Theoreticallyhugo
commited on
Commit
•
e0b80a0
1
Parent(s):
97e112e
Training in progress, epoch 8, checkpoint
Browse files- checkpoint-648/model.safetensors +1 -1
- checkpoint-648/optimizer.pt +1 -1
- checkpoint-648/scheduler.pt +1 -1
- checkpoint-648/trainer_state.json +215 -215
- checkpoint-648/training_args.bin +1 -1
checkpoint-648/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592318676
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef3b1195d0304531dfe120fad82f347a800b05de84ae0067700459cd084cead0
|
3 |
size 592318676
|
checkpoint-648/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014645498
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4d8f5605b75f62f19769e646b627e21c744a51469564a2aa8dc7a30fa628b46
|
3 |
size 1014645498
|
checkpoint-648/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:e68c21d9797f6bcc1f3ee5d1e304d59033aecc6b5f99bd3c9e02fdf906ffee2b
|
3 |
size 1064
|
checkpoint-648/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
"epoch": 8.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 648,
|
@@ -11,327 +11,327 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_I": {
|
20 |
-
"f1-score": 0.
|
21 |
-
"precision": 0.
|
22 |
-
"recall": 0.
|
23 |
-
"support":
|
24 |
},
|
25 |
"eval_O": {
|
26 |
-
"f1-score": 0.
|
27 |
-
"precision": 0.
|
28 |
-
"recall": 0.
|
29 |
-
"support":
|
30 |
},
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"eval_loss": 0.
|
33 |
"eval_macro avg": {
|
34 |
-
"f1-score": 0.
|
35 |
-
"precision": 0.
|
36 |
-
"recall": 0.
|
37 |
-
"support":
|
38 |
-
},
|
39 |
-
"eval_runtime":
|
40 |
-
"eval_samples_per_second":
|
41 |
-
"eval_steps_per_second":
|
42 |
"eval_weighted avg": {
|
43 |
-
"f1-score": 0.
|
44 |
-
"precision": 0.
|
45 |
-
"recall": 0.
|
46 |
-
"support":
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
-
"f1-score": 0.
|
54 |
-
"precision": 0.
|
55 |
-
"recall": 0.
|
56 |
-
"support":
|
57 |
},
|
58 |
"eval_I": {
|
59 |
-
"f1-score": 0.
|
60 |
-
"precision": 0.
|
61 |
-
"recall": 0.
|
62 |
-
"support":
|
63 |
},
|
64 |
"eval_O": {
|
65 |
-
"f1-score": 0.
|
66 |
-
"precision": 0.
|
67 |
-
"recall": 0.
|
68 |
-
"support":
|
69 |
},
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_loss": 0.
|
72 |
"eval_macro avg": {
|
73 |
-
"f1-score": 0.
|
74 |
-
"precision": 0.
|
75 |
-
"recall": 0.
|
76 |
-
"support":
|
77 |
-
},
|
78 |
-
"eval_runtime":
|
79 |
-
"eval_samples_per_second":
|
80 |
-
"eval_steps_per_second":
|
81 |
"eval_weighted avg": {
|
82 |
-
"f1-score": 0.
|
83 |
-
"precision": 0.
|
84 |
-
"recall": 0.
|
85 |
-
"support":
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
-
"f1-score": 0.
|
93 |
-
"precision": 0.
|
94 |
-
"recall": 0.
|
95 |
-
"support":
|
96 |
},
|
97 |
"eval_I": {
|
98 |
-
"f1-score": 0.
|
99 |
-
"precision": 0.
|
100 |
-
"recall": 0.
|
101 |
-
"support":
|
102 |
},
|
103 |
"eval_O": {
|
104 |
-
"f1-score": 0.
|
105 |
-
"precision": 0.
|
106 |
-
"recall": 0.
|
107 |
-
"support":
|
108 |
},
|
109 |
-
"eval_accuracy": 0.
|
110 |
-
"eval_loss": 0.
|
111 |
"eval_macro avg": {
|
112 |
-
"f1-score": 0.
|
113 |
-
"precision": 0.
|
114 |
-
"recall": 0.
|
115 |
-
"support":
|
116 |
-
},
|
117 |
-
"eval_runtime":
|
118 |
-
"eval_samples_per_second":
|
119 |
-
"eval_steps_per_second":
|
120 |
"eval_weighted avg": {
|
121 |
-
"f1-score": 0.
|
122 |
-
"precision": 0.
|
123 |
-
"recall": 0.
