Upload folder using huggingface_hub
Browse files- training_checkpoints/checkpoint-1929/README.md +2 -4
- training_checkpoints/checkpoint-1929/adapter_config.json +6 -6
- training_checkpoints/checkpoint-1929/adapter_model.safetensors +2 -2
- training_checkpoints/checkpoint-1929/optimizer.pt +2 -2
- training_checkpoints/checkpoint-1929/rng_state.pth +1 -1
- training_checkpoints/checkpoint-1929/trainer_state.json +222 -222
- training_checkpoints/checkpoint-1929/training_args.bin +1 -1
training_checkpoints/checkpoint-1929/README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
-
base_model: facebook/bart-
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
@@ -81,7 +81,7 @@ Use the code below to get started with the model.
|
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
84 |
-
### Training Procedure
|
85 |
|
86 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
|
@@ -197,8 +197,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
197 |
## Model Card Contact
|
198 |
|
199 |
[More Information Needed]
|
200 |
-
|
201 |
-
|
202 |
### Framework versions
|
203 |
|
204 |
- PEFT 0.10.0
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
+
base_model: facebook/bart-large
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
|
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
84 |
+
### Training Procedure
|
85 |
|
86 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
|
|
|
197 |
## Model Card Contact
|
198 |
|
199 |
[More Information Needed]
|
|
|
|
|
200 |
### Framework versions
|
201 |
|
202 |
- PEFT 0.10.0
|
training_checkpoints/checkpoint-1929/adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "facebook/bart-
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"dense",
|
24 |
-
"v_proj",
|
25 |
"fc1",
|
26 |
-
"fc2",
|
27 |
-
"out_proj",
|
28 |
"q_proj",
|
29 |
-
"
|
|
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "SEQ_CLS",
|
32 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "facebook/bart-large",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"fc1",
|
|
|
|
|
24 |
"q_proj",
|
25 |
+
"dense",
|
26 |
+
"k_proj",
|
27 |
+
"out_proj",
|
28 |
+
"fc2",
|
29 |
+
"v_proj"
|
30 |
],
|
31 |
"task_type": "SEQ_CLS",
|
32 |
"use_dora": false,
|
training_checkpoints/checkpoint-1929/adapter_model.safetensors
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:ad6c9fcb0e264de761cae3de3675ea4e4db4e8457580d5e7ffc719987a790c32
|
3 |
+
size 34854640
|
training_checkpoints/checkpoint-1929/optimizer.pt
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 sha256:9329dfb63e8b9a7667d39c83e18090a41411e0cbb006af089906abc031568be0
|
3 |
+
size 69927198
|
training_checkpoints/checkpoint-1929/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1a7e3cec094ac8478269f33411ba9e7fec6a42db97502b52e62be227b2201fd
|
3 |
size 14244
|
training_checkpoints/checkpoint-1929/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "bart-base-lora/checkpoint-
|
4 |
"epoch": 12.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1929,
|
@@ -10,284 +10,284 @@
|
|
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":
|
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": 3.958333333333333e-05,
|
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":
|
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":
|
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": 2.916666666666667e-05,
|
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":
|
172 |
-
"eval_weighted_fpr": 0.
|
173 |
-
"eval_weighted_sensitivity": 0.
|
174 |
-
"eval_weighted_specificity": 0.
|
175 |
"step": 1125
|
176 |
},
|
177 |
{
|
178 |
"epoch": 8.0,
|
179 |
-
"eval_accuracy": 0.
|
180 |
-
"eval_f1_macro": 0.
|
181 |
-
"eval_f1_micro": 0.
|
182 |
-
"eval_f1_weighted": 0.
|
183 |
-
"eval_loss": 0.
|
184 |
-
"eval_macro_fpr": 0.
|
185 |
-
"eval_macro_sensitivity": 0.
|
186 |
-
"eval_macro_specificity": 0.
|
187 |
-
"eval_precision": 0.
