ana-grassmann
commited on
Commit
•
a6354c3
1
Parent(s):
0687c8b
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-0/checkpoint-835/model.safetensors +1 -1
- run-0/checkpoint-835/optimizer.pt +1 -1
- run-0/checkpoint-835/rng_state.pth +2 -2
- run-0/checkpoint-835/scheduler.pt +1 -1
- run-0/checkpoint-835/trainer_state.json +17 -17
- run-0/checkpoint-835/training_args.bin +1 -1
- runs/Apr07_21-55-44_2e7e2ed6349a/events.out.tfevents.1712526953.2e7e2ed6349a.1594.0 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b7007f61a373deb00621503390180c0e6f3f5a8b37facf65d670c423f04bf45
|
3 |
size 437958648
|
run-0/checkpoint-835/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b7007f61a373deb00621503390180c0e6f3f5a8b37facf65d670c423f04bf45
|
3 |
size 437958648
|
run-0/checkpoint-835/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 876038394
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:689215e4c792f6166d0118e585f169e4d148fde656b6b2c563f10ba34e78cff3
|
3 |
size 876038394
|
run-0/checkpoint-835/rng_state.pth
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 sha256:75ed4da7e346747904cd447e9e439d252e2df784c7284cb65dfa06e0438c83c4
|
3 |
+
size 14244
|
run-0/checkpoint-835/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 sha256:8ce115f7f9f39f62399e8ec9058e4bc072c178a1495bb1914e4a0db53323eed0
|
3 |
size 1064
|
run-0/checkpoint-835/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-0/checkpoint-835",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,33 +10,33 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.6,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_accuracy": 0.
|
21 |
-
"eval_loss": 0.
|
22 |
-
"eval_runtime":
|
23 |
-
"eval_samples_per_second":
|
24 |
-
"eval_steps_per_second": 3.
|
25 |
"step": 835
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 500,
|
29 |
-
"max_steps":
|
30 |
"num_input_tokens_seen": 0,
|
31 |
-
"num_train_epochs":
|
32 |
"save_steps": 500,
|
33 |
-
"total_flos":
|
34 |
-
"train_batch_size":
|
35 |
"trial_name": null,
|
36 |
"trial_params": {
|
37 |
-
"learning_rate":
|
38 |
-
"num_train_epochs":
|
39 |
-
"per_device_train_batch_size":
|
40 |
-
"seed":
|
41 |
}
|
42 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9488915518274416,
|
3 |
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-0/checkpoint-835",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.6,
|
13 |
+
"grad_norm": 0.30469822883605957,
|
14 |
+
"learning_rate": 3.878567975913952e-06,
|
15 |
+
"loss": 0.3154,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.9488915518274416,
|
21 |
+
"eval_loss": 0.22129623591899872,
|
22 |
+
"eval_runtime": 335.9128,
|
23 |
+
"eval_samples_per_second": 49.686,
|
24 |
+
"eval_steps_per_second": 3.108,
|
25 |
"step": 835
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 500,
|
29 |
+
"max_steps": 1670,
|
30 |
"num_input_tokens_seen": 0,
|
31 |
+
"num_train_epochs": 2,
|
32 |
"save_steps": 500,
|
33 |
+
"total_flos": 1289101310183160.0,
|
34 |
+
"train_batch_size": 4,
|
35 |
"trial_name": null,
|
36 |
"trial_params": {
|
37 |
+
"learning_rate": 5.536075657928461e-06,
|
38 |
+
"num_train_epochs": 2,
|
39 |
+
"per_device_train_batch_size": 4,
|
40 |
+
"seed": 30
|
41 |
}
|
42 |
}
|
run-0/checkpoint-835/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3cf64e30d88e54cc8c23684bd03a07683ebeb538447855e2dd3ae4132912700
|
3 |
size 4920
|
runs/Apr07_21-55-44_2e7e2ed6349a/events.out.tfevents.1712526953.2e7e2ed6349a.1594.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1c754fb390b048cd7352780ed6b5b6add8708074d691787374dabd5ce6af6a1
|
3 |
+
size 14275
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3cf64e30d88e54cc8c23684bd03a07683ebeb538447855e2dd3ae4132912700
|
3 |
size 4920
|