SiddharthaM
commited on
Commit
·
5db9bb2
1
Parent(s):
691d32a
End of training
Browse files- all_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Nov08_03-08-54_teesta/events.out.tfevents.1667857146.teesta.30780.0 +2 -2
- train_results.json +6 -6
- trainer_state.json +685 -85
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 49.8,
|
3 |
+
"total_flos": 3.197753854288036e+17,
|
4 |
+
"train_loss": 0.3222511351108551,
|
5 |
+
"train_runtime": 425.6784,
|
6 |
+
"train_samples_per_second": 74.704,
|
7 |
+
"train_steps_per_second": 0.235
|
8 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 44790413
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0216682802b08cfae03ccddd163dfb1cc827ba7be19fb8d48a91a8354b08617
|
3 |
size 44790413
|
runs/Nov08_03-08-54_teesta/events.out.tfevents.1667857146.teesta.30780.0
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 sha256:80fce727f490fe37bbfa6a867ff97ddf3c6ece236584580ed1954c6f25becb8b
|
3 |
+
size 31186
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 49.8,
|
3 |
+
"total_flos": 3.197753854288036e+17,
|
4 |
+
"train_loss": 0.3222511351108551,
|
5 |
+
"train_runtime": 425.6784,
|
6 |
+
"train_samples_per_second": 74.704,
|
7 |
+
"train_steps_per_second": 0.235
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,135 +1,735 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "resnet-18-feature-extraction/checkpoint-
|
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": 0.8,
|
12 |
-
"eval_accuracy": 0.
|
13 |
-
"eval_f1": 0.
|
14 |
-
"eval_loss":
|
15 |
-
"eval_precision": 0.
|
16 |
-
"eval_recall": 0.
|
17 |
-
"eval_roc_auc": 0.
|
18 |
-
"eval_runtime":
|
19 |
-
"eval_samples_per_second":
|
20 |
-
"eval_steps_per_second": 0.
|
21 |
"step": 2
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.8,
|
25 |
-
"eval_accuracy": 0.
|
26 |
-
"eval_f1": 0.
|
27 |
-
"eval_loss":
|
28 |
-
"eval_precision":
|
29 |
-
"eval_recall": 0.
|
30 |
-
"eval_roc_auc": 0.
|
31 |
-
"eval_runtime": 4.
|
32 |
-
"eval_samples_per_second": 38.
|
33 |
-
"eval_steps_per_second": 0.
|
34 |
"step": 4
|
35 |
},
|
36 |
{
|
37 |
"epoch": 2.8,
|
38 |
-
"eval_accuracy": 0.
|
39 |
-
"eval_f1": 0.
|
40 |
-
"eval_loss":
|
41 |
-
"eval_precision":
|
42 |
-
"eval_recall": 0.
|
43 |
-
"eval_roc_auc": 0.
|
44 |
-
"eval_runtime": 4.
|
45 |
-
"eval_samples_per_second":
|
46 |
-
"eval_steps_per_second": 0.
|
47 |
"step": 6
|
48 |
},
|
49 |
{
|
50 |
"epoch": 3.8,
|
51 |
-
"eval_accuracy": 0.
|
52 |
-
"eval_f1": 0.
|
53 |
-
"eval_loss":
|
54 |
-
"eval_precision":
|
55 |
-
"eval_recall": 0.
|
56 |
-
"eval_roc_auc": 0.
|
57 |
-
"eval_runtime":
|
58 |
-
"eval_samples_per_second":
|
59 |
-
"eval_steps_per_second": 0.
|
60 |
"step": 8
|
61 |
},
|
62 |
{
|
63 |
"epoch": 4.8,
|
64 |
-
"learning_rate":
|
65 |
-
"loss":
|
66 |
"step": 10
|
67 |
},
|
68 |
{
|
69 |
"epoch": 4.8,
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_f1": 0.
|
72 |
-
"eval_loss":
|
73 |
"eval_precision": 1.0,
|
74 |
-
"eval_recall": 0.
|
75 |
-
"eval_roc_auc": 0.
|
76 |
-
"eval_runtime": 4.
|
77 |
-
"eval_samples_per_second": 38.
|
78 |
-
"eval_steps_per_second": 0.
|
79 |
"step": 10
|
80 |
},
|
81 |
{
|
82 |
"epoch": 5.8,
|
83 |
-
"eval_accuracy": 0.
|
84 |
-
"eval_f1": 0.
|
85 |
-
"eval_loss": 0.
|
86 |
"eval_precision": 1.0,
|
87 |
-
"eval_recall": 0.
|
88 |
-
"eval_roc_auc": 0.
|
89 |
-
"eval_runtime":
|
90 |
-
"eval_samples_per_second":
|
91 |
-
"eval_steps_per_second": 0.
|
92 |
"step": 12
|
93 |
},
|
94 |
{
|
95 |
"epoch": 6.8,
|
96 |
-
"eval_accuracy": 0.
|
97 |
-
"eval_f1": 0.
|
98 |
-
"eval_loss": 0.