|
124 |
-
"support":
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
-
"f1-score": 0.
|
132 |
-
"precision": 0.
|
133 |
-
"recall": 0.
|
134 |
-
"support":
|
135 |
},
|
136 |
"eval_I": {
|
137 |
-
"f1-score": 0.
|
138 |
-
"precision": 0.
|
139 |
-
"recall": 0.
|
140 |
-
"support":
|
141 |
},
|
142 |
"eval_O": {
|
143 |
-
"f1-score": 0.
|
144 |
-
"precision": 0.
|
145 |
-
"recall": 0.
|
146 |
-
"support":
|
147 |
},
|
148 |
-
"eval_accuracy": 0.
|
149 |
-
"eval_loss": 0.
|
150 |
"eval_macro avg": {
|
151 |
-
"f1-score": 0.
|
152 |
-
"precision": 0.
|
153 |
-
"recall": 0.
|
154 |
-
"support":
|
155 |
-
},
|
156 |
-
"eval_runtime":
|
157 |
-
"eval_samples_per_second":
|
158 |
-
"eval_steps_per_second":
|
159 |
"eval_weighted avg": {
|
160 |
-
"f1-score": 0.
|
161 |
-
"precision": 0.
|
162 |
-
"recall": 0.
|
163 |
-
"support":
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
-
"f1-score": 0.
|
171 |
-
"precision": 0.
|
172 |
-
"recall": 0.
|
173 |
-
"support":
|
174 |
},
|
175 |
"eval_I": {
|
176 |
-
"f1-score": 0.
|
177 |
-
"precision": 0.
|
178 |
-
"recall": 0.
|
179 |
-
"support":
|
180 |
},
|
181 |
"eval_O": {
|
182 |
-
"f1-score": 0.
|
183 |
-
"precision": 0.
|
184 |
-
"recall": 0.
|
185 |
-
"support":
|
186 |
},
|
187 |
-
"eval_accuracy": 0.
|
188 |
-
"eval_loss": 0.
|
189 |
"eval_macro avg": {
|
190 |
-
"f1-score": 0.
|
191 |
-
"precision": 0.
|
192 |
-
"recall": 0.
|
193 |
-
"support":
|
194 |
-
},
|
195 |
-
"eval_runtime":
|
196 |
-
"eval_samples_per_second":
|
197 |
-
"eval_steps_per_second":
|
198 |
"eval_weighted avg": {
|
199 |
-
"f1-score": 0.
|
200 |
-
"precision": 0.
|
201 |
-
"recall": 0.
|
202 |
-
"support":
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
-
"f1-score": 0.
|
210 |
-
"precision": 0.
|
211 |
-
"recall": 0.
|
212 |
-
"support":
|
213 |
},
|
214 |
"eval_I": {
|
215 |
-
"f1-score": 0.
|
216 |
-
"precision": 0.
|
217 |
-
"recall": 0.
|
218 |
-
"support":
|
219 |
},
|
220 |
"eval_O": {
|
221 |
-
"f1-score": 0.
|
222 |
-
"precision": 0.
|
223 |
-
"recall": 0.
|
224 |
-
"support":
|
225 |
},
|
226 |
-
"eval_accuracy": 0.
|
227 |
-
"eval_loss": 0.
|
228 |
"eval_macro avg": {
|
229 |
-
"f1-score": 0.
|
230 |
-
"precision": 0.
|
231 |
-
"recall": 0.
|
232 |
-
"support":
|
233 |
-
},
|
234 |
-
"eval_runtime":
|
235 |
-
"eval_samples_per_second":
|
236 |
-
"eval_steps_per_second":
|
237 |
"eval_weighted avg": {
|
238 |
-
"f1-score": 0.
|
239 |
-
"precision": 0.
|
240 |
-
"recall": 0.
|
241 |
-
"support":
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
-
"grad_norm":
|
248 |
-
"learning_rate": 1.
|
249 |
-
"loss": 0.
