Training in progress, step 4000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +141 -3
- pytorch_model.bin +1 -1
- runs/Apr27_08-37-21_cef3a7eee143/events.out.tfevents.1651048661.cef3a7eee143.38.2 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2216876959
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03d412e81a61d6d60043deb1f0cee257eb7b78051ac0f5df86eff142ee2f5736
|
3 |
size 2216876959
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1112207913
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59a6b1471b3ef908655ec530f423c5206aac64f29eb05381e44ccf96ab8c46ae
|
3 |
size 1112207913
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05787dac35dbdd37b3c745474cd2392f29710943747278ff59522a6996f89d5e
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e46694c7d98c5e4fefed63b336298efa60e63e823245b087b045057fdceba48
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba4e799bc93ae8495865ed3fc239390cae62ebcc293d859b2256ac77ecd355e0
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -144,11 +144,149 @@
|
|
144 |
"eval_samples_per_second": 5.087,
|
145 |
"eval_steps_per_second": 0.318,
|
146 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
147 |
}
|
148 |
],
|
149 |
"max_steps": 4230,
|
150 |
"num_train_epochs": 5,
|
151 |
-
"total_flos":
|
152 |
"trial_name": null,
|
153 |
"trial_params": null
|
154 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.7281323877068555,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
144 |
"eval_samples_per_second": 5.087,
|
145 |
"eval_steps_per_second": 0.318,
|
146 |
"step": 2000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.48,
|
150 |
+
"learning_rate": 2.5342789598108745e-05,
|
151 |
+
"loss": 3.9868,
|
152 |
+
"step": 2100
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.6,
|
156 |
+
"learning_rate": 2.4160756501182033e-05,
|
157 |
+
"loss": 3.9224,
|
158 |
+
"step": 2200
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.72,
|
162 |
+
"learning_rate": 2.297872340425532e-05,
|
163 |
+
"loss": 3.8934,
|
164 |
+
"step": 2300
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.84,
|
168 |
+
"learning_rate": 2.179669030732861e-05,
|
169 |
+
"loss": 3.8838,
|
170 |
+
"step": 2400
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.96,
|
174 |
+
"learning_rate": 2.061465721040189e-05,
|
175 |
+
"loss": 3.8895,
|
176 |
+
"step": 2500
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 3.07,
|
180 |
+
"learning_rate": 1.9432624113475178e-05,
|
181 |
+
"loss": 3.8267,
|
182 |
+
"step": 2600
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 3.19,
|
186 |
+
"learning_rate": 1.8250591016548466e-05,
|
187 |
+
"loss": 3.8143,
|
188 |
+
"step": 2700
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 3.31,
|
192 |
+
"learning_rate": 1.706855791962175e-05,
|
193 |
+
"loss": 3.7788,
|
194 |
+
"step": 2800
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.43,
|
198 |
+
"learning_rate": 1.5886524822695038e-05,
|
199 |
+
"loss": 3.7714,
|
200 |
+
"step": 2900
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 3.55,
|
204 |
+
"learning_rate": 1.470449172576832e-05,
|
205 |
+
"loss": 3.752,
|
206 |
+
"step": 3000
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 3.55,
|
210 |
+
"eval_cer": 10.867020421289597,
|
211 |
+
"eval_loss": 7.850170612335205,
|
212 |
+
"eval_runtime": 147.6097,
|
213 |
+
"eval_samples_per_second": 5.088,
|
214 |
+
"eval_steps_per_second": 0.318,
|
215 |
+
"step": 3000
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 3.66,
|
219 |
+
"learning_rate": 1.3522458628841609e-05,
|
220 |
+
"loss": 3.7711,
|
221 |
+
"step": 3100
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 3.78,
|
225 |
+
"learning_rate": 1.2340425531914895e-05,
|
226 |
+
"loss": 3.7428,
|
227 |
+
"step": 3200
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 3.9,
|
231 |
+
"learning_rate": 1.115839243498818e-05,
|
232 |
+
"loss": 3.6924,
|
233 |
+
"step": 3300
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 4.02,
|
237 |
+
"learning_rate": 9.976359338061467e-06,
|
238 |
+
"loss": 3.6697,
|
239 |
+
"step": 3400
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 4.14,
|
243 |
+
"learning_rate": 8.794326241134753e-06,
|
244 |
+
"loss": 3.6303,
|
245 |
+
"step": 3500
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 4.26,
|
249 |
+
"learning_rate": 7.612293144208038e-06,
|
250 |
+
"loss": 3.641,
|
251 |
+
"step": 3600
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 4.37,
|
255 |
+
"learning_rate": 6.430260047281324e-06,
|
256 |
+
"loss": 3.6441,
|
257 |
+
"step": 3700
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 4.49,
|
261 |
+
"learning_rate": 5.24822695035461e-06,
|
262 |
+
"loss": 3.6077,
|
263 |
+
"step": 3800
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 4.61,
|
267 |
+
"learning_rate": 4.066193853427896e-06,
|
268 |
+
"loss": 3.5844,
|
269 |
+
"step": 3900
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 4.73,
|
273 |
+
"learning_rate": 2.884160756501182e-06,
|
274 |
+
"loss": 3.5919,
|
275 |
+
"step": 4000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 4.73,
|
279 |
+
"eval_cer": 10.43849493487699,
|
280 |
+
"eval_loss": 8.424138069152832,
|
281 |
+
"eval_runtime": 147.3939,
|
282 |
+
"eval_samples_per_second": 5.095,
|
283 |
+
"eval_steps_per_second": 0.319,
|
284 |
+
"step": 4000
|
285 |
}
|
286 |
],
|
287 |
"max_steps": 4230,
|
288 |
"num_train_epochs": 5,
|
289 |
+
"total_flos": 1.1545495360528712e+19,
|
290 |
"trial_name": null,
|
291 |
"trial_params": null
|
292 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1112207913
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59a6b1471b3ef908655ec530f423c5206aac64f29eb05381e44ccf96ab8c46ae
|
3 |
size 1112207913
|
runs/Apr27_08-37-21_cef3a7eee143/events.out.tfevents.1651048661.cef3a7eee143.38.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e71b8f231ee1e34cd0a1e0474e2f3172d0e6a3f9547cfc08c2c6ba86cbbcaf75
|
3 |
+
size 88755
|