|
99 |
"eval_precision": 1.0,
|
100 |
-
"eval_recall": 0.
|
101 |
-
"eval_roc_auc": 0.
|
102 |
-
"eval_runtime": 4.
|
103 |
-
"eval_samples_per_second": 39.
|
104 |
-
"eval_steps_per_second": 0.
|
105 |
"step": 14
|
106 |
},
|
107 |
{
|
108 |
"epoch": 7.8,
|
109 |
-
"eval_accuracy": 0.
|
110 |
-
"eval_f1": 0.
|
111 |
-
"eval_loss": 0.
|
112 |
-
"eval_precision":
|
113 |
-
"eval_recall": 0.
|
114 |
-
"eval_roc_auc": 0.
|
115 |
-
"eval_runtime": 4.
|
116 |
-
"eval_samples_per_second":
|
117 |
-
"eval_steps_per_second": 0.
|
118 |
"step": 16
|
119 |
},
|
120 |
{
|
121 |
-
"epoch":
|
122 |
-
"
|
123 |
-
"
|
124 |
-
"
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
}
|
129 |
],
|
130 |
-
"max_steps":
|
131 |
-
"num_train_epochs":
|
132 |
-
"total_flos":
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|
135 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.95625,
|
3 |
+
"best_model_checkpoint": "resnet-18-feature-extraction/checkpoint-26",
|
4 |
+
"epoch": 49.8,
|
5 |
+
"global_step": 100,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.8,
|
12 |
+
"eval_accuracy": 0.75,
|
13 |
+
"eval_f1": 0.8412698412698413,
|
14 |
+
"eval_loss": 0.6231745481491089,
|
15 |
+
"eval_precision": 0.9636363636363636,
|
16 |
+
"eval_recall": 0.7464788732394366,
|
17 |
+
"eval_roc_auc": 0.7621283255086071,
|
18 |
+
"eval_runtime": 5.3474,
|
19 |
+
"eval_samples_per_second": 29.921,
|
20 |
+
"eval_steps_per_second": 0.561,
|
21 |
"step": 2
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.8,
|
25 |
+
"eval_accuracy": 0.4875,
|
26 |
+
"eval_f1": 0.5940594059405941,
|
27 |
+
"eval_loss": 0.6971184611320496,
|
28 |
+
"eval_precision": 1.0,
|
29 |
+
"eval_recall": 0.4225352112676056,
|
30 |
+
"eval_roc_auc": 0.7112676056338028,
|
31 |
+
"eval_runtime": 4.1245,
|
32 |
+
"eval_samples_per_second": 38.792,
|
33 |
+
"eval_steps_per_second": 0.727,
|
34 |
"step": 4
|
35 |
},
|
36 |
{
|
37 |
"epoch": 2.8,
|
38 |
+
"eval_accuracy": 0.2875,
|
39 |
+
"eval_f1": 0.32941176470588235,
|
40 |
+
"eval_loss": 0.7914562821388245,
|
41 |
+
"eval_precision": 1.0,
|
42 |
+
"eval_recall": 0.19718309859154928,
|
43 |
+
"eval_roc_auc": 0.5985915492957746,
|
44 |
+
"eval_runtime": 4.0788,
|
45 |
+
"eval_samples_per_second": 39.227,
|
46 |
+
"eval_steps_per_second": 0.736,
|
47 |
"step": 6
|
48 |
},
|
49 |
{
|
50 |
"epoch": 3.8,
|
51 |
+
"eval_accuracy": 0.2875,
|
52 |
+
"eval_f1": 0.32941176470588235,
|
53 |
+
"eval_loss": 0.8479948043823242,
|
54 |
+
"eval_precision": 1.0,
|
55 |
+
"eval_recall": 0.19718309859154928,
|
56 |
+
"eval_roc_auc": 0.5985915492957746,
|
57 |
+
"eval_runtime": 3.9544,
|
58 |
+
"eval_samples_per_second": 40.462,
|
59 |
+
"eval_steps_per_second": 0.759,
|
60 |
"step": 8
|
61 |
},
|
62 |
{
|
63 |
"epoch": 4.8,
|
64 |
+
"learning_rate": 2e-05,
|
65 |
+
"loss": 0.8651,
|
66 |
"step": 10
|
67 |
},
|
68 |
{
|
69 |
"epoch": 4.8,
|
70 |
+
"eval_accuracy": 0.25625,
|
71 |
+
"eval_f1": 0.2787878787878788,
|
72 |
+
"eval_loss": 0.9093517065048218,
|
73 |
"eval_precision": 1.0,
|
74 |
+
"eval_recall": 0.1619718309859155,
|
75 |
+
"eval_roc_auc": 0.5809859154929577,
|
76 |
+
"eval_runtime": 4.143,
|
77 |
+
"eval_samples_per_second": 38.62,
|
78 |
+
"eval_steps_per_second": 0.724,
|
79 |
"step": 10
|
80 |
},
|
81 |
{
|
82 |
"epoch": 5.8,
|
83 |
+
"eval_accuracy": 0.5625,
|
84 |
+
"eval_f1": 0.6728971962616822,
|
85 |
+
"eval_loss": 0.7470346689224243,
|
86 |
"eval_precision": 1.0,
|
87 |
+
"eval_recall": 0.5070422535211268,
|
88 |
+
"eval_roc_auc": 0.7535211267605634,
|
89 |
+
"eval_runtime": 3.9679,
|
90 |
+
"eval_samples_per_second": 40.323,
|
91 |
+
"eval_steps_per_second": 0.756,
|
92 |
"step": 12
|
