Theoreticallyhugo
commited on
Commit
•
49e3891
1
Parent(s):
6901f72
Training in progress, epoch 7, checkpoint
Browse files- checkpoint-567/model.safetensors +1 -1
- checkpoint-567/optimizer.pt +1 -1
- checkpoint-567/scheduler.pt +1 -1
- checkpoint-567/trainer_state.json +217 -217
- checkpoint-567/training_args.bin +1 -1
checkpoint-567/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 sha256:9da3b0483e8a5e76bf862089cc29bcc2b94fd1772e0003284d98a559a01e39a8
|
3 |
size 592324828
|
checkpoint-567/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:ced80ab3e9765720ac9368e7dbee4519728f6c24b1c97f30ff05c5f45741f63d
|
3 |
size 1014657786
|
checkpoint-567/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:ff3bd6bda568947eb5d7a73d9adae4043762d42004c1ccb619b636603f95daa0
|
3 |
size 1064
|
checkpoint-567/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
"epoch": 7.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 567,
|
@@ -11,330 +11,330 @@
|
|
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": 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":
|
46 |
-
"eval_samples_per_second":
|
47 |
-
"eval_steps_per_second":
|
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":
|
92 |
-
"eval_steps_per_second":
|
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":
|
136 |
-
"eval_samples_per_second":
|
137 |
-
"eval_steps_per_second":
|
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":
|
181 |
-
"eval_samples_per_second":
|
182 |
-
"eval_steps_per_second":
|
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":
|
226 |
-
"eval_samples_per_second":
|
227 |
-
"eval_steps_per_second":
|
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":
|
271 |
-
"eval_samples_per_second":
|
272 |
-
"eval_steps_per_second":
|
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": 6.
|
284 |
-
"learning_rate": 1.
|
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":
|
323 |
-
"eval_samples_per_second":
|
324 |
-
"eval_steps_per_second":
|
325 |
"eval_weighted avg": {
|
326 |
-
"f1-score": 0.
|
327 |
-
"precision": 0.
|
328 |
-
"recall": 0.
|
329 |
-
"support":
|
330 |
},
|
331 |
"step": 567
|
332 |
}
|
333 |
],
|
334 |
"logging_steps": 500,
|
335 |
-
"max_steps":
|
336 |
"num_input_tokens_seen": 0,
|
337 |
-
"num_train_epochs":
|
338 |
"save_steps": 500,
|
339 |
"total_flos": 1006521129087600.0,
|
340 |
"train_batch_size": 4,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.4725272059440613,
|
3 |
+
"best_model_checkpoint": "longformer-simple/checkpoint-324",
|
4 |
"epoch": 7.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 567,
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
+
"f1-score": 0.46242900830056793,
|
15 |
+
"precision": 0.43257049448304047,
|
16 |
+
"recall": 0.496715157203191,
|
17 |
+
"support": 4262.0
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
+
"f1-score": 0.5626477541371159,
|
21 |
+
"precision": 0.6522533495736906,
|
22 |
+
"recall": 0.49468822170900695,
|
23 |
+
"support": 2165.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8691687871077185,
|
27 |
+
"precision": 0.911293908403735,
|
28 |
+
"recall": 0.8307661126874747,
|
29 |
+
"support": 9868.0
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
+
"f1-score": 0.8615178272046495,
