Theoreticallyhugo
commited on
Commit
•
49b784c
1
Parent(s):
143087c
Training in progress, epoch 8, checkpoint
Browse files- checkpoint-648/model.safetensors +1 -1
- checkpoint-648/optimizer.pt +1 -1
- checkpoint-648/rng_state.pth +1 -1
- checkpoint-648/trainer_state.json +243 -243
- 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 592324828
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30a2bd9f27ea76f90298e2d3d87eee485d2c6087ee37d4390aa2064a154d87bf
|
3 |
size 592324828
|
checkpoint-648/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014657786
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba98e3c6caf863835deccbfdbffc1869d37ffbb53455172a2c09eaecb8a50c8b
|
3 |
size 1014657786
|
checkpoint-648/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:e241cb4a4c96fc25c055fcd71173708b81cd84562a71b4d7503d9ffa5397d596
|
3 |
size 14244
|
checkpoint-648/trainer_state.json
CHANGED
@@ -11,367 +11,367 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
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":
|
29 |
-
"support":
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
-
"f1-score": 0.
|
33 |
-
"precision": 0.
|
34 |
-
"recall": 0.
|
35 |
-
"support":
|
36 |
},
|
37 |
-
"eval_accuracy": 0.
|
38 |
-
"eval_loss": 0.
|
39 |
"eval_macro avg": {
|
40 |
-
"f1-score": 0.
|
41 |
-
"precision": 0.
|
42 |
-
"recall": 0.
|
43 |
-
"support":
|
44 |
-
},
|
45 |
-
"eval_runtime": 4.
|
46 |
-
"eval_samples_per_second": 16.
|
47 |
-
"eval_steps_per_second": 2.
|
48 |
"eval_weighted avg": {
|
49 |
-
"f1-score": 0.
|
50 |
-
"precision": 0.
|
51 |
-
"recall": 0.
|
52 |
-
"support":
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
-
"f1-score": 0.
|
60 |
-
"precision": 0.
|
61 |
-
"recall": 0.
|
62 |
-
"support":
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
-
"f1-score": 0.
|
66 |
-
"precision": 0.
|
67 |
-
"recall": 0.
|
68 |
-
"support":
|
69 |
},
|
70 |
"eval_O": {
|
71 |
-
"f1-score": 0.
|
72 |
-
"precision": 0.
|
73 |
-
"recall": 0.
|
74 |
-
"support":
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
-
"f1-score": 0.
|
78 |
-
"precision": 0.
|
79 |
-
"recall": 0.
|
80 |
-
"support":
|
81 |
},
|
82 |
-
"eval_accuracy": 0.
|
83 |
-
"eval_loss": 0.
|
84 |
"eval_macro avg": {
|
85 |
-
"f1-score": 0.
|
86 |
-
"precision": 0.
|
87 |
-
"recall": 0.
|
88 |
-
"support":
|
89 |
-
},
|
90 |
-
"eval_runtime":
|
91 |
-
"eval_samples_per_second": 16.
|
92 |
-
"eval_steps_per_second": 2.
|
93 |
"eval_weighted avg": {
|
94 |
-
"f1-score": 0.
|
95 |
-
"precision": 0.
|
96 |
-
"recall": 0.
|
97 |
-
"support":
|
98 |
},
|
99 |
"step": 162
|
100 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
-
"f1-score": 0.
|
105 |
-
"precision": 0.
|
106 |
-
"recall": 0.
|
107 |
-
"support":
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
-
"f1-score": 0.
|
111 |
-
"precision": 0.
|
112 |
-
"recall": 0.
|
113 |
-
"support":
|
114 |
},
|
115 |
"eval_O": {
|
116 |
-
"f1-score": 0.
|
117 |
-
"precision": 0.
|
118 |
-
"recall": 0.
|
119 |
-
"support":
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
-
"f1-score": 0.
|
123 |
-
"precision": 0.
|
124 |
-
"recall": 0.
|
125 |
-
"support":
|
126 |
},
|
127 |
-
"eval_accuracy": 0.
|
128 |
-
"eval_loss": 0.
|
129 |
"eval_macro avg": {
|
130 |
-
"f1-score": 0.
|
131 |
-
"precision": 0.
|
132 |
-
"recall": 0.
