Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-3/checkpoint-267/model.safetensors +1 -1
- run-3/checkpoint-267/optimizer.pt +1 -1
- run-3/checkpoint-267/scheduler.pt +1 -1
- run-3/checkpoint-267/trainer_state.json +9 -9
- run-3/checkpoint-267/training_args.bin +1 -1
- runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713522305.dcdaa3e6ec43.789.3 +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 409103316
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01943b36fe2d099072ef77b2811221d172183457a8423ec8462545bbe2d496e3
|
3 |
size 409103316
|
run-3/checkpoint-267/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 409103316
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01943b36fe2d099072ef77b2811221d172183457a8423ec8462545bbe2d496e3
|
3 |
size 409103316
|
run-3/checkpoint-267/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 818327802
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65e47361cac1e35bd4bb3eca381d3691bf21be971b356c5736ccb58b481861fe
|
3 |
size 818327802
|
run-3/checkpoint-267/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:ef3be8be9037b2d6a9348611f95c19fb1d17ca7cb1da92486df22b7e0a3c655a
|
3 |
size 1064
|
run-3/checkpoint-267/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "BERT-WMM/run-3/checkpoint-267",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,23 +10,23 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_loss": 0.
|
15 |
-
"eval_runtime": 2.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second":
|
18 |
"step": 267
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
-
"max_steps":
|
23 |
"num_input_tokens_seen": 0,
|
24 |
-
"num_train_epochs":
|
25 |
"save_steps": 500,
|
26 |
"total_flos": 0,
|
27 |
"train_batch_size": 32,
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
-
"
|
31 |
}
|
32 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6065873503684998,
|
3 |
"best_model_checkpoint": "BERT-WMM/run-3/checkpoint-267",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.7530516431924883,
|
14 |
+
"eval_loss": 0.6065873503684998,
|
15 |
+
"eval_runtime": 2.5921,
|
16 |
+
"eval_samples_per_second": 821.724,
|
17 |
+
"eval_steps_per_second": 51.695,
|
18 |
"step": 267
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
+
"max_steps": 534,
|
23 |
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 2,
|
25 |
"save_steps": 500,
|
26 |
"total_flos": 0,
|
27 |
"train_batch_size": 32,
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
+
"weight_decay": 0.021167311357718124
|
31 |
}
|
32 |
}
|
run-3/checkpoint-267/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1238f3e9130ff13042dcb9e0ded88b87b25d59c0eb7bc889417ea846582c3c9b
|
3 |
size 4856
|
runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713522305.dcdaa3e6ec43.789.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5908acf12b09c9364f37fdcc1828450a70123a37e71027bfb4acc38d127db0d0
|
3 |
+
size 5233
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1238f3e9130ff13042dcb9e0ded88b87b25d59c0eb7bc889417ea846582c3c9b
|
3 |
size 4856
|