Training in progress, epoch 1
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +8 -156
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Aug01_18-12-22_8ec249145423/1659377547.8062894/events.out.tfevents.1659377547.8ec249145423.72.3 +3 -0
- runs/Aug01_18-12-22_8ec249145423/events.out.tfevents.1659377547.8ec249145423.72.2 +3 -0
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 29835597
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:258a274dd340f236596df67f85372240918dc7df85673ce21a5535bcbfddc2d9
|
3 |
size 29835597
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14929953
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaafecba9c15d4a5aa7d768fc9d23505ef16daef82a897de40db243930b97861
|
3 |
size 14929953
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6aedcf31eb6261a0dcc73febed368fca8d2943d0bc56e7533476200b3da7d60f
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c450fb6a607305a3f4aa96cbf2242c050112bb2d3f04b2e837ccb7c3ef2fef3b
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -10,161 +10,13 @@
|
|
10 |
{
|
11 |
"epoch": 1.0,
|
12 |
"learning_rate": 5.5e-05,
|
13 |
-
"loss": 0.
|
14 |
"step": 340
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 2.0,
|
18 |
-
"learning_rate": 5e-05,
|
19 |
-
"loss": 0.0283,
|
20 |
-
"step": 680
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 3.0,
|
24 |
-
"learning_rate": 4.5e-05,
|
25 |
-
"loss": 0.0248,
|
26 |
-
"step": 1020
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 4.0,
|
30 |
-
"learning_rate": 3.9999999999999996e-05,
|
31 |
-
"loss": 0.0226,
|
32 |
-
"step": 1360
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 5.0,
|
36 |
-
"learning_rate": 3.5000000000000004e-05,
|
37 |
-
"loss": 0.022,
|
38 |
-
"step": 1700
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 6.0,
|
42 |
-
"learning_rate": 3e-05,
|
43 |
-
"loss": 0.0205,
|
44 |
-
"step": 2040
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 7.0,
|
48 |
-
"learning_rate": 2.5e-05,
|
49 |
-
"loss": 0.02,
|
50 |
-
"step": 2380
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 8.0,
|
54 |
-
"learning_rate": 1.9999999999999998e-05,
|
55 |
-
"loss": 0.0196,
|
56 |
-
"step": 2720
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 9.0,
|
60 |
-
"learning_rate": 1.5e-05,
|
61 |
-
"loss": 0.0188,
|
62 |
-
"step": 3060
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 9.0,
|
66 |
-
"eval_loss": 0.0258250143378973,
|
67 |
-
"eval_mean_accuracy": 0.9853669490855483,
|
68 |
-
"eval_mean_iou": 0.49268347454277417,
|
69 |
-
"eval_overall_accuracy": 0.9853669490855483,
|
70 |
-
"eval_per_category_accuracy": [
|
71 |
-
NaN,
|
72 |
-
0.9853669490855483
|
73 |
-
],
|
74 |
-
"eval_per_category_iou": [
|
75 |
-
0.0,
|
76 |
-
0.9853669490855483
|
77 |
-
],
|
78 |
-
"eval_runtime": 562.4034,
|
79 |
-
"eval_samples_per_second": 0.768,
|
80 |
-
"eval_steps_per_second": 0.032,
|
81 |
-
"step": 3060
|
82 |
-
},
|
83 |
-
{
|
84 |
-
"epoch": 10.0,
|
85 |
-
"learning_rate": 9.999999999999999e-06,
|
86 |
-
"loss": 0.0188,
|
87 |
-
"step": 3400
|
88 |
-
},
|
89 |
-
{
|
90 |
-
"epoch": 10.0,
|
91 |
-
"eval_loss": 0.02450972981750965,
|
92 |
-
"eval_mean_accuracy": 0.9862322846315924,
|
93 |
-
"eval_mean_iou": 0.4931161423157962,
|
94 |
-
"eval_overall_accuracy": 0.9862322846315924,
|
95 |
-
"eval_per_category_accuracy": [
|
96 |
-
NaN,
|
97 |
-
0.9862322846315924
|
98 |
-
],
|
99 |
-
"eval_per_category_iou": [
|
100 |
-
0.0,
