dougtrajano
commited on
Commit
•
024565b
1
Parent(s):
54b6b70
Training in progress, epoch 9
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 871513885
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3abd9e432cd17aa227c77a4602995a7d44a2d5b8db7d09756643847c4bdb3b4a
|
3 |
size 871513885
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 435769709
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea0028124c16c42b0173d84c15dfc6aaf99389e964846d869e1df752e59e8dec
|
3 |
size 435769709
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69726e2727b419acf15202f62187cf0581b6c2bfd7c023bc96716f05fa3e0d08
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -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:c784665c0bd4de01cbb7e9c50f86d2b0ebff72eead0e3ffd23f231c6475b92bf
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.8580479726153486,
|
3 |
"best_model_checkpoint": "./output/toxic-comment-classification-2023-02-12-03-38-39-438/model/checkpoint-5632",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -234,11 +234,41 @@
|
|
234 |
"eval_samples_per_second": 216.234,
|
235 |
"eval_steps_per_second": 27.054,
|
236 |
"step": 11264
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
237 |
}
|
238 |
],
|
239 |
"max_steps": 42240,
|
240 |
"num_train_epochs": 30,
|
241 |
-
"total_flos":
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
244 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.8580479726153486,
|
3 |
"best_model_checkpoint": "./output/toxic-comment-classification-2023-02-12-03-38-39-438/model/checkpoint-5632",
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 12672,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
234 |
"eval_samples_per_second": 216.234,
|
235 |
"eval_steps_per_second": 27.054,
|
236 |
"step": 11264
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 8.17,
|
240 |
+
"learning_rate": 2.3693879284305067e-05,
|
241 |
+
"loss": 0.1896,
|
242 |
+
"step": 11500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 8.52,
|
246 |
+
"learning_rate": 2.3308487623857682e-05,
|
247 |
+
"loss": 0.1932,
|
248 |
+
"step": 12000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 8.88,
|
252 |
+
"learning_rate": 2.29230959634103e-05,
|
253 |
+
"loss": 0.1989,
|
254 |
+
"step": 12500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 9.0,
|
258 |
+
"eval_accuracy": 0.8499844382197324,
|
259 |
+
"eval_f1": 0.8496464092791962,
|
260 |
+
"eval_loss": 0.6235840320587158,
|
261 |
+
"eval_precision": 0.8498702852768623,
|
262 |
+
"eval_recall": 0.8499844382197324,
|
263 |
+
"eval_runtime": 15.7802,
|
264 |
+
"eval_samples_per_second": 203.61,
|
265 |
+
"eval_steps_per_second": 25.475,
|
266 |
+
"step": 12672
|
267 |
}
|
268 |
],
|
269 |
"max_steps": 42240,
|
270 |
"num_train_epochs": 30,
|
271 |
+
"total_flos": 3931395111413520.0,
|
272 |
"trial_name": null,
|
273 |
"trial_params": null
|
274 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 435769709
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea0028124c16c42b0173d84c15dfc6aaf99389e964846d869e1df752e59e8dec
|
3 |
size 435769709
|