Upload folder using huggingface_hub
Browse files- training_checkpoints/checkpoint-1125/adapter_config.json +1 -1
- training_checkpoints/checkpoint-1125/adapter_model.safetensors +1 -1
- training_checkpoints/checkpoint-1125/optimizer.pt +1 -1
- training_checkpoints/checkpoint-1125/scheduler.pt +1 -1
- training_checkpoints/checkpoint-1125/trainer_state.json +133 -133
- training_checkpoints/checkpoint-1125/training_args.bin +1 -1
training_checkpoints/checkpoint-1125/adapter_config.json
CHANGED
@@ -21,8 +21,8 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"key",
|
24 |
-
"dense",
|
25 |
"value",
|
|
|
26 |
"query"
|
27 |
],
|
28 |
"task_type": "SEQ_CLS",
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"key",
|
|
|
24 |
"value",
|
25 |
+
"dense",
|
26 |
"query"
|
27 |
],
|
28 |
"task_type": "SEQ_CLS",
|
training_checkpoints/checkpoint-1125/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 104549068
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca6b02a5f83d3d6b2bbc636ee862fc1d6896a112b391969b1379ff2a2cc6774f
|
3 |
size 104549068
|
training_checkpoints/checkpoint-1125/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21646778
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a285e2020d2e294d6d26b5d7bc54971b751e4a19b4dfb1e292413766f04ab231
|
3 |
size 21646778
|
training_checkpoints/checkpoint-1125/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 sha256:40224493aacf0cd0f7038028ae3514743b7f864ad570d1dd323ebd02caa1c08b
|
3 |
size 1064
|
training_checkpoints/checkpoint-1125/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "legal-bert-lora/checkpoint-1125",
|
4 |
"epoch": 6.998444790046657,
|
5 |
"eval_steps": 500,
|
@@ -10,174 +10,174 @@
|
|
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": 1.
|
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":
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_steps_per_second":
|
28 |
-
"eval_weighted_fpr": 0.
|
29 |
-
"eval_weighted_sensitivity": 0.
|
30 |
-
"eval_weighted_specificity": 0.
|
31 |
"step": 160
|
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":
|
49 |
-
"eval_steps_per_second":
|
50 |
-
"eval_weighted_fpr": 0.
|
51 |
-
"eval_weighted_sensitivity": 0.
|
52 |
-
"eval_weighted_specificity": 0.
|
53 |
"step": 321
|
54 |
},
|
55 |
{
|
56 |
"epoch": 3.0,
|
57 |
-
"eval_accuracy": 0.
|
58 |
-
"eval_f1_macro": 0.
|
59 |
-
"eval_f1_micro": 0.
|
60 |
-
"eval_f1_weighted": 0.
|
61 |
-
"eval_loss": 0.
|
62 |
-
"eval_macro_fpr": 0.
|
63 |
-
"eval_macro_sensitivity": 0.
|
64 |
-
"eval_macro_specificity": 0.
|
65 |
-
"eval_precision": 0.
|
66 |
-
"eval_precision_macro": 0.
|
67 |
-
"eval_recall": 0.
|
68 |
-
"eval_recall_macro": 0.
|
69 |
-
"eval_runtime":
|
70 |
-
"eval_samples_per_second":
|
71 |
-
"eval_steps_per_second":
|
72 |
-
"eval_weighted_fpr": 0.
|
73 |
-
"eval_weighted_sensitivity": 0.
|
74 |
-
"eval_weighted_specificity": 0.
|
75 |
"step": 482
|
76 |
},
|
77 |
{
|
78 |
"epoch": 3.11,
|
79 |
-
"learning_rate": 3.
|
80 |
-
"loss": 1.
|
81 |
"step": 500
|
82 |
},
|
83 |
{
|
84 |
"epoch": 4.0,
|
85 |
-
"eval_accuracy": 0.
|
86 |
-
"eval_f1_macro": 0.
