Theoreticallyhugo
commited on
Commit
•
0a50b28
1
Parent(s):
bb125fe
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 +242 -242
- 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 sha256:82fac11de2928d262ac777e9e1eb094dccab48fe21fa80462c3c801a42b6eea6
|
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 sha256:946ff8be95b183667afb6843e2ef0129b5efe62e7403cdc73902b8f5741ba527
|
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:dffdf7f1c15f3344dffce2b259bf63e6131cbf6af7c2108c97e9b326dccb1d62
|
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": 1.0,
|
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": 4.
|
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":
|
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":
|
349 |
-
"precision":
|
350 |
-
"recall":
|
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": 0.5724454649827784,
|
15 |
+
"precision": 0.6002889477486154,
|
16 |
+
"recall": 0.5470704410796576,
|
17 |
+
"support": 4557.0
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
+
"f1-score": 0.7860447185813415,
|
21 |
+
"precision": 0.698526892771497,
|
22 |
+
"recall": 0.8986337593653592,
|
23 |
+
"support": 2269.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.9987820830889982,
|
27 |
+
"precision": 0.9975671292124707,
|
28 |
"recall": 1.0,
|
29 |
+
"support": 11071.0
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
+
"f1-score": 0.8965445389824622,
|
33 |
+
"precision": 0.9051258677512096,
|
34 |
+
"recall": 0.8881243979633962,
|
35 |
+
"support": 14534.0
|
36 |
},
|
37 |
+
"eval_accuracy": 0.8791279948197712,
|
38 |
+
"eval_loss": 0.3157936632633209,
|
39 |
"eval_macro avg": {
|
40 |
+
"f1-score": 0.8134542014088951,
|
41 |
+
"precision": 0.8003772093709481,
|
42 |
+
"recall": 0.8334571496021033,
|
43 |
+
"support": 32431.0
|
44 |
+
},
|
45 |
+
"eval_runtime": 4.8184,
|
46 |
+
"eval_samples_per_second": 16.603,
|
47 |
+
"eval_steps_per_second": 2.075,
|
48 |
"eval_weighted avg": {
|
49 |
+
"f1-score": 0.8781740995293698,
|
50 |
+
"precision": 0.8793943851252293,
|
51 |
+
"recall": 0.8791279948197712,
|
52 |
+
"support": 32431.0
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
+
"f1-score": 0.6090644692195831,
|
60 |
+
"precision": 0.680108254397835,
|
61 |
+
"recall": 0.5514592933947773,
|
62 |
+
"support": 4557.0
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
+
"f1-score": 0.8585858585858586,
|
66 |
+
"precision": 0.8960229995208433,
|
67 |
+
"recall": 0.8241516086381666,
|
68 |
+
"support": 2269.0
|
69 |
},
|
70 |
"eval_O": {
|
71 |
+
"f1-score": 0.999458141425088,
|
72 |
+
"precision": 0.9992776523702032,
|
73 |
+
"recall": 0.9996386956914461,
|
74 |
+
"support": 11071.0
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
+
"f1-score": 0.9105885478942475,
|
78 |
+
"precision": 0.8801849235905997,
|
79 |
+
"recall": 0.9431677445988716,
|
80 |
+
"support": 14534.0
|
81 |
},
|
82 |
+
"eval_accuracy": 0.8990780426135487,
|
83 |
+
"eval_loss": 0.24451124668121338,
|
84 |
"eval_macro avg": {
|
85 |
+
"f1-score": 0.8444242542811943,
|
86 |
+
"precision": 0.8638984574698704,
|
87 |
+
