Commit
•
5231ac5
1
Parent(s):
09096e1
Training in progress, step 1500, 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 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfdb7a77d08b547c9c6992da199c063102f2b6c903aeaded67a582185a7a9a63
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2648dbe15b2f12a7a27e77dc5a033f32672097c1fa4da3c801f2f4394e3a081
|
3 |
size 1155772233
|
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 sha256:50c476b54e3f06971186d630174c9829d4b9b06eb8eab96946ff7745f50fcfcc
|
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 sha256:1a94e74103068a5fb8b31be8524087df4f57bd43f07d1db2b9d36084882fdbb5
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.39941468834877014,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-1000",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -163,6 +163,84 @@
|
|
163 |
"eval_samples_per_second": 24.123,
|
164 |
"eval_steps_per_second": 3.082,
|
165 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 50,
|
@@ -182,7 +260,7 @@
|
|
182 |
"attributes": {}
|
183 |
}
|
184 |
},
|
185 |
-
"total_flos": 1.
|
186 |
"train_batch_size": 16,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.39941468834877014,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-1000",
|
4 |
+
"epoch": 59.40594059405941,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
163 |
"eval_samples_per_second": 24.123,
|
164 |
"eval_steps_per_second": 3.082,
|
165 |
"step": 1000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 41.584158415841586,
|
169 |
+
"grad_norm": 2.8653476238250732,
|
170 |
+
"learning_rate": 5.245e-05,
|
171 |
+
"loss": 0.4268,
|
172 |
+
"step": 1050
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 43.56435643564357,
|
176 |
+
"grad_norm": 1.5550223588943481,
|
177 |
+
"learning_rate": 5.495e-05,
|
178 |
+
"loss": 0.4265,
|
179 |
+
"step": 1100
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 45.54455445544554,
|
183 |
+
"grad_norm": 1.804150104522705,
|
184 |
+
"learning_rate": 5.745e-05,
|
185 |
+
"loss": 0.4192,
|
186 |
+
"step": 1150
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 47.524752475247524,
|
190 |
+
"grad_norm": 1.9916889667510986,
|
191 |
+
"learning_rate": 5.995000000000001e-05,
|
192 |
+
"loss": 0.4149,
|
193 |
+
"step": 1200
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 49.504950495049506,
|
197 |
+
"grad_norm": 2.1027019023895264,
|
198 |
+
"learning_rate": 6.245000000000001e-05,
|
199 |
+
"loss": 0.4203,
|
200 |
+
"step": 1250
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 51.48514851485149,
|
204 |
+
"grad_norm": 1.1542466878890991,
|
205 |
+
"learning_rate": 6.494999999999999e-05,
|
206 |
+
"loss": 0.4127,
|
207 |
+
"step": 1300
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 53.46534653465346,
|
211 |
+
"grad_norm": 1.8733513355255127,
|
212 |
+
"learning_rate": 6.745e-05,
|
213 |
+
"loss": 0.4165,
|
214 |
+
"step": 1350
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 55.445544554455445,
|
218 |
+
"grad_norm": 2.544435739517212,
|
219 |
+
"learning_rate": 6.995e-05,
|
220 |
+
"loss": 0.4156,
|
221 |
+
"step": 1400
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 57.42574257425743,
|
225 |
+
"grad_norm": 2.9764773845672607,
|
226 |
+
"learning_rate": 7.245000000000001e-05,
|
227 |
+
"loss": 0.4045,
|
228 |
+
"step": 1450
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 59.40594059405941,
|
232 |
+
"grad_norm": 1.334035038948059,
|
233 |
+
"learning_rate": 7.495e-05,
|
234 |
+
"loss": 0.4075,
|
235 |
+
"step": 1500
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 59.40594059405941,
|
239 |
+
"eval_loss": 0.40177610516548157,
|
240 |
+
"eval_runtime": 6.8721,
|
241 |
+
"eval_samples_per_second": 26.193,
|
242 |
+
"eval_steps_per_second": 3.347,
|
243 |
+
"step": 1500
|
244 |
}
|
245 |
],
|
246 |
"logging_steps": 50,
|
|
|
260 |
"attributes": {}
|
261 |
}
|
262 |
},
|
263 |
+
"total_flos": 1.6206373863449352e+16,
|
264 |
"train_batch_size": 16,
|
265 |
"trial_name": null,
|
266 |
"trial_params": null
|