Upload folder using huggingface_hub
Browse files
training_checkpoints/checkpoint-1120/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 263153912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83cf3cd7d40235337bb018df172211a6db8d4c24219c88f1cf56b863fca8f9bd
|
3 |
size 263153912
|
training_checkpoints/checkpoint-1120/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 526369978
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91735e8a702fdc76bf72c71a50431395bab39ece2b243d6a8eec0841aab84933
|
3 |
size 526369978
|
training_checkpoints/checkpoint-1120/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fc72debd89cf987f645165b85aacd28e6c9fb02087f12ec8a85ab200479cd04
|
3 |
size 1064
|
training_checkpoints/checkpoint-1120/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "case-analysis-distilbert-base-cased/checkpoint-
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1120,
|
@@ -10,126 +10,126 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_f1_macro": 0.
|
15 |
-
"eval_f1_micro": 0.
|
16 |
-
"eval_f1_weighted": 0.
|
17 |
-
"eval_loss": 0.
|
18 |
-
"eval_macro_fpr": 0.
|
19 |
-
"eval_macro_sensitivity": 0.
|
20 |
-
"eval_macro_specificity": 0.
|
21 |
-
"eval_precision": 0.
|
22 |
-
"eval_precision_macro": 0.
|
23 |
-
"eval_recall": 0.
|
24 |
-
"eval_recall_macro": 0.
|
25 |
-
"eval_runtime": 5.
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_steps_per_second": 10.
|
28 |
-
"eval_weighted_fpr": 0.
|
29 |
-
"eval_weighted_sensitivity": 0.
|
30 |
-
"eval_weighted_specificity": 0.
|
31 |
"step": 224
|
32 |
},
|
33 |
{
|
34 |
"epoch": 2.0,
|
35 |
-
"eval_accuracy": 0.
|
36 |
-
"eval_f1_macro": 0.
|
37 |
-
"eval_f1_micro": 0.
|
38 |
-
"eval_f1_weighted": 0.
|
39 |
-
"eval_loss": 0.
|
40 |
-
"eval_macro_fpr": 0.
|
41 |
-
"eval_macro_sensitivity": 0.
|
42 |
-
"eval_macro_specificity": 0.
|
43 |
-
"eval_precision": 0.
|
44 |
-
"eval_precision_macro": 0.
|
45 |
-
"eval_recall": 0.
|
46 |
-
"eval_recall_macro": 0.
|
47 |
-
"eval_runtime":
|
48 |
-
"eval_samples_per_second": 19.
|
49 |
-
"eval_steps_per_second": 2.
|
50 |
-
"eval_weighted_fpr": 0.
|
51 |
-
"eval_weighted_sensitivity": 0.
|
52 |
-
"eval_weighted_specificity": 0.
|
53 |
"step": 448
|
54 |
},
|
55 |
{
|
56 |
"epoch": 2.232142857142857,
|
57 |
-
"grad_norm":
|
58 |
-
"learning_rate": 4.
|
59 |
-
"loss": 0.
|
60 |
"step": 500
|
61 |
},
|
62 |
{
|
63 |
"epoch": 3.0,
|
64 |
-
"eval_accuracy": 0.
|
65 |
-
"eval_f1_macro": 0.
|
66 |
-
"eval_f1_micro": 0.
|
67 |
-
"eval_f1_weighted": 0.
|
68 |
-
"eval_loss": 0.
|
69 |
-
"eval_macro_fpr": 0.
|
70 |
-
"eval_macro_sensitivity": 0.
|
71 |
-
"eval_macro_specificity": 0.
|
72 |
-
"eval_precision": 0.
|
73 |
-
"eval_precision_macro": 0.
|
74 |
-
"eval_recall": 0.
|
75 |
-
"eval_recall_macro": 0.
|
76 |
-
"eval_runtime":
|
77 |
-
"eval_samples_per_second":
|
78 |
-
"eval_steps_per_second":
|
79 |
-
"eval_weighted_fpr": 0.
|
80 |
-
"eval_weighted_sensitivity": 0.
|
81 |
-
"eval_weighted_specificity": 0.
|
82 |
"step": 672
|
83 |
},
|
84 |
{
|
85 |
"epoch": 4.0,
|
86 |
-
"eval_accuracy": 0.
|
87 |
-
"eval_f1_macro": 0.
|
88 |
-
"eval_f1_micro": 0.
|
89 |
-
"eval_f1_weighted": 0.
|
90 |
-
"eval_loss": 0.
|
91 |
-
"eval_macro_fpr": 0.
|
92 |
-
"eval_macro_sensitivity": 0.
|
93 |
-
"eval_macro_specificity": 0.
|
94 |
-
"eval_precision": 0.
|
95 |
-
"eval_precision_macro": 0.
|
96 |
-
"eval_recall": 0.