|
101 |
-
0.9862322846315924
|
102 |
-
],
|
103 |
-
"eval_runtime": 552.922,
|
104 |
-
"eval_samples_per_second": 0.781,
|
105 |
-
"eval_steps_per_second": 0.033,
|
106 |
-
"step": 3400
|
107 |
-
},
|
108 |
-
{
|
109 |
-
"epoch": 11.0,
|
110 |
-
"learning_rate": 4.9999999999999996e-06,
|
111 |
-
"loss": 0.0188,
|
112 |
-
"step": 3740
|
113 |
-
},
|
114 |
-
{
|
115 |
-
"epoch": 11.0,
|
116 |
-
"eval_loss": 0.025399092584848404,
|
117 |
-
"eval_mean_accuracy": 0.9860250481098571,
|
118 |
-
"eval_mean_iou": 0.49301252405492857,
|
119 |
-
"eval_overall_accuracy": 0.9860250481098571,
|
120 |
-
"eval_per_category_accuracy": [
|
121 |
-
NaN,
|
122 |
-
0.9860250481098571
|
123 |
-
],
|
124 |
-
"eval_per_category_iou": [
|
125 |
-
0.0,
|
126 |
-
0.9860250481098571
|
127 |
-
],
|
128 |
-
"eval_runtime": 551.1038,
|
129 |
-
"eval_samples_per_second": 0.784,
|
130 |
-
"eval_steps_per_second": 0.033,
|
131 |
-
"step": 3740
|
132 |
-
},
|
133 |
-
{
|
134 |
-
"epoch": 12.0,
|
135 |
-
"learning_rate": 0.0,
|
136 |
-
"loss": 0.0178,
|
137 |
-
"step": 4080
|
138 |
-
},
|
139 |
-
{
|
140 |
-
"epoch": 12.0,
|
141 |
-
"eval_loss": 0.025657424703240395,
|
142 |
-
"eval_mean_accuracy": 0.9860068051184235,
|
143 |
-
"eval_mean_iou": 0.49300340255921177,
|
144 |
-
"eval_overall_accuracy": 0.9860068051184235,
|
145 |
-
"eval_per_category_accuracy": [
|
146 |
-
NaN,
|
147 |
-
0.9860068051184235
|
148 |
-
],
|
149 |
-
"eval_per_category_iou": [
|
150 |
-
0.0,
|
151 |
-
0.9860068051184235
|
152 |
-
],
|
153 |
-
"eval_runtime": 551.8762,
|
154 |
-
"eval_samples_per_second": 0.783,
|
155 |
-
"eval_steps_per_second": 0.033,
|
156 |
-
"step": 4080
|
157 |
-
},
|
158 |
-
{
|
159 |
-
"epoch": 13.0,
|
160 |
-
"learning_rate": 3.4e-05,
|
161 |
-
"loss": 0.0189,
|
162 |
-
"step": 4420
|
163 |
}
|
164 |
],
|
165 |
-
"max_steps":
|
166 |
-
"num_train_epochs":
|
167 |
-
"total_flos": 1.
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|
170 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 340,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
10 |
{
|
11 |
"epoch": 1.0,
|
12 |
"learning_rate": 5.5e-05,
|
13 |
+
"loss": 0.0183,
|
14 |
"step": 340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
16 |
],
|
17 |
+
"max_steps": 4080,
|
18 |
+
"num_train_epochs": 12,
|
19 |
+
"total_flos": 1.4294047727812608e+17,
|
20 |
"trial_name": null,
|
21 |
"trial_params": null
|
22 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3439
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71e42506d5cb3204d32acc9bb14ecf3f97efcc7ecc6326a8c573d37a7c31522e
|
3 |
size 3439
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14929953
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaafecba9c15d4a5aa7d768fc9d23505ef16daef82a897de40db243930b97861
|
3 |
size 14929953
|
runs/Aug01_18-12-22_8ec249145423/1659377547.8062894/events.out.tfevents.1659377547.8ec249145423.72.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64b27bab2e73c3c076b245cf182b31e68cbf2acc48ed3f559a4980254bc16d1a
|
3 |
+
size 5522
|
runs/Aug01_18-12-22_8ec249145423/events.out.tfevents.1659377547.8ec249145423.72.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3270582c2a0f06ce7f5b55527551d24136fe6469de8df70a052756ff6d420b59
|
3 |
+
size 4409
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3439
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71e42506d5cb3204d32acc9bb14ecf3f97efcc7ecc6326a8c573d37a7c31522e
|
3 |
size 3439
|