SjardiWillems
commited on
Commit
•
e32a80f
1
Parent(s):
e975186
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-2/checkpoint-108/model.safetensors +1 -1
- run-2/checkpoint-108/optimizer.pt +1 -1
- run-2/checkpoint-108/rng_state.pth +2 -2
- run-2/checkpoint-108/scheduler.pt +1 -1
- run-2/checkpoint-108/trainer_state.json +23 -23
- run-2/checkpoint-108/training_args.bin +1 -1
- run-2/checkpoint-135/model.safetensors +1 -1
- run-2/checkpoint-135/optimizer.pt +1 -1
- run-2/checkpoint-135/rng_state.pth +2 -2
- run-2/checkpoint-135/scheduler.pt +1 -1
- run-2/checkpoint-135/trainer_state.json +28 -28
- run-2/checkpoint-135/training_args.bin +1 -1
- run-2/checkpoint-54/model.safetensors +1 -1
- run-2/checkpoint-54/optimizer.pt +1 -1
- run-2/checkpoint-54/rng_state.pth +2 -2
- run-2/checkpoint-54/scheduler.pt +1 -1
- run-2/checkpoint-54/trainer_state.json +13 -13
- run-2/checkpoint-54/training_args.bin +1 -1
- run-2/checkpoint-81/model.safetensors +1 -1
- run-2/checkpoint-81/optimizer.pt +1 -1
- run-2/checkpoint-81/rng_state.pth +2 -2
- run-2/checkpoint-81/scheduler.pt +1 -1
- run-2/checkpoint-81/trainer_state.json +18 -18
- run-2/checkpoint-81/training_args.bin +1 -1
- run-3/checkpoint-54/config.json +25 -0
- run-3/checkpoint-54/model.safetensors +3 -0
- run-3/checkpoint-54/optimizer.pt +3 -0
- run-3/checkpoint-54/rng_state.pth +3 -0
- run-3/checkpoint-54/scheduler.pt +3 -0
- run-3/checkpoint-54/special_tokens_map.json +7 -0
- run-3/checkpoint-54/tokenizer.json +0 -0
- run-3/checkpoint-54/tokenizer_config.json +55 -0
- run-3/checkpoint-54/trainer_state.json +35 -0
- run-3/checkpoint-54/training_args.bin +3 -0
- run-3/checkpoint-54/vocab.txt +0 -0
- runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709677008.418b5b5ae03a.490.5 +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 sha256:24476bddf0cd9468d4ab74ae6bbe580c634cd59d759787b10ec33290ff875f39
|
3 |
size 267832560
|
run-2/checkpoint-108/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 sha256:3b809c09fd0721275c7613c4539e3476ef185fea9a6785d0239089b89441dd57
|
3 |
size 267832560
|
run-2/checkpoint-108/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:b8cd00ed6133374e44a63d1c2c8db52df1c6702484d6934306dd7fdd297c23dc
|
3 |
size 535727290
|
run-2/checkpoint-108/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:c2bab5c54956ce02c868031e68e39f45dcf50f10173ae5b404670e2427e13730
|
3 |
+
size 14308
|
run-2/checkpoint-108/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:da0234b76ca0b05154312aa7dcf16dceb2db5647258e7b3d597bceb9fb500ee9
|
3 |
size 1064
|
run-2/checkpoint-108/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": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 108,
|
@@ -10,38 +10,38 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
-
"eval_runtime": 0.
|
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": 0.
|
25 |
-
"eval_samples_per_second":
|
26 |
-
"eval_steps_per_second":
|
27 |
"step": 54
|
28 |
},
|
29 |
{
|
30 |
"epoch": 3.0,
|
31 |
-
"eval_loss": 0.
|
32 |
-
"eval_matthews_correlation": 0.
|
33 |
-
"eval_runtime": 0.
|
34 |
-
"eval_samples_per_second":
|
35 |
-
"eval_steps_per_second":
|
36 |
"step": 81
|
37 |
},
|
38 |
{
|
39 |
"epoch": 4.0,
|
40 |
-
"eval_loss": 0.
|
41 |
-
"eval_matthews_correlation": 0.
|
42 |
-
"eval_runtime": 0.