93 |
},
|
94 |
{
|
95 |
"epoch": 6.8,
|
96 |
+
"eval_accuracy": 0.85,
|
97 |
+
"eval_f1": 0.9076923076923077,
|
98 |
+
"eval_loss": 0.5915343165397644,
|
99 |
"eval_precision": 1.0,
|
100 |
+
"eval_recall": 0.8309859154929577,
|
101 |
+
"eval_roc_auc": 0.9154929577464789,
|
102 |
+
"eval_runtime": 4.0338,
|
103 |
+
"eval_samples_per_second": 39.665,
|
104 |
+
"eval_steps_per_second": 0.744,
|
105 |
"step": 14
|
106 |
},
|
107 |
{
|
108 |
"epoch": 7.8,
|
109 |
+
"eval_accuracy": 0.8875,
|
110 |
+
"eval_f1": 0.9333333333333333,
|
111 |
+
"eval_loss": 0.4816938042640686,
|
112 |
+
"eval_precision": 0.984375,
|
113 |
+
"eval_recall": 0.8873239436619719,
|
114 |
+
"eval_roc_auc": 0.8881064162754304,
|
115 |
+
"eval_runtime": 4.0258,
|
116 |
+
"eval_samples_per_second": 39.743,
|
117 |
+
"eval_steps_per_second": 0.745,
|
118 |
"step": 16
|
119 |
},
|
120 |
{
|
121 |
+
"epoch": 8.8,
|
122 |
+
"eval_accuracy": 0.91875,
|
123 |
+
"eval_f1": 0.9530685920577617,
|
124 |
+
"eval_loss": 0.34547853469848633,
|
125 |
+
"eval_precision": 0.9777777777777777,
|
126 |
+
"eval_recall": 0.9295774647887324,
|
127 |
+
"eval_roc_auc": 0.881455399061033,
|
128 |
+
"eval_runtime": 3.9749,
|
129 |
+
"eval_samples_per_second": 40.253,
|
130 |
+
"eval_steps_per_second": 0.755,
|
131 |
+
"step": 18
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 9.8,
|
135 |
+
"learning_rate": 1.7777777777777777e-05,
|
136 |
+
"loss": 0.5349,
|
137 |
+
"step": 20
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 9.8,
|
141 |
+
"eval_accuracy": 0.91875,
|
142 |
+
"eval_f1": 0.9534050179211471,
|
143 |
+
"eval_loss": 0.29664501547813416,
|
144 |
+
"eval_precision": 0.9708029197080292,
|
145 |
+
"eval_recall": 0.9366197183098591,
|
146 |
+
"eval_roc_auc": 0.8571987480438183,
|
147 |
+
"eval_runtime": 4.2704,
|
148 |
+
"eval_samples_per_second": 37.467,
|
149 |
+
"eval_steps_per_second": 0.703,
|
150 |
+
"step": 20
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 10.8,
|
154 |
+
"eval_accuracy": 0.95,
|
155 |
+
"eval_f1": 0.972027972027972,
|
156 |
+
"eval_loss": 0.23471388220787048,
|
157 |
+
"eval_precision": 0.9652777777777778,
|
158 |
+
"eval_recall": 0.9788732394366197,
|
159 |
+
"eval_roc_auc": 0.850547730829421,
|
160 |
+
"eval_runtime": 3.9069,
|
161 |
+
"eval_samples_per_second": 40.953,
|
162 |
+
"eval_steps_per_second": 0.768,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 11.8,
|
167 |
+
"eval_accuracy": 0.93125,
|
168 |
+
"eval_f1": 0.9611307420494699,
|
169 |
+
"eval_loss": 0.2467934787273407,
|
170 |
+
"eval_precision": 0.9645390070921985,
|
171 |
+
"eval_recall": 0.9577464788732394,
|
172 |
+
"eval_roc_auc": 0.8399843505477309,
|
173 |
+
"eval_runtime": 4.025,
|
174 |
+
"eval_samples_per_second": 39.751,
|
175 |
+
"eval_steps_per_second": 0.745,
|
176 |
+
"step": 24
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 12.8,
|
180 |
+
"eval_accuracy": 0.95625,
|
181 |
+
"eval_f1": 0.9754385964912281,
|
182 |
+
"eval_loss": 0.23101434111595154,
|
183 |
+
"eval_precision": 0.972027972027972,
|
184 |
+
"eval_recall": 0.9788732394366197,
|
185 |
+
"eval_roc_auc": 0.8783255086071988,
|
186 |
+
"eval_runtime": 4.0457,
|
187 |
+
"eval_samples_per_second": 39.548,
|
188 |
+
"eval_steps_per_second": 0.742,
|
189 |
+
"step": 26
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 13.8,
|
193 |
+
"eval_accuracy": 0.93125,
|
194 |
+
"eval_f1": 0.9614035087719298,
|
195 |
+
"eval_loss": 0.2082931101322174,
|
196 |
+
"eval_precision": 0.958041958041958,
|
197 |
+
"eval_recall": 0.9647887323943662,
|
198 |
+
"eval_roc_auc": 0.8157276995305165,
|
199 |
+
"eval_runtime": 4.0645,
|
200 |
+
"eval_samples_per_second": 39.366,
