camilum commited on
Commit
4fa343e
·
verified ·
1 Parent(s): 0a237c1

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
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": 0.0,
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
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7
35
+ },
36
+ "layer_norm_eps": 1e-05,
37
+ "max_position_embeddings": 514,
38
+ "model_type": "roberta",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 1,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.23.1",
46
+ "type_vocab_size": 1,
47
+ "use_cache": true,
48
+ "vocab_size": 50262
49
+ }
hyperpameters/experiment_state-2022-12-20_16-21-04.json ADDED
The diff for this file is too large to render. See raw diff
 
hyperpameters/search_gen_state-2022-12-20_16-21-04.json ADDED
Binary file (1.21 kB). View file
 
hyperpameters/searcher-state-2022-12-20_16-21-04.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55cacf51c25ea3f7859339f85b247ea83aa1a231ffbb487ebdca124c78aeaabe
3
+ size 6775
hyperparameters.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ objective,best,learning_rate,num_train_epochs,per_device_train_batch_size,warmup_steps,weight_decay,time_this_iter_s
2
+ 0.6443113896695691,True,3.180777925533466e-05,4,8,0,0.120996580489383,298.83673191070557
3
+ 0.6089856418323499,False,4.2608362046060736e-05,5,16,250,0.013431860702755793,277.2320647239685
4
+ 0.5095106557666577,False,1.0637577579349663e-05,2,8,250,0.1877430771288012,301.0902969837189
5
+ 0.472259840186323,False,4.1563816188891756e-05,5,8,1000,0.1161026692593292,300.9598762989044
6
+ 0.529856443331991,False,2.452236326363528e-05,1,8,500,0.10445925926224571,301.152028799057
7
+ 0.47216204569436443,False,3.933498237560027e-05,2,16,1000,0.24544607439873792,279.3527762889862
8
+ 0.5418994731991358,False,4.773883883904306e-05,1,8,0,0.06315173766701002,300.95647048950195
9
+ 0.5093720595534817,False,2.815232779630741e-05,2,16,0,0.10288070790935573,279.3547649383545
10
+ 0.5178339691369227,False,4.194670456106283e-05,3,16,250,0.20101691147250575,279.44476771354675
11
+ 0.4614279300033849,False,4.925349517520429e-05,1,8,1000,0.2706428191074305,300.6847951412201
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62578cf7cad109803c4dbea866db795c4ab3cd42bb3abefc0d893dab56b700fd
3
+ size 997363397
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce44e1a4be2ab3436c3db0824a5a447623f014a4b16c3b54c201bfad1c9a97bb
3
+ size 498671285
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7af3a64371d143c28cd7bebe6ce3d701696b700d984c227bd1b50c4691394e
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8564009070396423,
3
+ "best_model_checkpoint": "./results/run-eb32b854/checkpoint-882",
4
+ "epoch": 4.0,
5
+ "global_step": 3528,
6
+ "is_hyper_param_search": true,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 3.1798763444888135e-05,
13
+ "loss": 2.0373,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_f1": 0.4929364503071642,
19
+ "eval_loss": 0.8564009070396423,
20
+ "eval_runtime": 19.2818,
21
+ "eval_samples_per_second": 121.98,
22
+ "eval_steps_per_second": 15.248,
23
+ "step": 882
24
+ },
25
+ {
26
+ "epoch": 1.13,
27
+ "learning_rate": 2.2791968808811233e-05,
28
+ "loss": 0.9246,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_f1": 0.6146216192253161,
34
+ "eval_loss": 0.8962076306343079,
35
+ "eval_runtime": 19.3209,
36
+ "eval_samples_per_second": 121.734,
37
+ "eval_steps_per_second": 15.217,
38
+ "step": 1764
39
+ },
40
+ {
41
+ "epoch": 2.27,
42
+ "learning_rate": 1.3776158362287801e-05,
43
+ "loss": 0.4402,
44
+ "step": 2000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_f1": 0.6171442898225464,
49
+ "eval_loss": 1.2047011852264404,
50
+ "eval_runtime": 19.3331,
51
+ "eval_samples_per_second": 121.656,
52
+ "eval_steps_per_second": 15.207,
53
+ "step": 2646
54
+ },
55
+ {
56
+ "epoch": 3.4,
57
+ "learning_rate": 4.760347915764371e-06,
58
+ "loss": 0.169,
59
+ "step": 3000
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_f1": 0.6443113896695691,
64
+ "eval_loss": 1.3850061893463135,
65
+ "eval_runtime": 19.3579,
66
+ "eval_samples_per_second": 121.501,
67
+ "eval_steps_per_second": 15.188,
68
+ "step": 3528
69
+ }
70
+ ],
71
+ "max_steps": 3528,
72
+ "num_train_epochs": 4,
73
+ "total_flos": 5472186620003712.0,
74
+ "trial_name": null,
75
+ "trial_params": {
76
+ "learning_rate": 3.180777925533466e-05,
77
+ "num_train_epochs": 4,
78
+ "per_device_train_batch_size": 8,
79
+ "warmup_steps": 0,
80
+ "weight_decay": 0.120996580489383
81
+ }
82
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333dc0af7c718e703087a10096dc81062d9882971033588cac5592dc17d98477
3
+ size 3387
training_resume.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "batch_train_size": 16,
3
+ "batch_val_size": 32,
4
+ "corpus": "text",
5
+ "dataset": "safercity",
6
+ "epochs": [
7
+ 1,
8
+ 2,
9
+ 3,
10
+ 4,
11
+ 5
12
+ ],
13
+ "folder": "marIA",
14
+ "iterations": 10,
15
+ "labels": 8,
16
+ "model": "transformers",
17
+ "original_pretrained_model": "PlanTL-GOB-ES/roberta-base-bne",
18
+ "pretrained_model": "../assets/safercity/text/models/marIA",
19
+ "resources_per_trial": {
20
+ "gpu": 1
21
+ },
22
+ "run_id": "eb32b854",
23
+ "task": "",
24
+ "task_type": "classification",
25
+ "tokenizer_field": "tweet",
26
+ "tokenizer_model": "PlanTL-GOB-ES/roberta-base-bne",
27
+ "warmup_steps": 500,
28
+ "weight_decay": 0.01
29
+ }