Upload ./ with huggingface_hub
Browse files- checkpoint-500/config.json +53 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +38 -0
- checkpoint-500/training_args.bin +3 -0
- runs/Feb10_01-22-58_58d2569e5fea/1675992183.6354697/events.out.tfevents.1675992183.58d2569e5fea.163.1 +3 -0
- runs/Feb10_01-22-58_58d2569e5fea/events.out.tfevents.1675992183.58d2569e5fea.163.0 +3 -0
checkpoint-500/config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "burakaytan/roberta-base-turkish-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "LABEL_0",
|
16 |
+
"1": "LABEL_1",
|
17 |
+
"2": "LABEL_2",
|
18 |
+
"3": "LABEL_3",
|
19 |
+
"4": "LABEL_4",
|
20 |
+
"5": "LABEL_5",
|
21 |
+
"6": "LABEL_6",
|
22 |
+
"7": "LABEL_7",
|
23 |
+
"8": "LABEL_8",
|
24 |
+
"9": "LABEL_9"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"LABEL_0": 0,
|
30 |
+
"LABEL_1": 1,
|
31 |
+
"LABEL_2": 2,
|
32 |
+
"LABEL_3": 3,
|
33 |
+
"LABEL_4": 4,
|
34 |
+
"LABEL_5": 5,
|
35 |
+
"LABEL_6": 6,
|
36 |
+
"LABEL_7": 7,
|
37 |
+
"LABEL_8": 8,
|
38 |
+
"LABEL_9": 9
|
39 |
+
},
|
40 |
+
"layer_norm_eps": 1e-05,
|
41 |
+
"max_position_embeddings": 514,
|
42 |
+
"model_type": "roberta",
|
43 |
+
"num_attention_heads": 12,
|
44 |
+
"num_hidden_layers": 12,
|
45 |
+
"pad_token_id": 1,
|
46 |
+
"position_embedding_type": "absolute",
|
47 |
+
"problem_type": "multi_label_classification",
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.26.1",
|
50 |
+
"type_vocab_size": 1,
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 50265
|
53 |
+
}
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b07f7cd3191a3cd37c9a73a2ff9b8f9b087e9e97c7d0dd5dacacc2d90912c4ae
|
3 |
+
size 997344389
|
checkpoint-500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9821a6fcf7e02b118b18945dd27d0218f65723f9e4406b5a733183bec437085
|
3 |
+
size 498686645
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f62defffab696e05555871caf3704d29b553f948aa0206bebb6149f66bb37530
|
3 |
+
size 14575
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db0e39a44acab9e018c22b17648402b3a366f4fa1554d51de408a4da2a2c114
|
3 |
+
size 627
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.5125628140703515,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_loss": 0.2354260766343148,
|
13 |
+
"eval_runtime": 2.5395,
|
14 |
+
"eval_samples_per_second": 278.011,
|
15 |
+
"eval_steps_per_second": 9.057,
|
16 |
+
"step": 199
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.0,
|
20 |
+
"eval_loss": 0.19823549999644394,
|
21 |
+
"eval_runtime": 2.5363,
|
22 |
+
"eval_samples_per_second": 278.357,
|
23 |
+
"eval_steps_per_second": 9.068,
|
24 |
+
"step": 398
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.51,
|
28 |
+
"learning_rate": 8.123953098827471e-06,
|
29 |
+
"loss": 0.2647,
|
30 |
+
"step": 500
|
31 |
+
}
|
32 |
+
],
|
33 |
+
"max_steps": 597,
|
34 |
+
"num_train_epochs": 3,
|
35 |
+
"total_flos": 524812693859328.0,
|
36 |
+
"trial_name": null,
|
37 |
+
"trial_params": null
|
38 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57372fdcbc0c4ea99d59a7ef362764a17b61a6b307b244e0e4859b04880fdc83
|
3 |
+
size 3451
|
runs/Feb10_01-22-58_58d2569e5fea/1675992183.6354697/events.out.tfevents.1675992183.58d2569e5fea.163.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b126a7e30f1ca37a2980e48150983a453543c69ae06ba540d51788e448010a54
|
3 |
+
size 5637
|
runs/Feb10_01-22-58_58d2569e5fea/events.out.tfevents.1675992183.58d2569e5fea.163.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7781b51673aa4ff097af2a2f4238bfba7efa421d6c273980948b44394ae653b5
|
3 |
+
size 5643
|