time": "0:51:15", "remaining_time": "6:47:26"}
|
59 |
+
{"current_steps": 59, "total_steps": 519, "loss": 0.5007, "lr": 7.995565835458286e-05, "epoch": 0.34054834054834054, "percentage": 11.37, "elapsed_time": "0:52:07", "remaining_time": "6:46:24"}
|
60 |
+
{"current_steps": 60, "total_steps": 519, "loss": 0.5142, "lr": 7.994208765775267e-05, "epoch": 0.3463203463203463, "percentage": 11.56, "elapsed_time": "0:52:59", "remaining_time": "6:45:20"}
|
61 |
+
{"current_steps": 61, "total_steps": 519, "loss": 0.5039, "lr": 7.992670939099704e-05, "epoch": 0.35209235209235207, "percentage": 11.75, "elapsed_time": "0:53:50", "remaining_time": "6:44:18"}
|
62 |
+
{"current_steps": 62, "total_steps": 519, "loss": 0.5018, "lr": 7.99095242502559e-05, "epoch": 0.3578643578643579, "percentage": 11.95, "elapsed_time": "0:54:42", "remaining_time": "6:43:16"}
|
63 |
+
{"current_steps": 63, "total_steps": 519, "loss": 0.4986, "lr": 7.989053301323881e-05, "epoch": 0.36363636363636365, "percentage": 12.14, "elapsed_time": "0:55:34", "remaining_time": "6:42:15"}
|
64 |
+
{"current_steps": 64, "total_steps": 519, "loss": 0.4983, "lr": 7.986973653938977e-05, "epoch": 0.3694083694083694, "percentage": 12.33, "elapsed_time": "0:56:26", "remaining_time": "6:41:13"}
|
65 |
+
{"current_steps": 65, "total_steps": 519, "loss": 0.509, "lr": 7.984713576984842e-05, "epoch": 0.37518037518037517, "percentage": 12.52, "elapsed_time": "0:57:17", "remaining_time": "6:40:12"}
|
66 |
+
{"current_steps": 66, "total_steps": 519, "loss": 0.5126, "lr": 7.982273172740734e-05, "epoch": 0.38095238095238093, "percentage": 12.72, "elapsed_time": "0:58:09", "remaining_time": "6:39:12"}
|
67 |
+
{"current_steps": 67, "total_steps": 519, "loss": 0.5, "lr": 7.979652551646583e-05, "epoch": 0.38672438672438675, "percentage": 12.91, "elapsed_time": "0:59:01", "remaining_time": "6:38:12"}
|
68 |
+
{"current_steps": 68, "total_steps": 519, "loss": 0.5132, "lr": 7.976851832297987e-05, "epoch": 0.3924963924963925, "percentage": 13.1, "elapsed_time": "0:59:53", "remaining_time": "6:37:11"}
|
69 |
+
{"current_steps": 69, "total_steps": 519, "loss": 0.5052, "lr": 7.973871141440853e-05, "epoch": 0.39826839826839827, "percentage": 13.29, "elapsed_time": "1:00:45", "remaining_time": "6:36:12"}
|
70 |
+
{"current_steps": 70, "total_steps": 519, "loss": 0.5078, "lr": 7.970710613965657e-05, "epoch": 0.40404040404040403, "percentage": 13.49, "elapsed_time": "1:01:36", "remaining_time": "6:35:12"}
|
71 |
+
{"current_steps": 71, "total_steps": 519, "loss": 0.5023, "lr": 7.967370392901334e-05, "epoch": 0.4098124098124098, "percentage": 13.68, "elapsed_time": "1:02:29", "remaining_time": "6:34:16"}
|
72 |
+
{"current_steps": 72, "total_steps": 519, "loss": 7.192, "lr": 7.963850629408817e-05, "epoch": 0.4155844155844156, "percentage": 13.87, "elapsed_time": "1:03:31", "remaining_time": "6:34:23"}
|
73 |
+
{"current_steps": 73, "total_steps": 519, "loss": 0.5501, "lr": 7.960151482774188e-05, "epoch": 0.4213564213564214, "percentage": 14.07, "elapsed_time": "1:04:23", "remaining_time": "6:33:22"}