|
133 |
-
"support":
|
134 |
-
},
|
135 |
-
"eval_runtime": 4.
|
136 |
-
"eval_samples_per_second": 16.
|
137 |
-
"eval_steps_per_second": 2.
|
138 |
"eval_weighted avg": {
|
139 |
-
"f1-score": 0.
|
140 |
-
"precision": 0.
|
141 |
-
"recall": 0.
|
142 |
-
"support":
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
-
"f1-score": 0.
|
150 |
-
"precision": 0.
|
151 |
-
"recall": 0.
|
152 |
-
"support":
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
-
"f1-score": 0.
|
156 |
-
"precision": 0.
|
157 |
-
"recall": 0.
|
158 |
-
"support":
|
159 |
},
|
160 |
"eval_O": {
|
161 |
-
"f1-score": 0.
|
162 |
-
"precision": 0.
|
163 |
-
"recall": 0.
|
164 |
-
"support":
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
-
"f1-score": 0.
|
168 |
-
"precision": 0.
|
169 |
-
"recall": 0.
|
170 |
-
"support":
|
171 |
},
|
172 |
-
"eval_accuracy": 0.
|
173 |
-
"eval_loss": 0.
|
174 |
"eval_macro avg": {
|
175 |
-
"f1-score": 0.
|
176 |
-
"precision": 0.
|
177 |
-
"recall": 0.
|
178 |
-
"support":
|
179 |
-
},
|
180 |
-
"eval_runtime": 4.
|
181 |
-
"eval_samples_per_second": 16.
|
182 |
-
"eval_steps_per_second": 2.
|
183 |
"eval_weighted avg": {
|
184 |
-
"f1-score": 0.
|
185 |
-
"precision": 0.
|
186 |
-
"recall": 0.
|
187 |
-
"support":
|
188 |
},
|
189 |
"step": 324
|
190 |
},
|
191 |
{
|
192 |
"epoch": 5.0,
|
193 |
"eval_Claim": {
|
194 |
-
"f1-score": 0.
|
195 |
-
"precision": 0.
|
196 |
-
"recall": 0.
|
197 |
-
"support":
|
198 |
},
|
199 |
"eval_MajorClaim": {
|
200 |
-
"f1-score": 0.
|
201 |
-
"precision": 0.
|
202 |
-
"recall": 0.
|
203 |
-
"support":
|
204 |
},
|
205 |
"eval_O": {
|
206 |
-
"f1-score": 0.
|
207 |
-
"precision": 0.
|
208 |
-
"recall": 0.
|
209 |
-
"support":
|
210 |
},
|
211 |
"eval_Premise": {
|
212 |
-
"f1-score": 0.
|
213 |
-
"precision": 0.
|
214 |
-
"recall": 0.
|
215 |
-
"support":
|
216 |
},
|
217 |
-
"eval_accuracy": 0.
|
218 |
-
"eval_loss": 0.
|
219 |
"eval_macro avg": {
|
220 |
-
"f1-score": 0.
|
221 |
-
"precision": 0.
|
222 |
-
"recall": 0.
|
223 |
-
"support":
|
224 |
-
},
|
225 |
-
"eval_runtime": 4.
|
226 |
-
"eval_samples_per_second": 16.
|
227 |
-
"eval_steps_per_second": 2.
|
228 |
"eval_weighted avg": {
|
229 |
-
"f1-score": 0.
|
230 |
-
"precision": 0.
|
231 |
-
"recall": 0.
|
232 |
-
"support":
|
233 |
},
|
234 |
"step": 405
|
235 |
},
|
236 |
{
|
237 |
"epoch": 6.0,
|
238 |
"eval_Claim": {
|
239 |
-
"f1-score": 0.
|
240 |
-
"precision": 0.
|
241 |
-
"recall": 0.
|
242 |
-
"support":
|
243 |
},
|
244 |
"eval_MajorClaim": {
|
245 |
-
"f1-score": 0.
|
246 |
-
"precision": 0.
|
247 |
-
"recall": 0.
|
248 |
-
"support":
|
249 |
},
|
250 |
"eval_O": {
|
251 |
-
"f1-score": 0.
|
252 |
-
"precision": 0.
|
253 |
-
"recall": 0.
|
254 |
-
"support":
|
255 |
},
|
256 |
"eval_Premise": {
|
257 |
-
"f1-score": 0.
