Training in progress, step 8000
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 sha256:6aa75d51acc72b972c60f979ad39492a701ea584d9e88daffaa59b3b9ecd2287
|
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 sha256:5b00a1b339ea0df14b5514813577f3d3c0ad8a81cacf6246a13afaad83d6812b
|
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:ef822c822befad20edb481677f91411aa95dbf2a3cc497b9c01b51bde80e299e
|
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:ec5cb6a91b5efe98fa3e0e292ef028ef5632c1c350423319a25a6302b0dcb075
|
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,
|
@@ -286,11 +286,27 @@
|
|
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.
|
294 |
"trial_name": null,
|
295 |
"trial_params": null
|
296 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8394543546694648,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
286 |
"eval_samples_per_second": 202.167,
|
287 |
"eval_steps_per_second": 0.791,
|
288 |
"step": 7600
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.84,
|
292 |
+
"learning_rate": 9.916232948583422e-06,
|
293 |
+
"loss": 0.6907,
|
294 |
+
"step": 8000
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.84,
|
298 |
+
"eval_accuracy": 0.8782776785846036,
|
299 |
+
"eval_f1": 0.8778960944609727,
|
300 |
+
"eval_loss": 0.6746197938919067,
|
301 |
+
"eval_runtime": 670.9876,
|
302 |
+
"eval_samples_per_second": 201.998,
|
303 |
+
"eval_steps_per_second": 0.79,
|
304 |
+
"step": 8000
|
305 |
}
|
306 |
],
|
307 |
"max_steps": 953000,
|
308 |
"num_train_epochs": 100,
|
309 |
+
"total_flos": 3.3594285032391936e+17,
|
310 |
"trial_name": null,
|
311 |
"trial_params": null
|
312 |
}
|
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 sha256:5b00a1b339ea0df14b5514813577f3d3c0ad8a81cacf6246a13afaad83d6812b
|
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:a69520f836680eb568bd6fa48d616a8661f055f2a03a2bb29df43cc253efa2af
|
3 |
+
size 7351
|