SjardiWillems
commited on
Commit
•
1b34238
1
Parent(s):
08445ef
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-0/checkpoint-54/model.safetensors +1 -1
- run-0/checkpoint-54/optimizer.pt +2 -2
- run-0/checkpoint-54/rng_state.pth +2 -2
- run-0/checkpoint-54/scheduler.pt +1 -1
- run-0/checkpoint-54/trainer_state.json +13 -22
- run-0/checkpoint-54/training_args.bin +1 -1
- runs/Mar06_18-56-30_6942db43b48a/events.out.tfevents.1709753297.6942db43b48a.1479.2 +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 sha256:855c6f746caab4870f70894f4c492d3f4be82dee793721a0dabf917b4ca472a0
|
3 |
size 267832560
|
run-0/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 sha256:855c6f746caab4870f70894f4c492d3f4be82dee793721a0dabf917b4ca472a0
|
3 |
size 267832560
|
run-0/checkpoint-54/optimizer.pt
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 sha256:59db34a7e97bd5aaa813075140c09b650a9a68c1ecaac8cf7de9f990241db0c2
|
3 |
+
size 535724410
|
run-0/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 sha256:150a9a1ace6da36d1f132463a7af23f51f83ae315239086ea0a746b6ed19f745
|
3 |
+
size 13990
|
run-0/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 sha256:4238c186fbd03f655e57f6a24b4ce04d63ce21a6c674df6e26ed1cfa28eac67d
|
3 |
size 1064
|
run-0/checkpoint-54/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-54",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 54,
|
7 |
"is_hyper_param_search": true,
|
@@ -10,35 +10,26 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
-
"eval_runtime":
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second":
|
18 |
-
"step": 27
|
19 |
-
},
|
20 |
-
{
|
21 |
-
"epoch": 2.0,
|
22 |
-
"eval_loss": 0.5681455731391907,
|
23 |
-
"eval_matthews_correlation": 0.2145337380780115,
|
24 |
-
"eval_runtime": 0.5534,
|
25 |
-
"eval_samples_per_second": 1884.845,
|
26 |
-
"eval_steps_per_second": 119.271,
|
27 |
"step": 54
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 500,
|
31 |
-
"max_steps":
|
32 |
"num_input_tokens_seen": 0,
|
33 |
-
"num_train_epochs":
|
34 |
"save_steps": 500,
|
35 |
"total_flos": 0,
|
36 |
-
"train_batch_size":
|
37 |
"trial_name": null,
|
38 |
"trial_params": {
|
39 |
-
"learning_rate":
|
40 |
-
"num_train_epochs":
|
41 |
-
"per_device_train_batch_size":
|
42 |
-
"seed":
|
43 |
}
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.0,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-54",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 54,
|
7 |
"is_hyper_param_search": true,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6089463829994202,
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 9.3765,
|
16 |
+
"eval_samples_per_second": 111.236,
|
17 |
+
"eval_steps_per_second": 7.039,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
"step": 54
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
+
"max_steps": 54,
|
23 |
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 1,
|
25 |
"save_steps": 500,
|
26 |
"total_flos": 0,
|
27 |
+
"train_batch_size": 16,
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
+
"learning_rate": 1.4310819337259506e-05,
|
31 |
+
"num_train_epochs": 1,
|
32 |
+
"per_device_train_batch_size": 16,
|
33 |
+
"seed": 4
|
34 |
}
|
35 |
}
|
run-0/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:cc4c2e0d09cfb872abf4d091e83249b3c92ab1d6b001b123a3b72db96c0a65c3
|
3 |
size 4984
|
runs/Mar06_18-56-30_6942db43b48a/events.out.tfevents.1709753297.6942db43b48a.1479.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a9df7b2e01ec300c3fddd43ae833189b079679aa1234023b6dc73aacc0fbce
|
3 |
+
size 5219
|
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:cc4c2e0d09cfb872abf4d091e83249b3c92ab1d6b001b123a3b72db96c0a65c3
|
3 |
size 4984
|