|
97 |
-
"eval_recall_macro": 0.
|
98 |
-
"eval_runtime":
|
99 |
-
"eval_samples_per_second":
|
100 |
-
"eval_steps_per_second":
|
101 |
-
"eval_weighted_fpr": 0.
|
102 |
-
"eval_weighted_sensitivity": 0.
|
103 |
-
"eval_weighted_specificity": 0.
|
104 |
"step": 896
|
105 |
},
|
106 |
{
|
107 |
"epoch": 4.464285714285714,
|
108 |
-
"grad_norm":
|
109 |
-
"learning_rate": 4.
|
110 |
-
"loss": 0.
|
111 |
"step": 1000
|
112 |
},
|
113 |
{
|
114 |
"epoch": 5.0,
|
115 |
-
"eval_accuracy": 0.
|
116 |
-
"eval_f1_macro": 0.
|
117 |
-
"eval_f1_micro": 0.
|
118 |
-
"eval_f1_weighted": 0.
|
119 |
-
"eval_loss":
|
120 |
-
"eval_macro_fpr": 0.
|
121 |
-
"eval_macro_sensitivity": 0.
|
122 |
-
"eval_macro_specificity": 0.
|
123 |
-
"eval_precision": 0.
|
124 |
-
"eval_precision_macro": 0.
|
125 |
-
"eval_recall": 0.
|
126 |
-
"eval_recall_macro": 0.
|
127 |
-
"eval_runtime":
|
128 |
-
"eval_samples_per_second":
|
129 |
-
"eval_steps_per_second": 2.
|
130 |
-
"eval_weighted_fpr": 0.
|
131 |
-
"eval_weighted_sensitivity": 0.
|
132 |
-
"eval_weighted_specificity": 0.
|
133 |
"step": 1120
|
134 |
}
|
135 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6301119928151375,
|
3 |
+
"best_model_checkpoint": "case-analysis-distilbert-base-cased/checkpoint-896",
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1120,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.7661469933184856,
|
14 |
+
"eval_f1_macro": 0.5270352134866867,
|
15 |
+
"eval_f1_micro": 0.7661469933184856,
|
16 |
+
"eval_f1_weighted": 0.7333313004442764,
|
17 |
+
"eval_loss": 0.7000867128372192,
|
18 |
+
"eval_macro_fpr": 0.1330263157894737,
|
19 |
+
"eval_macro_sensitivity": 0.5137440725676019,
|
20 |
+
"eval_macro_specificity": 0.8818942592408516,
|
21 |
+
"eval_precision": 0.7310834070149471,
|
22 |
+
"eval_precision_macro": 0.5790641299401408,
|
23 |
+
"eval_recall": 0.7661469933184856,
|
24 |
+
"eval_recall_macro": 0.5137440725676019,
|
25 |
+
"eval_runtime": 5.4998,
|
26 |
+
"eval_samples_per_second": 81.639,
|
27 |
+
"eval_steps_per_second": 10.364,
|
28 |
+
"eval_weighted_fpr": 0.09234828496042216,
|
29 |
+
"eval_weighted_sensitivity": 0.7661469933184856,
|
30 |
+
"eval_weighted_specificity": 0.761430043644921,
|
31 |
"step": 224
|
32 |
},
|
33 |
{
|
34 |
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.7750556792873051,
|
36 |
+
"eval_f1_macro": 0.5486718521990608,
|
37 |
+
"eval_f1_micro": 0.775055679287305,
|
38 |
+
"eval_f1_weighted": 0.7492575717498114,
|
39 |
+
"eval_loss": 0.7387592792510986,
|
40 |
+
"eval_macro_fpr": 0.12078200823200373,
|
41 |
+
"eval_macro_sensitivity": 0.5464266787796199,
|
42 |
+
"eval_macro_specificity": 0.8914743027952345,
|
43 |
+
"eval_precision": 0.7315284458297402,
|
44 |
+
"eval_precision_macro": 0.5585311316366537,
|
45 |
+
"eval_recall": 0.7750556792873051,
|
46 |
+
"eval_recall_macro": 0.5464266787796199,
|
47 |
+
"eval_runtime": 23.5227,
|
48 |
+
"eval_samples_per_second": 19.088,
|
49 |
+
"eval_steps_per_second": 2.423,
|
50 |
+
"eval_weighted_fpr": 0.08820960698689956,
|
51 |
+
"eval_weighted_sensitivity": 0.7750556792873051,
|
52 |
+
"eval_weighted_specificity": 0.7908415318936333,
|
53 |
"step": 448
|
54 |
},
|
55 |
{
|
56 |
"epoch": 2.232142857142857,
|
57 |
+
"grad_norm": 22.91168785095215,
|
58 |
+
