yeshpanovrustem
commited on
Commit
•
9be8159
1
Parent(s):
ec15925
Upload 9 files
Browse files- .gitattributes +1 -0
- config.json +162 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
- trainer_state.json +160 -0
- training_args.bin +3 -0
.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 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11",
|
26 |
+
"12": "LABEL_12",
|
27 |
+
"13": "LABEL_13",
|
28 |
+
"14": "LABEL_14",
|
29 |
+
"15": "LABEL_15",
|
30 |
+
"16": "LABEL_16",
|
31 |
+
"17": "LABEL_17",
|
32 |
+
"18": "LABEL_18",
|
33 |
+
"19": "LABEL_19",
|
34 |
+
"20": "LABEL_20",
|
35 |
+
"21": "LABEL_21",
|
36 |
+
"22": "LABEL_22",
|
37 |
+
"23": "LABEL_23",
|
38 |
+
"24": "LABEL_24",
|
39 |
+
"25": "LABEL_25",
|
40 |
+
"26": "LABEL_26",
|
41 |
+
"27": "LABEL_27",
|
42 |
+
"28": "LABEL_28",
|
43 |
+
"29": "LABEL_29",
|
44 |
+
"30": "LABEL_30",
|
45 |
+
"31": "LABEL_31",
|
46 |
+
"32": "LABEL_32",
|
47 |
+
"33": "LABEL_33",
|
48 |
+
"34": "LABEL_34",
|
49 |
+
"35": "LABEL_35",
|
50 |
+
"36": "LABEL_36",
|
51 |
+
"37": "LABEL_37",
|
52 |
+
"38": "LABEL_38",
|
53 |
+
"39": "LABEL_39",
|
54 |
+
"40": "LABEL_40",
|
55 |
+
"41": "LABEL_41",
|
56 |
+
"42": "LABEL_42",
|
57 |
+
"43": "LABEL_43",
|
58 |
+
"44": "LABEL_44",
|
59 |
+
"45": "LABEL_45",
|
60 |
+
"46": "LABEL_46",
|
61 |
+
"47": "LABEL_47",
|
62 |
+
"48": "LABEL_48",
|
63 |
+
"49": "LABEL_49",
|
64 |
+
"50": "LABEL_50",
|
65 |
+
"51": "LABEL_51",
|
66 |
+
"52": "LABEL_52",
|
67 |
+
"53": "LABEL_53",
|
68 |
+
"54": "LABEL_54",
|
69 |
+
"55": "LABEL_55",
|
70 |
+
"56": "LABEL_56",
|
71 |
+
"57": "LABEL_57",
|
72 |
+
"58": "LABEL_58",
|
73 |
+
"59": "LABEL_59",
|
74 |
+
"60": "LABEL_60",
|
75 |
+
"61": "LABEL_61",
|
76 |
+
"62": "LABEL_62",
|
77 |
+
"63": "LABEL_63",
|
78 |
+
"64": "LABEL_64"
|
79 |
+
},
|
80 |
+
"initializer_range": 0.02,
|
81 |
+
"intermediate_size": 4096,
|
82 |
+
"label2id": {
|
83 |
+
"LABEL_0": 0,
|
84 |
+
"LABEL_1": 1,
|
85 |
+
"LABEL_10": 10,
|
86 |
+
"LABEL_11": 11,
|
87 |
+
"LABEL_12": 12,
|
88 |
+
"LABEL_13": 13,
|
89 |
+
"LABEL_14": 14,
|
90 |
+
"LABEL_15": 15,
|
91 |
+
"LABEL_16": 16,
|
92 |
+
"LABEL_17": 17,
|
93 |
+
"LABEL_18": 18,
|
94 |
+
"LABEL_19": 19,
|
95 |
+
"LABEL_2": 2,
|
96 |
+
"LABEL_20": 20,
|
97 |
+
"LABEL_21": 21,
|
98 |
+
"LABEL_22": 22,
|
99 |
+
"LABEL_23": 23,
|
100 |
+
"LABEL_24": 24,
|
101 |
+
"LABEL_25": 25,
|
102 |
+
"LABEL_26": 26,
|
103 |
+
"LABEL_27": 27,
|
104 |
+
"LABEL_28": 28,
|
105 |
+
"LABEL_29": 29,
|
106 |
+
"LABEL_3": 3,
|
107 |
+
"LABEL_30": 30,
|
108 |
+
"LABEL_31": 31,
|
109 |
+
"LABEL_32": 32,
|
110 |
+
"LABEL_33": 33,
|
111 |
+
"LABEL_34": 34,
|
112 |
+
"LABEL_35": 35,
|
113 |
+
"LABEL_36": 36,
|
114 |
+
"LABEL_37": 37,
|
115 |
+
"LABEL_38": 38,
|
116 |
+
"LABEL_39": 39,
|
117 |
+
"LABEL_4": 4,
|
118 |
+
"LABEL_40": 40,
|
119 |
+
"LABEL_41": 41,
|
120 |
+
"LABEL_42": 42,
|
121 |
+
"LABEL_43": 43,
|
122 |
+
"LABEL_44": 44,
|
123 |
+
"LABEL_45": 45,
|
124 |
+
"LABEL_46": 46,
|
125 |
+
"LABEL_47": 47,
|
126 |
+
"LABEL_48": 48,
|
127 |
+
"LABEL_49": 49,
|
128 |
+
"LABEL_5": 5,
|
129 |
+
"LABEL_50": 50,
|
130 |
+
"LABEL_51": 51,
|
131 |
+
"LABEL_52": 52,
|
132 |
+
"LABEL_53": 53,
|
133 |
+
"LABEL_54": 54,
|
134 |
+
"LABEL_55": 55,