|
258 |
-
"precision": 0.
|
259 |
-
"recall": 0.
|
260 |
-
"support":
|
261 |
},
|
262 |
-
"eval_accuracy": 0.
|
263 |
-
"eval_loss": 0.
|
264 |
"eval_macro avg": {
|
265 |
-
"f1-score": 0.
|
266 |
-
"precision": 0.
|
267 |
-
"recall": 0.
|
268 |
-
"support":
|
269 |
-
},
|
270 |
-
"eval_runtime": 4.
|
271 |
-
"eval_samples_per_second": 16.
|
272 |
-
"eval_steps_per_second": 2.
|
273 |
"eval_weighted avg": {
|
274 |
-
"f1-score": 0.
|
275 |
-
"precision": 0.
|
276 |
-
"recall": 0.
|
277 |
-
"support":
|
278 |
},
|
279 |
"step": 486
|
280 |
},
|
281 |
{
|
282 |
"epoch": 6.17,
|
283 |
-
"grad_norm":
|
284 |
"learning_rate": 1.7530864197530865e-05,
|
285 |
-
"loss": 0.
|
286 |
"step": 500
|
287 |
},
|
288 |
{
|
289 |
"epoch": 7.0,
|
290 |
"eval_Claim": {
|
291 |
-
"f1-score": 0.
|
292 |
-
"precision": 0.
|
293 |
-
"recall": 0.
|
294 |
-
"support":
|
295 |
},
|
296 |
"eval_MajorClaim": {
|
297 |
-
"f1-score": 0.
|
298 |
-
"precision": 0.
|
299 |
-
"recall": 0.
|
300 |
-
"support":
|
301 |
},
|
302 |
"eval_O": {
|
303 |
-
"f1-score": 0.
|
304 |
-
"precision": 0.
|
305 |
-
"recall": 0.
|
306 |
-
"support":
|
307 |
},
|
308 |
"eval_Premise": {
|
309 |
-
"f1-score": 0.
|
310 |
-
"precision": 0.
|
311 |
-
"recall": 0.
|
312 |
-
"support":
|
313 |
},
|
314 |
-
"eval_accuracy": 0.
|
315 |
-
"eval_loss": 0.
|
316 |
"eval_macro avg": {
|
317 |
-
"f1-score": 0.
|
318 |
-
"precision": 0.
|
319 |
-
"recall": 0.
|
320 |
-
"support":
|
321 |
-
},
|
322 |
-
"eval_runtime": 4.
|
323 |
-
"eval_samples_per_second": 16.
|
324 |
-
"eval_steps_per_second": 2.
|
325 |
"eval_weighted avg": {
|
326 |
-
"f1-score": 0.
|
327 |
-
"precision": 0.
|
328 |
-
"recall": 0.
|
329 |
-
"support":
|
330 |
},
|
331 |
"step": 567
|
332 |
},
|
333 |
{
|
334 |
"epoch": 8.0,
|
335 |
"eval_Claim": {
|
336 |
-
"f1-score": 0.
|
337 |
-
"precision": 0.
|
338 |
-
"recall": 0.
|
339 |
-
"support":
|
340 |
},
|
341 |
"eval_MajorClaim": {
|
342 |
-
"f1-score": 0.
|
343 |
-
"precision": 0.
|
344 |
-
"recall": 0.
|
345 |
-
"support":
|
346 |
},
|
347 |
"eval_O": {
|
348 |
-
"f1-score": 0.
|
349 |
-
"precision": 0.
|
350 |
-
"recall": 0.
|
351 |
-
"support":
|
352 |
},
|
353 |
"eval_Premise": {
|
354 |
-
"f1-score": 0.
|
355 |
-
"precision": 0.
|
356 |
-
"recall": 0.
|
357 |
-
"support":
|
358 |
},
|
359 |
-
"eval_accuracy": 0.
|
360 |
-
"eval_loss": 0.
|
361 |
"eval_macro avg": {
|
362 |
-
"f1-score": 0.
|
363 |
-
"precision": 0.
|
364 |
-
"recall": 0.
|
365 |
-
"support":
|
366 |
-
},
|
367 |
-
"eval_runtime": 4.
|
368 |
-
"eval_samples_per_second": 16.
|
369 |
-
"eval_steps_per_second": 2.
