mbruton commited on
Commit
b94698b
·
1 Parent(s): d6aca00

Upload 11 files

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "liaad/srl-pt_xlmr-base",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "XLMRobertaForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
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": "O",
16
+ "1": "r0:arg0",
17
+ "2": "r0:arg1",
18
+ "3": "r0:arg2",
19
+ "4": "r0:root",
20
+ "5": "r10:arg0",
21
+ "6": "r10:arg1",
22
+ "7": "r10:root",
23
+ "8": "r11:arg0",
24
+ "9": "r11:root",
25
+ "10": "r12:arg1",
26
+ "11": "r12:root",
27
+ "12": "r13:arg1",
28
+ "13": "r13:root",
29
+ "14": "r1:arg0",
30
+ "15": "r1:arg1",
31
+ "16": "r1:arg2",
32
+ "17": "r1:root",
33
+ "18": "r2:arg0",
34
+ "19": "r2:arg1",
35
+ "20": "r2:arg2",
36
+ "21": "r2:root",
37
+ "22": "r3:arg0",
38
+ "23": "r3:arg1",
39
+ "24": "r3:arg2",
40
+ "25": "r3:root",
41
+ "26": "r4:arg0",
42
+ "27": "r4:arg1",
43
+ "28": "r4:arg2",
44
+ "29": "r4:root",
45
+ "30": "r5:arg0",
46
+ "31": "r5:arg1",
47
+ "32": "r5:arg2",
48
+ "33": "r5:root",
49
+ "34": "r6:arg0",
50
+ "35": "r6:arg1",
51
+ "36": "r6:arg2",
52
+ "37": "r6:root",
53
+ "38": "r7:arg0",
54
+ "39": "r7:arg1",
55
+ "40": "r7:arg2",
56
+ "41": "r7:root",
57
+ "42": "r8:arg0",
58
+ "43": "r8:arg1",
59
+ "44": "r8:arg2",
60
+ "45": "r8:root",
61
+ "46": "r9:arg0",
62
+ "47": "r9:arg1",
63
+ "48": "r9:arg2",
64
+ "49": "r9:root"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 3072,
68
+ "label2id": {
69
+ "O": 0,
70
+ "r0:arg0": 1,
71
+ "r0:arg1": 2,
72
+ "r0:arg2": 3,
73
+ "r0:root": 4,
74
+ "r10:arg0": 5,
75
+ "r10:arg1": 6,
76
+ "r10:root": 7,
77
+ "r11:arg0": 8,
78
+ "r11:root": 9,
79
+ "r12:arg1": 10,
80
+ "r12:root": 11,
81
+ "r13:arg1": 12,
82
+ "r13:root": 13,
83
+ "r1:arg0": 14,
84
+ "r1:arg1": 15,
85
+ "r1:arg2": 16,
86
+ "r1:root": 17,
87
+ "r2:arg0": 18,
88
+ "r2:arg1": 19,
89
+ "r2:arg2": 20,
90
+ "r2:root": 21,
91
+ "r3:arg0": 22,
92
+ "r3:arg1": 23,
93
+ "r3:arg2": 24,
94
+ "r3:root": 25,
95
+ "r4:arg0": 26,
96
+ "r4:arg1": 27,
97
+ "r4:arg2": 28,
98
+ "r4:root": 29,
99
+ "r5:arg0": 30,
100
+ "r5:arg1": 31,
101
+ "r5:arg2": 32,
102
+ "r5:root": 33,
103
+ "r6:arg0": 34,
104
+ "r6:arg1": 35,
105
+ "r6:arg2": 36,
106
+ "r6:root": 37,
107
+ "r7:arg0": 38,
108
+ "r7:arg1": 39,
109
+ "r7:arg2": 40,
110
+ "r7:root": 41,
111
+ "r8:arg0": 42,
112
+ "r8:arg1": 43,
113
+ "r8:arg2": 44,
114
+ "r8:root": 45,
115
+ "r9:arg0": 46,
116
+ "r9:arg1": 47,
117
+ "r9:arg2": 48,
118
+ "r9:root": 49
119
+ },
120
+ "layer_norm_eps": 1e-05,
121
+ "max_position_embeddings": 514,
122
+ "model_type": "xlm-roberta",
123
+ "num_attention_heads": 12,
124
+ "num_hidden_layers": 12,
125
+ "output_past": true,
126
+ "pad_token_id": 1,
127
+ "position_embedding_type": "absolute",
128
+ "torch_dtype": "float32",
129
+ "transformers_version": "4.27.4",
130
+ "type_vocab_size": 2,
131
+ "use_cache": true,
132
+ "vocab_size": 250002
133
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6229be9aab48376a75cd975394b1913685a2667383d633cd7c4a48119fcdf4f7
3
+ size 2220053605
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf9c02e3dff6bb6d8e6cfacb221d48414d460241514a13811dad4a71d652bd3
3
+ size 1110040177
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067a3d9d4296a0274f96eb2257ae1d69ee29e64b2d5ab3e3a4d2593d403c095c
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14881f8352737c801b7e15ff2544419ace05937680ded1c03cfe4be45005e78
3