|
74 |
+
{"current_steps": 74, "total_steps": 519, "loss": 0.5197, "lr": 7.95627312040147e-05, "epoch": 0.42712842712842713, "percentage": 14.26, "elapsed_time": "1:05:14", "remaining_time": "6:32:22"}
|
75 |
+
{"current_steps": 75, "total_steps": 519, "loss": 0.5043, "lr": 7.952215717805055e-05, "epoch": 0.4329004329004329, "percentage": 14.45, "elapsed_time": "1:06:06", "remaining_time": "6:31:22"}
|
76 |
+
{"current_steps": 76, "total_steps": 519, "loss": 0.5184, "lr": 7.947979458601756e-05, "epoch": 0.43867243867243866, "percentage": 14.64, "elapsed_time": "1:06:58", "remaining_time": "6:30:22"}
|
77 |
+
{"current_steps": 77, "total_steps": 519, "loss": 0.5184, "lr": 7.943564534502503e-05, "epoch": 0.4444444444444444, "percentage": 14.84, "elapsed_time": "1:07:50", "remaining_time": "6:29:23"}
|
78 |
+
{"current_steps": 78, "total_steps": 519, "loss": 0.5054, "lr": 7.938971145303666e-05, "epoch": 0.45021645021645024, "percentage": 15.03, "elapsed_time": "1:08:41", "remaining_time": "6:28:24"}
|
79 |
+
{"current_steps": 79, "total_steps": 519, "loss": 0.4974, "lr": 7.934199498878005e-05, "epoch": 0.455988455988456, "percentage": 15.22, "elapsed_time": "1:09:33", "remaining_time": "6:27:25"}
|
80 |
+
{"current_steps": 80, "total_steps": 519, "loss": 0.4979, "lr": 7.929249811165274e-05, "epoch": 0.46176046176046176, "percentage": 15.41, "elapsed_time": "1:10:25", "remaining_time": "6:26:27"}
|
81 |
+
{"current_steps": 81, "total_steps": 519, "loss": 0.5227, "lr": 7.924122306162448e-05, "epoch": 0.4675324675324675, "percentage": 15.61, "elapsed_time": "1:11:17", "remaining_time": "6:25:28"}
|
82 |
+
{"current_steps": 82, "total_steps": 519, "loss": 0.5384, "lr": 7.918817215913574e-05, "epoch": 0.4733044733044733, "percentage": 15.8, "elapsed_time": "1:12:08", "remaining_time": "6:24:29"}
|
83 |
+
{"current_steps": 83, "total_steps": 519, "loss": 0.5193, "lr": 7.913334780499284e-05, "epoch": 0.4790764790764791, "percentage": 15.99, "elapsed_time": "1:13:00", "remaining_time": "6:23:31"}
|
84 |
+
{"current_steps": 84, "total_steps": 519, "loss": 0.5178, "lr": 7.907675248025926e-05, "epoch": 0.48484848484848486, "percentage": 16.18, "elapsed_time": "1:13:52", "remaining_time": "6:22:32"}
|
85 |
+
{"current_steps": 85, "total_steps": 519, "loss": 0.565, "lr": 7.901838874614325e-05, "epoch": 0.4906204906204906, "percentage": 16.38, "elapsed_time": "1:14:44", "remaining_time": "6:21:36"}
|
86 |
+
{"current_steps": 86, "total_steps": 519, "loss": 0.574, "lr": 7.895825924388214e-05, "epoch": 0.4963924963924964, "percentage": 16.57, "elapsed_time": "1:15:36", "remaining_time": "6:20:40"}
|
87 |
+
{"current_steps": 87, "total_steps": 519, "loss": 0.5636, "lr": 7.889636669462257e-05, "epoch": 0.5021645021645021, "percentage": 16.76, "elapsed_time": "1:16:38", "remaining_time": "6:20:35"}
|
88 |
+