|
33 |
+
"precision": 0.8377046804810897,
|
34 |
+
"recall": 0.88672444205844,
|
35 |
+
"support": 13039.0
|
36 |
},
|
37 |
+
"eval_accuracy": 0.7823004022635849,
|
38 |
+
"eval_loss": 0.5488611459732056,
|
39 |
"eval_macro avg": {
|
40 |
+
"f1-score": 0.6889408441875129,
|
41 |
+
"precision": 0.708455608235389,
|
42 |
+
"recall": 0.6772234834145282,
|
43 |
+
"support": 29334.0
|
44 |
+
},
|
45 |
+
"eval_runtime": 5.8698,
|
46 |
+
"eval_samples_per_second": 13.629,
|
47 |
+
"eval_steps_per_second": 1.704,
|
48 |
"eval_weighted avg": {
|
49 |
+
"f1-score": 0.7840489998358311,
|
50 |
+
"precision": 0.7899101236188295,
|
51 |
+
"recall": 0.7823004022635849,
|
52 |
+
"support": 29334.0
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
+
"f1-score": 0.5457327068079991,
|
60 |
+
"precision": 0.5107383923092657,
|
61 |
+
"recall": 0.5858751759737213,
|
62 |
+
"support": 4262.0
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
+
"f1-score": 0.6722085773663329,
|
66 |
+
"precision": 0.5687340153452686,
|
67 |
+
"recall": 0.8217090069284064,
|
68 |
+
"support": 2165.0
|
69 |
},
|
70 |
"eval_O": {
|
71 |
+
"f1-score": 0.8773589977955805,
|
72 |
+
"precision": 0.9344863131370977,
|
73 |
+
"recall": 0.8268139440616133,
|
74 |
+
"support": 9868.0
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
+
"f1-score": 0.8678243902439025,
|
78 |
+
"precision": 0.8834419195931988,
|
79 |
+
"recall": 0.852749443975765,
|
80 |
+
"support": 13039.0
|
81 |
},
|
82 |
+
"eval_accuracy": 0.8029590236585532,
|
83 |
+
"eval_loss": 0.5075464248657227,
|
84 |
"eval_macro avg": {
|
85 |
+
"f1-score": 0.7407811680534537,
|
86 |
+
"precision": 0.7243501600962077,
|
87 |
+
"recall": 0.7717868927348766,
|
88 |
+
"support": 29334.0
|
89 |
+
},
|
90 |
+
"eval_runtime": 5.9473,
|
91 |
+
"eval_samples_per_second": 13.451,
|
92 |
+
"eval_steps_per_second": 1.681,
|
93 |
"eval_weighted avg": {
|
94 |
+
"f1-score": 0.8097969994222006,
|
95 |
+
"precision": 0.8232353684753937,
|
96 |
+
"recall": 0.8029590236585532,
|
97 |
+
"support": 29334.0
|
98 |
},
|
99 |
"step": 162
|
100 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
+
"f1-score": 0.4978109708987896,
|
105 |
+
"precision": 0.5516552511415526,
|
106 |
+
"recall": 0.45354293758798686,
|
107 |
+
"support": 4262.0
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
+
"f1-score": 0.7357876283496118,
|
111 |
+
"precision": 0.8036105032822757,
|
112 |
+
"recall": 0.6785219399538106,
|
113 |
+
"support": 2165.0
|
114 |
},
|
115 |
"eval_O": {
|
116 |
+
"f1-score": 0.8891011355194736,
|
117 |
+
"precision": 0.9331699710403207,
|
118 |
+
"recall": 0.8490068909606809,
|
119 |
+
"support": 9868.0
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
+
"f1-score": 0.8770979581655561,
|
123 |
+
"precision": 0.8191560170394037,
|
124 |
+
"recall": 0.9438607255157604,
|
125 |
+
"support": 13039.0
|
126 |
},
|
127 |
+
"eval_accuracy": 0.821129065248517,
|
128 |
+
"eval_loss": 0.5219377279281616,
|
129 |
"eval_macro avg": {
|
130 |
+
"f1-score": 0.7499494232333578,
|
131 |
+
"precision": 0.7768979356258882,
|
132 |
+
"recall": 0.7312331235045597,
|
133 |
+
"support": 29334.0
|
134 |
+
},
|
135 |
+
"eval_runtime": 5.8364,
|
136 |
+
"eval_samples_per_second": 13.707,
|