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
-
"f1-score": 0.
|
256 |
-
"precision": 0.
|
257 |
-
"recall": 0.
|
258 |
-
"support":
|
259 |
},
|
260 |
"eval_I": {
|
261 |
-
"f1-score": 0.
|
262 |
-
"precision": 0.
|
263 |
-
"recall": 0.
|
264 |
-
"support":
|
265 |
},
|
266 |
"eval_O": {
|
267 |
-
"f1-score": 0.
|
268 |
-
"precision": 0.
|
269 |
-
"recall": 0.
|
270 |
-
"support":
|
271 |
},
|
272 |
-
"eval_accuracy": 0.
|
273 |
-
"eval_loss": 0.
|
274 |
"eval_macro avg": {
|
275 |
-
"f1-score": 0.
|
276 |
-
"precision": 0.
|
277 |
-
"recall": 0.
|
278 |
-
"support":
|
279 |
-
},
|
280 |
-
"eval_runtime":
|
281 |
-
"eval_samples_per_second":
|
282 |
-
"eval_steps_per_second":
|
283 |
"eval_weighted avg": {
|
284 |
-
"f1-score": 0.
|
285 |
-
"precision": 0.
|
286 |
-
"recall": 0.
|
287 |
-
"support":
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
-
"f1-score": 0.
|
295 |
-
"precision": 0.
|
296 |
-
"recall": 0.
|
297 |
-
"support":
|
298 |
},
|
299 |
"eval_I": {
|
300 |
-
"f1-score": 0.
|
301 |
-
"precision": 0.
|
302 |
-
"recall": 0.
|
303 |
-
"support":
|
304 |
},
|
305 |
"eval_O": {
|
306 |
-
"f1-score": 0.
|
307 |
-
"precision": 0.
|
308 |
-
"recall": 0.
|
309 |
-
"support":
|
310 |
},
|
311 |
-
"eval_accuracy": 0.
|
312 |
-
"eval_loss": 0.
|
313 |
"eval_macro avg": {
|
314 |
-
"f1-score": 0.
|
315 |
-
"precision": 0.
|
316 |
-
"recall": 0.
|
317 |
-
"support":
|
318 |
-
},
|
319 |
-
"eval_runtime":
|
320 |
-
"eval_samples_per_second":
|
321 |
-
"eval_steps_per_second":
|
322 |
"eval_weighted avg": {
|
323 |
-
"f1-score": 0.
|
324 |
-
"precision": 0.
|
325 |
-
"recall": 0.
|
326 |
-
"support":
|
327 |
},
|
328 |
"step": 648
|
329 |
}
|
330 |
],
|
331 |
"logging_steps": 500,
|
332 |
-
"max_steps":
|
333 |
"num_input_tokens_seen": 0,
|
334 |
-
"num_train_epochs":
|
335 |
"save_steps": 500,
|
336 |
"total_flos": 1150293221884800.0,
|
337 |
"train_batch_size": 4,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.2252955436706543,
|
3 |
+
"best_model_checkpoint": "longformer-spans/checkpoint-162",
|
4 |
"epoch": 8.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 648,
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
+
"f1-score": 0.816,
|
15 |
+
"precision": 0.7461594732991953,
|
16 |
+
"recall": 0.9002647837599294,
|
17 |
+
"support": 1133.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9321376763813793,
|
21 |
+
"precision": 0.9024103768767235,
|
22 |
+
"recall": 0.9638902525500463,
|
23 |
+
"support": 18333.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8560784528570645,
|
27 |
+
"precision": 0.931782945736434,
|
28 |
+
"recall": 0.7917511147142278,
|
29 |
+
"support": 9868.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.9035249198881844,
|
32 |
+
"eval_loss": 0.2619660496711731,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.8680720430794812,
|
35 |
+
"precision": 0.860117598637451,
|
36 |
+
"recall": 0.8853020503414012,
|
37 |
+
"support": 29334.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 5.5032,
|
40 |
+
"eval_samples_per_second": 14.537,
|
41 |
+
"eval_steps_per_second": 1.817,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.9020655278480035,
|
44 |
+
"precision": 0.9062562975065145,
|
45 |
+
"recall": 0.9035249198881844,
|
46 |
+
"support": 29334.0
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8512256973795435,
|
54 |
+
"precision": 0.8167072181670721,
|
55 |
+
"recall": 0.8887908208296558,
|
56 |
+
"support": 1133.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9416781438711729,
|
60 |
+
"precision": 0.9152551099212274,
|
61 |
+
"recall": 0.9696721758577429,
|
62 |
+
"support": 18333.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.8778173190984578,
|
66 |
+
"precision": 0.9380041484212952,
|
67 |
+
"recall": 0.8248885285772193,
|
68 |
+
"support": 9868.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9178427763005387,
|
71 |
+
"eval_loss": 0.2252955436706543,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.8902403867830581,
|
74 |
+