+ size 623
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa919170495afbc86481b2ba28b16bfef241790e322601b4edc6bdc1f913d71f
3
+ size 17098179
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "max_len": 512,
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "sp_model_kwargs": {},
18
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--liaad--srl-pt_xlmr-base/snapshots/07030ec73ebc895a16423d30f8b34355e27e0861/special_tokens_map.json",
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "unk_token": "<unk>"
21
+ }
trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3014024496078491,
3
+ "best_model_checkpoint": "gal_pt_XLM-R/checkpoint-1250",
4
+ "epoch": 6.0,
5
+ "global_step": 1500,
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
+ "eval_accuracy": 0.8764106967615309,
13
+ "eval_f1": 0.5194326468467025,
14
+ "eval_loss": 0.4419800043106079,
15
+ "eval_precision": 0.583648478300018,
16
+ "eval_recall": 0.4679468668784291,
17
+ "eval_runtime": 5.1555,
18
+ "eval_samples_per_second": 193.384,
19
+ "eval_steps_per_second": 12.22,
20
+ "step": 250
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "learning_rate": 1.9600000000000002e-05,
25
+ "loss": 0.5661,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.8951177625122669,
31
+ "eval_f1": 0.6106744516805149,
32
+ "eval_loss": 0.3635525107383728,
33
+ "eval_precision": 0.634074304368102,
34
+ "eval_recall": 0.5889402252382328,
35
+ "eval_runtime": 5.1045,
36
+ "eval_samples_per_second": 195.319,
37
+ "eval_steps_per_second": 12.342,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "eval_accuracy": 0.8999938665358195,
43
+ "eval_f1": 0.6414069202173291,
44
+ "eval_loss": 0.33455267548561096,
45
+ "eval_precision": 0.6352308128009062,
46
+ "eval_recall": 0.6477043026277793,
47
+ "eval_runtime": 5.0422,
48
+ "eval_samples_per_second": 197.733,
49
+ "eval_steps_per_second": 12.495,
50
+ "step": 750
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 1.9200000000000003e-05,
55
+ "loss": 0.2931,
56
+ "step": 1000
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_accuracy": 0.9071700196270854,
61
+ "eval_f1": 0.6772389380530973,
62
+ "eval_loss": 0.3290555477142334,
63
+ "eval_precision": 0.6643978330323657,
64
+ "eval_recall": 0.6905861969390702,
65
+ "eval_runtime": 5.0586,
66
+ "eval_samples_per_second": 197.092,
67
+ "eval_steps_per_second": 12.454,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "eval_accuracy": 0.9161248773307163,
73
+ "eval_f1": 0.7046489769358687,
74
+ "eval_loss": 0.3014024496078491,
75
+ "eval_precision": 0.7057204923968139,
76
+ "eval_recall": 0.7035807103667341,
77
+ "eval_runtime": 5.0677,
78
+ "eval_samples_per_second": 196.736,
79
+ "eval_steps_per_second": 12.432,
80
+ "step": 1250
81
+ },
82
+ {
83
+ "epoch": 6.0,
84
+ "learning_rate": 1.88e-05,
85
+ "loss": 0.2199,
86
+ "step": 1500
87
+ },
88
+ {
89
+ "epoch": 6.0,
90
+ "eval_accuracy": 0.9111567713444554,
91
+ "eval_f1": 0.6965250965250965,
92
+ "eval_loss": 0.317579060792923,
93
+ "eval_precision": 0.6778248394589425,
94
+ "eval_recall": 0.7162864568293387,
95
+ "eval_runtime": 5.1483,
96
+ "eval_samples_per_second": 193.655,
97
+ "eval_steps_per_second": 12.237,
98
+ "step": 1500
99
+ }
100
+ ],
101
+ "max_steps": 25000,
102
+ "num_train_epochs": 100,
103
+ "total_flos": 925793237842200.0,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515100ab657571787d5d22498b64c75583388363544b1e8e7367767afaab1970
3
+ size 3503