137 |
+
"eval_steps_per_second": 1.713,
|
138 |
"eval_weighted avg": {
|
139 |
+
"f1-score": 0.815598992812927,
|
140 |
+
"precision": 0.8174973750724106,
|
141 |
+
"recall": 0.821129065248517,
|
142 |
+
"support": 29334.0
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
+
"f1-score": 0.5811481218993623,
|
150 |
+
"precision": 0.5851569933396765,
|
151 |
+
"recall": 0.5771938057250118,
|
152 |
+
"support": 4262.0
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
+
"f1-score": 0.761714412613813,
|
156 |
+
"precision": 0.7335329341317365,
|
157 |
+
"recall": 0.792147806004619,
|
158 |
+
"support": 2165.0
|
159 |
},
|
160 |
"eval_O": {
|
161 |
+
"f1-score": 0.8977645611156685,
|
162 |
+
"precision": 0.9085720215857203,
|
163 |
+
"recall": 0.8872111876773409,
|
164 |
+
"support": 9868.0
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
+
"f1-score": 0.8891009734682191,
|
168 |
+
"precision": 0.8851474612344178,
|
169 |
+
"recall": 0.8930899608865711,
|
170 |
+
"support": 13039.0
|
171 |
},
|
172 |
+
"eval_accuracy": 0.8377650507943001,
|
173 |
+
"eval_loss": 0.4725272059440613,
|
174 |
"eval_macro avg": {
|
175 |
+
"f1-score": 0.7824320172742658,
|
176 |
+
"precision": 0.7781023525728877,
|
177 |
+
"recall": 0.7874106900733857,
|
178 |
+
"support": 29334.0
|
179 |
+
},
|
180 |
+
"eval_runtime": 5.8763,
|
181 |
+
"eval_samples_per_second": 13.614,
|
182 |
+
"eval_steps_per_second": 1.702,
|
183 |
"eval_weighted avg": {
|
184 |
+
"f1-score": 0.8378705011585708,
|
185 |
+
"precision": 0.8382513248807655,
|
186 |
+
"recall": 0.8377650507943001,
|
187 |
+
"support": 29334.0
|
188 |
},
|
189 |
"step": 324
|
190 |
},
|
191 |
{
|
192 |
"epoch": 5.0,
|
193 |
"eval_Claim": {
|
194 |
+
"f1-score": 0.5790953831731895,
|
195 |
+
"precision": 0.5784176029962547,
|
196 |
+
"recall": 0.5797747536367902,
|
197 |
+
"support": 4262.0
|
198 |
},
|
199 |
"eval_MajorClaim": {
|
200 |
+
"f1-score": 0.7450592885375493,
|
201 |
+
"precision": 0.8008497079129049,
|
202 |
+
"recall": 0.6965357967667436,
|
203 |
+
"support": 2165.0
|
204 |
},
|
205 |
"eval_O": {
|
206 |
+
"f1-score": 0.8897467572575665,
|
207 |
+
"precision": 0.9040794979079498,
|
208 |
+
"recall": 0.8758613700851237,
|
209 |
+
"support": 9868.0
|
210 |
},
|
211 |
"eval_Premise": {
|
212 |
+
"f1-score": 0.8861129867206842,
|
213 |
+
"precision": 0.8672442910639547,
|
214 |
+
"recall": 0.905820998542833,
|
215 |
+
"support": 13039.0
|
216 |
},
|
217 |
+
"eval_accuracy": 0.8329242517215518,
|
218 |
+
"eval_loss": 0.5538631081581116,
|
219 |
"eval_macro avg": {
|
220 |
+
"f1-score": 0.7750036039222473,
|
221 |
+
"precision": 0.787647774970266,
|
222 |
+
"recall": 0.7644982297578727,
|
223 |
+
"support": 29334.0
|
224 |
+
},
|
225 |
+
"eval_runtime": 5.8534,
|
226 |
+
"eval_samples_per_second": 13.667,
|
227 |
+
"eval_steps_per_second": 1.708,
|
228 |
"eval_weighted avg": {
|
229 |
+
"f1-score": 0.8323176558681596,
|
230 |
+
"precision": 0.8327711951367025,
|
231 |
+
"recall": 0.8329242517215518,
|
232 |
+
"support": 29334.0
|
233 |
},
|
234 |
"step": 405
|
235 |
},
|
236 |
{
|
237 |
"epoch": 6.0,
|
238 |
"eval_Claim": {
|
239 |
+
"f1-score": 0.5991994252283692,
|
240 |
+
"precision": 0.5325670498084292,
|
241 |
+
"recall": 0.6848897231346786,