"precision": 0.8899888255031981,
|
75 |
+
"recall": 0.8944505084215394,
|
76 |
+
"support": 29334.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 5.4972,
|
79 |
+
"eval_samples_per_second": 14.553,
|
80 |
+
"eval_steps_per_second": 1.819,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.9167016237671239,
|
83 |
+
"precision": 0.9191015935430046,
|
84 |
+
"recall": 0.9178427763005387,
|
85 |
+
"support": 29334.0
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8531120331950207,
|
93 |
+
"precision": 0.8050117462803446,
|
94 |
+
"recall": 0.9073256840247131,
|
95 |
+
"support": 1133.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.9469915571230095,
|
99 |
+
"precision": 0.9280963603037444,
|
100 |
+
"recall": 0.9666721213112965,
|
101 |
+
"support": 18333.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.8903876792352629,
|
105 |
+
"precision": 0.9353938852934612,
|
106 |
+
"recall": 0.8495135792460479,
|
107 |
+
"support": 9868.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.9249676143724006,
|
110 |
+
"eval_loss": 0.22786012291908264,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.8968304231844311,
|
113 |
+
"precision": 0.8895006639591835,
|
114 |
+
"recall": 0.9078371281940192,
|
115 |
+
"support": 29334.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 5.5036,
|
118 |
+
"eval_samples_per_second": 14.536,
|
119 |
+
"eval_steps_per_second": 1.817,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9243239165827936,
|
122 |
+
"precision": 0.9257972230878861,
|
123 |
+
"recall": 0.9249676143724006,
|
124 |
+
"support": 29334.0
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8567807351077312,
|
132 |
+
"precision": 0.8217179902755267,
|
133 |
+
"recall": 0.8949691085613416,
|
134 |
+
"support": 1133.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.9472597903427299,
|
138 |
+
"precision": 0.9432635621180161,
|
139 |
+
"recall": 0.9512900234549719,
|
140 |
+
"support": 18333.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.8979927100980543,
|
144 |
+
"precision": 0.9099989595255437,
|
145 |
+
"recall": 0.8862991487636805,
|
146 |
+
"support": 9868.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9272516533715143,
|
149 |
+
"eval_loss": 0.23897655308246613,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.9006777451828384,
|
152 |
+
"precision": 0.8916601706396955,
|
153 |
+
"recall": 0.910852760259998,
|
154 |
+
"support": 29334.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 5.4904,
|
157 |
+
"eval_samples_per_second": 14.571,
|
158 |
+
"eval_steps_per_second": 1.821,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9271915992526735,
|
161 |
+
"precision": 0.9273787107073643,
|
162 |
+
"recall": 0.9272516533715143,
|
163 |
+
"support": 29334.0
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.8624407072013798,
|
171 |
+
"precision": 0.8431703204047217,
|
172 |
+
"recall": 0.8826125330979699,
|
173 |
+
"support": 1133.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.948190701170407,
|
177 |
+
"precision": 0.9335059992600032,
|
178 |
+
"recall": 0.9633447880870561,
|
179 |
+
"support": 18333.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.8955333298423835,
|
183 |
+
"precision": 0.9265359193845487,
|
184 |
+
"recall": 0.8665383056343737,
|
185 |
+
"support": 9868.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9276607349832958,
|
188 |
+
"eval_loss": 0.25390708446502686,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.9020549127380568,
|
191 |
+
"precision": 0.9010707463497579,
|
192 |
+
"recall": 0.9041652089397999,
|
193 |
+
"support": 29334.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 5.4919,
|
196 |
+
"eval_samples_per_second": 14.567,
|
197 |
+
"eval_steps_per_second": 1.821,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9271646670996412,
|
200 |
+
"precision": 0.9276721180179627,
|
201 |
+
"recall": 0.9276607349832958,
|
202 |
+
"support": 29334.0
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.8601036269430052,
|
210 |
+
