kbberendsen
commited on
Commit
•
dcb78fe
1
Parent(s):
821263a
Training in progress, epoch 1
Browse files- config.json +6 -6
- model.safetensors +2 -2
- run-0/checkpoint-27/config.json +6 -6
- run-0/checkpoint-27/model.safetensors +2 -2
- run-0/checkpoint-27/optimizer.pt +2 -2
- run-0/checkpoint-27/rng_state.pth +2 -2
- run-0/checkpoint-27/scheduler.pt +1 -1
- run-0/checkpoint-27/trainer_state.json +10 -10
- run-0/checkpoint-27/training_args.bin +1 -1
- runs/Feb29_12-55-06_e1aa4b7a2e4c/events.out.tfevents.1709211387.e1aa4b7a2e4c.252.0 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,25 +1,25 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "microsoft/deberta-v3-
|
3 |
"architectures": [
|
4 |
"DebertaV2ForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"hidden_act": "gelu",
|
8 |
"hidden_dropout_prob": 0.1,
|
9 |
-
"hidden_size":
|
10 |
"initializer_range": 0.02,
|
11 |
-
"intermediate_size":
|
12 |
"layer_norm_eps": 1e-07,
|
13 |
"max_position_embeddings": 512,
|
14 |
"max_relative_positions": -1,
|
15 |
"model_type": "deberta-v2",
|
16 |
"norm_rel_ebd": "layer_norm",
|
17 |
-
"num_attention_heads":
|
18 |
-
"num_hidden_layers":
|
19 |
"pad_token_id": 0,
|
20 |
"pooler_dropout": 0,
|
21 |
"pooler_hidden_act": "gelu",
|
22 |
-
"pooler_hidden_size":
|
23 |
"pos_att_type": [
|
24 |
"p2c",
|
25 |
"c2p"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
"architectures": [
|
4 |
"DebertaV2ForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"hidden_act": "gelu",
|
8 |
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
"layer_norm_eps": 1e-07,
|
13 |
"max_position_embeddings": 512,
|
14 |
"max_relative_positions": -1,
|
15 |
"model_type": "deberta-v2",
|
16 |
"norm_rel_ebd": "layer_norm",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 0,
|
20 |
"pooler_dropout": 0,
|
21 |
"pooler_hidden_act": "gelu",
|
22 |
+
"pooler_hidden_size": 768,
|
23 |
"pos_att_type": [
|
24 |
"p2c",
|
25 |
"c2p"
|
model.safetensors
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:ed1ca670602465a09e34815d2a91e895491af587d899f2f9221d046f8418e488
|
3 |
+
size 737719272
|
run-0/checkpoint-27/config.json
CHANGED
@@ -1,25 +1,25 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "microsoft/deberta-v3-
|
3 |
"architectures": [
|
4 |
"DebertaV2ForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"hidden_act": "gelu",
|
8 |
"hidden_dropout_prob": 0.1,
|
9 |
-
"hidden_size":
|
10 |
"initializer_range": 0.02,
|
11 |
-
"intermediate_size":
|
12 |
"layer_norm_eps": 1e-07,
|
13 |
"max_position_embeddings": 512,
|
14 |
"max_relative_positions": -1,
|
15 |
"model_type": "deberta-v2",
|
16 |
"norm_rel_ebd": "layer_norm",
|
17 |
-
"num_attention_heads":
|
18 |
-
"num_hidden_layers":
|
19 |
"pad_token_id": 0,
|
20 |
"pooler_dropout": 0,
|
21 |
"pooler_hidden_act": "gelu",
|
22 |
-
"pooler_hidden_size":
|
23 |
"pos_att_type": [
|
24 |
"p2c",
|
25 |
"c2p"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
"architectures": [
|
4 |
"DebertaV2ForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"hidden_act": "gelu",
|
8 |
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
"layer_norm_eps": 1e-07,
|
13 |
"max_position_embeddings": 512,
|
14 |
"max_relative_positions": -1,
|
15 |
"model_type": "deberta-v2",
|
16 |
"norm_rel_ebd": "layer_norm",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 0,
|
20 |
"pooler_dropout": 0,
|
21 |
"pooler_hidden_act": "gelu",
|
22 |
+
"pooler_hidden_size": 768,
|
23 |
"pos_att_type": [
|
24 |
"p2c",
|
25 |
"c2p"
|
run-0/checkpoint-27/model.safetensors
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:ed1ca670602465a09e34815d2a91e895491af587d899f2f9221d046f8418e488
|
3 |
+
size 737719272
|
run-0/checkpoint-27/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:e9f7fa6b21ebbdc8b9fc9c6bc85aee0d8e8ae05efc4a1b8c3c87b707a3ed0907
|
3 |
+
size 1475558394
|
run-0/checkpoint-27/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:f0fce9eb55c0fdd6af139024ee02e7031cd5bd6b03707d2bb5484decd5f5b448
|
3 |
+
size 14308
|
run-0/checkpoint-27/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 sha256:029be0abaf4172d8d79d3fe3569afed060aca3e4a5ee2358fb92bfcebf064181
|
3 |
size 1064
|
run-0/checkpoint-27/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-0/checkpoint-27",
|
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": 27
|
19 |
}
|
20 |
],
|
@@ -24,12 +24,12 @@
|
|
24 |
"num_train_epochs": 2,
|
25 |
"save_steps": 500,
|
26 |
"total_flos": 0,
|
27 |
-
"train_batch_size":
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
-
"learning_rate":
|
31 |
"num_train_epochs": 2,
|
32 |
-
"per_device_train_batch_size":
|
33 |
-
"seed":
|
34 |
}
|
35 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.048639888821286496,
|
3 |
"best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-0/checkpoint-27",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.691221296787262,
|
14 |
+
"eval_matthews_correlation": 0.048639888821286496,
|
15 |
+
"eval_runtime": 2.4651,
|
16 |
+
"eval_samples_per_second": 423.102,
|
17 |
+
"eval_steps_per_second": 26.773,
|
18 |
"step": 27
|
19 |
}
|
20 |
],
|
|
|
24 |
"num_train_epochs": 2,
|
25 |
"save_steps": 500,
|
26 |
"total_flos": 0,
|
27 |
+
"train_batch_size": 16,
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
+
"learning_rate": 1.295113530605781e-06,
|
31 |
"num_train_epochs": 2,
|
32 |
+
"per_device_train_batch_size": 16,
|
33 |
+
"seed": 29
|
34 |
}
|
35 |
}
|
run-0/checkpoint-27/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 sha256:1ca2192d898bc34b22b60030a4c304d30c36cac0af471e752e5be729bc08981c
|
3 |
size 4984
|
runs/Feb29_12-55-06_e1aa4b7a2e4c/events.out.tfevents.1709211387.e1aa4b7a2e4c.252.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bafa5acd0f7ee6a2073f29d9b20884b1390f9674e2c8893f5a872a7bd8342ac
|
3 |
+
size 5812
|
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 sha256:1ca2192d898bc34b22b60030a4c304d30c36cac0af471e752e5be729bc08981c
|
3 |
size 4984
|