|
43 |
-
"eval_samples_per_second":
|
44 |
-
"eval_steps_per_second":
|
45 |
"step": 108
|
46 |
}
|
47 |
],
|
@@ -54,9 +54,9 @@
|
|
54 |
"train_batch_size": 32,
|
55 |
"trial_name": null,
|
56 |
"trial_params": {
|
57 |
-
"learning_rate":
|
58 |
"num_train_epochs": 5,
|
59 |
"per_device_train_batch_size": 32,
|
60 |
-
"seed":
|
61 |
}
|
62 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-27",
|
4 |
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 108,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6132858991622925,
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4871,
|
16 |
+
"eval_samples_per_second": 2141.162,
|
17 |
+
"eval_steps_per_second": 135.491,
|
18 |
"step": 27
|
19 |
},
|
20 |
{
|
21 |
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6033318638801575,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.5208,
|
25 |
+
"eval_samples_per_second": 2002.541,
|
26 |
+
"eval_steps_per_second": 126.719,
|
27 |
"step": 54
|
28 |
},
|
29 |
{
|
30 |
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.5928357243537903,
|
32 |
+
"eval_matthews_correlation": 0.0,
|
33 |
+
"eval_runtime": 0.5199,
|
34 |
+
"eval_samples_per_second": 2006.182,
|
35 |
+
"eval_steps_per_second": 126.949,
|
36 |
"step": 81
|
37 |
},
|
38 |
{
|
39 |
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.5839361548423767,
|
41 |
+
"eval_matthews_correlation": 0.0,
|
42 |
+
"eval_runtime": 0.5244,
|
43 |
+
"eval_samples_per_second": 1989.096,
|
44 |
+
"eval_steps_per_second": 125.868,
|
45 |
"step": 108
|
46 |
}
|
47 |
],
|
|
|
54 |
"train_batch_size": 32,
|
55 |
"trial_name": null,
|
56 |
"trial_params": {
|
57 |
+
"learning_rate": 7.921646169086052e-06,
|
58 |
"num_train_epochs": 5,
|
59 |
"per_device_train_batch_size": 32,
|
60 |
+
"seed": 29
|
61 |
}
|
62 |
}
|
run-2/checkpoint-108/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 sha256:04b1732029c3014268c6be62d578a5b5765a6136da335617e7db8f5a0380b6d4
|
3 |
size 4984
|
run-2/checkpoint-135/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:ba682247e8c2364b057acd7d7491f60aa4634e1c4b28fb53c87ceaf7c8a6f1fe
|
3 |
size 267832560
|
run-2/checkpoint-135/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 sha256:5ebcd5ea143ab11bc9f21e111b4dae51ffd599402efd2a049e46d9266c994993
|
3 |
size 535727290
|
run-2/checkpoint-135/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 sha256:1e9692bbe9f70233d5dd22d4b568822c4594c04bb430e956201c9c885dd09ff4
|
3 |
+
size 14308
|
run-2/checkpoint-135/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 sha256:233557d554fd21c793e66fa23ece2c97940ac8318ea0aa24a6941b2ff0159d71
|
3 |
size 1064
|
run-2/checkpoint-135/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": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 135,
|
@@ -10,47 +10,47 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
-
"eval_runtime": 0.
|
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": 0.
|
25 |
-
"eval_samples_per_second":
|
26 |
-
"eval_steps_per_second":
|
27 |
"step": 54
|
28 |
},
|
29 |
{
|
30 |
"epoch": 3.0,
|
31 |
-
"eval_loss": 0.
|
32 |
-
"eval_matthews_correlation": 0.
|
33 |
-
"eval_runtime": 0.
|
34 |
-
"eval_samples_per_second":
|
35 |
-
"eval_steps_per_second":
|
36 |
"step": 81
|
37 |
},
|
38 |
{
|
39 |
"epoch": 4.0,
|
40 |
-
"eval_loss": 0.
|
41 |
-
"eval_matthews_correlation": 0.
|
42 |
-
"eval_runtime": 0.
|
43 |
-
"eval_samples_per_second":
|
44 |
-
"eval_steps_per_second":
|
45 |
"step": 108
|
46 |
},
|
47 |
{
|
48 |
"epoch": 5.0,
|
49 |
-
"eval_loss": 0.
|
50 |
-
"eval_matthews_correlation": 0.
|
51 |
-
"eval_runtime": 0.
