marinone94
commited on
Commit
β’
ac1c759
1
Parent(s):
71a393f
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 +1 -1
- {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 sha256:94e544ed6fc2d04d9e3d9655de3eea506999b2814daab419e0d050c27a4a370f
|
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 sha256:3baffe7a116d58666fc0726fb4fa6188834614eac15e96843270fc53529b943e
|
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 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f58a88b760d3a9745a43789af262417186d48a5e0a471e8a2a080c8b3681cf9a
|
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 sha256:4e8415b86bbce347c0df306b84a695add049c2a3b2d0b6f4dda3bf036d341150
|
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:a6b4eb516015852d76c10d5b0c139cec1e488aa3b53e560bc99f9c2300e33423
|
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":
|
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": 0.782,
|
124 |
"eval_wer": 1.0,
|
125 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
126 |
}
|
127 |
],
|
128 |
"max_steps": 4550,
|
129 |
"num_train_epochs": 50,
|
130 |
-
"total_flos":
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|
133 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.590163934426229,
|
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": 0.782,
|
124 |
"eval_wer": 1.0,
|
125 |
"step": 300
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 3.51,
|
129 |
+
"learning_rate": 4e-05,
|
130 |
+
"loss": 3.0511,
|
131 |
+
"step": 320
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 3.73,
|
135 |
+
"learning_rate": 4.25e-05,
|
136 |
+
"loss": 3.0358,
|
137 |
+
"step": 340
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 3.95,
|
141 |
+
"learning_rate": 4.4999999999999996e-05,
|
142 |
+
"loss": 3.0416,
|
143 |
+
"step": 360
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 4.17,
|
147 |
+
"learning_rate": 4.75e-05,
|
148 |
+
"loss": 3.1053,
|
149 |
+
"step": 380
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.39,
|
153 |
+
"learning_rate": 5e-05,
|
154 |
+
"loss": 3.0314,
|
155 |
+
"step": 400
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 4.39,
|
159 |
+
"eval_loss": 3.0990231037139893,
|
160 |
+
"eval_runtime": 198.3688,
|
161 |
+
"eval_samples_per_second": 24.414,
|
162 |
+
"eval_steps_per_second": 0.766,
|
163 |
+
"eval_wer": 1.0,
|
164 |
+
"step": 400
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 4.61,
|
168 |
+
"learning_rate": 5.25e-05,
|
169 |
+
"loss": 3.0309,
|
170 |
+
"step": 420
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.83,
|
174 |
+
"learning_rate": 5.5e-05,
|
175 |
+
"loss": 3.0259,
|
176 |
+
"step": 440
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 5.05,
|
180 |
+
"learning_rate": 5.75e-05,
|
181 |
+
"loss": 3.0998,
|
182 |
+
"step": 460
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 5.27,
|
186 |
+
"learning_rate": 6e-05,
|
187 |
+
"loss": 3.0152,
|
188 |
+
"step": 480
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 5.49,
|
192 |
+
"learning_rate": 6.25e-05,
|
193 |
+
"loss": 3.0129,
|
194 |
+
"step": 500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 5.49,
|
198 |
+
"eval_loss": 3.039973497390747,
|
199 |
+
"eval_runtime": 190.8567,
|
200 |
+
"eval_samples_per_second": 25.375,
|
201 |
+
"eval_steps_per_second": 0.796,
|
202 |
+
"eval_wer": 1.0,
|
203 |
+
"step": 500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 5.71,
|
207 |
+
"learning_rate": 6.500000000000001e-05,
|
208 |
+
"loss": 3.0088,
|
209 |
+
"step": 520
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 5.93,
|
213 |
+
"learning_rate": 6.75e-05,
|
214 |
+
"loss": 3.0051,
|
215 |
+
"step": 540
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 6.15,
|
219 |
+
"learning_rate": 7.000000000000001e-05,
|
220 |
+
"loss": 3.073,
|
221 |
+
"step": 560
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 6.37,
|
225 |
+
"learning_rate": 7.25e-05,
|
226 |
+
"loss": 3.0031,
|
227 |
+
"step": 580
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 6.59,
|
231 |
+
"learning_rate": 7.5e-05,
|
232 |
+
"loss": 2.9964,
|
233 |
+
"step": 600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 6.59,
|
237 |
+
"eval_loss": 2.998962640762329,
|
238 |
+
"eval_runtime": 193.5213,
|
239 |
+
"eval_samples_per_second": 25.026,
|
240 |
+
"eval_steps_per_second": 0.785,
|
241 |
+
"eval_wer": 1.0,
|
242 |
+
"step": 600
|
243 |
}
|
244 |
],
|
245 |
"max_steps": 4550,
|
246 |
"num_train_epochs": 50,
|
247 |
+
"total_flos": 9.32024224555606e+18,
|
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 sha256:3baffe7a116d58666fc0726fb4fa6188834614eac15e96843270fc53529b943e
|
3 |
size 1262063089
|