Upload folder using huggingface_hub
Browse files- checkpoint-6250/config.json +36 -0
- checkpoint-6250/optimizer.pt +3 -0
- checkpoint-6250/pytorch_model.bin +3 -0
- checkpoint-6250/rng_state_0.pth +3 -0
- checkpoint-6250/rng_state_1.pth +3 -0
- checkpoint-6250/scheduler.pt +3 -0
- checkpoint-6250/trainer_state.json +28 -0
- checkpoint-6250/training_args.bin +3 -0
- runs/Aug11_10-32-12_beast/events.out.tfevents.1691742733.beast.1746407.0 +3 -0
- runs/Aug11_10-33-06_beast/events.out.tfevents.1691742786.beast.1746608.0 +3 -0
- runs/Aug11_10-36-47_beast/events.out.tfevents.1691743009.beast.1747152.0 +3 -0
- runs/Aug11_11-15-04_beast/events.out.tfevents.1691745305.beast.1751000.0 +3 -0
- runs/Aug11_11-42-17_beast/events.out.tfevents.1691746939.beast.1753947.0 +3 -0
- runs/Aug11_11-46-02_beast/events.out.tfevents.1691747163.beast.1754528.0 +3 -0
- runs/Aug11_11-46-34_beast/events.out.tfevents.1691747195.beast.1754668.0 +3 -0
- runs/Aug11_11-49-18_beast/events.out.tfevents.1691747358.beast.1755130.0 +3 -0
- training_params.json +28 -0
checkpoint-6250/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": 0,
|
15 |
+
"1": 1
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.32.0.dev0",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
checkpoint-6250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b726b129906e676640d8d8614c29933a90ee7fe22789808ac077549f62c0ac0
|
3 |
+
size 876037893
|
checkpoint-6250/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e491dcffd3d1214a6c270ffd8950169b9640b856d1566260e5fd2a613d069563
|
3 |
+
size 438003505
|
checkpoint-6250/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a74e2e1039010520a9b510eb59727d93d6c28e95e38a4ffcff55f1d825b33151
|
3 |
+
size 15607
|
checkpoint-6250/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eff1dffd64c4b113a3acd330feeb84479c0e2df37083d511ca7051480e11364
|
3 |
+
size 15607
|
checkpoint-6250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de9e16e74183614907a764f3391f23e9f3b5e11312845236bfc01de8f2ccebe9
|
3 |
+
size 627
|
checkpoint-6250/trainer_state.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 6250,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.4,
|
12 |
+
"learning_rate": 2.0032e-05,
|
13 |
+
"loss": 0.545,
|
14 |
+
"step": 2500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.8,
|
18 |
+
"learning_rate": 6.698666666666667e-06,
|
19 |
+
"loss": 0.4721,
|
20 |
+
"step": 5000
|
21 |
+
}
|
22 |
+
],
|
23 |
+
"max_steps": 6250,
|
24 |
+
"num_train_epochs": 1,
|
25 |
+
"total_flos": 1644444159836160.0,
|
26 |
+
"trial_name": null,
|
27 |
+
"trial_params": null
|
28 |
+
}
|
checkpoint-6250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c996273dea58053aa3566c47a5f8b88444799f22a7ad2891a57f49797f898864
|
3 |
+
size 3963
|
runs/Aug11_10-32-12_beast/events.out.tfevents.1691742733.beast.1746407.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e0a81090d6a6ac29ba2edc627805d85fced658bbf1b93d97d36d787dc3d3bff
|
3 |
+
size 4135
|
runs/Aug11_10-33-06_beast/events.out.tfevents.1691742786.beast.1746608.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c623ecfb5684fc3378fd28df840135181b4331a7a91bdf6199f9f83625b3b06
|
3 |
+
size 4135
|
runs/Aug11_10-36-47_beast/events.out.tfevents.1691743009.beast.1747152.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09ff46130d623e1862bafbd62b684de3a968c2c7b03bf620f3ae929c8ea0ea76
|
3 |
+
size 4804
|
runs/Aug11_11-15-04_beast/events.out.tfevents.1691745305.beast.1751000.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d451ccb2a6ba36ef985be8c1d409390fc9576d82abc9847a2d3b9750c802ce8
|
3 |
+
size 4804
|
runs/Aug11_11-42-17_beast/events.out.tfevents.1691746939.beast.1753947.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d68f9b3ab08dee2b8d9a4dd4dca4d3d8b3d5a07e49566e8069f18be3d356abd
|
3 |
+
size 4136
|
runs/Aug11_11-46-02_beast/events.out.tfevents.1691747163.beast.1754528.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df4fd997666c1b14d2e2b467ae0a6bdeb7f1bda3acfb6e225c56039859de2209
|
3 |
+
size 88
|
runs/Aug11_11-46-34_beast/events.out.tfevents.1691747195.beast.1754668.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97833253f5fe42e6637e00cf0243d1c287aaf95787e644f8216bfe215ad836a3
|
3 |
+
size 88
|
runs/Aug11_11-49-18_beast/events.out.tfevents.1691747358.beast.1755130.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c379970ef4f7b8ecafe51f8836215c405c88f36224c01bab68f40a4aefc97472
|
3 |
+
size 4804
|
training_params.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "imdb",
|
3 |
+
"model_name": "bert-base-uncased",
|
4 |
+
"lr": 3e-05,
|
5 |
+
"epochs": 1,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 2,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": null,
|
17 |
+
"text_column": "text",
|
18 |
+
"target_column": "label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "output",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"fp16": true,
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"save_strategy": "epoch",
|
25 |
+
"token": null,
|
26 |
+
"push_to_hub": true,
|
27 |
+
"repo_id": "abhishek/txtclfimdb2"
|
28 |
+
}
|