|
370 |
"eval_weighted avg": {
|
371 |
-
"f1-score": 0.
|
372 |
-
"precision": 0.
|
373 |
-
"recall": 0.
|
374 |
-
"support":
|
375 |
},
|
376 |
"step": 648
|
377 |
}
|
@@ -381,7 +381,7 @@
|
|
381 |
"num_input_tokens_seen": 0,
|
382 |
"num_train_epochs": 50,
|
383 |
"save_steps": 500,
|
384 |
-
"total_flos":
|
385 |
"train_batch_size": 4,
|
386 |
"trial_name": null,
|
387 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
+
"f1-score": 0.5385059461955894,
|
15 |
+
"precision": 0.6267132491265789,
|
16 |
+
"recall": 0.4720647773279352,
|
17 |
+
"support": 4940.0
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
+
"f1-score": 0.7814784727863526,
|
21 |
+
"precision": 0.9588039867109635,
|
22 |
+
"recall": 0.6595063985374772,
|
23 |
+
"support": 2188.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.9938608715302625,
|
27 |
+
"precision": 0.9996969237763298,
|
28 |
+
"recall": 0.9880925634688834,
|
29 |
+
"support": 13353.0
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
+
"f1-score": 0.8968837690149166,
|
33 |
+
"precision": 0.8455112497215416,
|
34 |
+
"recall": 0.954902824076986,
|
35 |
+
"support": 15899.0
|
36 |
},
|
37 |
+
"eval_accuracy": 0.8837548103353491,
|
38 |
+
"eval_loss": 0.2860471308231354,
|
39 |
"eval_macro avg": {
|
40 |
+
"f1-score": 0.8026822648817803,
|
41 |
+
"precision": 0.8576813523338533,
|
42 |
+
"recall": 0.7686416408528204,
|
43 |
+
"support": 36380.0
|
44 |
+
},
|
45 |
+
"eval_runtime": 4.9572,
|
46 |
+
"eval_samples_per_second": 16.34,
|
47 |
+
"eval_steps_per_second": 2.219,
|
48 |
"eval_weighted avg": {
|
49 |
+
"f1-score": 0.8768739289107891,
|
50 |
+
"precision": 0.8792073379911217,
|
51 |
+
"recall": 0.8837548103353491,
|
52 |
+
"support": 36380.0
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
+
"f1-score": 0.6469459868753155,
|
60 |
+
"precision": 0.6453172205438067,
|
61 |
+
"recall": 0.648582995951417,
|
62 |
+
"support": 4940.0
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
+
"f1-score": 0.8435970110796187,
|
66 |
+
"precision": 0.9669226225634967,
|
67 |
+
"recall": 0.7481718464351006,
|
68 |
+
"support": 2188.0
|
69 |
},
|
70 |
"eval_O": {
|
71 |
+
"f1-score": 0.998877245508982,
|
72 |
+
"precision": 0.9983541557567143,
|
73 |
+
"recall": 0.9994008836965476,
|
74 |
+
"support": 13353.0
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
+
"f1-score": 0.9099026477336144,
|
78 |
+
"precision": 0.8972179761540813,
|
79 |
+
"recall": 0.922951129001824,
|
80 |
+
"support": 15899.0
|
81 |
},
|
82 |
+
"eval_accuracy": 0.903243540406817,
|
83 |
+
"eval_loss": 0.24885737895965576,
|
84 |
"eval_macro avg": {
|
85 |
+
"f1-score": 0.8498307227993828,
|
86 |
+
"precision": 0.8769529937545246,
|
87 |
+
"recall": 0.8297767137712222,
|
88 |
+
"support": 36380.0
|
89 |
+
},
|
90 |
+
"eval_runtime": 5.0097,
|
91 |
+
"eval_samples_per_second": 16.169,
|
92 |
+
"eval_steps_per_second": 2.196,
|
93 |
"eval_weighted avg": {
|
94 |
+
"f1-score": 0.9028656814459712,
|
95 |
+
"precision": 0.9043261520711511,
|
96 |
+
"recall": 0.903243540406817,