|
87 |
-
"eval_f1_micro": 0.
|
88 |
-
"eval_f1_weighted": 0.
|
89 |
-
"eval_loss": 0.
|
90 |
-
"eval_macro_fpr": 0.
|
91 |
-
"eval_macro_sensitivity": 0.
|
92 |
-
"eval_macro_specificity": 0.
|
93 |
-
"eval_precision": 0.
|
94 |
-
"eval_precision_macro": 0.
|
95 |
-
"eval_recall": 0.
|
96 |
-
"eval_recall_macro": 0.
|
97 |
-
"eval_runtime":
|
98 |
-
"eval_samples_per_second":
|
99 |
-
"eval_steps_per_second":
|
100 |
-
"eval_weighted_fpr": 0.
|
101 |
-
"eval_weighted_sensitivity": 0.
|
102 |
-
"eval_weighted_specificity": 0.
|
103 |
"step": 643
|
104 |
},
|
105 |
{
|
106 |
"epoch": 5.0,
|
107 |
-
"eval_accuracy": 0.
|
108 |
-
"eval_f1_macro": 0.
|
109 |
-
"eval_f1_micro": 0.
|
110 |
-
"eval_f1_weighted": 0.
|
111 |
-
"eval_loss": 0.
|
112 |
-
"eval_macro_fpr": 0.
|
113 |
-
"eval_macro_sensitivity": 0.
|
114 |
-
"eval_macro_specificity": 0.
|
115 |
-
"eval_precision": 0.
|
116 |
-
"eval_precision_macro": 0.
|
117 |
-
"eval_recall": 0.
|
118 |
-
"eval_recall_macro": 0.
|
119 |
-
"eval_runtime":
|
120 |
-
"eval_samples_per_second":
|
121 |
-
"eval_steps_per_second": 5.
|
122 |
-
"eval_weighted_fpr": 0.
|
123 |
-
"eval_weighted_sensitivity": 0.
|
124 |
-
"eval_weighted_specificity": 0.
|
125 |
"step": 803
|
126 |
},
|
127 |
{
|
128 |
"epoch": 6.0,
|
129 |
-
"eval_accuracy": 0.
|
130 |
-
"eval_f1_macro": 0.
|
131 |
-
"eval_f1_micro": 0.
|
132 |
-
"eval_f1_weighted": 0.
|
133 |
-
"eval_loss": 0.
|
134 |
-
"eval_macro_fpr": 0.
|
135 |
-
"eval_macro_sensitivity": 0.
|
136 |
-
"eval_macro_specificity": 0.
|
137 |
-
"eval_precision": 0.
|
138 |
-
"eval_precision_macro": 0.
|
139 |
-
"eval_recall": 0.
|
140 |
-
"eval_recall_macro": 0.
|
141 |
-
"eval_runtime":
|
142 |
-
"eval_samples_per_second":
|
143 |
-
"eval_steps_per_second": 5.
|
144 |
-
"eval_weighted_fpr": 0.
|
145 |
-
"eval_weighted_sensitivity": 0.
|
146 |
-
"eval_weighted_specificity": 0.
|
147 |
"step": 964
|
148 |
},
|
149 |
{
|
150 |
"epoch": 6.22,
|
151 |
-
"learning_rate":
|
152 |
-
"loss": 0.
|
153 |
"step": 1000
|
154 |
},
|
155 |
{
|
156 |
"epoch": 7.0,
|
157 |
-
"eval_accuracy": 0.
|
158 |
-
"eval_f1_macro": 0.
|
159 |
-
"eval_f1_micro": 0.
|
160 |
-
"eval_f1_weighted": 0.
|
161 |
-
"eval_loss": 0.
|
162 |
-
"eval_macro_fpr": 0.
|
163 |
-
"eval_macro_sensitivity": 0.
|
164 |
-
"eval_macro_specificity": 0.