|
188 |
-
"eval_precision_macro": 0.
|
189 |
-
"eval_recall": 0.
|
190 |
-
"eval_recall_macro": 0.
|
191 |
-
"eval_runtime":
|
192 |
-
"eval_samples_per_second":
|
193 |
-
"eval_steps_per_second":
|
194 |
-
"eval_weighted_fpr": 0.
|
195 |
-
"eval_weighted_sensitivity": 0.
|
196 |
-
"eval_weighted_specificity": 0.
|
197 |
"step": 1286
|
198 |
},
|
199 |
{
|
200 |
"epoch": 9.0,
|
201 |
-
"eval_accuracy": 0.
|
202 |
-
"eval_f1_macro": 0.
|
203 |
-
"eval_f1_micro": 0.
|
204 |
-
"eval_f1_weighted": 0.
|
205 |
-
"eval_loss": 0.
|
206 |
-
"eval_macro_fpr": 0.
|
207 |
-
"eval_macro_sensitivity": 0.
|
208 |
-
"eval_macro_specificity": 0.
|
209 |
-
"eval_precision": 0.
|
210 |
-
"eval_precision_macro": 0.
|
211 |
-
"eval_recall": 0.
|
212 |
-
"eval_recall_macro": 0.
|
213 |
-
"eval_runtime":
|
214 |
-
"eval_samples_per_second":
|
215 |
-
"eval_steps_per_second":
|
216 |
-
"eval_weighted_fpr": 0.
|
217 |
-
"eval_weighted_sensitivity": 0.
|
218 |
-
"eval_weighted_specificity": 0.
|
219 |
"step": 1446
|
220 |
},
|
221 |
{
|
222 |
"epoch": 9.33,
|
223 |
"learning_rate": 1.8750000000000002e-05,
|
224 |
-
"loss": 0.
|
225 |
"step": 1500
|
226 |
},
|
227 |
{
|
228 |
"epoch": 10.0,
|
229 |
-
"eval_accuracy": 0.
|
230 |
-
"eval_f1_macro": 0.
|
231 |
-
"eval_f1_micro": 0.
|
232 |
-
"eval_f1_weighted": 0.
|
233 |
-
"eval_loss": 0.
|
234 |
-
"eval_macro_fpr": 0.
|
235 |
-
"eval_macro_sensitivity": 0.
|
236 |
-
"eval_macro_specificity": 0.
|
237 |
-
"eval_precision": 0.
|
238 |
-
"eval_precision_macro": 0.
|
239 |
-
"eval_recall": 0.
|
240 |
-
"eval_recall_macro": 0.
|
241 |
-
"eval_runtime":
|
242 |
-
"eval_samples_per_second":
|
243 |
-
"eval_steps_per_second":
|
244 |
-
"eval_weighted_fpr": 0.
|
245 |
-
"eval_weighted_sensitivity": 0.
|
246 |
-
"eval_weighted_specificity": 0.
|
247 |
"step": 1607
|
248 |
},
|
249 |
{
|
250 |
"epoch": 11.0,
|
251 |
-
"eval_accuracy": 0.
|
252 |
-
"eval_f1_macro": 0.
|
253 |
-
"eval_f1_micro": 0.
|
254 |
-
"eval_f1_weighted": 0.
|
255 |
-
"eval_loss": 0.
|
256 |
-
"eval_macro_fpr": 0.
|
257 |
-
"eval_macro_sensitivity": 0.
|
258 |
-
"eval_macro_specificity": 0.
|
259 |
-
"eval_precision": 0.
|
260 |
-
"eval_precision_macro": 0.
|
261 |
-
"eval_recall": 0.
|
262 |
-
"eval_recall_macro": 0.
|
263 |
-
"eval_runtime":
|
264 |
-
"eval_samples_per_second":
|
265 |
-
"eval_steps_per_second":
|
266 |
-
"eval_weighted_fpr": 0.
|
267 |
-
"eval_weighted_sensitivity": 0.
