Commit
β’
216b1e3
1
Parent(s):
57a6490
Training in progress, step 350
Browse files- {checkpoint-150 β checkpoint-350}/config.json +0 -0
- {checkpoint-150 β checkpoint-350}/optimizer.pt +2 -2
- {checkpoint-150 β checkpoint-350}/preprocessor_config.json +0 -0
- {checkpoint-150 β checkpoint-350}/pytorch_model.bin +1 -1
- {checkpoint-150 β checkpoint-350}/rng_state.pth +1 -1
- {checkpoint-150 β checkpoint-350}/scaler.pt +1 -1
- {checkpoint-150 β checkpoint-350}/scheduler.pt +1 -1
- {checkpoint-150 β checkpoint-350}/trainer_state.json +159 -3
- {checkpoint-150 β checkpoint-350}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-150 β checkpoint-350}/config.json
RENAMED
File without changes
|
{checkpoint-150 β checkpoint-350}/optimizer.pt
RENAMED
@@ -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 sha256:646667c125c12f737d1ffee17d6371268d6575f3796018a92eb4102f5f1fff0b
|
3 |
+
size 2490362385
|
{checkpoint-150 β checkpoint-350}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-150 β checkpoint-350}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262075377
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0d76767012f4da5dc0d5f53230af28368c23a384f4a2b862a3afb09aea2dc6d
|
3 |
size 1262075377
|
{checkpoint-150 β checkpoint-350}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4671c6ef20752fdeca41dd978833212c15422e660369baad61a24c693eba960d
|
3 |
size 14567
|
{checkpoint-150 β checkpoint-350}/scaler.pt
RENAMED
@@ -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 sha256:11a38190a29b2e515a160c453a45f3b2acc23e2c8c2240009e053ed0dbf017f0
|
3 |
size 559
|
{checkpoint-150 β checkpoint-350}/scheduler.pt
RENAMED
@@ -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 sha256:68cb16be7c67302d24fc36708cbe6b5ff6ca823143d0ed4ccd59b12de9852185
|
3 |
size 623
|
{checkpoint-150 β checkpoint-350}/trainer_state.json
RENAMED
@@ -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,
|
@@ -123,11 +123,167 @@
|
|
123 |
"eval_steps_per_second": 4.573,
|
124 |
"eval_wer": 1.0,
|
125 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
126 |
}
|
127 |
],
|
128 |
"max_steps": 688,
|
129 |
"num_train_epochs": 2,
|
130 |
-
"total_flos":
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|
133 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0174039158810733,
|
5 |
+
"global_step": 350,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
123 |
"eval_steps_per_second": 4.573,
|
124 |
"eval_wer": 1.0,
|
125 |
"step": 150
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.46,
|
129 |
+
"learning_rate": 5.9393712574850293e-05,
|
130 |
+
"loss": 3.0588,
|
131 |
+
"step": 160
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.49,
|
135 |
+
"learning_rate": 5.827095808383233e-05,
|
136 |
+
"loss": 3.0477,
|
137 |
+
"step": 170
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.52,
|
141 |
+
"learning_rate": 5.714820359281436e-05,
|
142 |
+
"loss": 3.045,
|
143 |
+
"step": 180
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.55,
|
147 |
+
"learning_rate": 5.602544910179641e-05,
|
148 |
+
"loss": 3.0439,
|
149 |
+
"step": 190
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.58,
|
153 |
+
"learning_rate": 5.490269461077844e-05,
|
154 |
+
"loss": 3.0846,
|
155 |
+
"step": 200
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.58,
|
159 |
+
"eval_loss": 3.079519271850586,
|
160 |
+
"eval_runtime": 125.7215,
|
161 |
+
"eval_samples_per_second": 36.748,
|
162 |
+
"eval_steps_per_second": 4.597,
|
163 |
+
"eval_wer": 1.0,
|
164 |
+
"step": 200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.61,