{"current_steps": 88, "total_steps": 519, "loss": 0.5266, "lr": 7.883271389929755e-05, "epoch": 0.5079365079365079, "percentage": 16.96, "elapsed_time": "1:17:30", "remaining_time": "6:19:36"}
|
89 |
+
{"current_steps": 89, "total_steps": 519, "loss": 0.5151, "lr": 7.87673037384996e-05, "epoch": 0.5137085137085137, "percentage": 17.15, "elapsed_time": "1:18:22", "remaining_time": "6:18:38"}
|
90 |
+
{"current_steps": 90, "total_steps": 519, "loss": 0.5138, "lr": 7.870013917235039e-05, "epoch": 0.5194805194805194, "percentage": 17.34, "elapsed_time": "1:19:13", "remaining_time": "6:17:39"}
|
91 |
+
{"current_steps": 91, "total_steps": 519, "loss": 0.5084, "lr": 7.86312232403668e-05, "epoch": 0.5252525252525253, "percentage": 17.53, "elapsed_time": "1:20:05", "remaining_time": "6:16:41"}
|
92 |
+
{"current_steps": 92, "total_steps": 519, "loss": 0.5013, "lr": 7.856055906132337e-05, "epoch": 0.5310245310245311, "percentage": 17.73, "elapsed_time": "1:20:57", "remaining_time": "6:15:43"}
|
93 |
+
{"current_steps": 93, "total_steps": 519, "loss": 0.4875, "lr": 7.848814983311114e-05, "epoch": 0.5367965367965368, "percentage": 17.92, "elapsed_time": "1:21:48", "remaining_time": "6:14:45"}
|
94 |
+
{"current_steps": 94, "total_steps": 519, "loss": 0.5072, "lr": 7.841399883259298e-05, "epoch": 0.5425685425685426, "percentage": 18.11, "elapsed_time": "1:22:40", "remaining_time": "6:13:48"}
|
95 |
+
{"current_steps": 95, "total_steps": 519, "loss": 0.4981, "lr": 7.833810941545525e-05, "epoch": 0.5483405483405484, "percentage": 18.3, "elapsed_time": "1:23:32", "remaining_time": "6:12:51"}
|
96 |
+
{"current_steps": 96, "total_steps": 519, "loss": 0.4976, "lr": 7.826048501605592e-05, "epoch": 0.5541125541125541, "percentage": 18.5, "elapsed_time": "1:24:24", "remaining_time": "6:11:54"}
|
97 |
+
{"current_steps": 97, "total_steps": 519, "loss": 0.4939, "lr": 7.818112914726922e-05, "epoch": 0.5598845598845599, "percentage": 18.69, "elapsed_time": "1:25:15", "remaining_time": "6:10:57"}
|
98 |
+
{"current_steps": 98, "total_steps": 519, "loss": 0.4973, "lr": 7.81000454003266e-05, "epoch": 0.5656565656565656, "percentage": 18.88, "elapsed_time": "1:26:07", "remaining_time": "6:09:59"}
|
99 |
+
{"current_steps": 99, "total_steps": 519, "loss": 0.4877, "lr": 7.801723744465427e-05, "epoch": 0.5714285714285714, "percentage": 19.08, "elapsed_time": "1:26:59", "remaining_time": "6:09:03"}
|
100 |
+
{"current_steps": 100, "total_steps": 519, "loss": 0.4847, "lr": 7.793270902770707e-05, "epoch": 0.5772005772005772, "percentage": 19.27, "elapsed_time": "1:27:51", "remaining_time": "6:08:07"}
|
101 |
+
{"current_steps": 101, "total_steps": 519, "loss": 0.4789, "lr": 7.784646397479892e-05, "epoch": 0.5829725829725829, "percentage": 19.46, "elapsed_time": "1:28:46", "remaining_time": "6:07:24"}
|
102 |
+
{"current_steps": 102, "total_steps": 519, "loss": 0.4826, "lr": 7.775850618892973e-05, "epoch": 0.5887445887445888, "percentage": 19.65, "elapsed_time": "1:29:47", "remaining_time": "6:07:04"}
|
103 |
+
