stuser2023
commited on
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-0/checkpoint-1069/config.json +1 -1
- run-0/checkpoint-1069/model.safetensors +1 -1
- run-0/checkpoint-1069/optimizer.pt +1 -1
- run-0/checkpoint-1069/rng_state.pth +2 -2
- run-0/checkpoint-1069/scheduler.pt +1 -1
- run-0/checkpoint-1069/trainer_state.json +17 -13
- run-0/checkpoint-1069/training_args.bin +2 -2
- runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710553602.6e5f088ca464.226.0 +2 -2
- runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710553809.6e5f088ca464.226.1 +3 -0
- runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710553848.6e5f088ca464.226.2 +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 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0719fed60e9318276761def82f7efa080ae59ab6c2baf25c074e5ce01b18e5ca
|
3 |
size 267832560
|
run-0/checkpoint-1069/config.json
CHANGED
@@ -20,6 +20,6 @@
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 30522
|
25 |
}
|
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
"vocab_size": 30522
|
25 |
}
|
run-0/checkpoint-1069/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 sha256:0719fed60e9318276761def82f7efa080ae59ab6c2baf25c074e5ce01b18e5ca
|
3 |
size 267832560
|
run-0/checkpoint-1069/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535727290
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e72e2af59534660a11d7b6c22a0e9bd6f1921d54cb18969f02bd57d0d8dab93
|
3 |
size 535727290
|
run-0/checkpoint-1069/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 sha256:55947eba1b2608c8969193d46e23df5c532e3a1b82fe3cbc92a214c25baa39ac
|
3 |
+
size 14308
|
run-0/checkpoint-1069/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 sha256:59dffb3b7e0e2d165a491ac5d933c5f60e16039244d7561a744edc3d654dec28
|
3 |
size 1064
|
run-0/checkpoint-1069/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1069",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,36 +10,40 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.47,
|
13 |
-
"
|
14 |
-
"
|
|
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.94,
|
19 |
-
"
|
20 |
-
"
|
|
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.0,
|
25 |
-
"eval_loss": 0.
|
26 |
-
"eval_matthews_correlation": 0.
|
27 |
-
"eval_runtime": 0.
|
28 |
-
"eval_samples_per_second":
|
29 |
-
"eval_steps_per_second":
|
30 |
"step": 1069
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 500,
|
34 |
"max_steps": 3207,
|
|
|
35 |
"num_train_epochs": 3,
|
36 |
"save_steps": 500,
|
37 |
-
"total_flos":
|
|
|
38 |
"trial_name": null,
|
39 |
"trial_params": {
|
40 |
-
"learning_rate":
|
41 |
"num_train_epochs": 3,
|
42 |
"per_device_train_batch_size": 8,
|
43 |
-
"seed":
|
44 |
}
|
45 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.29871168199754417,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1069",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.47,
|
13 |
+
"grad_norm": 5.35684061050415,
|
14 |
+
"learning_rate": 2.775809181053764e-06,
|
15 |
+
"loss": 0.5956,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.94,
|
20 |
+
"grad_norm": 11.188376426696777,
|
21 |
+
"learning_rate": 2.263099690648562e-06,
|
22 |
+
"loss": 0.5375,
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.0,
|
27 |
+
"eval_loss": 0.5379385948181152,
|
28 |
+
"eval_matthews_correlation": 0.29871168199754417,
|
29 |
+
"eval_runtime": 0.7649,
|
30 |
+
"eval_samples_per_second": 1363.614,
|
31 |
+
"eval_steps_per_second": 86.288,
|
32 |
"step": 1069
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 500,
|
36 |
"max_steps": 3207,
|
37 |
+
"num_input_tokens_seen": 0,
|
38 |
"num_train_epochs": 3,
|
39 |
"save_steps": 500,
|
40 |
+
"total_flos": 37784255663520.0,
|
41 |
+
"train_batch_size": 8,
|
42 |
"trial_name": null,
|
43 |
"trial_params": {
|
44 |
+
"learning_rate": 3.288518671458966e-06,
|
45 |
"num_train_epochs": 3,
|
46 |
"per_device_train_batch_size": 8,
|
47 |
+
"seed": 24
|
48 |
}
|
49 |
}
|
run-0/checkpoint-1069/training_args.bin
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 sha256:1d71decb8fd1c3b29f479f69dd55dfb41734b34761f0097d998f78bf9dd25bdb
|
3 |
+
size 4984
|
runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710553602.6e5f088ca464.226.0
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:f3a1d98b6ec332dcd3d59090bec642a3f340bdd4912c290bce02d1a7af120a15
|
3 |
+
size 7657
|
runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710553809.6e5f088ca464.226.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45794a660f169dc45d93cf54f5d734b292a22fc8a7364a56ce6196407dbd1546
|
3 |
+
size 423
|
runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710553848.6e5f088ca464.226.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0778b483e02ac32d52ec3b2a5dfa1bb4b42ba00cdcaa3f12b4939d2d6ca472f
|
3 |
+
size 5345
|
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 sha256:1d71decb8fd1c3b29f479f69dd55dfb41734b34761f0097d998f78bf9dd25bdb
|
3 |
size 4984
|