Hugging Face's logo

diogopaes10
/
018-microsoft-MiniLM-finetuned-yahoo-8000_2000

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
diogopaes10 commited on
Commit
4e00681
•
1 Parent(s): 6cb80d8

Training in progress, step 500

Browse files
Files changed (19) hide show
  1. checkpoint-500/config.json +50 -0
  2. checkpoint-500/optimizer.pt +3 -0
  3. checkpoint-500/pytorch_model.bin +3 -0
  4. checkpoint-500/rng_state.pth +3 -0
  5. checkpoint-500/scheduler.pt +3 -0
  6. checkpoint-500/special_tokens_map.json +7 -0
  7. checkpoint-500/tokenizer.json +0 -0
  8. checkpoint-500/tokenizer_config.json +15 -0
  9. checkpoint-500/trainer_state.json +126 -0
  10. checkpoint-500/training_args.bin +3 -0
  11. checkpoint-500/vocab.txt +0 -0
  12. config.json +50 -0
  13. pytorch_model.bin +3 -0
  14. runs/Jul23_00-54-01_c587bebf8fcc/events.out.tfevents.1690073651.c587bebf8fcc.2239.0 +3 -0
  15. special_tokens_map.json +7 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +15 -0
  18. training_args.bin +3 -0
  19. vocab.txt +0 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "Society & Culture",
13
+ "1": "Science & Mathematics",
14
+ "2": "Health",
15
+ "3": "Education & Reference",
16
+ "4": "Computers & Internet",
17
+ "5": "Sports",
18
+ "6": "Business & Finance",
19
+ "7": "Entertainment & Music",
20
+ "8": "Family & Relationships",
21
+ "9": "Politics & Government"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1536,
25
+ "label2id": {
26
+ "Business & Finance": 6,
27
+ "Computers & Internet": 4,
28
+ "Education & Reference": 3,
29
+ "Entertainment & Music": 7,
30
+ "Family & Relationships": 8,
31
+ "Health": 2,
32
+ "Politics & Government": 9,
33
+ "Science & Mathematics": 1,
34
+ "Society & Culture": 0,
35
+ "Sports": 5
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "single_label_classification",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.31.0",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30522
50
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53be9ac4c3e3bc910bd1c511da882f2163136352413508d0ba0925d92a23d986
3
+ size 267028677
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a60923e118f86e3152bed751de29e981cde48e94fddec16dd1c7e9e4db929f
3
+ size 133523761
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2062977cc6439fdbf2b3bf4cb31a2a1b3a0544d7f149a4e62f0f4cf86271c71
3
+ size 14575
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3fb23b4f309aebf5f097e2f3bd5ea473249f43b9a2473bebd6432c05590b3ed
3
+ size 627
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
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": 0.0,
12
+ "learning_rate": 1.9992e-05,
13
+ "loss": 2.3035,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.5,
18
+ "learning_rate": 1.9e-05,
19
+ "loss": 2.1461,
20
+ "step": 125
21
+ },
22
+ {
23
+ "epoch": 0.5,
24
+ "eval_accuracy": 0.5465,
25
+ "eval_disk_space_total": 78.1898422241211,
26
+ "eval_disk_space_used": 24.584102630615234,
27
+ "eval_f1": 0.4711252488920671,
28
+ "eval_gpu_ram_allocated": 0.3996291160583496,
29
+ "eval_gpu_ram_cached": 12.9296875,
30
+ "eval_gpu_ram_total": 39.56402587890625,
31
+ "eval_gpu_utilization": 28,
32
+ "eval_loss": 1.8486889600753784,
33
+ "eval_precision": 0.5180898369172832,
34
+ "eval_recall": 0.5465,
35
+ "eval_runtime": 1.5234,
36
+ "eval_samples_per_second": 1312.845,
37
+ "eval_steps_per_second": 41.355,
38
+ "eval_system_ram_total": 83.48074722290039,
39
+ "eval_system_ram_used": 3.8797760009765625,
40
+ "step": 125
41
+ },
42
+ {
43
+ "epoch": 1.0,
44
+ "learning_rate": 1.8e-05,
45
+ "loss": 1.6793,
46
+ "step": 250
47
+ },
48
+ {
49
+ "epoch": 1.0,
50
+ "eval_accuracy": 0.615,
51
+ "eval_disk_space_total": 78.1898422241211,
52
+ "eval_disk_space_used": 24.584190368652344,
53
+ "eval_f1": 0.5799151958404197,
54