{"current_steps": 103, "total_steps": 519, "loss": 0.4801, "lr": 7.766883965060871e-05, "epoch": 0.5945165945165946, "percentage": 19.85, "elapsed_time": "1:30:38", "remaining_time": "6:06:07"}
|
104 |
+
{"current_steps": 104, "total_steps": 519, "loss": 0.4871, "lr": 7.757746841767431e-05, "epoch": 0.6002886002886003, "percentage": 20.04, "elapsed_time": "1:31:30", "remaining_time": "6:05:10"}
|
105 |
+
{"current_steps": 105, "total_steps": 519, "loss": 0.4835, "lr": 7.748439662511049e-05, "epoch": 0.6060606060606061, "percentage": 20.23, "elapsed_time": "1:32:22", "remaining_time": "6:04:13"}
|
106 |
+
{"current_steps": 106, "total_steps": 519, "loss": 0.4768, "lr": 7.738962848485967e-05, "epoch": 0.6118326118326118, "percentage": 20.42, "elapsed_time": "1:33:14", "remaining_time": "6:03:16"}
|
107 |
+
{"current_steps": 107, "total_steps": 519, "loss": 0.4824, "lr": 7.729316828563207e-05, "epoch": 0.6176046176046176, "percentage": 20.62, "elapsed_time": "1:34:06", "remaining_time": "6:02:20"}
|
108 |
+
{"current_steps": 108, "total_steps": 519, "loss": 0.4826, "lr": 7.71950203927117e-05, "epoch": 0.6233766233766234, "percentage": 20.81, "elapsed_time": "1:34:57", "remaining_time": "6:01:23"}
|
109 |
+
{"current_steps": 109, "total_steps": 519, "loss": 0.4903, "lr": 7.709518924775869e-05, "epoch": 0.6291486291486291, "percentage": 21.0, "elapsed_time": "1:35:49", "remaining_time": "6:00:26"}
|
110 |
+
{"current_steps": 110, "total_steps": 519, "loss": 0.4827, "lr": 7.69936793686084e-05, "epoch": 0.6349206349206349, "percentage": 21.19, "elapsed_time": "1:36:41", "remaining_time": "5:59:30"}
|
111 |
+
{"current_steps": 111, "total_steps": 519, "loss": 0.4839, "lr": 7.689049534906688e-05, "epoch": 0.6406926406926406, "percentage": 21.39, "elapsed_time": "1:37:33", "remaining_time": "5:58:34"}
|
112 |
+
{"current_steps": 112, "total_steps": 519, "loss": 0.4905, "lr": 7.678564185870306e-05, "epoch": 0.6464646464646465, "percentage": 21.58, "elapsed_time": "1:38:24", "remaining_time": "5:57:37"}
|
113 |
+
{"current_steps": 113, "total_steps": 519, "loss": 0.4935, "lr": 7.667912364263734e-05, "epoch": 0.6522366522366523, "percentage": 21.77, "elapsed_time": "1:39:16", "remaining_time": "5:56:41"}
|
114 |
+
{"current_steps": 114, "total_steps": 519, "loss": 0.4753, "lr": 7.657094552132692e-05, "epoch": 0.658008658008658, "percentage": 21.97, "elapsed_time": "1:40:08", "remaining_time": "5:55:45"}
|
115 |
+
{"current_steps": 115, "total_steps": 519, "loss": 0.4847, "lr": 7.646111239034762e-05, "epoch": 0.6637806637806638, "percentage": 22.16, "elapsed_time": "1:41:00", "remaining_time": "5:54:50"}
|
116 |
+
{"current_steps": 116, "total_steps": 519, "loss": 0.4812, "lr": 7.634962922017234e-05, "epoch": 0.6695526695526696, "percentage": 22.35, "elapsed_time": "1:41:57", "remaining_time": "5:54:13"}
|
117 |
+
{"current_steps": 117, "total_steps": 519, "loss": 0.4789, "lr": 7.623650105594616e-05, "epoch": 0.6753246753246753, "percentage": 22.54, "elapsed_time": "1:42:57", "remaining_time": "5:53:45"}
|