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second":
|
54 |
"step": 135
|
55 |
}
|
56 |
],
|
@@ -63,9 +63,9 @@
|
|
63 |
"train_batch_size": 32,
|
64 |
"trial_name": null,
|
65 |
"trial_params": {
|
66 |
-
"learning_rate":
|
67 |
"num_train_epochs": 5,
|
68 |
"per_device_train_batch_size": 32,
|
69 |
-
"seed":
|
70 |
}
|
71 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-27",
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 135,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6132858991622925,
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4871,
|
16 |
+
"eval_samples_per_second": 2141.162,
|
17 |
+
"eval_steps_per_second": 135.491,
|
18 |
"step": 27
|
19 |
},
|
20 |
{
|
21 |
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6033318638801575,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.5208,
|
25 |
+
"eval_samples_per_second": 2002.541,
|
26 |
+
"eval_steps_per_second": 126.719,
|
27 |
"step": 54
|
28 |
},
|
29 |
{
|
30 |
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.5928357243537903,
|
32 |
+
"eval_matthews_correlation": 0.0,
|
33 |
+
"eval_runtime": 0.5199,
|
34 |
+
"eval_samples_per_second": 2006.182,
|
35 |
+
"eval_steps_per_second": 126.949,
|
36 |
"step": 81
|
37 |
},
|
38 |
{
|
39 |
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.5839361548423767,
|
41 |
+
"eval_matthews_correlation": 0.0,
|
42 |
+
"eval_runtime": 0.5244,
|
43 |
+
"eval_samples_per_second": 1989.096,
|
44 |
+
"eval_steps_per_second": 125.868,
|
45 |
"step": 108
|
46 |
},
|
47 |
{
|
48 |
"epoch": 5.0,
|
49 |
+
"eval_loss": 0.5813562870025635,
|
50 |
+
"eval_matthews_correlation": 0.0,
|
51 |
+
"eval_runtime": 0.5296,
|
52 |
+
"eval_samples_per_second": 1969.572,
|
53 |
+
"eval_steps_per_second": 124.633,
|
54 |
"step": 135
|
55 |
}
|
56 |
],
|
|
|
63 |
"train_batch_size": 32,
|
64 |
"trial_name": null,
|
65 |
"trial_params": {
|
66 |
+
"learning_rate": 7.921646169086052e-06,
|
67 |
"num_train_epochs": 5,
|
68 |
"per_device_train_batch_size": 32,
|
69 |
+
"seed": 29
|
70 |
}
|
71 |
}
|
run-2/checkpoint-135/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 sha256:04b1732029c3014268c6be62d578a5b5765a6136da335617e7db8f5a0380b6d4
|
3 |
size 4984
|
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 sha256:1cf670b1ad443f48e7dbc19f7228957836a9a1f368cc6bb0c19c09452aebdcfb
|
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 535727290
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f53747fd2f17a3c676997225927a1f022b40022751d05103d37e33f20c1f5bb6
|
3 |
size 535727290
|
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 sha256:258a2d3d5ffe25ac3a06205386f51e4e5da17129b550928d5e5233f797905d88
|
3 |
+
size 14308
|
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 sha256:7cf5925c3c299a82de863e52a9a4b1765b343a4bfecea36700a111277ad649ad
|
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,
|
@@ -10,20 +10,20 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
-
"eval_runtime": 0.
|
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": 0.
|
25 |
-
"eval_samples_per_second":
|
26 |
-
"eval_steps_per_second":
|
27 |
"step": 54
|
28 |
}
|
29 |
],
|
@@ -36,9 +36,9 @@
|
|
36 |
"train_batch_size": 32,
|
37 |
"trial_name": null,
|
38 |
"trial_params": {
|
39 |
-
"learning_rate":
|
40 |
"num_train_epochs": 5,
|
41 |
"per_device_train_batch_size": 32,
|
42 |
-
"seed":
|
43 |
}
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-27",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 54,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6132858991622925,
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4871,
|
16 |
+
"eval_samples_per_second": 2141.162,
|
17 |
+
"eval_steps_per_second": 135.491,
|
18 |
"step": 27
|
19 |
},
|
20 |
{
|
21 |
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6033318638801575,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.5208,
|
25 |
+
"eval_samples_per_second": 2002.541,
|
26 |
+
"eval_steps_per_second": 126.719,
|
27 |
"step": 54
|
28 |
}
|
29 |
],
|
|
|
36 |
"train_batch_size": 32,
|
37 |
"trial_name": null,
|
38 |
"trial_params": {
|
39 |
+
"learning_rate": 7.921646169086052e-06,
|
40 |
"num_train_epochs": 5,
|
41 |
"per_device_train_batch_size": 32,
|
42 |
+
"seed": 29
|
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 sha256:04b1732029c3014268c6be62d578a5b5765a6136da335617e7db8f5a0380b6d4
|
3 |
size 4984
|
run-2/checkpoint-81/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 sha256:1647efe1fa0b2681a2d7539477e01324d298662f4b87e080945636643c7e1b40
|
3 |
size 267832560
|
run-2/checkpoint-81/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 sha256:65a60313ed2a96a85f3355f70e01e9d4ade3844e7399e951ddb22dab37c54ed6
|
3 |
size 535727290
|
run-2/checkpoint-81/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:ebb5ac23b57e92300bdf0c086c285cb3503ed24b626a459ee1fac2fe0c7dde14
|
3 |
+
size 14308
|
run-2/checkpoint-81/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:eb51f9faffe32d43807d880e287b99a55b3940f8751e5ed67246c16af5bf8713
|
3 |
size 1064
|
run-2/checkpoint-81/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": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 81,
|
@@ -10,29 +10,29 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
-
"eval_runtime": 0.