|
201 |
+
"eval_steps_per_second": 0.738,
|
202 |
+
"step": 28
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 14.8,
|
206 |
+
"learning_rate": 1.555555555555556e-05,
|
207 |
+
"loss": 0.3593,
|
208 |
+
"step": 30
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 14.8,
|
212 |
+
"eval_accuracy": 0.9375,
|
213 |
+
"eval_f1": 0.9652777777777778,
|
214 |
+
"eval_loss": 0.18395133316516876,
|
215 |
+
"eval_precision": 0.952054794520548,
|
216 |
+
"eval_recall": 0.9788732394366197,
|
217 |
+
"eval_roc_auc": 0.7949921752738655,
|
218 |
+
"eval_runtime": 3.8518,
|
219 |
+
"eval_samples_per_second": 41.539,
|
220 |
+
"eval_steps_per_second": 0.779,
|
221 |
+
"step": 30
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 15.8,
|
225 |
+
"eval_accuracy": 0.9375,
|
226 |
+
"eval_f1": 0.9647887323943662,
|
227 |
+
"eval_loss": 0.19472570717334747,
|
228 |
+
"eval_precision": 0.9647887323943662,
|
229 |
+
"eval_recall": 0.9647887323943662,
|
230 |
+
"eval_roc_auc": 0.8435054773082942,
|
231 |
+
"eval_runtime": 4.1431,
|
232 |
+
"eval_samples_per_second": 38.618,
|
233 |
+
"eval_steps_per_second": 0.724,
|
234 |
+
"step": 32
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 16.8,
|
238 |
+
"eval_accuracy": 0.93125,
|
239 |
+
"eval_f1": 0.9616724738675958,
|
240 |
+
"eval_loss": 0.1836571842432022,
|
241 |
+
"eval_precision": 0.9517241379310345,
|
242 |
+
"eval_recall": 0.971830985915493,
|
243 |
+
"eval_roc_auc": 0.7914710485133021,
|
244 |
+
"eval_runtime": 4.0848,
|
245 |
+
"eval_samples_per_second": 39.17,
|
246 |
+
"eval_steps_per_second": 0.734,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 17.8,
|
251 |
+
"eval_accuracy": 0.94375,
|
252 |
+
"eval_f1": 0.9688581314878894,
|
253 |
+
"eval_loss": 0.1819494664669037,
|
254 |
+
"eval_precision": 0.9523809523809523,
|
255 |
+
"eval_recall": 0.9859154929577465,
|
256 |
+
"eval_roc_auc": 0.7985133020344288,
|
257 |
+
"eval_runtime": 3.9897,
|
258 |
+
"eval_samples_per_second": 40.104,
|
259 |
+
"eval_steps_per_second": 0.752,
|
260 |
+
"step": 36
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 18.8,
|
264 |
+
"eval_accuracy": 0.94375,
|
265 |
+
"eval_f1": 0.968421052631579,
|
266 |
+
"eval_loss": 0.19235201179981232,
|
267 |
+
"eval_precision": 0.965034965034965,
|
268 |
+
"eval_recall": 0.971830985915493,
|
269 |
+
"eval_roc_auc": 0.8470266040688575,
|
270 |
+
"eval_runtime": 4.041,
|
271 |
+
"eval_samples_per_second": 39.594,
|
272 |
+
"eval_steps_per_second": 0.742,
|
273 |
+
"step": 38
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 19.8,
|
277 |
+
"learning_rate": 1.3333333333333333e-05,
|
278 |
+
"loss": 0.2737,
|
279 |
+
"step": 40
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 19.8,
|
283 |
+
"eval_accuracy": 0.95,
|
284 |
+
"eval_f1": 0.972027972027972,
|
285 |
+
"eval_loss": 0.1990378201007843,
|
286 |
+
"eval_precision": 0.9652777777777778,
|
287 |
+
"eval_recall": 0.9788732394366197,
|
288 |
+
"eval_roc_auc": 0.850547730829421,
|
289 |
+
"eval_runtime": 4.1236,
|
290 |
+
"eval_samples_per_second": 38.801,
|
291 |
+
"eval_steps_per_second": 0.728,
|
292 |
+
"step": 40
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 20.8,
|
296 |
+
"eval_accuracy": 0.95,
|
297 |
+
"eval_f1": 0.971830985915493,
|
298 |
+
"eval_loss": 0.1758503019809723,
|
299 |
+
"eval_precision": 0.971830985915493,
|
300 |
+
"eval_recall": 0.971830985915493,
|
301 |
+
"eval_roc_auc": 0.8748043818466354,
|
302 |
+
"eval_runtime": 4.1193,
|
303 |
+
"eval_samples_per_second": 38.841,
|
304 |
+
"eval_steps_per_second": 0.728,
|
305 |
+
"step": 42
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 21.8,
|
309 |
+
