ShengdingHu
commited on
Commit
•
eccb4f7
1
Parent(s):
02d4d0f
Training in progress, step 200
Browse files- all_results.json +15 -9
- eval_results.json +6 -7
- pytorch_model.bin +1 -1
- runs/Feb01_00-07-44_node1/1643645355.1959577/events.out.tfevents.1643645355.node1 +3 -0
- runs/Feb01_00-07-44_node1/events.out.tfevents.1643645355.node1 +3 -0
- runs/Jan31_20-23-25_node1/events.out.tfevents.1643632055.node1 +2 -2
- runs/Jan31_20-23-25_node1/events.out.tfevents.1643632329.node1 +3 -0
- test_results.json +8 -0
- tokenizer.json +0 -0
- train_results.json +5 -5
- trainer_state.json +35 -107
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,14 +1,20 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy":
|
4 |
-
"
|
5 |
-
"
|
|
|
6 |
"eval_samples": 277,
|
7 |
-
"eval_samples_per_second":
|
8 |
"eval_steps_per_second": 6.498,
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
|
|
|
|
|
|
11 |
"train_samples": 2490,
|
12 |
-
"train_samples_per_second":
|
13 |
-
"train_steps_per_second":
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 75.36231884057972,
|
4 |
+
"eval_average_metrics": 75.36231884057972,
|
5 |
+
"eval_loss": 0.2184353768825531,
|
6 |
+
"eval_runtime": 0.505,
|
7 |
"eval_samples": 277,
|
8 |
+
"eval_samples_per_second": 273.265,
|
9 |
"eval_steps_per_second": 6.498,
|
10 |
+
"test_accuracy": 69.06474820143885,
|
11 |
+
"test_average_metrics": 69.06474820143885,
|
12 |
+
"test_loss": 0.26203805208206177,
|
13 |
+
"test_runtime": 0.5052,
|
14 |
+
"test_samples_per_second": 275.13,
|
15 |
+
"train_loss": 1.2798988037109376,
|
16 |
+
"train_runtime": 273.704,
|
17 |
"train_samples": 2490,
|
18 |
+
"train_samples_per_second": 181.948,
|
19 |
+
"train_steps_per_second": 1.827
|
20 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy":
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second": 6.498
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 75.36231884057972,
|
4 |
+
"eval_average_metrics": 75.36231884057972,
|
5 |
+
"eval_loss": 0.2184353768825531,
|
6 |
+
"eval_runtime": 0.505,
|
7 |
+
"eval_samples_per_second": 273.265
|
|
|
8 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1084131
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4779d2e8713715239b41a27c9b18d5cdab3da2fa582a864920cbc99d53191448
|
3 |
size 1084131
|
runs/Feb01_00-07-44_node1/1643645355.1959577/events.out.tfevents.1643645355.node1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e515efaad4d9cdeae1ee0df025c81ac44432fd6da84d7a172a360d29c5ce83e4
|
3 |
+
size 5008
|
runs/Feb01_00-07-44_node1/events.out.tfevents.1643645355.node1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14ccde1a1e9c47fc8a5c725b58f8cabb37d9015922ee898fffbb398f279eef0a
|
3 |
+
size 4301
|
runs/Jan31_20-23-25_node1/events.out.tfevents.1643632055.node1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21b275ce845e2942d13e0781632c37b6a26329d9cdaf390b4397fcb6fd5cafae
|
3 |
+
size 5456
|
runs/Jan31_20-23-25_node1/events.out.tfevents.1643632329.node1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c45e471d452b41652a038c57d839a3eeed2c7888282443217f676f871b148858
|
3 |
+
size 684
|
test_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"test_accuracy": 69.06474820143885,
|
4 |
+
"test_average_metrics": 69.06474820143885,
|
5 |
+
"test_loss": 0.26203805208206177,
|
6 |
+
"test_runtime": 0.5052,
|
7 |
+
"test_samples_per_second": 275.13
|
8 |
+
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 2490,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"train_loss": 1.2798988037109376,
|
4 |
+
"train_runtime": 273.704,
|
5 |
"train_samples": 2490,
|
6 |
+
"train_samples_per_second": 181.948,
|
7 |
+
"train_steps_per_second": 1.827
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,121 +1,49 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "outputs/
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 1.0,
|
12 |
-
"eval_accuracy": 0.4729241877256318,
|
13 |
-
"eval_loss": 0.755623996257782,
|
14 |
-
"eval_runtime": 0.4771,
|
15 |
-
"eval_samples_per_second": 580.569,
|
16 |
-
"eval_steps_per_second": 6.288,
|
17 |
-
"step": 78
|
18 |
-
},
|
19 |
-
{
|
20 |
-
"epoch": 2.0,
|
21 |
-
"eval_accuracy": 0.4729241877256318,
|
22 |