|
165 |
-
"eval_precision": 0.
|
166 |
-
"eval_precision_macro": 0.
|
167 |
-
"eval_recall": 0.
|
168 |
-
"eval_recall_macro": 0.
|
169 |
-
"eval_runtime":
|
170 |
-
"eval_samples_per_second":
|
171 |
-
"eval_steps_per_second": 5.
|
172 |
-
"eval_weighted_fpr": 0.
|
173 |
-
"eval_weighted_sensitivity": 0.
|
174 |
-
"eval_weighted_specificity": 0.
|
175 |
"step": 1125
|
176 |
}
|
177 |
],
|
178 |
"logging_steps": 500,
|
179 |
-
"max_steps":
|
180 |
-
"num_train_epochs":
|
181 |
"save_steps": 500,
|
182 |
"total_flos": 9761403521544192.0,
|
183 |
"trial_name": null,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6191969834738721,
|
3 |
"best_model_checkpoint": "legal-bert-lora/checkpoint-1125",
|
4 |
"epoch": 6.998444790046657,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.6374903175832688,
|
14 |
+
"eval_f1_macro": 0.3394539856434376,
|
15 |
+
"eval_f1_micro": 0.6374903175832688,
|
16 |
+
"eval_f1_weighted": 0.5765523433851403,
|
17 |
+
"eval_loss": 1.3127473592758179,
|
18 |
+
"eval_macro_fpr": 0.040137717078130394,
|
19 |
+
"eval_macro_sensitivity": 0.4017115530536667,
|
20 |
+
"eval_macro_specificity": 0.9725650393599338,
|
21 |
+
"eval_precision": 0.5466227876047401,
|
22 |
+
"eval_precision_macro": 0.31141306924471374,
|
23 |
+
"eval_recall": 0.6374903175832688,
|
24 |
+
"eval_recall_macro": 0.4017115530536667,
|
25 |
+
"eval_runtime": 44.4128,
|
26 |
+
"eval_samples_per_second": 29.068,
|
27 |
+
"eval_steps_per_second": 3.648,
|
28 |
+
"eval_weighted_fpr": 0.0390325271059216,
|
29 |
+
"eval_weighted_sensitivity": 0.6374903175832688,
|
30 |
+
"eval_weighted_specificity": 0.950985272815738,
|
31 |
"step": 160
|
32 |
},
|
33 |
{
|
34 |
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.7273431448489543,
|
36 |
+
"eval_f1_macro": 0.3969800602789428,
|
37 |
+
"eval_f1_micro": 0.7273431448489543,
|
38 |
+
"eval_f1_weighted": 0.6960627383550935,
|
39 |
+
"eval_loss": 0.8160030841827393,
|
40 |
+
"eval_macro_fpr": 0.026417996388603746,
|
41 |
+
"eval_macro_sensitivity": 0.450135625445356,
|
42 |
+
"eval_macro_specificity": 0.9796396430402219,
|
43 |
+
"eval_precision": 0.6997929823446861,
|
44 |
+
"eval_precision_macro": 0.39453164470926966,
|
45 |
+
"eval_recall": 0.7273431448489543,
|
46 |
+
"eval_recall_macro": 0.450135625445356,
|
47 |
+
"eval_runtime": 34.3148,
|
48 |
+
"eval_samples_per_second": 37.622,
|
49 |
+
"eval_steps_per_second": 4.721,
|
50 |
+
"eval_weighted_fpr": 0.026077937472218107,
|
51 |
+
"eval_weighted_sensitivity": 0.7273431448489543,
|
52 |
+
"eval_weighted_specificity": 0.9672515007543734,
|
53 |
"step": 321
|
54 |
},
|
55 |
{
|
56 |
"epoch": 3.0,
|
57 |
+