|
135 |
+
"LABEL_56": 56,
|
136 |
+
"LABEL_57": 57,
|
137 |
+
"LABEL_58": 58,
|
138 |
+
"LABEL_59": 59,
|
139 |
+
"LABEL_6": 6,
|
140 |
+
"LABEL_60": 60,
|
141 |
+
"LABEL_61": 61,
|
142 |
+
"LABEL_62": 62,
|
143 |
+
"LABEL_63": 63,
|
144 |
+
"LABEL_64": 64,
|
145 |
+
"LABEL_7": 7,
|
146 |
+
"LABEL_8": 8,
|
147 |
+
"LABEL_9": 9
|
148 |
+
},
|
149 |
+
"layer_norm_eps": 1e-05,
|
150 |
+
"max_position_embeddings": 514,
|
151 |
+
"model_type": "xlm-roberta",
|
152 |
+
"num_attention_heads": 16,
|
153 |
+
"num_hidden_layers": 24,
|
154 |
+
"output_past": true,
|
155 |
+
"pad_token_id": 1,
|
156 |
+
"position_embedding_type": "absolute",
|
157 |
+
"torch_dtype": "float32",
|
158 |
+
"transformers_version": "4.26.1",
|
159 |
+
"type_vocab_size": 1,
|
160 |
+
"use_cache": true,
|
161 |
+
"vocab_size": 250002
|
162 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6d95d650ef51a527c898cdcb1f657f6a74f2dee3ba2047be3f11dc02d0022b0
|
3 |
+
size 2235766385
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dd5f46a018cf368b1dad18c07c0690065d8fa88ba9cc6083a390290c06213d5
|
3 |
+
size 21579
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4015cdb5ec973cb4a90adabc352a0271a90d07a6e2e49428732f3c2d0e4d7318
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
|
3 |
+
size 17082758
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "xlm-roberta-large",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 2330,
|
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": 0.8702409035670884,
|
13 |
+
"eval_f1": 0.2995999407319603,
|
14 |
+
"eval_loss": 0.5389052033424377,
|
15 |
+
"eval_precision": 0.33331959612610756,
|
16 |
+
"eval_recall": 0.27207589060450094,
|
17 |
+
"eval_runtime": 14.1196,
|
18 |
+
"eval_samples_per_second": 1054.99,
|
19 |
+
"eval_steps_per_second": 2.125,
|
20 |
+
"step": 233
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_accuracy": 0.9681749946386446,
|
25 |
+
"eval_f1": 0.8514915583419936,
|
26 |
+
"eval_loss": 0.12146873772144318,
|
27 |
+
"eval_precision": 0.8626164998274076,
|
28 |
+
"eval_recall": 0.8406499142193965,
|
29 |
+
"eval_runtime": 15.0925,
|
30 |
+
"eval_samples_per_second": 986.983,
|
31 |
+
"eval_steps_per_second": 1.988,
|
32 |
+
"step": 466
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.15,
|
36 |
+
"learning_rate": 6.25e-06,
|
37 |
+
"loss": 1.2635,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"eval_accuracy": 0.9790478232897276,
|
43 |
+
"eval_f1": 0.9141998345125719,
|
44 |
+
"eval_loss": 0.0771816298365593,
|
45 |
+
"eval_precision": 0.9178421266784212,
|
46 |
+
"eval_recall": 0.9105863356544556,
|
47 |
+
"eval_runtime": 14.0091,
|
48 |
+
"eval_samples_per_second": 1063.307,
|
49 |
+
"eval_steps_per_second": 2.141,
|
50 |
+
"step": 699
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.98271141611266,
|
55 |
+
"eval_f1": 0.9309382867251821,
|
56 |
+
"eval_loss": 0.06554248929023743,
|
57 |
+
"eval_precision": 0.9416055882454148,
|
58 |
+
"eval_recall": 0.9205099740976217,
|
59 |
+
"eval_runtime": 14.0197,
|
60 |
+
"eval_samples_per_second": 1062.501,
|
61 |
+
"eval_steps_per_second": 2.14,
|
62 |
+
"step": 932
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.29,
|
66 |
+