|
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": 0.
|
25 |
-
"eval_samples_per_second":
|
26 |
-
"eval_steps_per_second":
|
27 |
"step": 54
|
28 |
},
|
29 |
{
|
30 |
"epoch": 3.0,
|
31 |
-
"eval_loss": 0.
|
32 |
-
"eval_matthews_correlation": 0.
|
33 |
-
"eval_runtime": 0.
|
34 |
-
"eval_samples_per_second":
|
35 |
-
"eval_steps_per_second":
|
36 |
"step": 81
|
37 |
}
|
38 |
],
|
@@ -45,9 +45,9 @@
|
|
45 |
"train_batch_size": 32,
|
46 |
"trial_name": null,
|
47 |
"trial_params": {
|
48 |
-
"learning_rate":
|
49 |
"num_train_epochs": 5,
|
50 |
"per_device_train_batch_size": 32,
|
51 |
-
"seed":
|
52 |
}
|
53 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-27",
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 81,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6132858991622925,
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4871,
|
16 |
+
"eval_samples_per_second": 2141.162,
|
17 |
+
"eval_steps_per_second": 135.491,
|
18 |
"step": 27
|
19 |
},
|
20 |
{
|
21 |
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6033318638801575,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.5208,
|
25 |
+
"eval_samples_per_second": 2002.541,
|
26 |
+
"eval_steps_per_second": 126.719,
|
27 |
"step": 54
|
28 |
},
|
29 |
{
|
30 |
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.5928357243537903,
|
32 |
+
"eval_matthews_correlation": 0.0,
|
33 |
+
"eval_runtime": 0.5199,
|
34 |
+
"eval_samples_per_second": 2006.182,
|
35 |
+
"eval_steps_per_second": 126.949,
|
36 |
"step": 81
|
37 |
}
|
38 |
],
|
|
|
45 |
"train_batch_size": 32,
|
46 |
"trial_name": null,
|
47 |
"trial_params": {
|
48 |
+
"learning_rate": 7.921646169086052e-06,
|
49 |
"num_train_epochs": 5,
|
50 |
"per_device_train_batch_size": 32,
|
51 |
+
"seed": 29
|
52 |
}
|
53 |
}
|
run-2/checkpoint-81/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 sha256:04b1732029c3014268c6be62d578a5b5765a6136da335617e7db8f5a0380b6d4
|
3 |
size 4984
|
run-3/checkpoint-54/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
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-3/checkpoint-54/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24476bddf0cd9468d4ab74ae6bbe580c634cd59d759787b10ec33290ff875f39
|
3 |
+
size 267832560
|
run-3/checkpoint-54/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23f6d4129597305e70974d7bec802922ca4aab9a8b24c532db92f79488204790
|
3 |
+
size 535727290
|
run-3/checkpoint-54/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ef8e8e72861ed66a7eb643b8e32a5ce0bbdf92b199ba291873affc70c991f94
|
3 |
+
size 14180
|
run-3/checkpoint-54/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c81342000103ad0bd403a3bf4c594059246081fd7734707db42d835ad6c4838
|
3 |
+
size 1064
|
run-3/checkpoint-54/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-3/checkpoint-54/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-54/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-3/checkpoint-54/trainer_state.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 54,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6160927414894104,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4953,
|
16 |
+
"eval_samples_per_second": 2105.607,
|
17 |
+
"eval_steps_per_second": 133.241,
|
18 |
+
"step": 54
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 270,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 5,
|
25 |
+
"save_steps": 500,
|
26 |
+
"total_flos": 0,
|
27 |
+
"train_batch_size": 16,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": {
|
30 |
+
"learning_rate": 4.118328225546516e-06,
|
31 |
+
"num_train_epochs": 5,
|
32 |
+
"per_device_train_batch_size": 16,
|
33 |
+
"seed": 10
|
34 |
+
}
|
35 |
+
}
|
run-3/checkpoint-54/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98eb71cc2a425fe99533b8db21e393132228db26f27ca6e23b50c5fe39be3492
|
3 |
+
size 4984
|
run-3/checkpoint-54/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709677008.418b5b5ae03a.490.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d2bc0f956294eb9bcc4f995d4f7fd0d5ecb8df07cf9750a3ef6b2297679ddb3
|
3 |
+
size 6559
|
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 sha256:98eb71cc2a425fe99533b8db21e393132228db26f27ca6e23b50c5fe39be3492
|
3 |
size 4984
|