"eval_accuracy": 0.7443841982958946,
|
58 |
+
"eval_f1_macro": 0.4210575074216338,
|
59 |
+
"eval_f1_micro": 0.7443841982958946,
|
60 |
+
"eval_f1_weighted": 0.7223603623418946,
|
61 |
+
"eval_loss": 0.7322217226028442,
|
62 |
+
"eval_macro_fpr": 0.024451015698283406,
|
63 |
+
"eval_macro_sensitivity": 0.46251578703813245,
|
64 |
+
"eval_macro_specificity": 0.9809603839363172,
|
65 |
+
"eval_precision": 0.711002444877192,
|
66 |
+
"eval_precision_macro": 0.4030436676815596,
|
67 |
+
"eval_recall": 0.7443841982958946,
|
68 |
+
"eval_recall_macro": 0.46251578703813245,
|
69 |
+
"eval_runtime": 32.8708,
|
70 |
+
"eval_samples_per_second": 39.275,
|
71 |
+
"eval_steps_per_second": 4.928,
|
72 |
+
"eval_weighted_fpr": 0.023940800928612886,
|
73 |
+
"eval_weighted_sensitivity": 0.7443841982958946,
|
74 |
+
"eval_weighted_specificity": 0.9700215607488639,
|
75 |
"step": 482
|
76 |
},
|
77 |
{
|
78 |
"epoch": 3.11,
|
79 |
+
"learning_rate": 3.958333333333333e-05,
|
80 |
+
"loss": 1.2229,
|
81 |
"step": 500
|
82 |
},
|
83 |
{
|
84 |
"epoch": 4.0,
|
85 |
+
"eval_accuracy": 0.7536793183578622,
|
86 |
+
"eval_f1_macro": 0.46141164864389705,
|
87 |
+
"eval_f1_micro": 0.7536793183578622,
|
88 |
+
"eval_f1_weighted": 0.7337325056665881,
|
89 |
+
"eval_loss": 0.7034952640533447,
|
90 |
+
"eval_macro_fpr": 0.023326126599014015,
|
91 |
+
"eval_macro_sensitivity": 0.4865735295815666,
|
92 |
+
"eval_macro_specificity": 0.9815978320880049,
|
93 |
+
"eval_precision": 0.7340611054176746,
|
94 |
+
"eval_precision_macro": 0.4982390488816621,
|
95 |
+
"eval_recall": 0.7536793183578622,
|
96 |
+
"eval_recall_macro": 0.4865735295815666,
|
97 |
+
"eval_runtime": 33.282,
|
98 |
+
"eval_samples_per_second": 38.79,
|
99 |
+
"eval_steps_per_second": 4.868,
|
100 |
+
"eval_weighted_fpr": 0.022812051649928264,
|
101 |
+
"eval_weighted_sensitivity": 0.7536793183578622,
|
102 |
+
"eval_weighted_specificity": 0.9702881629622103,
|
103 |
"step": 643
|
104 |
},
|
105 |
{
|
106 |
"epoch": 5.0,
|
107 |
+
"eval_accuracy": 0.7652982184353214,
|
108 |
+
"eval_f1_macro": 0.4824234674423381,
|
109 |
+
"eval_f1_micro": 0.7652982184353214,
|
110 |
+
"eval_f1_weighted": 0.7415202198150465,
|
111 |
+
"eval_loss": 0.6963701844215393,
|
112 |
+
"eval_macro_fpr": 0.022125198961045537,
|
113 |
+
"eval_macro_sensitivity": 0.5099998711032655,
|
114 |
+
"eval_macro_specificity": 0.982427621700107,
|
115 |
+
"eval_precision": 0.7403884847240659,
|
116 |
+
"eval_precision_macro": 0.5015009503316971,
|
117 |
+
"eval_recall": 0.7652982184353214,
|
118 |
+
"eval_recall_macro": 0.5099998711032655,
|
119 |
+
"eval_runtime": 29.8835,
|
120 |
+
"eval_samples_per_second": 43.201,
|