118 |
+
{"current_steps": 118, "total_steps": 519, "loss": 0.4782, "lr": 7.612173301725791e-05, "epoch": 0.6810966810966811, "percentage": 22.74, "elapsed_time": "1:43:49", "remaining_time": "5:52:48"}
|
119 |
+
{"current_steps": 119, "total_steps": 519, "loss": 0.4766, "lr": 7.600533029790859e-05, "epoch": 0.6868686868686869, "percentage": 22.93, "elapsed_time": "1:44:40", "remaining_time": "5:51:52"}
|
120 |
+
{"current_steps": 120, "total_steps": 519, "loss": 0.4742, "lr": 7.588729816567634e-05, "epoch": 0.6926406926406926, "percentage": 23.12, "elapsed_time": "1:45:32", "remaining_time": "5:50:55"}
|
121 |
+
{"current_steps": 121, "total_steps": 519, "loss": 0.4715, "lr": 7.576764196207793e-05, "epoch": 0.6984126984126984, "percentage": 23.31, "elapsed_time": "1:46:24", "remaining_time": "5:49:59"}
|
122 |
+
{"current_steps": 122, "total_steps": 519, "loss": 0.4727, "lr": 7.564636710212717e-05, "epoch": 0.7041847041847041, "percentage": 23.51, "elapsed_time": "1:47:15", "remaining_time": "5:49:03"}
|
123 |
+
{"current_steps": 123, "total_steps": 519, "loss": 0.4679, "lr": 7.552347907408973e-05, "epoch": 0.70995670995671, "percentage": 23.7, "elapsed_time": "1:48:07", "remaining_time": "5:48:06"}
|
124 |
+
{"current_steps": 124, "total_steps": 519, "loss": 0.4634, "lr": 7.539898343923487e-05, "epoch": 0.7157287157287158, "percentage": 23.89, "elapsed_time": "1:48:59", "remaining_time": "5:47:10"}
|
125 |
+
{"current_steps": 125, "total_steps": 519, "loss": 0.4685, "lr": 7.527288583158371e-05, "epoch": 0.7215007215007215, "percentage": 24.08, "elapsed_time": "1:49:50", "remaining_time": "5:46:14"}
|
126 |
+
{"current_steps": 126, "total_steps": 519, "loss": 0.4673, "lr": 7.514519195765428e-05, "epoch": 0.7272727272727273, "percentage": 24.28, "elapsed_time": "1:50:42", "remaining_time": "5:45:19"}
|
127 |
+
{"current_steps": 127, "total_steps": 519, "loss": 0.4725, "lr": 7.501590759620324e-05, "epoch": 0.733044733044733, "percentage": 24.47, "elapsed_time": "1:51:34", "remaining_time": "5:44:23"}
|
128 |
+
{"current_steps": 128, "total_steps": 519, "loss": 0.4621, "lr": 7.488503859796446e-05, "epoch": 0.7388167388167388, "percentage": 24.66, "elapsed_time": "1:52:26", "remaining_time": "5:43:28"}
|
129 |
+
{"current_steps": 129, "total_steps": 519, "loss": 0.4565, "lr": 7.475259088538412e-05, "epoch": 0.7445887445887446, "percentage": 24.86, "elapsed_time": "1:53:18", "remaining_time": "5:42:32"}
|
130 |
+
{"current_steps": 130, "total_steps": 519, "loss": 0.4643, "lr": 7.461857045235278e-05, "epoch": 0.7503607503607503, "percentage": 25.05, "elapsed_time": "1:54:10", "remaining_time": "5:41:37"}
|
131 |
+
{"current_steps": 131, "total_steps": 519, "loss": 0.4661, "lr": 7.448298336393409e-05, "epoch": 0.7561327561327561, "percentage": 25.24, "elapsed_time": "1:55:09", "remaining_time": "5:41:04"}
|
132 |
+
{"current_steps": 132, "total_steps": 519, "loss": 0.4653, "lr": 7.434583575609034e-05, "epoch": 0.7619047619047619, "percentage": 25.43, "elapsed_time": "1:56:08", "remaining_time": "5:40:30"}