|
97 |
+
"support": 36380.0
|
98 |
},
|
99 |
"step": 162
|
100 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
+
"f1-score": 0.7040630102775911,
|
105 |
+
"precision": 0.6698958142935478,
|
106 |
+
"recall": 0.7419028340080972,
|
107 |
+
"support": 4940.0
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
+
"f1-score": 0.8888411094388303,
|
111 |
+
"precision": 0.8392204628501827,
|
112 |
+
"recall": 0.9446983546617916,
|
113 |
+
"support": 2188.0
|
114 |
},
|
115 |
"eval_O": {
|
116 |
+
"f1-score": 0.998989104796136,
|
117 |
+
"precision": 0.9988769092542678,
|
118 |
+
"recall": 0.9991013255448213,
|
119 |
+
"support": 13353.0
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
+
"f1-score": 0.914582593823615,
|
123 |
+
"precision": 0.9390987408880053,
|
124 |
+
"recall": 0.8913139191144097,
|
125 |
+
"support": 15899.0
|
126 |
},
|
127 |
+
"eval_accuracy": 0.9137987905442551,
|
128 |
+
"eval_loss": 0.24298855662345886,
|
129 |
"eval_macro avg": {
|
130 |
+
"f1-score": 0.8766189545840432,
|
131 |
+
"precision": 0.8617729818215009,
|
132 |
+
"recall": 0.8942541083322799,
|
133 |
+
"support": 36380.0
|
134 |
+
},
|
135 |
+
"eval_runtime": 4.9876,
|
136 |
+
"eval_samples_per_second": 16.24,
|
137 |
+
"eval_steps_per_second": 2.205,
|
138 |
"eval_weighted avg": {
|
139 |
+
"f1-score": 0.9154289662937856,
|
140 |
+
"precision": 0.9184781183611038,
|
141 |
+
"recall": 0.9137987905442551,
|
142 |
+
"support": 36380.0
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
+
"f1-score": 0.6981611893583725,
|
150 |
+
"precision": 0.6754352763058289,
|
151 |
+
"recall": 0.7224696356275304,
|
152 |
+
"support": 4940.0
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
+
"f1-score": 0.901231802911534,
|
156 |
+
"precision": 0.8836187966622749,
|
157 |
+
"recall": 0.9195612431444241,
|
158 |
+
"support": 2188.0
|
159 |
},
|
160 |
"eval_O": {
|
161 |
+
"f1-score": 0.9989130842172332,
|
162 |
+
"precision": 0.9998499399759904,
|
163 |
+
"recall": 0.9979779824758481,
|
164 |
+
"support": 13353.0
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
+
"f1-score": 0.9146224912392481,
|
168 |
+
"precision": 0.9266670970240785,
|
169 |
+
"recall": 0.9028869740235235,
|
170 |
+
"support": 15899.0
|
171 |
},
|
172 |
+
"eval_accuracy": 0.9142935678944475,
|
173 |
+
"eval_loss": 0.23980534076690674,
|
174 |
"eval_macro avg": {
|
175 |
+
"f1-score": 0.8782321419315969,
|
176 |
+
"precision": 0.8713927774920431,
|
177 |
+
"recall": 0.8857239588178316,
|
178 |
+
"support": 36380.0
|
179 |
+
},
|
180 |
+
"eval_runtime": 4.9726,
|
181 |
+
"eval_samples_per_second": 16.289,
|
182 |
+
"eval_steps_per_second": 2.212,
|
183 |
"eval_weighted avg": {
|
184 |
+
"f1-score": 0.9153623106642749,
|
185 |
+
"precision": 0.9168247558035478,
|
186 |
+
"recall": 0.9142935678944475,
|
187 |
+
"support": 36380.0
|
188 |
},
|
189 |
"step": 324
|
190 |
},
|
191 |
{
|
192 |
"epoch": 5.0,
|
193 |
"eval_Claim": {
|
194 |
+
"f1-score": 0.6650318783717509,
|
195 |
+
"precision": 0.6450999048525214,
|
196 |
+
