MuafiraThasni commited on
Commit
7c6fccf
1 Parent(s): 0eecbcd

Training in progress, step 400, checkpoint

Browse files
checkpoint-400/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nielsr/lilt-xlm-roberta-base",
3
+ "architectures": [
4
+ "LiltForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "channel_shrink_ratio": 4,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "Caption",
16
+ "1": "Footnote",
17
+ "2": "Formula",
18
+ "3": "List-item",
19
+ "4": "Page-footer",
20
+ "5": "Page-header",
21
+ "6": "Picture",
22
+ "7": "Section-header",
23
+ "8": "Table",
24
+ "9": "Text",
25
+ "10": "Title"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "Caption": 0,
31
+ "Footnote": 1,
32
+ "Formula": 2,
33
+ "List-item": 3,
34
+ "Page-footer": 4,
35
+ "Page-header": 5,
36
+ "Picture": 6,
37
+ "Section-header": 7,
38
+ "Table": 8,
39
+ "Text": 9,
40
+ "Title": 10
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "max_2d_position_embeddings": 1024,
44
+ "max_position_embeddings": 514,
45
+ "model_type": "lilt",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 12,
48
+ "output_past": true,
49
+ "pad_token_id": 1,
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.42.4",
53
+ "type_vocab_size": 1,
54
+ "use_cache": true,
55
+ "vocab_size": 250002
56
+ }
checkpoint-400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f32caa3ade0bc4dd79232fd1456fae9603bb7c02292df8675852e005eff55e9
3
+ size 1134332228
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18282059758f7438f8035104343961dae0354a3bf096166da6d8f2c8402bc4a
3
+ size 2265924830
checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662e921e03fcf92563a3b2458b6412a5d7887e0762378509ed7fc9f2b0e4bae7
3
+ size 14244
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2d6ad579de8c53cc7768e169f4897cd81cf9311331caed421754d374415e90
3
+ size 1064
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:683eb7c7eca2f8d4661f33cb19ad5dcb7c826bbc4256f314d42c7d9d3ac93240
3
+ size 17083001
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7865890784233485,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-300",
4
+ "epoch": 0.21321961620469082,
5
+ "eval_steps": 100,
6
+ "global_step": 400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.053304904051172705,
13
+ "eval_accuracy": 0.6912373860880154,
14
+ "eval_f1": 0.6912373860880154,
15
+ "eval_loss": 0.8656882047653198,
16
+ "eval_precision": 0.6912373860880154,
17
+ "eval_recall": 0.6912373860880154,
18
+ "eval_runtime": 41.8245,
19
+ "eval_samples_per_second": 38.422,
20
+ "eval_steps_per_second": 2.415,
21
+ "step": 100
22
+ },
23
+ {
24
+ "epoch": 0.10660980810234541,
25
+ "eval_accuracy": 0.7121482827113298,
26
+ "eval_f1": 0.7121482827113298,
27
+ "eval_loss": 0.856532096862793,
28
+ "eval_precision": 0.7121482827113298,
29
+ "eval_recall": 0.7121482827113298,
30
+ "eval_runtime": 42.6291,
31
+ "eval_samples_per_second": 37.697,
32
+ "eval_steps_per_second": 2.369,
33
+ "step": 200
34
+ },
35
+ {
36
+ "epoch": 0.15991471215351813,
37
+ "eval_accuracy": 0.7865890784233484,
38
+ "eval_f1": 0.7865890784233485,
39
+ "eval_loss": 0.6567804217338562,
40
+ "eval_precision": 0.7865890784233484,
41
+ "eval_recall": 0.7865890784233484,
42
+ "eval_runtime": 41.1268,
43
+ "eval_samples_per_second": 39.074,
44
+ "eval_steps_per_second": 2.456,
45
+ "step": 300
46
+ },
47
+ {
48
+ "epoch": 0.21321961620469082,
49
+ "eval_accuracy": 0.7400361324323516,
50
+ "eval_f1": 0.7400361324323516,
51
+ "eval_loss": 0.575270414352417,
52
+ "eval_precision": 0.7400361324323516,
53
+ "eval_recall": 0.7400361324323516,
54
+ "eval_runtime": 43.0681,
55
+ "eval_samples_per_second": 37.313,
56
+ "eval_steps_per_second": 2.345,
57
+ "step": 400
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1876,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 1,
64
+ "save_steps": 100,
65
+ "stateful_callbacks": {
66
+ "TrainerControl": {
67
+ "args": {
68
+ "should_epoch_stop": false,
69
+ "should_evaluate": false,
70
+ "should_log": false,
71
+ "should_save": true,
72
+ "should_training_stop": false
73
+ },
74
+ "attributes": {}
75
+ }
76
+ },
77
+ "total_flos": 890151164313600.0,
78
+ "train_batch_size": 8,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d884d25b9a0a1975c8ad8cdce24ef6b7c329f16153a80771adc673a879e2c8c3
3
+ size 5304