"recall": 0.8296043355808155,
|
88 |
+
"support": 32431.0
|
89 |
+
},
|
90 |
+
"eval_runtime": 4.8529,
|
91 |
+
"eval_samples_per_second": 16.485,
|
92 |
+
"eval_steps_per_second": 2.061,
|
93 |
"eval_weighted avg": {
|
94 |
+
"f1-score": 0.8949194640367888,
|
95 |
+
"precision": 0.8938342965082798,
|
96 |
+
"recall": 0.8990780426135487,
|
97 |
+
"support": 32431.0
|
98 |
},
|
99 |
"step": 162
|
100 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
+
"f1-score": 0.6542320859402667,
|
105 |
+
"precision": 0.7079713847726111,
|
106 |
+
"recall": 0.60807548825982,
|
107 |
+
"support": 4557.0
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
+
"f1-score": 0.8915187376725839,
|
111 |
+
"precision": 0.8866608544027899,
|
112 |
+
"recall": 0.8964301454385192,
|
113 |
+
"support": 2269.0
|
114 |
},
|
115 |
"eval_O": {
|
116 |
+
"f1-score": 0.9995936611133684,
|
117 |
+
"precision": 0.9992778479870013,
|
118 |
+
"recall": 0.9999096739228616,
|
119 |
+
"support": 11071.0
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
+
"f1-score": 0.9157990498332153,
|
123 |
+
"precision": 0.8973258501155497,
|
124 |
+
"recall": 0.935048850970139,
|
125 |
+
"support": 14534.0
|
126 |
},
|
127 |
+
"eval_accuracy": 0.9085442940396534,
|
128 |
+
"eval_loss": 0.22665414214134216,
|
129 |
"eval_macro avg": {
|
130 |
+
"f1-score": 0.8652858836398586,
|
131 |
+
"precision": 0.872808984319488,
|
132 |
+
"recall": 0.8598660396478349,
|
133 |
+
"support": 32431.0
|
134 |
+
},
|
135 |
+
"eval_runtime": 4.8494,
|
136 |
+
"eval_samples_per_second": 16.497,
|
137 |
+
"eval_steps_per_second": 2.062,
|
138 |
"eval_weighted avg": {
|
139 |
+
"f1-score": 0.9059516032151627,
|
140 |
+
"precision": 0.9047762338408377,
|
141 |
+
"recall": 0.9085442940396534,
|
142 |
+
"support": 32431.0
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
+
"f1-score": 0.6861642294713161,
|
150 |
+
"precision": 0.6424741478360781,
|
151 |
+
"recall": 0.7362299758613122,
|
152 |
+
"support": 4557.0
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
+
"f1-score": 0.8995515695067264,
|
156 |
+
"precision": 0.9155636695572797,
|
157 |
+
"recall": 0.884089907448215,
|
158 |
+
"support": 2269.0
|
159 |
},
|
160 |
"eval_O": {
|
161 |
+
"f1-score": 0.9976481230212574,
|
162 |
+
"precision": 0.9990941208442794,
|
163 |
+
"recall": 0.9962063047601842,
|
164 |
+
"support": 11071.0
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
+
"f1-score": 0.9062532879739067,
|
168 |
+
"precision": 0.9242435081193219,
|
169 |
+
"recall": 0.8889500481629283,
|
170 |
+
"support": 14534.0
|
171 |
},
|
172 |
+
"eval_accuracy": 0.9037649162838025,
|
173 |
+
"eval_loss": 0.2452327460050583,
|
174 |
"eval_macro avg": {
|
175 |
+
"f1-score": 0.8724043024933017,
|
176 |
+
"precision": 0.8703438615892398,
|
177 |
+
"recall": 0.8763690590581599,
|
178 |
+
"support": 32431.0
|
179 |
+
},
|
180 |
+
"eval_runtime": 4.8393,
|
181 |
+
"eval_samples_per_second": 16.531,
|
182 |
+
"eval_steps_per_second": 2.066,
|
183 |
"eval_weighted avg": {
|
184 |
+
"f1-score": 0.9060584182508294,
|
185 |
+
"precision": 0.9095955973231696,
|
186 |
+
"recall": 0.9037649162838025,