"recall": 0.6862348178137652,
|
197 |
+
"support": 4940.0
|
198 |
},
|
199 |
"eval_MajorClaim": {
|
200 |
+
"f1-score": 0.9172031076581575,
|
201 |
+
"precision": 0.8916702632714717,
|
202 |
+
"recall": 0.9442413162705667,
|
203 |
+
"support": 2188.0
|
204 |
},
|
205 |
"eval_O": {
|
206 |
+
"f1-score": 0.9982383147794145,
|
207 |
+
"precision": 0.9992495872730002,
|
208 |
+
"recall": 0.9972290870965326,
|
209 |
+
"support": 13353.0
|
210 |
},
|
211 |
"eval_Premise": {
|
212 |
+
"f1-score": 0.8998438545616774,
|
213 |
+
"precision": 0.9119622787753521,
|
214 |
+
"recall": 0.8880432731618341,
|
215 |
+
"support": 15899.0
|
216 |
},
|
217 |
+
"eval_accuracy": 0.9040956569543706,
|
218 |
+
"eval_loss": 0.2932502031326294,
|
219 |
"eval_macro avg": {
|
220 |
+
"f1-score": 0.87007928884275,
|
221 |
+
"precision": 0.8619955085430864,
|
222 |
+
"recall": 0.8789371235856747,
|
223 |
+
"support": 36380.0
|
224 |
+
},
|
225 |
+
"eval_runtime": 4.9595,
|
226 |
+
"eval_samples_per_second": 16.332,
|
227 |
+
"eval_steps_per_second": 2.218,
|
228 |
"eval_weighted avg": {
|
229 |
+
"f1-score": 0.9051179642561333,
|
230 |
+
"precision": 0.9065430476942037,
|
231 |
+
"recall": 0.9040956569543706,
|
232 |
+
"support": 36380.0
|
233 |
},
|
234 |
"step": 405
|
235 |
},
|
236 |
{
|
237 |
"epoch": 6.0,
|
238 |
"eval_Claim": {
|
239 |
+
"f1-score": 0.6622698072805139,
|
240 |
+
"precision": 0.5740163325909429,
|
241 |
+
"recall": 0.7825910931174089,
|
242 |
+
"support": 4940.0
|
243 |
},
|
244 |
"eval_MajorClaim": {
|
245 |
+
"f1-score": 0.9223704351629127,
|
246 |
+
"precision": 0.8842767295597485,
|
247 |
+
"recall": 0.9638939670932358,
|
248 |
+
"support": 2188.0
|
249 |
},
|
250 |
"eval_O": {
|
251 |
+
"f1-score": 0.9982004948639124,
|
252 |
+
"precision": 0.9993994444861497,
|
253 |
+
"recall": 0.9970044184827379,
|
254 |
+
"support": 13353.0
|
255 |
},
|
256 |
"eval_Premise": {
|
257 |
+
"f1-score": 0.8780749379985253,
|
258 |
+
"precision": 0.9398091685199799,
|
259 |
+
"recall": 0.8239511918988616,
|
260 |
+
"support": 15899.0
|
261 |
},
|
262 |
+
"eval_accuracy": 0.8902693787795491,
|
263 |
+
"eval_loss": 0.3604726195335388,
|
264 |
"eval_macro avg": {
|
265 |
+
"f1-score": 0.865228918826466,
|
266 |
+
"precision": 0.8493754187892053,
|
267 |
+
"recall": 0.8918601676480611,
|
268 |
+
"support": 36380.0
|
269 |
+
},
|
270 |
+
"eval_runtime": 4.991,
|
271 |
+
"eval_samples_per_second": 16.229,
|
272 |
+
"eval_steps_per_second": 2.204,
|
273 |
"eval_weighted avg": {
|
274 |
+
"f1-score": 0.8955262233990811,
|
275 |
+
"precision": 0.9086708334194257,
|
276 |
+
"recall": 0.8902693787795491,
|
277 |
+
"support": 36380.0
|
278 |
},
|
279 |
"step": 486
|
280 |
},
|
281 |
{
|
282 |
"epoch": 6.17,
|
283 |
+
"grad_norm": 17.04454231262207,
|
284 |
"learning_rate": 1.7530864197530865e-05,
|
285 |
+
"loss": 0.2104,
|
286 |
"step": 500
|
287 |
},
|
288 |
{
|
289 |
"epoch": 7.0,
|
290 |
"eval_Claim": {
|
291 |
+
"f1-score": 0.7037529399734124,
|
292 |
+
"precision": 0.7110973341599504,
|
293 |
+
"recall": 0.6965587044534413,