|
133 |
+
{"current_steps": 133, "total_steps": 519, "loss": 0.4693, "lr": 7.420713383540476e-05, "epoch": 0.7676767676767676, "percentage": 25.63, "elapsed_time": "1:57:00", "remaining_time": "5:39:34"}
|
134 |
+
{"current_steps": 134, "total_steps": 519, "loss": 0.4623, "lr": 7.406688387880064e-05, "epoch": 0.7734487734487735, "percentage": 25.82, "elapsed_time": "1:57:52", "remaining_time": "5:38:38"}
|
135 |
+
{"current_steps": 135, "total_steps": 519, "loss": 0.4625, "lr": 7.392509223325727e-05, "epoch": 0.7792207792207793, "percentage": 26.01, "elapsed_time": "1:58:43", "remaining_time": "5:37:43"}
|
136 |
+
{"current_steps": 136, "total_steps": 519, "loss": 0.4695, "lr": 7.378176531552272e-05, "epoch": 0.784992784992785, "percentage": 26.2, "elapsed_time": "1:59:35", "remaining_time": "5:36:47"}
|
137 |
+
{"current_steps": 137, "total_steps": 519, "loss": 0.4603, "lr": 7.363690961182348e-05, "epoch": 0.7907647907647908, "percentage": 26.4, "elapsed_time": "2:00:27", "remaining_time": "5:35:51"}
|
138 |
+
{"current_steps": 138, "total_steps": 519, "loss": 0.4729, "lr": 7.349053167757087e-05, "epoch": 0.7965367965367965, "percentage": 26.59, "elapsed_time": "2:01:18", "remaining_time": "5:34:56"}
|
139 |
+
{"current_steps": 139, "total_steps": 519, "loss": 0.4901, "lr": 7.334263813706438e-05, "epoch": 0.8023088023088023, "percentage": 26.78, "elapsed_time": "2:02:10", "remaining_time": "5:34:01"}
|
140 |
+
{"current_steps": 140, "total_steps": 519, "loss": 0.4643, "lr": 7.319323568319195e-05, "epoch": 0.8080808080808081, "percentage": 26.97, "elapsed_time": "2:03:02", "remaining_time": "5:33:05"}
|
141 |
+
{"current_steps": 141, "total_steps": 519, "loss": 0.4732, "lr": 7.304233107712699e-05, "epoch": 0.8138528138528138, "percentage": 27.17, "elapsed_time": "2:03:54", "remaining_time": "5:32:10"}
|
142 |
+
{"current_steps": 142, "total_steps": 519, "loss": 0.4805, "lr": 7.288993114802251e-05, "epoch": 0.8196248196248196, "percentage": 27.36, "elapsed_time": "2:04:45", "remaining_time": "5:31:14"}
|
143 |
+
{"current_steps": 143, "total_steps": 519, "loss": 0.4575, "lr": 7.273604279270203e-05, "epoch": 0.8253968253968254, "percentage": 27.55, "elapsed_time": "2:05:37", "remaining_time": "5:30:19"}
|
144 |
+
{"current_steps": 144, "total_steps": 519, "loss": 0.461, "lr": 7.25806729753474e-05, "epoch": 0.8311688311688312, "percentage": 27.75, "elapsed_time": "2:06:29", "remaining_time": "5:29:24"}
|
145 |
+
{"current_steps": 145, "total_steps": 519, "loss": 0.4587, "lr": 7.242382872718371e-05, "epoch": 0.836940836940837, "percentage": 27.94, "elapsed_time": "2:07:21", "remaining_time": "5:28:29"}
|
146 |
+
{"current_steps": 146, "total_steps": 519, "loss": 0.4647, "lr": 7.226551714616111e-05, "epoch": 0.8427128427128427, "percentage": 28.13, "elapsed_time": "2:08:22", "remaining_time": "5:27:59"}
|
147 |
+