"eval_accuracy": 0.93125,
|
310 |
+
"eval_f1": 0.9616724738675958,
|
311 |
+
"eval_loss": 0.18040268123149872,
|
312 |
+
"eval_precision": 0.9517241379310345,
|
313 |
+
"eval_recall": 0.971830985915493,
|
314 |
+
"eval_roc_auc": 0.7914710485133021,
|
315 |
+
"eval_runtime": 3.8662,
|
316 |
+
"eval_samples_per_second": 41.384,
|
317 |
+
"eval_steps_per_second": 0.776,
|
318 |
+
"step": 44
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 22.8,
|
322 |
+
"eval_accuracy": 0.93125,
|
323 |
+
"eval_f1": 0.9616724738675958,
|
324 |
+
"eval_loss": 0.16663400828838348,
|
325 |
+
"eval_precision": 0.9517241379310345,
|
326 |
+
"eval_recall": 0.971830985915493,
|
327 |
+
"eval_roc_auc": 0.7914710485133021,
|
328 |
+
"eval_runtime": 4.3016,
|
329 |
+
"eval_samples_per_second": 37.195,
|
330 |
+
"eval_steps_per_second": 0.697,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 23.8,
|
335 |
+
"eval_accuracy": 0.94375,
|
336 |
+
"eval_f1": 0.9688581314878894,
|
337 |
+
"eval_loss": 0.15337304770946503,
|
338 |
+
"eval_precision": 0.9523809523809523,
|
339 |
+
"eval_recall": 0.9859154929577465,
|
340 |
+
"eval_roc_auc": 0.7985133020344288,
|
341 |
+
"eval_runtime": 4.0456,
|
342 |
+
"eval_samples_per_second": 39.549,
|
343 |
+
"eval_steps_per_second": 0.742,
|
344 |
+
"step": 48
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 24.8,
|
348 |
+
"learning_rate": 1.1111111111111113e-05,
|
349 |
+
"loss": 0.2278,
|
350 |
+
"step": 50
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 24.8,
|
354 |
+
"eval_accuracy": 0.9375,
|
355 |
+
"eval_f1": 0.9652777777777778,
|
356 |
+
"eval_loss": 0.16116251051425934,
|
357 |
+
"eval_precision": 0.952054794520548,
|
358 |
+
"eval_recall": 0.9788732394366197,
|
359 |
+
"eval_roc_auc": 0.7949921752738655,
|
360 |
+
"eval_runtime": 4.0452,
|
361 |
+
"eval_samples_per_second": 39.553,
|
362 |
+
"eval_steps_per_second": 0.742,
|
363 |
+
"step": 50
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 25.8,
|
367 |
+
"eval_accuracy": 0.94375,
|
368 |
+
"eval_f1": 0.9686411149825783,
|
369 |
+
"eval_loss": 0.15349864959716797,
|
370 |
+
"eval_precision": 0.9586206896551724,
|
371 |
+
"eval_recall": 0.9788732394366197,
|
372 |
+
"eval_roc_auc": 0.8227699530516432,
|
373 |
+
"eval_runtime": 6.0991,
|
374 |
+
"eval_samples_per_second": 26.233,
|
375 |
+
"eval_steps_per_second": 0.492,
|
376 |
+
"step": 52
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 26.8,
|
380 |
+
"eval_accuracy": 0.94375,
|
381 |
+
"eval_f1": 0.9681978798586572,
|
382 |
+
"eval_loss": 0.1568022519350052,
|
383 |
+
"eval_precision": 0.9716312056737588,
|
384 |
+
"eval_recall": 0.9647887323943662,
|
385 |
+
"eval_roc_auc": 0.871283255086072,
|
386 |
+
"eval_runtime": 4.0891,
|
387 |
+
"eval_samples_per_second": 39.128,
|
388 |
+
"eval_steps_per_second": 0.734,
|
389 |
+
"step": 54
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 27.8,
|
393 |
+
"eval_accuracy": 0.9375,
|
394 |
+
"eval_f1": 0.9645390070921985,
|
395 |
+
"eval_loss": 0.21069078147411346,
|
396 |
+
"eval_precision": 0.9714285714285714,
|
397 |
+
"eval_recall": 0.9577464788732394,
|
398 |
+
"eval_roc_auc": 0.8677621283255086,
|
399 |
+
"eval_runtime": 4.1257,
|
400 |
+
"eval_samples_per_second": 38.781,
|
401 |
+
"eval_steps_per_second": 0.727,
|
402 |
+
"step": 56
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 28.8,
|
406 |
+
"eval_accuracy": 0.93125,
|
407 |
+
"eval_f1": 0.9616724738675958,
|
408 |
+
"eval_loss": 0.15922358632087708,
|
409 |
+
"eval_precision": 0.9517241379310345,
|
410 |
+
"eval_recall": 0.971830985915493,
|
411 |
+
"eval_roc_auc": 0.7914710485133021,
|
412 |
+
"eval_runtime": 3.944,
|
413 |
+