|
187 |
+
"support": 32431.0
|
188 |
},
|
189 |
"step": 324
|
190 |
},
|
191 |
{
|
192 |
"epoch": 5.0,
|
193 |
"eval_Claim": {
|
194 |
+
"f1-score": 0.6640249759846301,
|
195 |
+
"precision": 0.7332272606735614,
|
196 |
+
"recall": 0.6067588325652842,
|
197 |
+
"support": 4557.0
|
198 |
},
|
199 |
"eval_MajorClaim": {
|
200 |
+
"f1-score": 0.8848007008322383,
|
201 |
+
"precision": 0.8794079233783195,
|
202 |
+
"recall": 0.8902600264433671,
|
203 |
+
"support": 2269.0
|
204 |
},
|
205 |
"eval_O": {
|
206 |
+
"f1-score": 0.999367774566474,
|
207 |
+
"precision": 0.9992775219001174,
|
208 |
+
"recall": 0.9994580435371692,
|
209 |
+
"support": 11071.0
|
210 |
},
|
211 |
"eval_Premise": {
|
212 |
+
"f1-score": 0.9201314377682404,
|
213 |
+
"precision": 0.8973839110529758,
|
214 |
+
"recall": 0.9440621989816981,
|
215 |
+
"support": 14534.0
|
216 |
},
|
217 |
+
"eval_accuracy": 0.9118127717307515,
|
218 |
+
"eval_loss": 0.28411003947257996,
|
219 |
"eval_macro avg": {
|
220 |
+
"f1-score": 0.8670812222878956,
|
221 |
+
"precision": 0.8773241542512435,
|
222 |
+
"recall": 0.8601347753818797,
|
223 |
+
"support": 32431.0
|
224 |
+
},
|
225 |
+
"eval_runtime": 4.8228,
|
226 |
+
"eval_samples_per_second": 16.588,
|
227 |
+
"eval_steps_per_second": 2.073,
|
228 |
"eval_weighted avg": {
|
229 |
+
"f1-score": 0.9087220731552942,
|
230 |
+
"precision": 0.9078434958291443,
|
231 |
+
"recall": 0.9118127717307515,
|
232 |
+
"support": 32431.0
|
233 |
},
|
234 |
"step": 405
|
235 |
},
|
236 |
{
|
237 |
"epoch": 6.0,
|
238 |
"eval_Claim": {
|
239 |
+
"f1-score": 0.6496087442553721,
|
240 |
+
"precision": 0.7484258729250143,
|
241 |
+
"recall": 0.5738424402018872,
|
242 |
+
"support": 4557.0
|
243 |
},
|
244 |
"eval_MajorClaim": {
|
245 |
+
"f1-score": 0.8865800865800866,
|
246 |
+
"precision": 0.8711186729051468,
|
247 |
+
"recall": 0.9026002644336713,
|
248 |
+
"support": 2269.0
|
249 |
},
|
250 |
"eval_O": {
|
251 |
+
"f1-score": 0.9986892655367232,
|
252 |
+
"precision": 0.9994572100597069,
|
253 |
+
"recall": 0.9979225002258152,
|
254 |
+
"support": 11071.0
|
255 |
},
|
256 |
"eval_Premise": {
|
257 |
+
"f1-score": 0.9191778088205947,
|
258 |
+
"precision": 0.889647180015452,
|
259 |
+
"recall": 0.9507362047612495,
|
260 |
+
"support": 14534.0
|
261 |
},
|
262 |
+
"eval_accuracy": 0.9105177145323918,
|
263 |
+
"eval_loss": 0.3082066774368286,
|
264 |
"eval_macro avg": {
|
265 |
+
"f1-score": 0.8635139762981943,
|
266 |
+
"precision": 0.87716223397633,
|
267 |
+
"recall": 0.8562753524056559,
|
268 |
+
"support": 32431.0
|
269 |
+
},
|
270 |
+
"eval_runtime": 4.8389,
|
271 |
+
"eval_samples_per_second": 16.533,
|
272 |
+
"eval_steps_per_second": 2.067,
|
273 |
"eval_weighted avg": {
|
274 |
+
"f1-score": 0.9061618943658084,
|
275 |
+
"precision": 0.9059932736781678,
|
276 |
+
"recall": 0.9105177145323918,
|
277 |
+
"support": 32431.0
|
278 |
},
|
279 |
"step": 486
|
280 |
},
|
281 |
{
|
282 |
"epoch": 6.17,
|
283 |
+
"grad_norm": 0.8612700700759888,
|
284 |
"learning_rate": 1.7530864197530865e-05,
|
285 |
+
"loss": 0.2223,
|
286 |
"step": 500
|
287 |
},
|