"learning_rate": 4.629464285714286e-05,
|
59 |
+
"loss": 0.7066,
|
60 |
"step": 500
|
61 |
},
|
62 |
{
|
63 |
"epoch": 3.0,
|
64 |
+
"eval_accuracy": 0.8017817371937639,
|
65 |
+
"eval_f1_macro": 0.576677451756589,
|
66 |
+
"eval_f1_micro": 0.8017817371937639,
|
67 |
+
"eval_f1_weighted": 0.7759761601356532,
|
68 |
+
"eval_loss": 0.7228724956512451,
|
69 |
+
"eval_macro_fpr": 0.10757194512338594,
|
70 |
+
"eval_macro_sensitivity": 0.5707859310800487,
|
71 |
+
"eval_macro_specificity": 0.9026901603449184,
|
72 |
+
"eval_precision": 0.7604834726234316,
|
73 |
+
"eval_precision_macro": 0.5932281353135314,
|
74 |
+
"eval_recall": 0.8017817371937639,
|
75 |
+
"eval_recall_macro": 0.5707859310800487,
|
76 |
+
"eval_runtime": 17.5142,
|
77 |
+
"eval_samples_per_second": 25.636,
|
78 |
+
"eval_steps_per_second": 3.254,
|
79 |
+
"eval_weighted_fpr": 0.07613344739093242,
|
80 |
+
"eval_weighted_sensitivity": 0.8017817371937639,
|
81 |
+
"eval_weighted_specificity": 0.8089789041859096,
|
82 |
"step": 672
|
83 |
},
|
84 |
{
|
85 |
"epoch": 4.0,
|
86 |
+
"eval_accuracy": 0.8062360801781737,
|
87 |
+
"eval_f1_macro": 0.6301119928151375,
|
88 |
+
"eval_f1_micro": 0.8062360801781738,
|
89 |
+
"eval_f1_weighted": 0.7933630533945198,
|
90 |
+
"eval_loss": 0.8331468105316162,
|
91 |
+
"eval_macro_fpr": 0.10175133159747105,
|
92 |
+
"eval_macro_sensitivity": 0.6114882070764424,
|
93 |
+
"eval_macro_specificity": 0.9069973738423197,
|
94 |
+
"eval_precision": 0.7896315051078991,
|
95 |
+
"eval_precision_macro": 0.6674639062867935,
|
96 |
+
"eval_recall": 0.8062360801781737,
|
97 |
+
"eval_recall_macro": 0.6114882070764424,
|
98 |
+
"eval_runtime": 17.9901,
|
99 |
+
"eval_samples_per_second": 24.958,
|
100 |
+
"eval_steps_per_second": 3.168,
|
101 |
+
"eval_weighted_fpr": 0.0741687979539642,
|
102 |
+
"eval_weighted_sensitivity": 0.8062360801781737,
|
103 |
+
"eval_weighted_specificity": 0.8217534151911048,
|
104 |
"step": 896
|
105 |
},
|
106 |
{
|
107 |
"epoch": 4.464285714285714,
|
108 |
+
"grad_norm": 0.23617026209831238,
|
109 |
+
"learning_rate": 4.258184523809524e-05,
|
110 |
+
"loss": 0.3654,
|
111 |
"step": 1000
|
112 |
},
|
113 |
{
|
114 |
"epoch": 5.0,
|
115 |
+
"eval_accuracy": 0.7683741648106904,
|
116 |
+
"eval_f1_macro": 0.5896043825978781,
|
117 |
+
"eval_f1_micro": 0.7683741648106904,
|
118 |
+
"eval_f1_weighted": 0.7610828501277613,
|
119 |
+
"eval_loss": 1.2299734354019165,
|
120 |
+
"eval_macro_fpr": 0.10662840460883276,
|
121 |
+
"eval_macro_sensitivity": 0.6130556645262528,
|
122 |
+
"eval_macro_specificity": 0.9056447032260023,
|
123 |
+
"eval_precision": 0.7698582566254396,
|
124 |
+
"eval_precision_macro": 0.6085394130060126,
|
125 |
+
"eval_recall": 0.7683741648106904,
|
126 |
+
"eval_recall_macro": 0.6130556645262528,
|
127 |
+
"eval_runtime": 19.5517,
|
128 |
+
"eval_samples_per_second": 22.965,
|
129 |
+
"eval_steps_per_second": 2.915,
|
130 |
+
"eval_weighted_fpr": 0.0913081650570676,
|
131 |
+
"eval_weighted_sensitivity": 0.7683741648106904,
|
132 |
+
"eval_weighted_specificity": 0.8542046480933186,
|
133 |
"step": 1120
|
134 |
}
|
135 |
],
|
training_checkpoints/checkpoint-1120/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3168244efe16c0aeafe631cea29ca8c9c2bbb665a169c0d40c2e4d22eaca40d9
|
3 |
size 5048
|