"eval_samples_per_second": 40.568,
|
414 |
+
"eval_steps_per_second": 0.761,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 29.8,
|
419 |
+
"learning_rate": 8.888888888888888e-06,
|
420 |
+
"loss": 0.2057,
|
421 |
+
"step": 60
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 29.8,
|
425 |
+
"eval_accuracy": 0.9375,
|
426 |
+
"eval_f1": 0.9647887323943662,
|
427 |
+
"eval_loss": 0.15567776560783386,
|
428 |
+
"eval_precision": 0.9647887323943662,
|
429 |
+
"eval_recall": 0.9647887323943662,
|
430 |
+
"eval_roc_auc": 0.8435054773082942,
|
431 |
+
"eval_runtime": 3.9386,
|
432 |
+
"eval_samples_per_second": 40.624,
|
433 |
+
"eval_steps_per_second": 0.762,
|
434 |
+
"step": 60
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 30.8,
|
438 |
+
"eval_accuracy": 0.94375,
|
439 |
+
"eval_f1": 0.968421052631579,
|
440 |
+
"eval_loss": 0.1714434176683426,
|
441 |
+
"eval_precision": 0.965034965034965,
|
442 |
+
"eval_recall": 0.971830985915493,
|
443 |
+
"eval_roc_auc": 0.8470266040688575,
|
444 |
+
"eval_runtime": 4.1925,
|
445 |
+
"eval_samples_per_second": 38.164,
|
446 |
+
"eval_steps_per_second": 0.716,
|
447 |
+
"step": 62
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 31.8,
|
451 |
+
"eval_accuracy": 0.95,
|
452 |
+
"eval_f1": 0.972027972027972,
|
453 |
+
"eval_loss": 0.15714499354362488,
|
454 |
+
"eval_precision": 0.9652777777777778,
|
455 |
+
"eval_recall": 0.9788732394366197,
|
456 |
+
"eval_roc_auc": 0.850547730829421,
|
457 |
+
"eval_runtime": 4.3684,
|
458 |
+
"eval_samples_per_second": 36.627,
|
459 |
+
"eval_steps_per_second": 0.687,
|
460 |
+
"step": 64
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 32.8,
|
464 |
+
"eval_accuracy": 0.9375,
|
465 |
+
"eval_f1": 0.965034965034965,
|
466 |
+
"eval_loss": 0.15739548206329346,
|
467 |
+
"eval_precision": 0.9583333333333334,
|
468 |
+
"eval_recall": 0.971830985915493,
|
469 |
+
"eval_roc_auc": 0.8192488262910799,
|
470 |
+
"eval_runtime": 3.9613,
|
471 |
+
"eval_samples_per_second": 40.39,
|
472 |
+
"eval_steps_per_second": 0.757,
|
473 |
+
"step": 66
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 33.8,
|
477 |
+
"eval_accuracy": 0.95625,
|
478 |
+
"eval_f1": 0.9754385964912281,
|
479 |
+
"eval_loss": 0.1422826498746872,
|
480 |
+
"eval_precision": 0.972027972027972,
|
481 |
+
"eval_recall": 0.9788732394366197,
|
482 |
+
"eval_roc_auc": 0.8783255086071988,
|
483 |
+
"eval_runtime": 3.9825,
|
484 |
+
"eval_samples_per_second": 40.175,
|
485 |
+
"eval_steps_per_second": 0.753,
|
486 |
+
"step": 68
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 34.8,
|
490 |
+
"learning_rate": 6.666666666666667e-06,
|
491 |
+
"loss": 0.2,
|
492 |
+
"step": 70
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 34.8,
|
496 |
+
"eval_accuracy": 0.94375,
|
497 |
+
"eval_f1": 0.968421052631579,
|
498 |
+
"eval_loss": 0.16770192980766296,
|
499 |
+
"eval_precision": 0.965034965034965,
|
500 |
+
"eval_recall": 0.971830985915493,
|
501 |
+
"eval_roc_auc": 0.8470266040688575,
|
502 |
+
"eval_runtime": 4.1697,
|
503 |
+
"eval_samples_per_second": 38.372,
|
504 |
+
"eval_steps_per_second": 0.719,
|
505 |
+
"step": 70
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 35.8,
|
509 |
+
"eval_accuracy": 0.9375,
|
510 |
+
"eval_f1": 0.965034965034965,
|
511 |
+
"eval_loss": 0.1559743881225586,
|
512 |
+
"eval_precision": 0.9583333333333334,
|
513 |
+
"eval_recall": 0.971830985915493,
|
514 |
+
"eval_roc_auc": 0.8192488262910799,
|
515 |
+
"eval_runtime": 4.0897,
|
516 |
+
"eval_samples_per_second": 39.123,
|
517 |
+
"eval_steps_per_second": 0.734,
|
518 |
+
"step": 72
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 36.8,
|
522 |