288 |
{
|
289 |
"epoch": 7.0,
|
290 |
"eval_Claim": {
|
291 |
+
"f1-score": 0.6977381768334475,
|
292 |
+
"precision": 0.629950495049505,
|
293 |
+
"recall": 0.7818740399385561,
|
294 |
+
"support": 4557.0
|
295 |
},
|
296 |
"eval_MajorClaim": {
|
297 |
+
"f1-score": 0.8892209178228387,
|
298 |
+
"precision": 0.8621688741721855,
|
299 |
+
"recall": 0.9180255619215514,
|
300 |
+
"support": 2269.0
|
301 |
},
|
302 |
"eval_O": {
|
303 |
+
"f1-score": 0.9988698521766648,
|
304 |
+
"precision": 0.9998190045248869,
|
305 |
+
"recall": 0.9979225002258152,
|
306 |
+
"support": 11071.0
|
307 |
},
|
308 |
"eval_Premise": {
|
309 |
+
"f1-score": 0.9034227633516503,
|
310 |
+
"precision": 0.9449996243143738,
|
311 |
+
"recall": 0.8653502132929682,
|
312 |
+
"support": 14534.0
|
313 |
},
|
314 |
+
"eval_accuracy": 0.9025623631710401,
|
315 |
+
"eval_loss": 0.3512111008167267,
|
316 |
"eval_macro avg": {
|
317 |
+
"f1-score": 0.8723129275461503,
|
318 |
+
"precision": 0.8592344995152377,
|
319 |
+
"recall": 0.8907930788447227,
|
320 |
+
"support": 32431.0
|
321 |
+
},
|
322 |
+
"eval_runtime": 4.8174,
|
323 |
+
"eval_samples_per_second": 16.607,
|
324 |
+
"eval_steps_per_second": 2.076,
|
325 |
"eval_weighted avg": {
|
326 |
+
"f1-score": 0.9061105026169647,
|
327 |
+
"precision": 0.9136494810618672,
|
328 |
+
"recall": 0.9025623631710401,
|
329 |
+
"support": 32431.0
|
330 |
},
|
331 |
"step": 567
|
332 |
},
|
333 |
{
|
334 |
"epoch": 8.0,
|
335 |
"eval_Claim": {
|
336 |
+
"f1-score": 0.6987032799389779,
|
337 |
+
"precision": 0.6177710335525206,
|
338 |
+
"recall": 0.80403774412991,
|
339 |
+
"support": 4557.0
|
340 |
},
|
341 |
"eval_MajorClaim": {
|
342 |
+
"f1-score": 0.9015364639688379,
|
343 |
+
"precision": 0.8856292517006803,
|
344 |
+
"recall": 0.9180255619215514,
|
345 |
+
"support": 2269.0
|
346 |
},
|
347 |
"eval_O": {
|
348 |
+
"f1-score": 0.998915499322187,
|
349 |
+
"precision": 0.9994574554661362,
|
350 |
+
"recall": 0.9983741306115076,
|
351 |
+
"support": 11071.0
|
352 |
},
|
353 |
"eval_Premise": {
|
354 |
+
"f1-score": 0.8976577489773016,
|
355 |
+
"precision": 0.9472075788830315,
|
356 |
+
"recall": 0.8530342644832806,
|
357 |
+
"support": 14534.0
|
358 |
},
|
359 |
+
"eval_accuracy": 0.9003114304215103,
|
360 |
+
"eval_loss": 0.3705728054046631,
|
361 |
"eval_macro avg": {
|
362 |
+
"f1-score": 0.8742032480518261,
|
363 |
+
"precision": 0.8625163299005921,
|
364 |
+
"recall": 0.8933679252865624,
|
365 |
+
"support": 32431.0
|
366 |
+
},
|
367 |
+
"eval_runtime": 4.8542,
|
368 |
+
"eval_samples_per_second": 16.48,
|
369 |
+
"eval_steps_per_second": 2.06,
|
370 |
"eval_weighted avg": {
|
371 |
+
"f1-score": 0.9045397397569994,
|
372 |
+
"precision": 0.9144455555782818,
|
373 |
+
"recall": 0.9003114304215103,
|
374 |
+
"support": 32431.0
|
375 |
},
|
376 |
"step": 648
|
377 |
}
|
|
|
381 |
"num_input_tokens_seen": 0,
|
382 |
"num_train_epochs": 50,
|
383 |
"save_steps": 500,
|
384 |
+
"total_flos": 1150309861814400.0,
|
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:b2dd7b387b7349843b62a9d5b4facde1d14a6a35003d55f9e21a477105ecd1d3
|
3 |
size 4856
|