Training in progress, step 700, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:363a18dff03938cbab3ea0517e5fd8baacab97d4647e9d18d67491af3678daa6
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1925064044
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec51eb4084dc7356ccd5e4f6e60d6eb446a9f6b453cb22d3a3f27e5a78818d65
|
3 |
size 1925064044
|
last-checkpoint/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 sha256:140766ee026fe5edfef0f038f98f0479f8a9d10cfc1f7fe43d81468743578807
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5923d5ad322acc38eebeb7826b39a3fb9c19734502e2060fc78e9bf4e91b73b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -139,6 +139,105 @@
|
|
139 |
"eval_steps_per_second": 0.102,
|
140 |
"eval_wer": 101.62922906267333,
|
141 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
142 |
}
|
143 |
],
|
144 |
"logging_steps": 25,
|
@@ -146,7 +245,7 @@
|
|
146 |
"num_input_tokens_seen": 0,
|
147 |
"num_train_epochs": 8,
|
148 |
"save_steps": 100,
|
149 |
-
"total_flos":
|
150 |
"trial_name": null,
|
151 |
"trial_params": null
|
152 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 1.33587786259542,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
139 |
"eval_steps_per_second": 0.102,
|
140 |
"eval_wer": 101.62922906267333,
|
141 |
"step": 400
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.81,
|
145 |
+
"learning_rate": 8.380000000000001e-06,
|
146 |
+
"loss": 0.2514,
|
147 |
+
"step": 425
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.86,
|
151 |
+
"learning_rate": 8.880000000000001e-06,
|
152 |
+
"loss": 0.2826,
|
153 |
+
"step": 450
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.91,
|
157 |
+
"learning_rate": 9.38e-06,
|
158 |
+
"loss": 0.2381,
|
159 |
+
"step": 475
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.95,
|
163 |
+
"learning_rate": 9.88e-06,
|
164 |
+
"loss": 0.2491,
|
165 |
+
"step": 500
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.95,
|
169 |
+
"eval_loss": 0.3922654092311859,
|
170 |
+
"eval_runtime": 1735.7941,
|
171 |
+
"eval_samples_per_second": 0.864,
|
172 |
+
"eval_steps_per_second": 0.108,
|
173 |
+
"eval_wer": 112.23655019412091,
|
174 |
+
"step": 500
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.0,
|
178 |
+
"learning_rate": 9.945714285714286e-06,
|
179 |
+
"loss": 0.2621,
|
180 |
+
"step": 525
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 1.05,
|
184 |
+
"learning_rate": 9.874285714285715e-06,
|
185 |
+
"loss": 0.1729,
|
186 |
+
"step": 550
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 1.1,
|
190 |
+
"learning_rate": 9.802857142857144e-06,
|
191 |
+
"loss": 0.1725,
|
192 |
+
"step": 575
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 1.15,
|
196 |
+
"learning_rate": 9.731428571428573e-06,
|
197 |
+
"loss": 0.17,
|
198 |
+
"step": 600
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.15,
|
202 |
+
"eval_loss": 0.3860141336917877,
|
203 |
+
"eval_runtime": 1739.7902,
|
204 |
+
"eval_samples_per_second": 0.862,
|
205 |
+
"eval_steps_per_second": 0.108,
|
206 |
+
"eval_wer": 107.05074875207987,
|
207 |
+
"step": 600
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.19,
|
211 |
+
"learning_rate": 9.66e-06,
|
212 |
+
"loss": 0.1744,
|
213 |
+
"step": 625
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 1.24,
|
217 |
+
"learning_rate": 9.58857142857143e-06,
|
218 |
+
"loss": 0.1843,
|
219 |
+
"step": 650
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.29,
|
223 |
+
"learning_rate": 9.517142857142859e-06,
|
224 |
+
"loss": 0.1708,
|
225 |
+
"step": 675
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.34,
|
229 |
+
"learning_rate": 9.445714285714288e-06,
|
230 |
+
"loss": 0.1603,
|
231 |
+
"step": 700
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.34,
|
235 |
+
"eval_loss": 0.38356906175613403,
|
236 |
+
"eval_runtime": 1678.1272,
|
237 |
+
"eval_samples_per_second": 0.894,
|
238 |
+
"eval_steps_per_second": 0.112,
|
239 |
+
"eval_wer": 90.3563505268996,
|
240 |
+
"step": 700
|
241 |
}
|
242 |
],
|
243 |
"logging_steps": 25,
|
|
|
245 |
"num_input_tokens_seen": 0,
|
246 |
"num_train_epochs": 8,
|
247 |
"save_steps": 100,
|
248 |
+
"total_flos": 6.46229286936576e+18,
|
249 |
"trial_name": null,
|
250 |
"trial_params": null
|
251 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8639ff321d8732686fcd47480f025401063d95f80a6017764993068cc24ca794
|
3 |
size 4792
|