|
168 |
+
"learning_rate": 5.3779940119760477e-05,
|
169 |
+
"loss": 3.0512,
|
170 |
+
"step": 210
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.64,
|
174 |
+
"learning_rate": 5.265718562874251e-05,
|
175 |
+
"loss": 3.0143,
|
176 |
+
"step": 220
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.67,
|
180 |
+
"learning_rate": 5.1534431137724546e-05,
|
181 |
+
"loss": 3.0387,
|
182 |
+
"step": 230
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.7,
|
186 |
+
"learning_rate": 5.0411676646706584e-05,
|
187 |
+
"loss": 3.0311,
|
188 |
+
"step": 240
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.73,
|
192 |
+
"learning_rate": 4.9288922155688615e-05,
|
193 |
+
"loss": 3.0417,
|
194 |
+
"step": 250
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.73,
|
198 |
+
"eval_loss": 3.069390058517456,
|
199 |
+
"eval_runtime": 125.7339,
|
200 |
+
"eval_samples_per_second": 36.744,
|
201 |
+
"eval_steps_per_second": 4.597,
|
202 |
+
"eval_wer": 1.0,
|
203 |
+
"step": 250
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.75,
|
207 |
+
"learning_rate": 4.816616766467066e-05,
|
208 |
+
"loss": 3.0219,
|
209 |
+
"step": 260
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.78,
|
213 |
+
"learning_rate": 4.704341317365269e-05,
|
214 |
+
"loss": 3.0194,
|
215 |
+
"step": 270
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.81,
|
219 |
+
"learning_rate": 4.592065868263473e-05,
|
220 |
+
"loss": 2.9974,
|
221 |
+
"step": 280
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.84,
|
225 |
+
"learning_rate": 4.479790419161676e-05,
|
226 |
+
"loss": 2.9996,
|
227 |
+
"step": 290
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.87,
|
231 |
+
"learning_rate": 4.36751497005988e-05,
|
232 |
+
"loss": 3.0016,
|
233 |
+
"step": 300
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.87,
|
237 |
+
"eval_loss": 3.0347490310668945,
|
238 |
+
"eval_runtime": 132.3039,
|
239 |
+
"eval_samples_per_second": 34.92,
|
240 |
+
"eval_steps_per_second": 4.369,
|
241 |
+
"eval_wer": 1.0,
|
242 |
+
"step": 300
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.9,
|
246 |
+
"learning_rate": 4.255239520958083e-05,
|
247 |
+
"loss": 3.0052,
|
248 |
+
"step": 310
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.93,
|
252 |
+
"learning_rate": 4.142964071856287e-05,
|
253 |
+
"loss": 2.9826,
|
254 |
+
"step": 320
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.96,
|
258 |
+
"learning_rate": 4.030688622754491e-05,
|
259 |
+
"loss": 2.9747,
|
260 |
+
"step": 330
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.99,
|
264 |
+
"learning_rate": 3.918413173652694e-05,
|
265 |
+
"loss": 2.9617,
|
266 |
+
"step": 340
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.02,
|
270 |
+
"learning_rate": 3.806137724550898e-05,
|
271 |
+
"loss": 3.2053,
|
272 |
+
"step": 350
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.02,
|
276 |
+
"eval_loss": 2.984886407852173,
|
277 |
+
"eval_runtime": 149.1508,
|
278 |
+
"eval_samples_per_second": 30.975,
|
279 |
+
"eval_steps_per_second": 3.875,
|
280 |
+
"eval_wer": 1.0,
|
281 |
+
"step": 350
|
282 |
}
|
283 |
],
|
284 |
"max_steps": 688,
|
285 |
"num_train_epochs": 2,
|
286 |
+
"total_flos": 1.0437262031798554e+18,
|
287 |
"trial_name": null,
|
288 |
"trial_params": null
|
289 |
}
|
{checkpoint-150 β checkpoint-350}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262075377
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0d76767012f4da5dc0d5f53230af28368c23a384f4a2b862a3afb09aea2dc6d
|
3 |
size 1262075377
|