|
268 |
-
"eval_weighted_specificity": 0.
|
269 |
"step": 1768
|
270 |
},
|
271 |
{
|
272 |
"epoch": 12.0,
|
273 |
-
"eval_accuracy": 0.
|
274 |
-
"eval_f1_macro": 0.
|
275 |
-
"eval_f1_micro": 0.
|
276 |
-
"eval_f1_weighted": 0.
|
277 |
-
"eval_loss": 0.
|
278 |
-
"eval_macro_fpr": 0.
|
279 |
-
"eval_macro_sensitivity": 0.
|
280 |
-
"eval_macro_specificity": 0.
|
281 |
-
"eval_precision": 0.
|
282 |
-
"eval_precision_macro": 0.
|
283 |
-
"eval_recall": 0.
|
284 |
-
"eval_recall_macro": 0.
|
285 |
-
"eval_runtime":
|
286 |
-
"eval_samples_per_second":
|
287 |
-
"eval_steps_per_second":
|
288 |
-
"eval_weighted_fpr": 0.
|
289 |
-
"eval_weighted_sensitivity": 0.
|
290 |
-
"eval_weighted_specificity": 0.
|
291 |
"step": 1929
|
292 |
}
|
293 |
],
|
@@ -295,7 +295,7 @@
|
|
295 |
"max_steps": 2400,
|
296 |
"num_train_epochs": 15,
|
297 |
"save_steps": 500,
|
298 |
-
"total_flos":
|
299 |
"trial_name": null,
|
300 |
"trial_params": null
|
301 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7393184269658342,
|
3 |
+
"best_model_checkpoint": "bart-base-lora/checkpoint-1125",
|
4 |
"epoch": 12.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1929,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.715724244771495,
|
14 |
+
"eval_f1_macro": 0.3957532686340496,
|
15 |
+
"eval_f1_micro": 0.715724244771495,
|
16 |
+
"eval_f1_weighted": 0.6834645556416842,
|
17 |
+
"eval_loss": 0.9525313973426819,
|
18 |
+
"eval_macro_fpr": 0.028501626692807605,
|
19 |
+
"eval_macro_sensitivity": 0.4415906678049911,
|
20 |
+
"eval_macro_specificity": 0.9786637894661117,
|
21 |
+
"eval_precision": 0.6787596592263883,
|
22 |
+
"eval_precision_macro": 0.38751339695744513,
|
23 |
+
"eval_recall": 0.715724244771495,
|
24 |
+
"eval_recall_macro": 0.4415906678049911,
|
25 |
+
"eval_runtime": 120.9594,
|
26 |
+
"eval_samples_per_second": 10.673,
|
27 |
+
"eval_steps_per_second": 1.339,
|
28 |
+
"eval_weighted_fpr": 0.027587762158911525,
|
29 |
+
"eval_weighted_sensitivity": 0.715724244771495,
|
30 |
+
"eval_weighted_specificity": 0.9642325972201805,
|
31 |
"step": 160
|
32 |
},
|
33 |
{
|
34 |
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.7412858249419055,
|
36 |
+
"eval_f1_macro": 0.43370046411892155,
|
37 |
+
"eval_f1_micro": 0.7412858249419055,
|
38 |
+
"eval_f1_weighted": 0.7231329193382661,
|
39 |
+
"eval_loss": 0.7733433842658997,
|
40 |
+
"eval_macro_fpr": 0.025167370687133015,
|
41 |
+
"eval_macro_sensitivity": 0.4686708989603177,
|
42 |
+
"eval_macro_specificity": 0.9805374797463638,
|
43 |
+
"eval_precision": 0.729625861926521,
|
44 |
+
"eval_precision_macro": 0.4491323101141271,
|
45 |
+
"eval_recall": 0.7412858249419055,
