Commit
•
8f75c56
1
Parent(s):
5770267
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-1/checkpoint-2138/model.safetensors +1 -1
- run-1/checkpoint-2138/optimizer.pt +1 -1
- run-1/checkpoint-2138/rng_state.pth +2 -2
- run-1/checkpoint-2138/scheduler.pt +1 -1
- run-1/checkpoint-2138/trainer_state.json +32 -41
- run-1/checkpoint-2138/training_args.bin +1 -1
- runs/Apr23_21-08-52_949a71f95aca/events.out.tfevents.1713915632.949a71f95aca.1272.3 +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 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff3df08caa0c5e98037019b5d56d98eaa6fe11a9bcdae02bfbde5be20fba20e5
|
3 |
size 267832560
|
run-1/checkpoint-2138/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:ff3df08caa0c5e98037019b5d56d98eaa6fe11a9bcdae02bfbde5be20fba20e5
|
3 |
size 267832560
|
run-1/checkpoint-2138/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535724410
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f5de18039268471c399f67329cc78a085cd09bdf8fec86f67845f9f58d830fc
|
3 |
size 535724410
|
run-1/checkpoint-2138/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:a19465d7b8e06894de84f452a1f87d9245fba61d92f8e977f1a67c420bf19cf1
|
3 |
+
size 13990
|
run-1/checkpoint-2138/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 sha256:852437654a4d4832fb56156864b4d8a03fff01279bd2bbb67d8c37e6da2245c0
|
3 |
size 1064
|
run-1/checkpoint-2138/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 2138,
|
7 |
"is_hyper_param_search": true,
|
@@ -9,64 +9,55 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate":
|
22 |
-
"loss": 0.
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
-
"epoch":
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"eval_samples_per_second": 36.794,
|
31 |
-
"eval_steps_per_second": 2.328,
|
32 |
-
"step": 1069
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 1.4031805425631432,
|
36 |
-
"grad_norm": 5.668572902679443,
|
37 |
-
"learning_rate": 2.014111102736307e-05,
|
38 |
-
"loss": 0.3878,
|
39 |
"step": 1500
|
40 |
},
|
41 |
{
|
42 |
-
"epoch":
|
43 |
-
"grad_norm":
|
44 |
-
"learning_rate":
|
45 |
-
"loss": 0.
|
46 |
"step": 2000
|
47 |
},
|
48 |
{
|
49 |
-
"epoch":
|
50 |
-
"eval_loss": 0.
|
51 |
-
"eval_matthews_correlation": 0.
|
52 |
-
"eval_runtime":
|
53 |
-
"eval_samples_per_second":
|
54 |
-
"eval_steps_per_second": 2.
|
55 |
"step": 2138
|
56 |
}
|
57 |
],
|
58 |
"logging_steps": 500,
|
59 |
-
"max_steps":
|
60 |
"num_input_tokens_seen": 0,
|
61 |
-
"num_train_epochs":
|
62 |
"save_steps": 500,
|
63 |
-
"total_flos":
|
64 |
-
"train_batch_size":
|
65 |
"trial_name": null,
|
66 |
"trial_params": {
|
67 |
-
"learning_rate":
|
68 |
-
"num_train_epochs":
|
69 |
-
"per_device_train_batch_size":
|
70 |
-
"seed":
|
71 |
}
|
72 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3084289905217366,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 2138,
|
7 |
"is_hyper_param_search": true,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.23386342376052385,
|
13 |
+
"grad_norm": 3.146369218826294,
|
14 |
+
"learning_rate": 1.653715321124928e-06,
|
15 |
+
"loss": 0.6079,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.4677268475210477,
|
20 |
+
"grad_norm": 5.078900337219238,
|
21 |
+
"learning_rate": 1.5725712916291023e-06,
|
22 |
+
"loss": 0.6126,
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.7015902712815716,
|
27 |
+
"grad_norm": 7.2771897315979,
|
28 |
+
"learning_rate": 1.4914272621332766e-06,
|
29 |
+
"loss": 0.5551,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.9354536950420954,
|
34 |
+
"grad_norm": 22.494115829467773,
|
35 |
+
"learning_rate": 1.4102832326374508e-06,
|
36 |
+
"loss": 0.523,
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_loss": 0.5956234335899353,
|
42 |
+
"eval_matthews_correlation": 0.3084289905217366,
|
43 |
+
"eval_runtime": 31.6888,
|
44 |
+
"eval_samples_per_second": 32.914,
|
45 |
+
"eval_steps_per_second": 2.083,
|
46 |
"step": 2138
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 500,
|
50 |
+
"max_steps": 10690,
|
51 |
"num_input_tokens_seen": 0,
|
52 |
+
"num_train_epochs": 5,
|
53 |
"save_steps": 500,
|
54 |
+
"total_flos": 32670807095088.0,
|
55 |
+
"train_batch_size": 4,
|
56 |
"trial_name": null,
|
57 |
"trial_params": {
|
58 |
+
"learning_rate": 1.7348593506207536e-06,
|
59 |
+
"num_train_epochs": 5,
|
60 |
+
"per_device_train_batch_size": 4,
|
61 |
+
"seed": 22
|
62 |
}
|
63 |
}
|
run-1/checkpoint-2138/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b505570bfabe2b3954b5c415db50fe70c16c7616859b303999126f730738b08
|
3 |
size 5048
|
runs/Apr23_21-08-52_949a71f95aca/events.out.tfevents.1713915632.949a71f95aca.1272.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cd1541b8f500be6968b250517007aad975c46818332b10b5fac09afa0274ac6
|
3 |
+
size 5829
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b505570bfabe2b3954b5c415db50fe70c16c7616859b303999126f730738b08
|
3 |
size 5048
|