|
242 |
+
"support": 4262.0
|
243 |
},
|
244 |
"eval_MajorClaim": {
|
245 |
+
"f1-score": 0.7586672669968483,
|
246 |
+
"precision": 0.7400087834870444,
|
247 |
+
"recall": 0.7782909930715936,
|
248 |
+
"support": 2165.0
|
249 |
},
|
250 |
"eval_O": {
|
251 |
+
"f1-score": 0.8972759409440632,
|
252 |
+
"precision": 0.9212211784799317,
|
253 |
+
"recall": 0.8745439805431698,
|
254 |
+
"support": 9868.0
|
255 |
},
|
256 |
"eval_Premise": {
|
257 |
+
"f1-score": 0.8764605695726225,
|
258 |
+
"precision": 0.9062909567496723,
|
259 |
+
"recall": 0.8485313290896541,
|
260 |
+
"support": 13039.0
|
261 |
},
|
262 |
+
"eval_accuracy": 0.8283220835890094,
|
263 |
+
"eval_loss": 0.5790187120437622,
|
264 |
"eval_macro avg": {
|
265 |
+
"f1-score": 0.7829008006854759,
|
266 |
+
"precision": 0.7750219921312693,
|
267 |
+
"recall": 0.796564006459774,
|
268 |
+
"support": 29334.0
|
269 |
+
},
|
270 |
+
"eval_runtime": 5.8468,
|
271 |
+
"eval_samples_per_second": 13.683,
|
272 |
+
"eval_steps_per_second": 1.71,
|
273 |
"eval_weighted avg": {
|
274 |
+
"f1-score": 0.8344852708551485,
|
275 |
+
"precision": 0.8447418748493872,
|
276 |
+
"recall": 0.8283220835890094,
|
277 |
+
"support": 29334.0
|
278 |
},
|
279 |
"step": 486
|
280 |
},
|
281 |
{
|
282 |
"epoch": 6.17,
|
283 |
+
"grad_norm": 6.636661529541016,
|
284 |
+
"learning_rate": 1.3827160493827162e-05,
|
285 |
+
"loss": 0.3561,
|
286 |
"step": 500
|
287 |
},
|
288 |
{
|
289 |
"epoch": 7.0,
|
290 |
"eval_Claim": {
|
291 |
+
"f1-score": 0.5628712871287128,
|
292 |
+
"precision": 0.5955997904662127,
|
293 |
+
"recall": 0.5335523228531206,
|
294 |
+
"support": 4262.0
|
295 |
},
|
296 |
"eval_MajorClaim": {
|
297 |
+
"f1-score": 0.7734199350487135,
|
298 |
+
"precision": 0.8422198041349293,
|
299 |
+
"recall": 0.7150115473441109,
|
300 |
+
"support": 2165.0
|
301 |
},
|
302 |
"eval_O": {
|
303 |
+
"f1-score": 0.9010954940057875,
|
304 |
+
"precision": 0.9193378321383383,
|
305 |
+
"recall": 0.8835630320226996,
|
306 |
+
"support": 9868.0
|
307 |
},
|
308 |
"eval_Premise": {
|
309 |
+
"f1-score": 0.8842947894099071,
|
310 |
+
"precision": 0.848316189939411,
|
311 |
+
"recall": 0.9234603880665695,
|
312 |
+
"support": 13039.0
|
313 |
},
|
314 |
+
"eval_accuracy": 0.838003681734506,
|
315 |
+
"eval_loss": 0.7058164477348328,
|
316 |
"eval_macro avg": {
|
317 |
+
"f1-score": 0.7804203763982802,
|
318 |
+
"precision": 0.8013684041697228,
|
319 |
+
"recall": 0.7638968225716252,
|
320 |
+
"support": 29334.0
|
321 |
+
},
|
322 |
+
"eval_runtime": 5.8534,
|
323 |
+
"eval_samples_per_second": 13.667,
|
324 |
+
"eval_steps_per_second": 1.708,
|
325 |
"eval_weighted avg": {
|
326 |
+
"f1-score": 0.835063123988816,
|
327 |
+
"precision": 0.8350403187795808,
|
328 |
+
"recall": 0.838003681734506,
|
329 |
+
"support": 29334.0
|
330 |
},
|
331 |
"step": 567
|
332 |
}
|
333 |
],
|
334 |
"logging_steps": 500,
|
335 |
+
"max_steps": 1620,
|
336 |
"num_input_tokens_seen": 0,
|
337 |
+
"num_train_epochs": 20,
|
338 |
"save_steps": 500,
|
339 |
"total_flos": 1006521129087600.0,
|
340 |
"train_batch_size": 4,
|
checkpoint-567/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 sha256:91855299d72d2ceb66b00b0c173ef2e96bd5d782fa49a7debc2d6f3b7cbd2cd4
|
3 |
size 4856
|