SjardiWillems
commited on
Commit
•
90c6d88
1
Parent(s):
9d64094
Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-2/checkpoint-54/model.safetensors +1 -1
- run-2/checkpoint-54/optimizer.pt +2 -2
- run-2/checkpoint-54/rng_state.pth +2 -2
- run-2/checkpoint-54/scheduler.pt +1 -1
- run-2/checkpoint-54/trainer_state.json +16 -16
- run-2/checkpoint-54/training_args.bin +1 -1
- runs/Mar06_18-56-30_6942db43b48a/events.out.tfevents.1709753687.6942db43b48a.1479.4 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:012492b62fa9e9812165c1c2dec1c814fd5eca1e1761eefe022d7365a6e4207e
|
3 |
size 267832560
|
run-2/checkpoint-54/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:012492b62fa9e9812165c1c2dec1c814fd5eca1e1761eefe022d7365a6e4207e
|
3 |
size 267832560
|
run-2/checkpoint-54/optimizer.pt
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:d5ef569d940d663b06a79f96cc6a14566b6fc310e05d5ea6d59cf53b6d1f3542
|
3 |
+
size 535724410
|
run-2/checkpoint-54/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:cec91bb12925db1daa87b96b792920c4b7c52a839f4dbd3b55edd6026128c718
|
3 |
+
size 13990
|
run-2/checkpoint-54/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:cf83323ba48bae024af14c0367540c8fa0df36f8174406ae89f3a3b1d1b318f2
|
3 |
size 1064
|
run-2/checkpoint-54/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 54,
|
@@ -10,35 +10,35 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
-
"eval_runtime":
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second":
|
18 |
"step": 27
|
19 |
},
|
20 |
{
|
21 |
"epoch": 2.0,
|
22 |
-
"eval_loss": 0.
|
23 |
-
"eval_matthews_correlation": 0.
|
24 |
-
"eval_runtime":
|
25 |
-
"eval_samples_per_second":
|
26 |
-
"eval_steps_per_second":
|
27 |
"step": 54
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 500,
|
31 |
-
"max_steps":
|
32 |
"num_input_tokens_seen": 0,
|
33 |
-
"num_train_epochs":
|
34 |
"save_steps": 500,
|
35 |
"total_flos": 0,
|
36 |
"train_batch_size": 32,
|
37 |
"trial_name": null,
|
38 |
"trial_params": {
|
39 |
-
"learning_rate":
|
40 |
-
"num_train_epochs":
|
41 |
"per_device_train_batch_size": 32,
|
42 |
-
"seed":
|
43 |
}
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.018148342420931135,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-54",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 54,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.5931227207183838,
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 12.8806,
|
16 |
+
"eval_samples_per_second": 80.974,
|
17 |
+
"eval_steps_per_second": 5.124,
|
18 |
"step": 27
|
19 |
},
|
20 |
{
|
21 |
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5773783326148987,
|
23 |
+
"eval_matthews_correlation": 0.018148342420931135,
|
24 |
+
"eval_runtime": 8.9766,
|
25 |
+
"eval_samples_per_second": 116.19,
|
26 |
+
"eval_steps_per_second": 7.352,
|
27 |
"step": 54
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 500,
|
31 |
+
"max_steps": 54,
|
32 |
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 2,
|
34 |
"save_steps": 500,
|
35 |
"total_flos": 0,
|
36 |
"train_batch_size": 32,
|
37 |
"trial_name": null,
|
38 |
"trial_params": {
|
39 |
+
"learning_rate": 3.992870159835505e-05,
|
40 |
+
"num_train_epochs": 2,
|
41 |
"per_device_train_batch_size": 32,
|
42 |
+
"seed": 40
|
43 |
}
|
44 |
}
|
run-2/checkpoint-54/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e328d83366ddcc587cd0492bd6c517f6551c74e72a0397bf5a558e1c49d5077e
|
3 |
size 4984
|
runs/Mar06_18-56-30_6942db43b48a/events.out.tfevents.1709753687.6942db43b48a.1479.4
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 sha256:47adc9600d704e81533e903455e06b46e74556d318ee72ceeb779d56d718fe23
|
3 |
+
size 5548
|