-
"eval_loss": 0.822638988494873,
|
23 |
-
"eval_runtime": 0.4598,
|
24 |
-
"eval_samples_per_second": 602.409,
|
25 |
-
"eval_steps_per_second": 6.524,
|
26 |
-
"step": 156
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 3.0,
|
30 |
-
"eval_accuracy": 0.4729241877256318,
|
31 |
-
"eval_loss": 0.7435575127601624,
|
32 |
-
"eval_runtime": 0.4678,
|
33 |
-
"eval_samples_per_second": 592.135,
|
34 |
-
"eval_steps_per_second": 6.413,
|
35 |
-
"step": 234
|
36 |
-
},
|
37 |
-
{
|
38 |
-
"epoch": 4.0,
|
39 |
-
"eval_accuracy": 0.5270758122743683,
|
40 |
-
"eval_loss": 0.7416719794273376,
|
41 |
-
"eval_runtime": 0.4671,
|
42 |
-
"eval_samples_per_second": 592.998,
|
43 |
-
"eval_steps_per_second": 6.422,
|
44 |
-
"step": 312
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 5.0,
|
48 |
-
"eval_accuracy": 0.5270758122743683,
|
49 |
-
"eval_loss": 0.694923996925354,
|
50 |
-
"eval_runtime": 0.4636,
|
51 |
-
"eval_samples_per_second": 597.536,
|
52 |
-
"eval_steps_per_second": 6.472,
|
53 |
-
"step": 390
|
54 |
-
},
|
55 |
-
{
|
56 |
-
"epoch": 6.0,
|
57 |
-
"eval_accuracy": 0.4729241877256318,
|
58 |
-
"eval_loss": 0.7276150584220886,
|
59 |
-
"eval_runtime": 0.469,
|
60 |
-
"eval_samples_per_second": 590.599,
|
61 |
-
"eval_steps_per_second": 6.396,
|
62 |
-
"step": 468
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 6.41,
|
66 |
-
"learning_rate": 0.001145975443383356,
|
67 |
-
"loss": 0.7468,
|
68 |
-
"step": 500
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 7.0,
|
72 |
-
"eval_accuracy": 0.4729241877256318,
|
73 |
-
"eval_loss": 0.7213642597198486,
|
74 |
-
"eval_runtime": 0.4575,
|
75 |
-
"eval_samples_per_second": 605.474,
|
76 |
-
"eval_steps_per_second": 6.557,
|
77 |
-
"step": 546
|
78 |
-
},
|
79 |
{
|
80 |
"epoch": 8.0,
|
81 |
-
"eval_accuracy":
|
82 |
-
"
|
83 |
-
"
|
84 |
-
"
|
85 |
-
"
|
86 |
-
"step":
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch":
|
90 |
-
"eval_accuracy":
|
91 |
-
"
|
92 |
-
"
|
93 |
-
"
|
94 |
-
"
|
95 |
-
"step":
|
96 |
-
},
|
97 |
-
{
|
98 |
-
"epoch":
|
99 |
-
"
|
100 |
-
"
|
101 |
-
"
|
102 |
-
"eval_samples_per_second": 585.163,
|
103 |
-
"eval_steps_per_second": 6.338,
|
104 |
-
"step": 780
|
105 |
},
|
106 |
{
|
107 |
-
"epoch":
|
108 |
-
"step":
|
109 |
-
"total_flos":
|
110 |
-
"train_loss":
|
111 |
-
"train_runtime":
|
112 |
-
"train_samples_per_second":
|
113 |
-
"train_steps_per_second":
|
114 |
}
|
115 |
],
|
116 |
-
"max_steps":
|
117 |
-
"num_train_epochs":
|
118 |
-
"total_flos":
|
119 |
"trial_name": null,
|
120 |
"trial_params": null
|
121 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 75.36231884057972,
|
3 |
+
"best_model_checkpoint": "outputs/bitfit/t5-base/rte/checkpoint-400",
|
4 |
+
"epoch": 20.0,
|
5 |
+
"global_step": 500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
{
|
11 |
"epoch": 8.0,
|
12 |
+
"eval_accuracy": 54.347826086956516,
|
13 |
+
"eval_average_metrics": 54.347826086956516,
|
14 |
+
"eval_loss": 0.3104463517665863,
|
15 |
+
"eval_runtime": 0.6899,
|
16 |
+
"eval_samples_per_second": 200.036,
|
17 |
+
"step": 200
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 16.0,
|
21 |
+
"eval_accuracy": 75.36231884057972,
|
22 |
+
"eval_average_metrics": 75.36231884057972,
|
23 |
+
"eval_loss": 0.2184353768825531,
|
24 |
+
"eval_runtime": 0.6861,
|
25 |
+
"eval_samples_per_second": 201.146,
|
26 |
+
"step": 400
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 20.0,
|
30 |
+
"learning_rate": 0.0,
|
31 |
+
"loss": 1.2799,
|
32 |
+
"step": 500
|
|
|
|
|
|
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 20.0,
|
36 |
+
"step": 500,
|
37 |
+
"total_flos": 7590919206297600.0,
|
38 |
+
"train_loss": 1.2798988037109376,
|
39 |
+
"train_runtime": 273.704,
|
40 |
+
"train_samples_per_second": 181.948,
|
41 |
+
"train_steps_per_second": 1.827
|
42 |
}
|
43 |
],
|
44 |
+
"max_steps": 500,
|
45 |
+
"num_train_epochs": 20,
|
46 |
+
"total_flos": 7590919206297600.0,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
49 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3183
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb2732fc0f205ecb2ff6a4dc01793c5bad05e44f957c3092d344cc75969c345d
|
3 |
size 3183
|