|
46 |
+
"eval_recall_macro": 0.4686708989603177,
|
47 |
+
"eval_runtime": 119.8649,
|
48 |
+
"eval_samples_per_second": 10.77,
|
49 |
+
"eval_steps_per_second": 1.352,
|
50 |
+
"eval_weighted_fpr": 0.024322749781532187,
|
51 |
+
"eval_weighted_sensitivity": 0.7412858249419055,
|
52 |
+
"eval_weighted_specificity": 0.9667763712535515,
|
53 |
"step": 321
|
54 |
},
|
55 |
{
|
56 |
"epoch": 3.0,
|
57 |
+
"eval_accuracy": 0.7738187451587917,
|
58 |
+
"eval_f1_macro": 0.5270593942960143,
|
59 |
+
"eval_f1_micro": 0.7738187451587917,
|
60 |
+
"eval_f1_weighted": 0.7610767338978833,
|
61 |
+
"eval_loss": 0.7104586958885193,
|
62 |
+
"eval_macro_fpr": 0.021211805484311928,
|
63 |
+
"eval_macro_sensitivity": 0.5407847836684627,
|
64 |
+
"eval_macro_specificity": 0.9830897092527341,
|
65 |
+
"eval_precision": 0.7630858215778352,
|
66 |
+
"eval_precision_macro": 0.5565386466479504,
|
67 |
+
"eval_recall": 0.7738187451587917,
|
68 |
+
"eval_recall_macro": 0.5407847836684627,
|
69 |
+
"eval_runtime": 119.5419,
|
70 |
+
"eval_samples_per_second": 10.8,
|
71 |
+
"eval_steps_per_second": 1.355,
|
72 |
+
"eval_weighted_fpr": 0.020451043563524302,
|
73 |
+
"eval_weighted_sensitivity": 0.7738187451587917,
|
74 |
+
"eval_weighted_specificity": 0.9725268936322198,
|
75 |
"step": 482
|
76 |
},
|
77 |
{
|
78 |
"epoch": 3.11,
|
79 |
"learning_rate": 3.958333333333333e-05,
|
80 |
+
"loss": 1.08,
|
81 |
"step": 500
|
82 |
},
|
83 |
{
|
84 |
"epoch": 4.0,
|
85 |
+
"eval_accuracy": 0.7575522850503486,
|
86 |
+
"eval_f1_macro": 0.5497163954183316,
|
87 |
+
"eval_f1_micro": 0.7575522850503486,
|
88 |
+
"eval_f1_weighted": 0.7437674055775699,
|
89 |
+
"eval_loss": 0.7538753151893616,
|
90 |
+
"eval_macro_fpr": 0.023393901824967867,
|
91 |
+
"eval_macro_sensitivity": 0.5613408412198008,
|
92 |
+
"eval_macro_specificity": 0.9817091819688993,
|
93 |
+
"eval_precision": 0.7583906478192325,
|
94 |
+
"eval_precision_macro": 0.5791225123984725,
|
95 |
+
"eval_recall": 0.7575522850503486,
|
96 |
+
"eval_recall_macro": 0.5613408412198008,
|
97 |
+
"eval_runtime": 120.3095,
|
98 |
+
"eval_samples_per_second": 10.731,
|
99 |
+
"eval_steps_per_second": 1.347,
|
100 |
+
"eval_weighted_fpr": 0.022349161013923598,
|
101 |
+
"eval_weighted_sensitivity": 0.7575522850503486,
|
102 |
+
"eval_weighted_specificity": 0.9680854444831427,
|
103 |
"step": 643
|
104 |
},
|
105 |
{
|
106 |
"epoch": 5.0,
|
107 |
+
"eval_accuracy": 0.7831138652207591,
|
108 |
+
"eval_f1_macro": 0.6353946839596228,
|
109 |
+
"eval_f1_micro": 0.783113865220759,
|
110 |
+
"eval_f1_weighted": 0.770250750407997,
|
111 |
+
"eval_loss": 0.6978110074996948,
|
112 |
+
"eval_macro_fpr": 0.020328728105215688,