"learning_rate": 8.69281045751634e-06,
|
67 |
+
"loss": 0.0906,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"eval_accuracy": 0.984880977911216,
|
73 |
+
"eval_f1": 0.9419223941161552,
|
74 |
+
"eval_loss": 0.06115253269672394,
|
75 |
+
"eval_precision": 0.9468692637160921,
|
76 |
+
"eval_recall": 0.9370269452013321,
|
77 |
+
"eval_runtime": 14.0288,
|
78 |
+
"eval_samples_per_second": 1061.817,
|
79 |
+
"eval_steps_per_second": 2.138,
|
80 |
+
"step": 1165
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 6.0,
|
84 |
+
"eval_accuracy": 0.9843269711916506,
|
85 |
+
"eval_f1": 0.9446501919062689,
|
86 |
+
"eval_loss": 0.062205445021390915,
|
87 |
+
"eval_precision": 0.9454459682582471,
|
88 |
+
"eval_recall": 0.9438557540283244,
|
89 |
+
"eval_runtime": 14.4851,
|
90 |
+
"eval_samples_per_second": 1028.367,
|
91 |
+
"eval_steps_per_second": 2.071,
|
92 |
+
"step": 1398
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.44,
|
96 |
+
"learning_rate": 5.4248366013071894e-06,
|
97 |
+
"loss": 0.0429,
|
98 |
+
"step": 1500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_accuracy": 0.9854850239473872,
|
103 |
+
"eval_f1": 0.9466268938436389,
|
104 |
+
"eval_loss": 0.06088804826140404,
|
105 |
+
"eval_precision": 0.9484971293481932,
|
106 |
+
"eval_recall": 0.9447640192417668,
|
107 |
+
"eval_runtime": 14.327,
|
108 |
+
"eval_samples_per_second": 1039.716,
|
109 |
+
"eval_steps_per_second": 2.094,
|
110 |
+
"step": 1631
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 8.0,
|
114 |
+
"eval_accuracy": 0.9853885195510759,
|
115 |
+
"eval_f1": 0.9475256832068758,
|
116 |
+
"eval_loss": 0.06388872861862183,
|
117 |
+
"eval_precision": 0.9456525381135868,
|
118 |
+
"eval_recall": 0.9494062636660275,
|
119 |
+
"eval_runtime": 14.5864,
|
120 |
+
"eval_samples_per_second": 1021.225,
|
121 |
+
"eval_steps_per_second": 2.057,
|
122 |
+
"step": 1864
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 8.58,
|
126 |
+
"learning_rate": 2.1568627450980393e-06,
|
127 |
+
"loss": 0.0265,
|
128 |
+
"step": 2000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"eval_accuracy": 0.9858710415326328,
|
133 |
+
"eval_f1": 0.9485348353785288,
|
134 |
+
"eval_loss": 0.06375858187675476,
|
135 |
+
"eval_precision": 0.9453968253968253,
|
136 |
+
"eval_recall": 0.9516937464258082,
|
137 |
+
"eval_runtime": 14.1094,
|
138 |
+
"eval_samples_per_second": 1055.751,
|
139 |
+
"eval_steps_per_second": 2.126,
|
140 |
+
"step": 2097
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.0,
|
144 |
+
"eval_accuracy": 0.9859925655872471,
|
145 |
+
"eval_f1": 0.949012494961709,
|
146 |
+
"eval_loss": 0.06480085104703903,
|
147 |
+
"eval_precision": 0.9475802394607103,
|
148 |
+
"eval_recall": 0.9504490866888687,
|
149 |
+
"eval_runtime": 13.7245,
|
150 |
+
"eval_samples_per_second": 1085.359,
|
151 |
+
"eval_steps_per_second": 2.186,
|
152 |
+
"step": 2330
|
153 |
+
}
|
154 |
+
],
|
155 |
+
"max_steps": 2330,
|
156 |
+
"num_train_epochs": 10,
|
157 |
+
"total_flos": 1.6349634872247114e+17,
|
158 |
+
"trial_name": null,
|
159 |
+
"trial_params": null
|
160 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd8a00aa1635f17eb171e09f3e680880d6cdbba456e917c1919a2eee40427010
|
3 |
+
size 3503
|