{"current_steps": 147, "total_steps": 519, "loss": 0.4595, "lr": 7.210574539663351e-05, "epoch": 0.8484848484848485, "percentage": 28.32, "elapsed_time": "2:09:19", "remaining_time": "5:27:15"}
|
148 |
+
{"current_steps": 148, "total_steps": 519, "loss": 0.4592, "lr": 7.194452070903443e-05, "epoch": 0.8542568542568543, "percentage": 28.52, "elapsed_time": "2:10:11", "remaining_time": "5:26:20"}
|
149 |
+
{"current_steps": 149, "total_steps": 519, "loss": 0.4556, "lr": 7.178185037954977e-05, "epoch": 0.86002886002886, "percentage": 28.71, "elapsed_time": "2:11:03", "remaining_time": "5:25:25"}
|
150 |
+
{"current_steps": 150, "total_steps": 519, "loss": 0.461, "lr": 7.16177417697876e-05, "epoch": 0.8658008658008658, "percentage": 28.9, "elapsed_time": "2:11:54", "remaining_time": "5:24:30"}
|
151 |
+
{"current_steps": 151, "total_steps": 519, "loss": 0.4597, "lr": 7.145220230644507e-05, "epoch": 0.8715728715728716, "percentage": 29.09, "elapsed_time": "2:12:46", "remaining_time": "5:23:35"}
|
152 |
+
{"current_steps": 152, "total_steps": 519, "loss": 0.4626, "lr": 7.128523948097222e-05, "epoch": 0.8773448773448773, "percentage": 29.29, "elapsed_time": "2:13:38", "remaining_time": "5:22:39"}
|
153 |
+
{"current_steps": 153, "total_steps": 519, "loss": 0.4599, "lr": 7.111686084923306e-05, "epoch": 0.8831168831168831, "percentage": 29.48, "elapsed_time": "2:14:30", "remaining_time": "5:21:44"}
|
154 |
+
{"current_steps": 154, "total_steps": 519, "loss": 0.4595, "lr": 7.094707403116356e-05, "epoch": 0.8888888888888888, "percentage": 29.67, "elapsed_time": "2:15:21", "remaining_time": "5:20:49"}
|
155 |
+
{"current_steps": 155, "total_steps": 519, "loss": 0.4544, "lr": 7.077588671042686e-05, "epoch": 0.8946608946608947, "percentage": 29.87, "elapsed_time": "2:16:13", "remaining_time": "5:19:54"}
|
156 |
+
{"current_steps": 156, "total_steps": 519, "loss": 0.4435, "lr": 7.06033066340655e-05, "epoch": 0.9004329004329005, "percentage": 30.06, "elapsed_time": "2:17:05", "remaining_time": "5:18:59"}
|
157 |
+
{"current_steps": 157, "total_steps": 519, "loss": 0.4608, "lr": 7.042934161215085e-05, "epoch": 0.9062049062049062, "percentage": 30.25, "elapsed_time": "2:17:57", "remaining_time": "5:18:04"}
|
158 |
+
{"current_steps": 158, "total_steps": 519, "loss": 0.4583, "lr": 7.02539995174297e-05, "epoch": 0.911976911976912, "percentage": 30.44, "elapsed_time": "2:18:49", "remaining_time": "5:17:10"}
|
159 |
+
{"current_steps": 159, "total_steps": 519, "loss": 0.4524, "lr": 7.007728828496793e-05, "epoch": 0.9177489177489178, "percentage": 30.64, "elapsed_time": "2:19:40", "remaining_time": "5:16:15"}
|
160 |
+
{"current_steps": 160, "total_steps": 519, "loss": 0.4519, "lr": 6.989921591179145e-05, "epoch": 0.9235209235209235, "percentage": 30.83, "elapsed_time": "2:20:33", "remaining_time": "5:15:22"}
|
161 |
+
{"current_steps": 161, "total_steps": 519, "loss": 0.4504, "lr": 6.97197904565242e-05, "epoch": 0.9292929292929293, "percentage": 31.02, "elapsed_time": "2:21:37", "remaining_time": "5:14:55"}
|
162 |
+