|
113 |
+
"eval_macro_sensitivity": 0.6491872351233146,
|
114 |
+
"eval_macro_specificity": 0.983610303127039,
|
115 |
+
"eval_precision": 0.790031827496624,
|
116 |
+
"eval_precision_macro": 0.7409525878258343,
|
117 |
+
"eval_recall": 0.7831138652207591,
|
118 |
+
"eval_recall_macro": 0.6491872351233146,
|
119 |
+
"eval_runtime": 119.9411,
|
120 |
+
"eval_samples_per_second": 10.764,
|
121 |
+
"eval_steps_per_second": 1.351,
|
122 |
+
"eval_weighted_fpr": 0.019398642095053348,
|
123 |
+
"eval_weighted_sensitivity": 0.7831138652207591,
|
124 |
+
"eval_weighted_specificity": 0.9710406816848265,
|
125 |
"step": 803
|
126 |
},
|
127 |
{
|
128 |
"epoch": 6.0,
|
129 |
+
"eval_accuracy": 0.8156467854376452,
|
130 |
+
"eval_f1_macro": 0.686011065139391,
|
131 |
+
"eval_f1_micro": 0.8156467854376452,
|
132 |
+
"eval_f1_weighted": 0.8087620976325791,
|
133 |
+
"eval_loss": 0.5920090675354004,
|
134 |
+
"eval_macro_fpr": 0.016634568189926056,
|
135 |
+
"eval_macro_sensitivity": 0.6889168814632094,
|
136 |
+
"eval_macro_specificity": 0.9860196319752603,
|
137 |
+
"eval_precision": 0.8053079350996695,
|
138 |
+
"eval_precision_macro": 0.7051361586363433,
|
139 |
+
"eval_recall": 0.8156467854376452,
|
140 |
+
"eval_recall_macro": 0.6889168814632094,
|
141 |
+
"eval_runtime": 121.4244,
|
142 |
+
"eval_samples_per_second": 10.632,
|
143 |
+
"eval_steps_per_second": 1.334,
|
144 |
+
"eval_weighted_fpr": 0.01588785046728972,
|
145 |
+
"eval_weighted_sensitivity": 0.8156467854376452,
|
146 |
+
"eval_weighted_specificity": 0.974647694191258,
|
147 |
"step": 964
|
148 |
},
|
149 |
{
|
150 |
"epoch": 6.22,
|
151 |
"learning_rate": 2.916666666666667e-05,
|
152 |
+
"loss": 0.5581,
|
153 |
"step": 1000
|
154 |
},
|
155 |
{
|
156 |
"epoch": 7.0,
|
157 |
+
"eval_accuracy": 0.8187451587916343,
|
158 |
+
"eval_f1_macro": 0.7393184269658342,
|
159 |
+
"eval_f1_micro": 0.8187451587916342,
|
160 |
+
"eval_f1_weighted": 0.8146848849127107,
|
161 |
+
"eval_loss": 0.6230757236480713,
|
162 |
+
"eval_macro_fpr": 0.016206558639896132,
|
163 |
+
"eval_macro_sensitivity": 0.7424574536250088,
|
164 |
+
"eval_macro_specificity": 0.9863587851767341,
|
165 |
+
"eval_precision": 0.8177894369587694,
|
166 |
+
"eval_precision_macro": 0.7626654223433325,
|
167 |
+
"eval_recall": 0.8187451587916343,
|
168 |
+
"eval_recall_macro": 0.7424574536250088,
|
169 |
+
"eval_runtime": 122.7775,
|
170 |
+
"eval_samples_per_second": 10.515,
|
171 |
+
"eval_steps_per_second": 1.319,
|
172 |
+
"eval_weighted_fpr": 0.015566790846194785,
|
173 |
+
"eval_weighted_sensitivity": 0.8187451587916343,
|
174 |
+
"eval_weighted_specificity": 0.9766366188593788,