|
294 |
+
"support": 4940.0
|
295 |
},
|
296 |
"eval_MajorClaim": {
|
297 |
+
"f1-score": 0.9196885428253615,
|
298 |
+
"precision": 0.8959687906371911,
|
299 |
+
"recall": 0.9446983546617916,
|
300 |
+
"support": 2188.0
|
301 |
},
|
302 |
"eval_O": {
|
303 |
+
"f1-score": 0.9987257327036954,
|
304 |
+
"precision": 0.9996248780853777,
|
305 |
+
"recall": 0.997828203399985,
|
306 |
+
"support": 13353.0
|
307 |
},
|
308 |
"eval_Premise": {
|
309 |
+
"f1-score": 0.9188781285372909,
|
310 |
+
"precision": 0.9187048098082364,
|
311 |
+
"recall": 0.9190515126737531,
|
312 |
+
"support": 15899.0
|
313 |
},
|
314 |
+
"eval_accuracy": 0.9192963166575041,
|
315 |
+
"eval_loss": 0.36414769291877747,
|
316 |
"eval_macro avg": {
|
317 |
+
"f1-score": 0.8852613360099401,
|
318 |
+
"precision": 0.8813489531726889,
|
319 |
+
"recall": 0.8895341937972427,
|
320 |
+
"support": 36380.0
|
321 |
+
},
|
322 |
+
"eval_runtime": 4.9835,
|
323 |
+
"eval_samples_per_second": 16.254,
|
324 |
+
"eval_steps_per_second": 2.207,
|
325 |
"eval_weighted avg": {
|
326 |
+
"f1-score": 0.9190227083446231,
|
327 |
+
"precision": 0.9188476996393494,
|
328 |
+
"recall": 0.9192963166575041,
|
329 |
+
"support": 36380.0
|
330 |
},
|
331 |
"step": 567
|
332 |
},
|
333 |
{
|
334 |
"epoch": 8.0,
|
335 |
"eval_Claim": {
|
336 |
+
"f1-score": 0.7025399811853246,
|
337 |
+
"precision": 0.6562390158172232,
|
338 |
+
"recall": 0.7558704453441295,
|
339 |
+
"support": 4940.0
|
340 |
},
|
341 |
"eval_MajorClaim": {
|
342 |
+
"f1-score": 0.9105835367206567,
|
343 |
+
"precision": 0.8848641655886158,
|
344 |
+
"recall": 0.9378427787934186,
|
345 |
+
"support": 2188.0
|
346 |
},
|
347 |
"eval_O": {
|
348 |
+
"f1-score": 0.9986513823331086,
|
349 |
+
"precision": 0.9991005172026085,
|
350 |
+
"recall": 0.9982026510896428,
|
351 |
+
"support": 13353.0
|
352 |
},
|
353 |
"eval_Premise": {
|
354 |
+
"f1-score": 0.9083384525849526,
|
355 |
+
"precision": 0.9345974717232203,
|
356 |
+
"recall": 0.8835146864582678,
|
357 |
+
"support": 15899.0
|
358 |
},
|
359 |
+
"eval_accuracy": 0.911544804837823,
|
360 |
+
"eval_loss": 0.35222452878952026,
|
361 |
"eval_macro avg": {
|
362 |
+
"f1-score": 0.8800283382060107,
|
363 |
+
"precision": 0.8687002925829169,
|
364 |
+
"recall": 0.8938576404213647,
|
365 |
+
"support": 36380.0
|
366 |
+
},
|
367 |
+
"eval_runtime": 4.9741,
|
368 |
+
"eval_samples_per_second": 16.285,
|
369 |
+
"eval_steps_per_second": 2.211,
|
370 |
"eval_weighted avg": {
|
371 |
+
"f1-score": 0.9136769997620249,
|
372 |
+
"precision": 0.9174837257168467,
|
373 |
+
"recall": 0.911544804837823,
|
374 |
+
"support": 36380.0
|
375 |
},
|
376 |
"step": 648
|
377 |
}
|
|
|
381 |
"num_input_tokens_seen": 0,
|
382 |
"num_train_epochs": 50,
|
383 |
"save_steps": 500,
|
384 |
+
"total_flos": 1146737470939200.0,
|
385 |
"train_batch_size": 4,
|
386 |
"trial_name": null,
|
387 |
"trial_params": null
|
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 sha256:95e8ce1619d475b315f2cb3494747dc2424fb9856a35d6759fcf75e79995f1f1
|
3 |
size 4856
|