quim-motger commited on
Commit
be82165
1 Parent(s): 32c3f12

upload model files

Browse files
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlnet-large-cased",
3
+ "architectures": [
4
+ "XLNetForTokenClassification"
5
+ ],
6
+ "attn_type": "bi",
7
+ "bi_data": false,
8
+ "bos_token_id": 1,
9
+ "clamp_len": -1,
10
+ "d_head": 64,
11
+ "d_inner": 4096,
12
+ "d_model": 1024,
13
+ "dropout": 0.1,
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
+ "id2label": {
18
+ "0": "O",
19
+ "1": "B-feature",
20
+ "2": "I-feature"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "B-feature": 1,
25
+ "I-feature": 2,
26
+ "O": 0
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "mem_len": null,
30
+ "model_type": "xlnet",
31
+ "n_head": 16,
32
+ "n_layer": 24,
33
+ "pad_token_id": 5,
34
+ "reuse_len": null,
35
+ "same_length": false,
36
+ "start_n_top": 5,
37
+ "summary_activation": "tanh",
38
+ "summary_last_dropout": 0.1,
39
+ "summary_type": "last",
40
+ "summary_use_proj": true,
41
+ "task_specific_params": {
42
+ "text-generation": {
43
+ "do_sample": true,
44
+ "max_length": 250
45
+ }
46
+ },
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.30.2",
49
+ "untie_r": true,
50
+ "use_mems_eval": true,
51
+ "use_mems_train": false,
52
+ "vocab_size": 32000
53
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2faa41336c927c289261e2147f320bdf4b19a5c75013f9fa48e5b7504eb7e0
3
+ size 2882410053
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539a89dc5c71ed4b8ac22b235d8a2d34851a0d7522ed11ce380e836d4ac69357
3
+ size 1441225277
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0edd2ceb30d6babc1f3e5958a8417a2569537b5352b92d741a4661c167a82c5
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81b9e64a6d36ab9d27ca33efaa732434676daf622cfdf89ee1179762e733965
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<cls>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "<sep>",
18
+ "unk_token": "<unk>"
19
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "clean_up_tokenization_spaces": true,
8
+ "cls_token": "<cls>",
9
+ "do_lower_case": false,
10
+ "eos_token": "</s>",
11
+ "keep_accents": false,
12
+ "mask_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<mask>",
15
+ "lstrip": true,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": "<pad>",
22
+ "remove_space": true,
23
+ "sep_token": "<sep>",
24
+ "tokenizer_class": "XLNetTokenizer",
25
+ "unk_token": "<unk>"
26
+ }
trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.004898133222013712,
3
+ "best_model_checkpoint": "data/train-test///model/checkpoint-3351",
4
+ "epoch": 1.0,
5
+ "global_step": 3351,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.15,
12
+ "learning_rate": 1.850790808713817e-05,
13
+ "loss": 0.1149,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.3,
18
+ "learning_rate": 1.7015816174276335e-05,
19
+ "loss": 0.0198,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.45,
24
+ "learning_rate": 1.5523724261414504e-05,
25
+ "loss": 0.0101,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.6,
30
+ "learning_rate": 1.4031632348552673e-05,
31
+ "loss": 0.0063,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.75,
36
+ "learning_rate": 1.253954043569084e-05,
37
+ "loss": 0.0067,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.9,
42
+ "learning_rate": 1.1047448522829008e-05,
43
+ "loss": 0.0068,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_accuracy": null,
49
+ "eval_f1": 0.9943977591036415,
50
+ "eval_loss": 0.004898133222013712,
51
+ "eval_precision": 0.9943977591036415,
52
+ "eval_recall": 0.9943977591036415,
53
+ "eval_runtime": 1.5284,
54
+ "eval_samples_per_second": 634.661,
55
+ "eval_steps_per_second": 79.823,
56
+ "step": 3351
57
+ }
58
+ ],
59
+ "max_steps": 6702,
60
+ "num_train_epochs": 2,
61
+ "total_flos": 2597776456686000.0,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d97d2a8f287fdc8b9e66604d38c2f4463bc68b55cef78f20bc93ec03f39e104
3
+ size 3963