+ "eval_gpu_ram_allocated": 0.3996119499206543,
55
+ "eval_gpu_ram_cached": 12.9296875,
56
+ "eval_gpu_ram_total": 39.56402587890625,
57
+ "eval_gpu_utilization": 28,
58
+ "eval_loss": 1.5279773473739624,
59
+ "eval_precision": 0.6206909881233017,
60
+ "eval_recall": 0.615,
61
+ "eval_runtime": 1.5357,
62
+ "eval_samples_per_second": 1302.337,
63
+ "eval_steps_per_second": 41.024,
64
+ "eval_system_ram_total": 83.48074722290039,
65
+ "eval_system_ram_used": 3.8827476501464844,
66
+ "step": 250
67
+ },
68
+ {
69
+ "epoch": 1.5,
70
+ "learning_rate": 1.7e-05,
71
+ "loss": 1.4163,
72
+ "step": 375
73
+ },
74
+ {
75
+ "epoch": 1.5,
76
+ "eval_accuracy": 0.6675,
77
+ "eval_disk_space_total": 78.1898422241211,
78
+ "eval_disk_space_used": 24.584190368652344,
79
+ "eval_f1": 0.6507803054121275,
80
+ "eval_gpu_ram_allocated": 0.3996291160583496,
81
+ "eval_gpu_ram_cached": 12.9296875,
82
+ "eval_gpu_ram_total": 39.56402587890625,
83
+ "eval_gpu_utilization": 28,
84
+ "eval_loss": 1.3395830392837524,
85
+ "eval_precision": 0.6690538200035159,
86
+ "eval_recall": 0.6675,
87
+ "eval_runtime": 1.5175,
88
+ "eval_samples_per_second": 1317.927,
89
+ "eval_steps_per_second": 41.515,
90
+ "eval_system_ram_total": 83.48074722290039,
91
+ "eval_system_ram_used": 3.883075714111328,
92
+ "step": 375
93
+ },
94
+ {
95
+ "epoch": 2.0,
96
+ "learning_rate": 1.6000000000000003e-05,
97
+ "loss": 1.2855,
98
+ "step": 500
99
+ },
100
+ {
101
+ "epoch": 2.0,
102
+ "eval_accuracy": 0.6745,
103
+ "eval_disk_space_total": 78.1898422241211,
104
+ "eval_disk_space_used": 24.584270477294922,
105
+ "eval_f1": 0.6633189544214071,
106
+ "eval_gpu_ram_allocated": 0.3995933532714844,
107
+ "eval_gpu_ram_cached": 12.9296875,
108
+ "eval_gpu_ram_total": 39.56402587890625,
109
+ "eval_gpu_utilization": 30,
110
+ "eval_loss": 1.2413243055343628,
111
+ "eval_precision": 0.6741774761001332,
112
+ "eval_recall": 0.6745,
113
+ "eval_runtime": 1.5166,
114
+ "eval_samples_per_second": 1318.761,
115
+ "eval_steps_per_second": 41.541,
116
+ "eval_system_ram_total": 83.48074722290039,
117
+ "eval_system_ram_used": 3.897541046142578,
118
+ "step": 500
119
+ }
120
+ ],
121
+ "max_steps": 2500,
122
+ "num_train_epochs": 10,
123
+ "total_flos": 252176442301056.0,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b163d01ba6550b4d0ea94aab97f417a764349c69c3237b0edc7b5507f1235fe6
3
+ size 4091
checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "Society & Culture",
13
+ "1": "Science & Mathematics",
14
+ "2": "Health",
15
+ "3": "Education & Reference",
16
+ "4": "Computers & Internet",
17
+ "5": "Sports",
18
+ "6": "Business & Finance",
19
+ "7": "Entertainment & Music",
20
+ "8": "Family & Relationships",
21
+ "9": "Politics & Government"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1536,
25
+ "label2id": {
26
+ "Business & Finance": 6,
27
+ "Computers & Internet": 4,
28
+ "Education & Reference": 3,
29
+ "Entertainment & Music": 7,
30
+ "Family & Relationships": 8,
31
+ "Health": 2,
32
+ "Politics & Government": 9,
33
+ "Science & Mathematics": 1,
34
+ "Society & Culture": 0,
35
+ "Sports": 5
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "single_label_classification",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.31.0",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30522
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a60923e118f86e3152bed751de29e981cde48e94fddec16dd1c7e9e4db929f
3
+ size 133523761
runs/Jul23_00-54-01_c587bebf8fcc/events.out.tfevents.1690073651.c587bebf8fcc.2239.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0105507a7dc18b7339a48cda035d074d7d3cf2e1c02937aa42eba5c5d8a377
3
+ size 9265
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b163d01ba6550b4d0ea94aab97f417a764349c69c3237b0edc7b5507f1235fe6
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff