sibstrider
commited on
Commit
•
2ca3c1d
1
Parent(s):
d95c13c
Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-2/checkpoint-1100/model.safetensors +1 -1
- run-2/checkpoint-1100/optimizer.pt +1 -1
- run-2/checkpoint-1100/rng_state.pth +1 -1
- run-2/checkpoint-1100/scheduler.pt +1 -1
- run-2/checkpoint-1100/trainer_state.json +21 -21
- run-2/checkpoint-1100/training_args.bin +1 -1
- run-2/checkpoint-1650/trainer_state.json +28 -28
- runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705269786.DESKTOP-RFEED41.20976.18 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 116795404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2ced358dc3bc4605895c8027d988748fb8764af9b57b5edaad008d467ac9df5
|
3 |
size 116795404
|
run-2/checkpoint-1100/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 116795404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2ced358dc3bc4605895c8027d988748fb8764af9b57b5edaad008d467ac9df5
|
3 |
size 116795404
|
run-2/checkpoint-1100/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 233621882
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:171427067aaa2194d8a81db089c70b669189c9c98fde6c739061a0a3a2068e40
|
3 |
size 233621882
|
run-2/checkpoint-1100/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13990
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ada2bb04b88d0294fe44121ff921a07d99208db29ca33d0b0f391e55a9684bc
|
3 |
size 13990
|
run-2/checkpoint-1100/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:cee9d68d7ffd6e02e89ecadac88c09363aa50fa3ffbe10ea51c490d81f296210
|
3 |
size 1064
|
run-2/checkpoint-1100/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-1100",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
@@ -10,47 +10,47 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.91,
|
13 |
-
"learning_rate":
|
14 |
-
"loss":
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.0,
|
19 |
-
"eval_accuracy": 0.
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime": 1.
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 550
|
25 |
},
|
26 |
{
|
27 |
"epoch": 1.82,
|
28 |
-
"learning_rate":
|
29 |
-
"loss": 1.
|
30 |
"step": 1000
|
31 |
},
|
32 |
{
|
33 |
"epoch": 2.0,
|
34 |
-
"eval_accuracy": 0.
|
35 |
-
"eval_loss":
|
36 |
-
"eval_runtime": 1.
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 1100
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 500,
|
43 |
-
"max_steps":
|
44 |
"num_input_tokens_seen": 0,
|
45 |
-
"num_train_epochs":
|
46 |
"save_steps": 500,
|
47 |
-
"total_flos":
|
48 |
"train_batch_size": 4,
|
49 |
"trial_name": null,
|
50 |
"trial_params": {
|
51 |
-
"learning_rate":
|
52 |
-
"num_train_epochs":
|
53 |
"per_device_train_batch_size": 4,
|
54 |
-
"seed":
|
55 |
}
|
56 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7755102040816326,
|
3 |
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-1100",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.91,
|
13 |
+
"learning_rate": 7.123150895957912e-06,
|
14 |
+
"loss": 2.1151,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.6326530612244898,
|
20 |
+
"eval_loss": 1.7264677286148071,
|
21 |
+
"eval_runtime": 1.125,
|
22 |
+
"eval_samples_per_second": 217.778,
|
23 |
+
"eval_steps_per_second": 14.222,
|
24 |
"step": 550
|
25 |
},
|
26 |
{
|
27 |
"epoch": 1.82,
|
28 |
+
"learning_rate": 5.540228474633931e-06,
|
29 |
+
"loss": 1.5823,
|
30 |
"step": 1000
|
31 |
},
|
32 |
{
|
33 |
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.7755102040816326,
|
35 |
+
"eval_loss": 1.2948896884918213,
|
36 |
+
"eval_runtime": 1.575,
|
37 |
+
"eval_samples_per_second": 155.555,
|
38 |
+
"eval_steps_per_second": 10.159,
|
39 |
"step": 1100
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 500,
|
43 |
+
"max_steps": 2750,
|
44 |
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 5,
|
46 |
"save_steps": 500,
|
47 |
+
"total_flos": 1945715472750.0,
|
48 |
"train_batch_size": 4,
|
49 |
"trial_name": null,
|
50 |
"trial_params": {
|
51 |
+
"learning_rate": 8.706073317281892e-06,
|
52 |
+
"num_train_epochs": 5,
|
53 |
"per_device_train_batch_size": 4,
|
54 |
+
"seed": 1
|
55 |
}
|
56 |
}
|
run-2/checkpoint-1100/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bf6249fcaffd3bf1a6e41efb7044edf4d8222cdd0729549fa8f87e1c5b20556
|
3 |
size 4728
|
run-2/checkpoint-1650/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-1650",
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
@@ -10,62 +10,62 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.91,
|
13 |
-
"learning_rate":
|
14 |
-
"loss":
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.0,
|
19 |
-
"eval_accuracy": 0.