|
175 |
"step": 1125
|
176 |
},
|
177 |
{
|
178 |
"epoch": 8.0,
|
179 |
+
"eval_accuracy": 0.8140975987606507,
|
180 |
+
"eval_f1_macro": 0.7328585966804847,
|
181 |
+
"eval_f1_micro": 0.8140975987606507,
|
182 |
+
"eval_f1_weighted": 0.8088643288992207,
|
183 |
+
"eval_loss": 0.6290707588195801,
|
184 |
+
"eval_macro_fpr": 0.01671628651715199,
|
185 |
+
"eval_macro_sensitivity": 0.730719512015592,
|
186 |
+
"eval_macro_specificity": 0.985990627132147,
|
187 |
+
"eval_precision": 0.8133783130550384,
|
188 |
+
"eval_precision_macro": 0.7636063765511063,
|
189 |
+
"eval_recall": 0.8140975987606507,
|
190 |
+
"eval_recall_macro": 0.730719512015592,
|
191 |
+
"eval_runtime": 122.8754,
|
192 |
+
"eval_samples_per_second": 10.507,
|
193 |
+
"eval_steps_per_second": 1.318,
|
194 |
+
"eval_weighted_fpr": 0.016049217600641968,
|
195 |
+
"eval_weighted_sensitivity": 0.8140975987606507,
|
196 |
+
"eval_weighted_specificity": 0.975761808221554,
|
197 |
"step": 1286
|
198 |
},
|
199 |
{
|
200 |
"epoch": 9.0,
|
201 |
+
"eval_accuracy": 0.8241673121611154,
|
202 |
+
"eval_f1_macro": 0.7364711129039813,
|
203 |
+
"eval_f1_micro": 0.8241673121611154,
|
204 |
+
"eval_f1_weighted": 0.8190822404938951,
|
205 |
+
"eval_loss": 0.6226187348365784,
|
206 |
+
"eval_macro_fpr": 0.015759087941173786,
|
207 |
+
"eval_macro_sensitivity": 0.7340167949600996,
|
208 |
+
"eval_macro_specificity": 0.9866810242390173,
|
209 |
+
"eval_precision": 0.8212295601295609,
|
210 |
+
"eval_precision_macro": 0.7665878963082912,
|
211 |
+
"eval_recall": 0.8241673121611154,
|
212 |
+
"eval_recall_macro": 0.7340167949600996,
|
213 |
+
"eval_runtime": 119.2726,
|
214 |
+
"eval_samples_per_second": 10.824,
|
215 |
+
"eval_steps_per_second": 1.358,
|
216 |
+
"eval_weighted_fpr": 0.015010249289162203,
|
217 |
+
"eval_weighted_sensitivity": 0.8241673121611154,
|
218 |
+
"eval_weighted_specificity": 0.9760480514241424,
|
219 |
"step": 1446
|
220 |
},
|
221 |
{
|
222 |
"epoch": 9.33,
|
223 |
"learning_rate": 1.8750000000000002e-05,
|
224 |
+
"loss": 0.3924,
|
225 |
"step": 1500
|
226 |
},
|
227 |
{
|
228 |
"epoch": 10.0,
|
229 |
+
"eval_accuracy": 0.8109992254066615,
|
230 |
+
"eval_f1_macro": 0.7240137823928982,
|
231 |
+
"eval_f1_micro": 0.8109992254066615,
|
232 |
+
"eval_f1_weighted": 0.8047604071311991,
|
233 |
+
"eval_loss": 0.672822892665863,
|
234 |
+
"eval_macro_fpr": 0.017004063571327103,
|
235 |
+
"eval_macro_sensitivity": 0.7288750805513627,
|
236 |
+
"eval_macro_specificity": 0.9858130697255809,
|
237 |
+
"eval_precision": 0.8123042127541057,
|
238 |
+
"eval_precision_macro": 0.7417780746962291,
|
239 |
+
"eval_recall": 0.8109992254066615,
|
240 |
+
