Theoreticallyhugo
commited on
Commit
•
206120c
1
Parent(s):
fce63c6
Training in progress, epoch 7, checkpoint
Browse files- checkpoint-567/model.safetensors +1 -1
- checkpoint-567/optimizer.pt +1 -1
- checkpoint-567/rng_state.pth +1 -1
- checkpoint-567/trainer_state.json +185 -185
- 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 592318676
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f9c6a09cd7cdbc44cd9c5d5be4300ebd76ed5cadace359e5f88bc54fa975047
|
3 |
size 592318676
|
checkpoint-567/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 sha256:5177201dd8fc2ea9132bae4ae3357e486b783934c73c4200078a18bbbc80856f
|
3 |
size 1014645498
|
checkpoint-567/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:df74477c8049c831c537fb964d31e59ec8d12121ecfdafd2834f9022f29cfdc5
|
3 |
size 14244
|
checkpoint-567/trainer_state.json
CHANGED
@@ -11,280 +11,280 @@
|
|
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": 4.
|
40 |
-
"eval_samples_per_second": 17.
|
41 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
79 |
-
"eval_samples_per_second": 17.
|
80 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
118 |
-
"eval_samples_per_second": 17.
|
119 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
157 |
-
"eval_samples_per_second": 17.
|
158 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
196 |
-
"eval_samples_per_second":
|
197 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
235 |
-
"eval_samples_per_second":
|
236 |
-
"eval_steps_per_second": 2.
|
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": 1.7530864197530865e-05,
|
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": 4.
|
281 |
-
"eval_samples_per_second":
|
282 |
-
"eval_steps_per_second": 2.
|
283 |
"eval_weighted avg": {
|
284 |
-
"f1-score": 0.
|
285 |
-
"precision": 0.
|
286 |
-
"recall": 0.
|
287 |
-
"support":
|
288 |
},
|
289 |
"step": 567
|
290 |
}
|
@@ -294,7 +294,7 @@
|
|
294 |
"num_input_tokens_seen": 0,
|
295 |
"num_train_epochs": 50,
|
296 |
"save_steps": 500,
|
297 |
-
"total_flos":
|
298 |
"train_batch_size": 4,
|
299 |
"trial_name": null,
|
300 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
+
"f1-score": 0.7905866302864938,
|
15 |
+
"precision": 0.7768096514745308,
|
16 |
+
"recall": 0.8048611111111111,
|
17 |
+
"support": 1440.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9005331227169513,
|
21 |
+
"precision": 0.9637593111099372,
|
22 |
+
"recall": 0.8450919534905267,
|
23 |
+
"support": 21587.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8288892663043479,
|
27 |
+
"precision": 0.7463108800367001,
|
28 |
+
"recall": 0.9320156593144275,
|
29 |
+
"support": 10473.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.8705373134328358,
|
32 |
+
"eval_loss": 0.32930415868759155,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.8400030064359308,
|
35 |
+
"precision": 0.8289599475403894,
|
36 |
+
"recall": 0.8606562413053552,
|
37 |
+
"support": 33500.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 4.7349,
|
40 |
+
"eval_samples_per_second": 17.107,
|
41 |
+
"eval_steps_per_second": 2.323,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.8734092702599646,
|
44 |
+
"precision": 0.8877430445874,
|
45 |
+
"recall": 0.8705373134328358,
|
46 |
+
"support": 33500.0
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8656218739579861,
|
54 |
+
"precision": 0.8325849903784477,
|
55 |
+
"recall": 0.9013888888888889,
|
56 |
+
"support": 1440.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9547168948727912,
|
60 |
+
"precision": 0.9423736462093862,
|
61 |
+
"recall": 0.9673877796822161,
|
62 |
+
"support": 21587.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.9013528191962081,
|
66 |
+
"precision": 0.9332379102341274,
|
67 |
+
"recall": 0.8715745249689678,
|
68 |
+
"support": 10473.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9345970149253732,
|
71 |
+
"eval_loss": 0.2162298709154129,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.9072305293423284,
|
74 |
+
"precision": 0.902732182273987,
|
75 |
+
"recall": 0.9134503978466909,
|
76 |
+
"support": 33500.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 4.753,
|
79 |
+
"eval_samples_per_second": 17.042,
|
80 |
+
"eval_steps_per_second": 2.314,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.9342040950316517,
|
83 |
+
"precision": 0.9347982961417612,
|
84 |
+
"recall": 0.9345970149253732,
|
85 |
+
"support": 33500.0
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8603587759409076,
|
93 |
+
"precision": 0.8717034925160371,
|
94 |
+
"recall": 0.8493055555555555,
|
95 |
+
"support": 1440.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.9434195218082959,
|
99 |
+
"precision": 0.9677057963955188,
|
100 |
+
"recall": 0.9203224162690509,
|
101 |
+
"support": 21587.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.8879310344827586,
|
105 |
+
"precision": 0.8459410391631365,
|
106 |
+
"recall": 0.9343072663038289,
|
107 |
+
"support": 10473.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.9216417910447762,
|
110 |
+
"eval_loss": 0.24082203209400177,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.8972364440773206,
|
113 |
+
"precision": 0.8951167760248975,
|
114 |
+
"recall": 0.9013117460428117,
|
115 |
+
"support": 33500.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 4.7554,
|
118 |
+
"eval_samples_per_second": 17.033,
|
119 |
+