+
"eval_accuracy": 0.9375,
|
523 |
+
"eval_f1": 0.9652777777777778,
|
524 |
+
"eval_loss": 0.15941758453845978,
|
525 |
+
"eval_precision": 0.952054794520548,
|
526 |
+
"eval_recall": 0.9788732394366197,
|
527 |
+
"eval_roc_auc": 0.7949921752738655,
|
528 |
+
"eval_runtime": 4.0474,
|
529 |
+
"eval_samples_per_second": 39.531,
|
530 |
+
"eval_steps_per_second": 0.741,
|
531 |
+
"step": 74
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 37.8,
|
535 |
+
"eval_accuracy": 0.94375,
|
536 |
+
"eval_f1": 0.9686411149825783,
|
537 |
+
"eval_loss": 0.15121030807495117,
|
538 |
+
"eval_precision": 0.9586206896551724,
|
539 |
+
"eval_recall": 0.9788732394366197,
|
540 |
+
"eval_roc_auc": 0.8227699530516432,
|
541 |
+
"eval_runtime": 4.2667,
|
542 |
+
"eval_samples_per_second": 37.499,
|
543 |
+
"eval_steps_per_second": 0.703,
|
544 |
+
"step": 76
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 38.8,
|
548 |
+
"eval_accuracy": 0.95625,
|
549 |
+
"eval_f1": 0.975609756097561,
|
550 |
+
"eval_loss": 0.13959212601184845,
|
551 |
+
"eval_precision": 0.9655172413793104,
|
552 |
+
"eval_recall": 0.9859154929577465,
|
553 |
+
"eval_roc_auc": 0.8540688575899843,
|
554 |
+
"eval_runtime": 4.0576,
|
555 |
+
"eval_samples_per_second": 39.432,
|
556 |
+
"eval_steps_per_second": 0.739,
|
557 |
+
"step": 78
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 39.8,
|
561 |
+
"learning_rate": 4.444444444444444e-06,
|
562 |
+
"loss": 0.1838,
|
563 |
+
"step": 80
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 39.8,
|
567 |
+
"eval_accuracy": 0.9375,
|
568 |
+
"eval_f1": 0.965034965034965,
|
569 |
+
"eval_loss": 0.15085594356060028,
|
570 |
+
"eval_precision": 0.9583333333333334,
|
571 |
+
"eval_recall": 0.971830985915493,
|
572 |
+
"eval_roc_auc": 0.8192488262910799,
|
573 |
+
"eval_runtime": 3.9857,
|
574 |
+
"eval_samples_per_second": 40.144,
|
575 |
+
"eval_steps_per_second": 0.753,
|
576 |
+
"step": 80
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 40.8,
|
580 |
+
"eval_accuracy": 0.95,
|
581 |
+
"eval_f1": 0.971830985915493,
|
582 |
+
"eval_loss": 0.15287616848945618,
|
583 |
+
"eval_precision": 0.971830985915493,
|
584 |
+
"eval_recall": 0.971830985915493,
|
585 |
+
"eval_roc_auc": 0.8748043818466354,
|
586 |
+
"eval_runtime": 5.1236,
|
587 |
+
"eval_samples_per_second": 31.228,
|
588 |
+
"eval_steps_per_second": 0.586,
|
589 |
+
"step": 82
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 41.8,
|
593 |
+
"eval_accuracy": 0.95,
|
594 |
+
"eval_f1": 0.972027972027972,
|
595 |
+
"eval_loss": 0.1505597084760666,
|
596 |
+
"eval_precision": 0.9652777777777778,
|
597 |
+
"eval_recall": 0.9788732394366197,
|
598 |
+
"eval_roc_auc": 0.850547730829421,
|
599 |
+
"eval_runtime": 4.2192,
|
600 |
+
"eval_samples_per_second": 37.921,
|
601 |
+
"eval_steps_per_second": 0.711,
|
602 |
+
"step": 84
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 42.8,
|
606 |
+
"eval_accuracy": 0.95,
|
607 |
+
"eval_f1": 0.972027972027972,
|
608 |
+
"eval_loss": 0.1549244374036789,
|
609 |
+
"eval_precision": 0.9652777777777778,
|
610 |
+
"eval_recall": 0.9788732394366197,
|
611 |
+
"eval_roc_auc": 0.850547730829421,
|
612 |
+
"eval_runtime": 3.8602,
|
613 |
+
"eval_samples_per_second": 41.448,
|
614 |
+
"eval_steps_per_second": 0.777,
|
615 |
+
"step": 86
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 43.8,
|
619 |
+
"eval_accuracy": 0.95625,
|
620 |
+
"eval_f1": 0.975609756097561,
|
621 |
+
"eval_loss": 0.13305585086345673,
|
622 |
+
"eval_precision": 0.9655172413793104,
|
623 |
+
"eval_recall": 0.9859154929577465,
|
624 |
+
"eval_roc_auc": 0.8540688575899843,
|
625 |
+
"eval_runtime": 4.2919,
