Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-0/checkpoint-144/model.safetensors +1 -1
- run-0/checkpoint-144/optimizer.pt +1 -1
- run-0/checkpoint-144/rng_state.pth +1 -1
- run-0/checkpoint-144/scheduler.pt +1 -1
- run-0/checkpoint-144/trainer_state.json +15 -25
- run-0/checkpoint-144/training_args.bin +1 -1
- runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709751864.8a0d46b883ab.2624.2 +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 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4ebbc80bdea594e9c45d0bd1ee785cd4c4ab9a369a7e11a11992bda11abc75a
|
3 |
size 267829484
|
run-0/checkpoint-144/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4ebbc80bdea594e9c45d0bd1ee785cd4c4ab9a369a7e11a11992bda11abc75a
|
3 |
size 267829484
|
run-0/checkpoint-144/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535721146
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6026f14ddf7e680eff17afcb685b793d514094ea5fb7ce8906f8bf669b00658b
|
3 |
size 535721146
|
run-0/checkpoint-144/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe3f45e7bb011fde7b10a81464c1dd03589c1e07ef2a99a155cfb9643dcdd4a2
|
3 |
size 14244
|
run-0/checkpoint-144/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 sha256:8ab6969c1d44574bdac80efcf373e8f30eba03534ab366addb8f4801a983bbe7
|
3 |
size 1064
|
run-0/checkpoint-144/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-144",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 144,
|
7 |
"is_hyper_param_search": true,
|
@@ -10,37 +10,27 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
-
"step": 72
|
20 |
-
},
|
21 |
-
{
|
22 |
-
"epoch": 2.0,
|
23 |
-
"eval_loss": 0.8653174042701721,
|
24 |
-
"eval_pearson": 0.8253446259273143,
|
25 |
-
"eval_runtime": 1.0205,
|
26 |
-
"eval_samples_per_second": 1469.804,
|
27 |
-
"eval_spearmanr": 0.8213518482816455,
|
28 |
-
"eval_steps_per_second": 92.108,
|
29 |
"step": 144
|
30 |
}
|
31 |
],
|
32 |
"logging_steps": 500,
|
33 |
-
"max_steps":
|
34 |
"num_input_tokens_seen": 0,
|
35 |
-
"num_train_epochs":
|
36 |
"save_steps": 500,
|
37 |
"total_flos": 0,
|
38 |
-
"train_batch_size":
|
39 |
"trial_name": null,
|
40 |
"trial_params": {
|
41 |
-
"learning_rate":
|
42 |
-
"num_train_epochs":
|
43 |
-
"per_device_train_batch_size":
|
44 |
-
"seed":
|
45 |
}
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7966375426002391,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-144",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 144,
|
7 |
"is_hyper_param_search": true,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.9918314814567566,
|
14 |
+
"eval_pearson": 0.7966375426002391,
|
15 |
+
"eval_runtime": 0.8021,
|
16 |
+
"eval_samples_per_second": 1870.124,
|
17 |
+
"eval_spearmanr": 0.7909051383387676,
|
18 |
+
"eval_steps_per_second": 117.194,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"step": 144
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
+
"max_steps": 720,
|
24 |
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 5,
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
+
"train_batch_size": 4,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
+
"learning_rate": 4.325876846375602e-05,
|
32 |
+
"num_train_epochs": 5,
|
33 |
+
"per_device_train_batch_size": 4,
|
34 |
+
"seed": 34
|
35 |
}
|
36 |
}
|
run-0/checkpoint-144/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a012d40728dc244700f11825615a9f3164fccd8635d4eae2a798016634c8eb7
|
3 |
size 4920
|
runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709751864.8a0d46b883ab.2624.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffdece789a2bfea47d24fd7a01dc8878e313a09cd31191537cdc07e5228dd3f3
|
3 |
+
size 4981
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a012d40728dc244700f11825615a9f3164fccd8635d4eae2a798016634c8eb7
|
3 |
size 4920
|