"eval_steps_per_second": 2.313,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9225019575751797,
|
122 |
+
"precision": 0.9255121957960801,
|
123 |
+
"recall": 0.9216417910447762,
|
124 |
+
"support": 33500.0
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8804020100502512,
|
132 |
+
"precision": 0.8504854368932039,
|
133 |
+
"recall": 0.9125,
|
134 |
+
"support": 1440.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.9589184992350025,
|
138 |
+
"precision": 0.945595388218339,
|
139 |
+
"recall": 0.9726224116366332,
|
140 |
+
"support": 21587.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.9091178797468354,
|
144 |
+
"precision": 0.9427750999897446,
|
145 |
+
"recall": 0.877780960565263,
|
146 |
+
"support": 10473.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9403880597014925,
|
149 |
+
"eval_loss": 0.22083505988121033,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.9161461296773631,
|
152 |
+
"precision": 0.9129519750337626,
|
153 |
+
"recall": 0.9209677907339654,
|
154 |
+
"support": 33500.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 4.7449,
|
157 |
+
"eval_samples_per_second": 17.071,
|
158 |
+
"eval_steps_per_second": 2.318,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9399744505088647,
|
161 |
+
"precision": 0.9406253819936745,
|
162 |
+
"recall": 0.9403880597014925,
|
163 |
+
"support": 33500.0
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.8879781420765027,
|
171 |
+
"precision": 0.8736559139784946,
|
172 |
+
"recall": 0.9027777777777778,
|
173 |
+
"support": 1440.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.9613201259451634,
|
177 |
+
"precision": 0.9539317642765919,
|
178 |
+
"recall": 0.9688238291564367,
|
179 |
+
"support": 21587.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.916006030835076,
|
183 |
+
"precision": 0.9334853291038858,
|
184 |
+
"recall": 0.899169292466342,
|
185 |
+
"support": 10473.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9442089552238806,
|
188 |
+
"eval_loss": 0.2257838249206543,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.921768099618914,
|
191 |
+
"precision": 0.9203576691196576,
|
192 |
+
"recall": 0.9235902998001855,
|
193 |
+
"support": 33500.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 4.7845,
|
196 |
+
"eval_samples_per_second": 16.93,
|
197 |
+
"eval_steps_per_second": 2.299,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9440011117702735,
|
200 |
+
"precision": 0.9440889959185916,
|
201 |
+
"recall": 0.9442089552238806,
|
202 |
+
"support": 33500.0
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.8873579056148813,
|
210 |
+
"precision": 0.8803827751196173,
|
211 |
+
"recall": 0.8944444444444445,
|
212 |
+
"support": 1440.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9622060984570168,
|
216 |
+
"precision": 0.9539267015706806,
|
217 |
+
"recall": 0.9706304720433594,
|
218 |
+
"support": 21587.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.9182769530299342,
|
222 |
+
"precision": 0.9365567911040509,
|
223 |
+
"recall": 0.9006970304592762,
|
224 |
+
"support": 10473.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.9454925373134329,
|
227 |
+
"eval_loss": 0.2242102175951004,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9226136523672773,
|
230 |
+
"precision": 0.923622089264783,
|
231 |
+
"recall": 0.9219239823156933,
|
232 |
+
"support": 33500.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 4.7715,
|
235 |
+
"eval_samples_per_second": 16.976,
|
236 |
+
"eval_steps_per_second": 2.305,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.945255312255509,
|
239 |
+
"precision": 0.9453351097376493,
|
240 |
+
"recall": 0.9454925373134329,
|
241 |
+
"support": 33500.0
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
+
"grad_norm": 1.8705081939697266,
|
248 |
"learning_rate": 1.7530864197530865e-05,
|
249 |
+
"loss": 0.1601,
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
+
"f1-score": 0.8876749743939911,
|
256 |
+
"precision": 0.8730691739422431,
|
257 |
+
"recall": 0.9027777777777778,
|
258 |
+
"support": 1440.0
|
259 |
},
|
260 |
"eval_I": {
|
261 |
+
"f1-score": 0.9611415113943341,
|
262 |
+
"precision": 0.9581108451482232,
|
263 |
+
"recall": 0.9641914114976606,
|
264 |
+
"support": 21587.0
|
265 |
},
|
266 |
"eval_O": {
|
267 |
+
"f1-score": 0.9164739884393064,
|
268 |
+
"precision": 0.9247594050743657,
|
269 |
+
"recall": 0.9083357204239473,
|
270 |
+
"support": 10473.0
|
271 |
},
|
272 |
+
"eval_accuracy": 0.944089552238806,
|
273 |
+
"eval_loss": 0.22517083585262299,
|
274 |
"eval_macro avg": {
|
275 |
+
"f1-score": 0.9217634914092105,
|
276 |
+
"precision": 0.9186464747216107,
|
277 |
+
"recall": 0.9251016365664619,
|
278 |
+
"support": 33500.0
|
279 |
+
},
|
280 |
+
"eval_runtime": 4.7926,
|
281 |
+
"eval_samples_per_second": 16.901,
|
282 |
+
"eval_steps_per_second": 2.295,
|
283 |
"eval_weighted avg": {
|
284 |
+
"f1-score": 0.9440192791200506,
|
285 |
+
"precision": 0.9440287663891153,
|
286 |
+
"recall": 0.944089552238806,
|
287 |
+
"support": 33500.0
|
288 |
},
|
289 |
"step": 567
|
290 |
}
|
|
|
294 |
"num_input_tokens_seen": 0,
|
295 |
"num_train_epochs": 50,
|
296 |
"save_steps": 500,
|
297 |
+
"total_flos": 1003380772350600.0,
|
298 |
"train_batch_size": 4,
|
299 |
"trial_name": null,
|
300 |
"trial_params": null
|
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:b8ca363922308e3892528dd031742ffedc372734b464a042d09444af9700901e
|
3 |
size 4856
|