Training in progress, step 7600
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -3
- pytorch_model.bin +1 -1
- runs/Jun20_22-52-08_0a0be1aa5e93/events.out.tfevents.1687302809.0a0be1aa5e93.956.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2117841669
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5dce2eed75fae2b0cb087b4ed5dc803e1b48c3a44b9536fc07498014380454c
|
3 |
size 2117841669
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:108931494f598e7baf364634ca0b2585a0d278bdf8b37b72caa1d449c9dc0120
|
3 |
size 2268278205
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab2c98311b3da566a29769562397dee5d4d32252b9baacdc4870f0ecd1df7745
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a07c207c837dd61db60cceabc35eccd2dd7cdf2cc7f79d3d5702c3a97f5cbe10
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -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,
|
@@ -270,11 +270,27 @@
|
|
270 |
"eval_samples_per_second": 202.103,
|
271 |
"eval_steps_per_second": 0.79,
|
272 |
"step": 7200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
273 |
}
|
274 |
],
|
275 |
"max_steps": 953000,
|
276 |
"num_train_epochs": 100,
|
277 |
-
"total_flos": 3.
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|
280 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7974816369359916,
|
5 |
+
"global_step": 7600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
270 |
"eval_samples_per_second": 202.103,
|
271 |
"eval_steps_per_second": 0.79,
|
272 |
"step": 7200
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.79,
|
276 |
+
"learning_rate": 9.921469045120673e-06,
|
277 |
+
"loss": 0.694,
|
278 |
+
"step": 7500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.8,
|
282 |
+
"eval_accuracy": 0.8757765349938763,
|
283 |
+
"eval_f1": 0.875946128594897,
|
284 |
+
"eval_loss": 0.6784085631370544,
|
285 |
+
"eval_runtime": 670.4256,
|
286 |
+
"eval_samples_per_second": 202.167,
|
287 |
+
"eval_steps_per_second": 0.791,
|
288 |
+
"step": 7600
|
289 |
}
|
290 |
],
|
291 |
"max_steps": 953000,
|
292 |
"num_train_epochs": 100,
|
293 |
+
"total_flos": 3.191217914973312e+17,
|
294 |
"trial_name": null,
|
295 |
"trial_params": null
|
296 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:108931494f598e7baf364634ca0b2585a0d278bdf8b37b72caa1d449c9dc0120
|
3 |
size 2268278205
|
runs/Jun20_22-52-08_0a0be1aa5e93/events.out.tfevents.1687302809.0a0be1aa5e93.956.0
CHANGED
@@ -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 sha256:6a701b147c483f23e182e17b51090796a86b9b877a7daef8fed6f1a9367e11da
|
3 |
+
size 6825
|