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime": 1.
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 550
|
25 |
},
|
26 |
{
|
27 |
"epoch": 1.82,
|
28 |
-
"learning_rate":
|
29 |
-
"loss": 1.
|
30 |
"step": 1000
|
31 |
},
|
32 |
{
|
33 |
"epoch": 2.0,
|
34 |
-
"eval_accuracy": 0.
|
35 |
-
"eval_loss":
|
36 |
-
"eval_runtime": 1.
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 1100
|
40 |
},
|
41 |
{
|
42 |
"epoch": 2.73,
|
43 |
-
"learning_rate":
|
44 |
-
"loss":
|
45 |
"step": 1500
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.0,
|
49 |
-
"eval_accuracy": 0.
|
50 |
-
"eval_loss":
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second":
|
54 |
"step": 1650
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 500,
|
58 |
-
"max_steps":
|
59 |
"num_input_tokens_seen": 0,
|
60 |
-
"num_train_epochs":
|
61 |
"save_steps": 500,
|
62 |
-
"total_flos":
|
63 |
"train_batch_size": 4,
|
64 |
"trial_name": null,
|
65 |
"trial_params": {
|
66 |
-
"learning_rate":
|
67 |
-
"num_train_epochs":
|
68 |
"per_device_train_batch_size": 4,
|
69 |
-
"seed":
|
70 |
}
|
71 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8,
|
3 |
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-1650",
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.91,
|
13 |
+
"learning_rate": 7.123150895957912e-06,
|
14 |
+
"loss": 2.1151,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.6326530612244898,
|
20 |
+
"eval_loss": 1.7264677286148071,
|
21 |
+
"eval_runtime": 1.125,
|
22 |
+
"eval_samples_per_second": 217.778,
|
23 |
+
"eval_steps_per_second": 14.222,
|
24 |
"step": 550
|
25 |
},
|
26 |
{
|
27 |
"epoch": 1.82,
|
28 |
+
"learning_rate": 5.540228474633931e-06,
|
29 |
+
"loss": 1.5823,
|
30 |
"step": 1000
|
31 |
},
|
32 |
{
|
33 |
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.7755102040816326,
|
35 |
+
"eval_loss": 1.2948896884918213,
|
36 |
+
"eval_runtime": 1.575,
|
37 |
+
"eval_samples_per_second": 155.555,
|
38 |
+
"eval_steps_per_second": 10.159,
|
39 |
"step": 1100
|
40 |
},
|
41 |
{
|
42 |
"epoch": 2.73,
|
43 |
+
"learning_rate": 3.9573060533099506e-06,
|
44 |
+
"loss": 1.2756,
|
45 |
"step": 1500
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.0,
|
49 |
+
"eval_accuracy": 0.8,
|
50 |
+
"eval_loss": 1.0647388696670532,
|
51 |
+
"eval_runtime": 2.6287,
|
52 |
+
"eval_samples_per_second": 93.202,
|
53 |
+
"eval_steps_per_second": 6.087,
|
54 |
"step": 1650
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 500,
|
58 |
+
"max_steps": 2750,
|
59 |
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 5,
|
61 |
"save_steps": 500,
|
62 |
+
"total_flos": 2905718091150.0,
|
63 |
"train_batch_size": 4,
|
64 |
"trial_name": null,
|
65 |
"trial_params": {
|
66 |
+
"learning_rate": 8.706073317281892e-06,
|
67 |
+
"num_train_epochs": 5,
|
68 |
"per_device_train_batch_size": 4,
|
69 |
+
"seed": 1
|
70 |
}
|
71 |
}
|
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705269786.DESKTOP-RFEED41.20976.18
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 sha256:335d341f4f46113a5629ed21e06e5ea529e9c101dd7cacbc2d2cd91116247770
|
3 |
+
size 6390
|