121 |
+
"eval_steps_per_second": 5.421,
|
122 |
+
"eval_weighted_fpr": 0.02143615139724089,
|
123 |
+
"eval_weighted_sensitivity": 0.7652982184353214,
|
124 |
+
"eval_weighted_specificity": 0.9711161070662828,
|
125 |
"step": 803
|
126 |
},
|
127 |
{
|
128 |
"epoch": 6.0,
|
129 |
+
"eval_accuracy": 0.7807900852052673,
|
130 |
+
"eval_f1_macro": 0.5371165387852578,
|
131 |
+
"eval_f1_micro": 0.7807900852052673,
|
132 |
+
"eval_f1_weighted": 0.7659242764458758,
|
133 |
+
"eval_loss": 0.684776246547699,
|
134 |
+
"eval_macro_fpr": 0.020129954279912522,
|
135 |
+
"eval_macro_sensitivity": 0.5604626117585171,
|
136 |
+
"eval_macro_specificity": 0.9836211797331506,
|
137 |
+
"eval_precision": 0.7919069236021963,
|
138 |
+
"eval_precision_macro": 0.5968972302554038,
|
139 |
+
"eval_recall": 0.7807900852052673,
|
140 |
+
"eval_recall_macro": 0.5604626117585171,
|
141 |
+
"eval_runtime": 29.4753,
|
142 |
+
"eval_samples_per_second": 43.799,
|
143 |
+
"eval_steps_per_second": 5.496,
|
144 |
+
"eval_weighted_fpr": 0.019659604029176797,
|
145 |
+
"eval_weighted_sensitivity": 0.7807900852052673,
|
146 |
+
"eval_weighted_specificity": 0.9735276107919913,
|
147 |
"step": 964
|
148 |
},
|
149 |
{
|
150 |
"epoch": 6.22,
|
151 |
+
"learning_rate": 2.916666666666667e-05,
|
152 |
+
"loss": 0.5985,
|
153 |
"step": 1000
|
154 |
},
|
155 |
{
|
156 |
"epoch": 7.0,
|
157 |
+
"eval_accuracy": 0.7978311386522076,
|
158 |
+
"eval_f1_macro": 0.6191969834738721,
|
159 |
+
"eval_f1_micro": 0.7978311386522076,
|
160 |
+
"eval_f1_weighted": 0.7857784690137476,
|
161 |
+
"eval_loss": 0.6644509434700012,
|
162 |
+
"eval_macro_fpr": 0.018390423375855742,
|
163 |
+
"eval_macro_sensitivity": 0.6251682037032721,
|
164 |
+
"eval_macro_specificity": 0.9848362780039965,
|
165 |
+
"eval_precision": 0.7880411922037887,
|
166 |
+
"eval_precision_macro": 0.6671036841379524,
|
167 |
+
"eval_recall": 0.7978311386522076,
|
168 |
+
"eval_recall_macro": 0.6251682037032721,
|
169 |
+
"eval_runtime": 29.8127,
|
170 |
+
"eval_samples_per_second": 43.304,
|
171 |
+
"eval_steps_per_second": 5.434,
|
172 |
+
"eval_weighted_fpr": 0.017778080512226686,
|
173 |
+
"eval_weighted_sensitivity": 0.7978311386522076,
|
174 |
+
"eval_weighted_specificity": 0.9747130314077416,
|
175 |
"step": 1125
|
176 |
}
|
177 |
],
|
178 |
"logging_steps": 500,
|
179 |
+
"max_steps": 2400,
|
180 |
+
"num_train_epochs": 15,
|
181 |
"save_steps": 500,
|
182 |
"total_flos": 9761403521544192.0,
|
183 |
"trial_name": null,
|
training_checkpoints/checkpoint-1125/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36a33fe5941ace0a96599f0a2229d1ce6d7002fe79c5372925862ab481915414
|
3 |
size 4600
|