|
626 |
+
"eval_samples_per_second": 37.28,
|
627 |
+
"eval_steps_per_second": 0.699,
|
628 |
+
"step": 88
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 44.8,
|
632 |
+
"learning_rate": 2.222222222222222e-06,
|
633 |
+
"loss": 0.1872,
|
634 |
+
"step": 90
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 44.8,
|
638 |
+
"eval_accuracy": 0.94375,
|
639 |
+
"eval_f1": 0.9688581314878894,
|
640 |
+
"eval_loss": 0.14087018370628357,
|
641 |
+
"eval_precision": 0.9523809523809523,
|
642 |
+
"eval_recall": 0.9859154929577465,
|
643 |
+
"eval_roc_auc": 0.7985133020344288,
|
644 |
+
"eval_runtime": 4.0748,
|
645 |
+
"eval_samples_per_second": 39.266,
|
646 |
+
"eval_steps_per_second": 0.736,
|
647 |
+
"step": 90
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 45.8,
|
651 |
+
"eval_accuracy": 0.9375,
|
652 |
+
"eval_f1": 0.965034965034965,
|
653 |
+
"eval_loss": 0.1639305055141449,
|
654 |
+
"eval_precision": 0.9583333333333334,
|
655 |
+
"eval_recall": 0.971830985915493,
|
656 |
+
"eval_roc_auc": 0.8192488262910799,
|
657 |
+
"eval_runtime": 3.9376,
|
658 |
+
"eval_samples_per_second": 40.634,
|
659 |
+
"eval_steps_per_second": 0.762,
|
660 |
+
"step": 92
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 46.8,
|
664 |
+
"eval_accuracy": 0.95,
|
665 |
+
"eval_f1": 0.9722222222222222,
|
666 |
+
"eval_loss": 0.1390833854675293,
|
667 |
+
"eval_precision": 0.958904109589041,
|
668 |
+
"eval_recall": 0.9859154929577465,
|
669 |
+
"eval_roc_auc": 0.8262910798122067,
|
670 |
+
"eval_runtime": 3.9934,
|
671 |
+
"eval_samples_per_second": 40.066,
|
672 |
+
"eval_steps_per_second": 0.751,
|
673 |
+
"step": 94
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 47.8,
|
677 |
+
"eval_accuracy": 0.95625,
|
678 |
+
"eval_f1": 0.975609756097561,
|
679 |
+
"eval_loss": 0.14361494779586792,
|
680 |
+
"eval_precision": 0.9655172413793104,
|
681 |
+
"eval_recall": 0.9859154929577465,
|
682 |
+
"eval_roc_auc": 0.8540688575899843,
|
683 |
+
"eval_runtime": 4.2477,
|
684 |
+
"eval_samples_per_second": 37.667,
|
685 |
+
"eval_steps_per_second": 0.706,
|
686 |
+
"step": 96
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 48.8,
|
690 |
+
"eval_accuracy": 0.94375,
|
691 |
+
"eval_f1": 0.9686411149825783,
|
692 |
+
"eval_loss": 0.1442493200302124,
|
693 |
+
"eval_precision": 0.9586206896551724,
|
694 |
+
"eval_recall": 0.9788732394366197,
|
695 |
+
"eval_roc_auc": 0.8227699530516432,
|
696 |
+
"eval_runtime": 4.0963,
|
697 |
+
"eval_samples_per_second": 39.059,
|
698 |
+
"eval_steps_per_second": 0.732,
|
699 |
+
"step": 98
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 49.8,
|
703 |
+
"learning_rate": 0.0,
|
704 |
+
"loss": 0.185,
|
705 |
+
"step": 100
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 49.8,
|
709 |
+
"eval_accuracy": 0.95,
|
710 |
+
"eval_f1": 0.972027972027972,
|
711 |
+
"eval_loss": 0.1484707146883011,
|
712 |
+
"eval_precision": 0.9652777777777778,
|
713 |
+
"eval_recall": 0.9788732394366197,
|
714 |
+
"eval_roc_auc": 0.850547730829421,
|
715 |
+
"eval_runtime": 3.8936,
|
716 |
+
"eval_samples_per_second": 41.093,
|
717 |
+
"eval_steps_per_second": 0.77,
|
718 |
+
"step": 100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 49.8,
|
722 |
+
"step": 100,
|
723 |
+
"total_flos": 3.197753854288036e+17,
|
724 |
+
"train_loss": 0.3222511351108551,
|
725 |
+
"train_runtime": 425.6784,
|
726 |
+
"train_samples_per_second": 74.704,
|
727 |
+
"train_steps_per_second": 0.235
|
728 |
}
|
729 |
],
|
730 |
+
"max_steps": 100,
|
731 |
+
"num_train_epochs": 50,
|
732 |
+
"total_flos": 3.197753854288036e+17,
|
733 |
"trial_name": null,
|
734 |
"trial_params": null
|
735 |
}
|