{"current_steps": 162, "total_steps": 519, "loss": 0.4535, "lr": 6.953902003902368e-05, "epoch": 0.935064935064935, "percentage": 31.21, "elapsed_time": "2:22:32", "remaining_time": "5:14:07"}
|
163 |
+
{"current_steps": 163, "total_steps": 519, "loss": 0.4495, "lr": 6.935691284001322e-05, "epoch": 0.9408369408369408, "percentage": 31.41, "elapsed_time": "2:23:24", "remaining_time": "5:13:12"}
|
164 |
+
{"current_steps": 164, "total_steps": 519, "loss": 0.4466, "lr": 6.917347710071193e-05, "epoch": 0.9466089466089466, "percentage": 31.6, "elapsed_time": "2:24:16", "remaining_time": "5:12:17"}
|
165 |
+
{"current_steps": 165, "total_steps": 519, "loss": 0.4458, "lr": 6.898872112246172e-05, "epoch": 0.9523809523809523, "percentage": 31.79, "elapsed_time": "2:25:07", "remaining_time": "5:11:22"}
|
166 |
+
{"current_steps": 166, "total_steps": 519, "loss": 0.4537, "lr": 6.880265326635159e-05, "epoch": 0.9581529581529582, "percentage": 31.98, "elapsed_time": "2:25:59", "remaining_time": "5:10:27"}
|
167 |
+
{"current_steps": 167, "total_steps": 519, "loss": 0.4392, "lr": 6.861528195283924e-05, "epoch": 0.963924963924964, "percentage": 32.18, "elapsed_time": "2:26:51", "remaining_time": "5:09:32"}
|
168 |
+
{"current_steps": 168, "total_steps": 519, "loss": 0.4453, "lr": 6.842661566137011e-05, "epoch": 0.9696969696969697, "percentage": 32.37, "elapsed_time": "2:27:43", "remaining_time": "5:08:37"}
|
169 |
+
{"current_steps": 169, "total_steps": 519, "loss": 0.4534, "lr": 6.82366629299935e-05, "epoch": 0.9754689754689755, "percentage": 32.56, "elapsed_time": "2:28:34", "remaining_time": "5:07:42"}
|
170 |
+
{"current_steps": 170, "total_steps": 519, "loss": 0.4427, "lr": 6.804543235497625e-05, "epoch": 0.9812409812409812, "percentage": 32.76, "elapsed_time": "2:29:26", "remaining_time": "5:06:47"}
|
171 |
+
{"current_steps": 171, "total_steps": 519, "loss": 0.4388, "lr": 6.785293259041376e-05, "epoch": 0.987012987012987, "percentage": 32.95, "elapsed_time": "2:30:18", "remaining_time": "5:05:52"}
|
172 |
+
{"current_steps": 172, "total_steps": 519, "loss": 0.4407, "lr": 6.76591723478383e-05, "epoch": 0.9927849927849928, "percentage": 33.14, "elapsed_time": "2:31:09", "remaining_time": "5:04:57"}
|
173 |
+
{"current_steps": 173, "total_steps": 519, "loss": 0.4422, "lr": 6.746416039582474e-05, "epoch": 0.9985569985569985, "percentage": 33.33, "elapsed_time": "2:32:01", "remaining_time": "5:04:03"}
|
174 |
+
{"current_steps": 174, "total_steps": 519, "loss": 0.7579, "lr": 6.726790555959383e-05, "epoch": 1.0043290043290043, "percentage": 33.53, "elapsed_time": "2:34:09", "remaining_time": "5:05:39"}
|
175 |
+
{"current_steps": 175, "total_steps": 519, "loss": 0.4294, "lr": 6.707041672061271e-05, "epoch": 1.0101010101010102, "percentage": 33.72, "elapsed_time": "2:35:03", "remaining_time": "5:04:47"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7160
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daa9e67212452e8eece8860aacfa30ded5c83bcbd36cda38e6895ce801dbecfd
|
3 |
size 7160
|