"eval_recall_macro": 0.7288750805513627,
|
241 |
+
"eval_runtime": 119.3649,
|
242 |
+
"eval_samples_per_second": 10.816,
|
243 |
+
"eval_steps_per_second": 1.357,
|
244 |
+
"eval_weighted_fpr": 0.016373641121997046,
|
245 |
+
"eval_weighted_sensitivity": 0.8109992254066615,
|
246 |
+
"eval_weighted_specificity": 0.976196820477052,
|
247 |
"step": 1607
|
248 |
},
|
249 |
{
|
250 |
"epoch": 11.0,
|
251 |
+
"eval_accuracy": 0.8094500387296669,
|
252 |
+
"eval_f1_macro": 0.7262574438118878,
|
253 |
+
"eval_f1_micro": 0.8094500387296669,
|
254 |
+
"eval_f1_weighted": 0.8026446222230169,
|
255 |
+
"eval_loss": 0.6805150508880615,
|
256 |
+
"eval_macro_fpr": 0.017269448415116812,
|
257 |
+
"eval_macro_sensitivity": 0.7303446738424816,
|
258 |
+
"eval_macro_specificity": 0.9856433903766489,
|
259 |
+
"eval_precision": 0.8123272064418959,
|
260 |
+
"eval_precision_macro": 0.7389776120628855,
|
261 |
+
"eval_recall": 0.8094500387296669,
|
262 |
+
"eval_recall_macro": 0.7303446738424816,
|
263 |
+
"eval_runtime": 119.049,
|
264 |
+
"eval_samples_per_second": 10.844,
|
265 |
+
"eval_steps_per_second": 1.361,
|
266 |
+
"eval_weighted_fpr": 0.016536703414896478,
|
267 |
+
"eval_weighted_sensitivity": 0.8094500387296669,
|
268 |
+
"eval_weighted_specificity": 0.9752008169200658,
|
269 |
"step": 1768
|
270 |
},
|
271 |
{
|
272 |
"epoch": 12.0,
|
273 |
+
"eval_accuracy": 0.8133230054221534,
|
274 |
+
"eval_f1_macro": 0.7283700928598721,
|
275 |
+
"eval_f1_micro": 0.8133230054221534,
|
276 |
+
"eval_f1_weighted": 0.8089952243674349,
|
277 |
+
"eval_loss": 0.670982301235199,
|
278 |
+
"eval_macro_fpr": 0.016803062086639158,
|
279 |
+
"eval_macro_sensitivity": 0.7306161057668827,
|
280 |
+
"eval_macro_specificity": 0.9859491188467968,
|
281 |
+
"eval_precision": 0.813705327621,
|
282 |
+
"eval_precision_macro": 0.7396207219727483,
|
283 |
+
"eval_recall": 0.8133230054221534,
|
284 |
+
"eval_recall_macro": 0.7306161057668827,
|
285 |
+
"eval_runtime": 179.3033,
|
286 |
+
"eval_samples_per_second": 7.2,
|
287 |
+
"eval_steps_per_second": 0.903,
|
288 |
+
"eval_weighted_fpr": 0.016130111772973698,
|
289 |
+
"eval_weighted_sensitivity": 0.8133230054221534,
|
290 |
+
"eval_weighted_specificity": 0.9759137772797981,
|
291 |
"step": 1929
|
292 |
}
|
293 |
],
|
|
|
295 |
"max_steps": 2400,
|
296 |
"num_train_epochs": 15,
|
297 |
"save_steps": 500,
|
298 |
+
"total_flos": 6.865708483384934e+16,
|
299 |
"trial_name": null,
|
300 |
"trial_params": null
|
301 |
}
|
training_checkpoints/checkpoint-1929/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 sha256:8cfeeb4079e0edbd60cad2df3b73a192a8e64f61f57cc52cfabb80fd9ff6105d
|
3 |
size 4600
|