"precision": 0.841927303465765,
|
211 |
+
"recall": 0.8790820829655781,
|
212 |
+
"support": 1133.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9474285714285714,
|
216 |
+
"precision": 0.9452679589509693,
|
217 |
+
"recall": 0.9495990836197021,
|
218 |
+
"support": 18333.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.8983777165595348,
|
222 |
+
"precision": 0.9045613314156564,
|
223 |
+
"recall": 0.8922780705310093,
|
224 |
+
"support": 9868.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.9275925547146656,
|
227 |
+
"eval_loss": 0.29299432039260864,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9019699716437038,
|
230 |
+
"precision": 0.8972521979441302,
|
231 |
+
"recall": 0.9069864123720964,
|
232 |
+
"support": 29334.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 5.4971,
|
235 |
+
"eval_samples_per_second": 14.553,
|
236 |
+
"eval_steps_per_second": 1.819,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.9275549436263691,
|
239 |
+
"precision": 0.9275827485063247,
|
240 |
+
"recall": 0.9275925547146656,
|
241 |
+
"support": 29334.0
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
+
"grad_norm": 2.853372573852539,
|
248 |
+
"learning_rate": 1.3827160493827162e-05,
|
249 |
+
"loss": 0.1621,
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
+
"f1-score": 0.8665526090675792,
|
256 |
+
"precision": 0.8406639004149378,
|
257 |
+
"recall": 0.8940864960282436,
|
258 |
+
"support": 1133.0
|
259 |
},
|
260 |
"eval_I": {
|
261 |
+
"f1-score": 0.9492722371967655,
|
262 |
+
"precision": 0.9382959450098577,
|
263 |
+
"recall": 0.9605083728795069,
|
264 |
+
"support": 18333.0
|
265 |
},
|
266 |
"eval_O": {
|
267 |
+
"f1-score": 0.8984919396775871,
|
268 |
+
"precision": 0.9227729117709891,
|
269 |
+
"recall": 0.8754560194568302,
|
270 |
+
"support": 9868.0
|
271 |
},
|
272 |
+
"eval_accuracy": 0.9293311515647371,
|
273 |
+
"eval_loss": 0.3148973286151886,
|
274 |
"eval_macro avg": {
|
275 |
+
"f1-score": 0.9047722619806439,
|
276 |
+
"precision": 0.9005775857319281,
|
277 |
+
"recall": 0.9100169627881934,
|
278 |
+
"support": 29334.0
|
279 |
+
},
|
280 |
+
"eval_runtime": 5.4821,
|
281 |
+
"eval_samples_per_second": 14.593,
|
282 |
+
"eval_steps_per_second": 1.824,
|
283 |
"eval_weighted avg": {
|
284 |
+
"f1-score": 0.9289946986889036,
|
285 |
+
"precision": 0.9293030221719495,
|
286 |
+
"recall": 0.9293311515647371,
|
287 |
+
"support": 29334.0
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
+
"f1-score": 0.8624629707998307,
|
295 |
+
"precision": 0.8284552845528456,
|
296 |
+
"recall": 0.8993821712268314,
|
297 |
+
"support": 1133.0
|
298 |
},
|
299 |
"eval_I": {
|
300 |
+
"f1-score": 0.9467755410030451,
|
301 |
+
"precision": 0.9356556940449557,
|
302 |
+
"recall": 0.9581628756886489,
|
303 |
+
"support": 18333.0
|
304 |
},
|
305 |
"eval_O": {
|
306 |
+
"f1-score": 0.8934263985831857,
|
307 |
+
"precision": 0.9191854233654877,
|
308 |
+
"recall": 0.8690717470612079,
|
309 |
+
"support": 9868.0
|
310 |
},
|
311 |
+
"eval_accuracy": 0.9259221381332242,
|
312 |
+
"eval_loss": 0.34766319394111633,
|
313 |
"eval_macro avg": {
|
314 |
+
"f1-score": 0.9008883034620205,
|
315 |
+
"precision": 0.8944321339877629,
|
316 |
+
"recall": 0.9088722646588961,
|
317 |
+
"support": 29334.0
|
318 |
+
},
|
319 |
+
"eval_runtime": 5.5202,
|
320 |
+
"eval_samples_per_second": 14.492,
|
321 |
+
"eval_steps_per_second": 1.812,
|
322 |
"eval_weighted avg": {
|
323 |
+
"f1-score": 0.9255723133682386,
|
324 |
+
"precision": 0.9259745494680297,
|
325 |
+
"recall": 0.9259221381332242,
|
326 |
+
"support": 29334.0
|
327 |
},
|
328 |
"step": 648
|
329 |
}
|
330 |
],
|
331 |
"logging_steps": 500,
|
332 |
+
"max_steps": 1620,
|
333 |
"num_input_tokens_seen": 0,
|
334 |
+
"num_train_epochs": 20,
|
335 |
"save_steps": 500,
|
336 |
"total_flos": 1150293221884800.0,
|
337 |
"train_batch_size": 4,
|
checkpoint-648/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1094850123635c13193a80398a7bb1e351dd871416d3ce265431b259bf603290
|
3 |
size 4856
|