poltextlab
commited on
Commit
•
86b2ff8
1
Parent(s):
4ceb29e
Upload with huggingface_hub
Browse files- checkpoint-2853/config.json +47 -0
- checkpoint-2853/optimizer.pt +3 -0
- checkpoint-2853/pytorch_model.bin +3 -0
- checkpoint-2853/rng_state.pth +3 -0
- checkpoint-2853/scheduler.pt +3 -0
- checkpoint-2853/trainer_state.json +61 -0
- checkpoint-2853/training_args.bin +3 -0
- config.json +47 -0
- logs/1678138399.8571055/events.out.tfevents.1678138399.238d2c00108b.502.1 +3 -0
- logs/events.out.tfevents.1678138399.238d2c00108b.502.0 +3 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
checkpoint-2853/config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SZTAKI-HLT/hubert-base-cc",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"LABEL_0": 0,
|
26 |
+
"LABEL_1": 1,
|
27 |
+
"LABEL_2": 2,
|
28 |
+
"LABEL_3": 3,
|
29 |
+
"LABEL_4": 4,
|
30 |
+
"LABEL_5": 5,
|
31 |
+
"LABEL_6": 6,
|
32 |
+
"LABEL_7": 7
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-12,
|
35 |
+
"max_position_embeddings": 512,
|
36 |
+
"model_type": "bert",
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"position_embedding_type": "absolute",
|
41 |
+
"problem_type": "multi_label_classification",
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.26.1",
|
44 |
+
"type_vocab_size": 2,
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 32001
|
47 |
+
}
|
checkpoint-2853/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:611132e7224d27010e40b9c7debc75cd01f785789c444296cc52102983d6354d
|
3 |
+
size 885111941
|
checkpoint-2853/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75ef525e912e48cd2814561a5affe3d00b62fbae02afbb15b9e850029778efc4
|
3 |
+
size 442569845
|
checkpoint-2853/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb87df3c2fdcadc2be33d99d5d864ef388706a4ca43f30eb777e78c4000c23b3
|
3 |
+
size 14575
|
checkpoint-2853/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae3a07eebc0e5c2787befc61c7588c9749a42bfe4cb2260485bb2d9167f2c014
|
3 |
+
size 627
|
checkpoint-2853/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.14511410892009735,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Models/hunEmPoli8/checkpoint-2853",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 2853,
|
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 |
+
"learning_rate": 4.5e-06,
|
13 |
+
"loss": 0.2167,
|
14 |
+
"step": 951
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.758421052631579,
|
19 |
+
"eval_loss": 0.1673167496919632,
|
20 |
+
"eval_runtime": 60.5676,
|
21 |
+
"eval_samples_per_second": 31.37,
|
22 |
+
"eval_steps_per_second": 1.965,
|
23 |
+
"step": 951
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 4.000000000000001e-06,
|
28 |
+
"loss": 0.1473,
|
29 |
+
"step": 1902
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.7642105263157895,
|
34 |
+
"eval_loss": 0.15218877792358398,
|
35 |
+
"eval_runtime": 60.2847,
|
36 |
+
"eval_samples_per_second": 31.517,
|
37 |
+
"eval_steps_per_second": 1.974,
|
38 |
+
"step": 1902
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 3.5e-06,
|
43 |
+
"loss": 0.1178,
|
44 |
+
"step": 2853
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.7742105263157895,
|
49 |
+
"eval_loss": 0.14511410892009735,
|
50 |
+
"eval_runtime": 60.3352,
|
51 |
+
"eval_samples_per_second": 31.491,
|
52 |
+
"eval_steps_per_second": 1.972,
|
53 |
+
"step": 2853
|
54 |
+
}
|
55 |
+
],
|
56 |
+
"max_steps": 9510,
|
57 |
+
"num_train_epochs": 10,
|
58 |
+
"total_flos": 1.1999299843989504e+16,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
checkpoint-2853/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03a85ad5c7eb2d5aaef92a13cfc21e840f264ed0dbc7426af7aa0a2a74997f0d
|
3 |
+
size 3515
|
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SZTAKI-HLT/hubert-base-cc",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"LABEL_0": 0,
|
26 |
+
"LABEL_1": 1,
|
27 |
+
"LABEL_2": 2,
|
28 |
+
"LABEL_3": 3,
|
29 |
+
"LABEL_4": 4,
|
30 |
+
"LABEL_5": 5,
|
31 |
+
"LABEL_6": 6,
|
32 |
+
"LABEL_7": 7
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-12,
|
35 |
+
"max_position_embeddings": 512,
|
36 |
+
"model_type": "bert",
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"position_embedding_type": "absolute",
|
41 |
+
"problem_type": "multi_label_classification",
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.26.1",
|
44 |
+
"type_vocab_size": 2,
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 32001
|
47 |
+
}
|
logs/1678138399.8571055/events.out.tfevents.1678138399.238d2c00108b.502.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41cf568d75e81d5f645aa75b23baae2775d0b3740e84a1059fa710e1daebec8c
|
3 |
+
size 5716
|
logs/events.out.tfevents.1678138399.238d2c00108b.502.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6fc5ca813437956db25d2bcac344d9a00b801b5fe5ce46b4a4678de992a61bd
|
3 |
+
size 6953
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75ef525e912e48cd2814561a5affe3d00b62fbae02afbb15b9e850029778efc4
|
3 |
+
size 442569845
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03a85ad5c7eb2d5aaef92a13cfc21e840f264ed0dbc7426af7aa0a2a74997f0d
|
3 |
+
size 3515
|