Commit
β’
b91d3fa
1
Parent(s):
9736d24
Training in progress, step 600
Browse files- {checkpoint-300 β checkpoint-600}/config.json +0 -0
- {checkpoint-300 β checkpoint-600}/optimizer.pt +1 -1
- {checkpoint-300 β checkpoint-600}/preprocessor_config.json +0 -0
- {checkpoint-300 β checkpoint-600}/pytorch_model.bin +1 -1
- {checkpoint-300 β checkpoint-600}/rng_state.pth +2 -2
- {checkpoint-300 β checkpoint-600}/scaler.pt +1 -1
- {checkpoint-300 β checkpoint-600}/scheduler.pt +1 -1
- {checkpoint-300 β checkpoint-600}/trainer_state.json +120 -3
- {checkpoint-300 β checkpoint-600}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-300 β checkpoint-600}/config.json
RENAMED
File without changes
|
{checkpoint-300 β checkpoint-600}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490337809
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49c514c1b2ff011d50c4a8e3b7e46c2148904652f6afdcc1f4a32fe18f672012
|
3 |
size 2490337809
|
{checkpoint-300 β checkpoint-600}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-300 β checkpoint-600}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:058906a444aeea71d083f349ade14c36ec6bf31aefcfd633c92657ebe41f3c14
|
3 |
size 1262063089
|
{checkpoint-300 β checkpoint-600}/rng_state.pth
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 sha256:796699f569c9be64a692307d8264b44b7adbdf8ac3e91d99def5b22f4808095a
|
3 |
+
size 14567
|
{checkpoint-300 β checkpoint-600}/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:d59c7740536b9634042b591d2769580fe65377ef904907588872cde90375d0b3
|
3 |
size 559
|
{checkpoint-300 β checkpoint-600}/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:ac6482ff77366a04d83b9e577d7ad673af6a0a7a1846af277e139c185db59118
|
3 |
size 623
|
{checkpoint-300 β checkpoint-600}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -123,11 +123,128 @@
|
|
123 |
"eval_steps_per_second": 0.775,
|
124 |
"eval_wer": 1.0,
|
125 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
126 |
}
|
127 |
],
|
128 |
"max_steps": 6516,
|
129 |
"num_train_epochs": 3,
|
130 |
-
"total_flos":
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|
133 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2761477390403866,
|
5 |
+
"global_step": 600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
123 |
"eval_steps_per_second": 0.775,
|
124 |
"eval_wer": 1.0,
|
125 |
"step": 300
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.15,
|
129 |
+
"learning_rate": 7.288566953797964e-05,
|
130 |
+
"loss": 2.9964,
|
131 |
+
"step": 320
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.16,
|
135 |
+
"learning_rate": 7.265074393108849e-05,
|
136 |
+
"loss": 3.0777,
|
137 |
+
"step": 340
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.17,
|
141 |
+
"learning_rate": 7.242756460454189e-05,
|
142 |
+
"loss": 3.2703,
|
143 |
+
"step": 360
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.17,
|
147 |
+
"learning_rate": 7.219263899765073e-05,
|
148 |
+
"loss": 3.1161,
|
149 |
+
"step": 380
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.18,
|
153 |
+
"learning_rate": 7.195771339075958e-05,
|
154 |
+
"loss": 3.2435,
|
155 |
+
"step": 400
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.18,
|
159 |
+
"eval_loss": 3.063333034515381,
|
160 |
+
"eval_runtime": 190.5938,
|
161 |
+
"eval_samples_per_second": 25.41,
|
162 |
+
"eval_steps_per_second": 0.798,
|
163 |
+
"eval_wer": 1.0,
|
164 |
+
"step": 400
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.19,
|
168 |
+
"learning_rate": 7.172278778386843e-05,
|
169 |
+
"loss": 2.9993,
|
170 |
+
"step": 420
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.2,
|
174 |
+
"learning_rate": 7.148786217697727e-05,
|
175 |
+
"loss": 3.0555,
|
176 |
+
"step": 440
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.21,
|
180 |
+
"learning_rate": 7.126468285043069e-05,
|
181 |
+
"loss": 3.1879,
|
182 |
+
"step": 460
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.22,
|
186 |
+
"learning_rate": 7.102975724353953e-05,
|
187 |
+
"loss": 2.9861,
|
188 |
+
"step": 480
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.23,
|
192 |
+
"learning_rate": 7.080657791699295e-05,
|
193 |
+
"loss": 3.0833,
|
194 |
+
"step": 500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.23,
|
198 |
+
"eval_loss": 2.9769718647003174,
|
199 |
+
"eval_runtime": 195.2639,
|
200 |
+
"eval_samples_per_second": 24.802,
|
201 |
+
"eval_steps_per_second": 0.778,
|
202 |
+
"eval_wer": 1.0,
|
203 |
+
"step": 500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.24,
|
207 |
+
"learning_rate": 7.05716523101018e-05,
|
208 |
+
"loss": 3.1608,
|
209 |
+
"step": 520
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.25,
|
213 |
+
"learning_rate": 7.033672670321064e-05,
|
214 |
+
"loss": 3.0206,
|
215 |
+
"step": 540
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.26,
|
219 |
+
"learning_rate": 7.01018010963195e-05,
|
220 |
+
"loss": 3.0523,
|
221 |
+
"step": 560
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.27,
|
225 |
+
"learning_rate": 6.986687548942835e-05,
|
226 |
+
"loss": 3.0222,
|
227 |
+
"step": 580
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.28,
|
231 |
+
"learning_rate": 6.964369616288175e-05,
|
232 |
+
"loss": 3.0913,
|
233 |
+
"step": 600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.28,
|
237 |
+
"eval_loss": 3.052091598510742,
|
238 |
+
"eval_runtime": 189.8149,
|
239 |
+
"eval_samples_per_second": 25.514,
|
240 |
+
"eval_steps_per_second": 0.801,
|
241 |
+
"eval_wer": 1.0,
|
242 |
+
"step": 600
|
243 |
}
|
244 |
],
|
245 |
"max_steps": 6516,
|
246 |
"num_train_epochs": 3,
|
247 |
+
"total_flos": 1.1416289792484741e+19,
|
248 |
"trial_name": null,
|
249 |
"trial_params": null
|
250 |
}
|
{checkpoint-300 β checkpoint-600}/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 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:058906a444aeea71d083f349ade14c36ec6bf31aefcfd633c92657ebe41f3c14
|
3 |
size 1262063089
|