Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-1/checkpoint-14/model.safetensors +1 -1
- run-1/checkpoint-14/optimizer.pt +2 -2
- run-1/checkpoint-14/rng_state.pth +2 -2
- run-1/checkpoint-14/scheduler.pt +1 -1
- run-1/checkpoint-14/trainer_state.json +8 -8
- run-1/checkpoint-14/training_args.bin +2 -2
- run-2/checkpoint-214/model.safetensors +1 -1
- run-2/checkpoint-214/optimizer.pt +2 -2
- run-2/checkpoint-214/rng_state.pth +2 -2
- run-2/checkpoint-214/scheduler.pt +1 -1
- run-2/checkpoint-214/trainer_state.json +9 -9
- run-2/checkpoint-214/training_args.bin +2 -2
- runs/Mar08_16-02-10_50bca828e3b2/events.out.tfevents.1709913804.50bca828e3b2.2324.4 +3 -0
- runs/Mar08_16-02-10_50bca828e3b2/events.out.tfevents.1709913834.50bca828e3b2.2324.5 +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 sha256:0b33bebca3c31b2a59033909ad09f352f795168df035fa5e21068f27d4fb1f40
|
3 |
size 267832560
|
run-1/checkpoint-14/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:aeedc397da2e50e1a369df839169ff3baed592b5728d9aafb1c487511f42da10
|
3 |
size 267832560
|
run-1/checkpoint-14/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 sha256:3a545043af087d88cb61946690dce0d4316653a781ff446f6dded8115db1ce97
|
3 |
+
size 535727290
|
run-1/checkpoint-14/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 sha256:67b9d795f1087cbe638ed3fc6f2a698bfc22c35fc0179fd12b285b35f69e1a1c
|
3 |
+
size 14308
|
run-1/checkpoint-14/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:ca1c6676752252a8249a2db6e352a680a5d9428014a5b912dfae3a454c2ec41b
|
3 |
size 1064
|
run-1/checkpoint-14/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-14",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,11 +10,11 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.
|
14 |
-
"eval_matthews_correlation": 0.
|
15 |
-
"eval_runtime":
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second":
|
18 |
"step": 14
|
19 |
}
|
20 |
],
|
@@ -27,9 +27,9 @@
|
|
27 |
"train_batch_size": 64,
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
-
"learning_rate":
|
31 |
"num_train_epochs": 1,
|
32 |
"per_device_train_batch_size": 64,
|
33 |
-
"seed":
|
34 |
}
|
35 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.010498792427994534,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-14",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6844037771224976,
|
14 |
+
"eval_matthews_correlation": 0.010498792427994534,
|
15 |
+
"eval_runtime": 2.387,
|
16 |
+
"eval_samples_per_second": 436.947,
|
17 |
+
"eval_steps_per_second": 27.65,
|
18 |
"step": 14
|
19 |
}
|
20 |
],
|
|
|
27 |
"train_batch_size": 64,
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
+
"learning_rate": 1.4416085092769088e-06,
|
31 |
"num_train_epochs": 1,
|
32 |
"per_device_train_batch_size": 64,
|
33 |
+
"seed": 32
|
34 |
}
|
35 |
}
|
run-1/checkpoint-14/training_args.bin
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:f9f8e48ec1e03a914d1ec7892684e65a5bc3727dd12f0f3c52c01699c33d2156
|
3 |
+
size 4984
|
run-2/checkpoint-214/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 sha256:0b33bebca3c31b2a59033909ad09f352f795168df035fa5e21068f27d4fb1f40
|
3 |
size 267832560
|
run-2/checkpoint-214/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:d3c50fc3ffbe867daf58825f8193d0cfba84cc14252afd8a598cd321986402aa
|
3 |
+
size 535727290
|
run-2/checkpoint-214/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 sha256:6642b66e64e0b7ca68e0c6a1ce3642e5ff680df66b6e523921454a079ed214ed
|
3 |
+
size 14244
|
run-2/checkpoint-214/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 sha256:353a0f8e9cdb591b044d3c5506a10aa1733632724e4365b86c27c74a86c0ae67
|
3 |
size 1064
|
run-2/checkpoint-214/trainer_state.json
CHANGED
@@ -10,26 +10,26 @@
|
|
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": 214
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
-
"max_steps":
|
23 |
"num_input_tokens_seen": 0,
|
24 |
-
"num_train_epochs":
|
25 |
"save_steps": 500,
|
26 |
"total_flos": 0,
|
27 |
"train_batch_size": 4,
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
-
"learning_rate":
|
31 |
-
"num_train_epochs":
|
32 |
"per_device_train_batch_size": 4,
|
33 |
-
"seed":
|
34 |
}
|
35 |
}
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.622901976108551,
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.6976,
|
16 |
+
"eval_samples_per_second": 1495.146,
|
17 |
+
"eval_steps_per_second": 94.611,
|
18 |
"step": 214
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
+
"max_steps": 1070,
|
23 |
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 5,
|
25 |
"save_steps": 500,
|
26 |
"total_flos": 0,
|
27 |
"train_batch_size": 4,
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
+
"learning_rate": 7.121152845919556e-05,
|
31 |
+
"num_train_epochs": 5,
|
32 |
"per_device_train_batch_size": 4,
|
33 |
+
"seed": 12
|
34 |
}
|
35 |
}
|
run-2/checkpoint-214/training_args.bin
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 sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
|
3 |
+
size 4984
|
runs/Mar08_16-02-10_50bca828e3b2/events.out.tfevents.1709913804.50bca828e3b2.2324.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cf9fd11392cdb0ff1f2f049a7ca682d6cba1e0b99d53a71c15997327f345906
|
3 |
+
size 5219
|
runs/Mar08_16-02-10_50bca828e3b2/events.out.tfevents.1709913834.50bca828e3b2.2324.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:435cd4f9ebbd7f6b8485cd1f7bb28face7d44957f87413ffca74d74c5e02d93c
|
3 |
+
size 5210
|
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 sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
|
3 |
size 4984
|