Upload 11 files
Browse files- .gitattributes +1 -0
- config.json +132 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
- trainer_state.json +106 -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 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "liaad/srl-enpt_xlmr-base",
|
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": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "r0:arg0",
|
16 |
+
"2": "r0:arg1",
|
17 |
+
"3": "r0:arg2",
|
18 |
+
"4": "r0:root",
|
19 |
+
"5": "r10:arg0",
|
20 |
+
"6": "r10:arg1",
|
21 |
+
"7": "r10:root",
|
22 |
+
"8": "r11:arg0",
|
23 |
+
"9": "r11:root",
|
24 |
+
"10": "r12:arg1",
|
25 |
+
"11": "r12:root",
|
26 |
+
"12": "r13:arg1",
|
27 |
+
"13": "r13:root",
|
28 |
+
"14": "r1:arg0",
|
29 |
+
"15": "r1:arg1",
|
30 |
+
"16": "r1:arg2",
|
31 |
+
"17": "r1:root",
|
32 |
+
"18": "r2:arg0",
|
33 |
+
"19": "r2:arg1",
|
34 |
+
"20": "r2:arg2",
|
35 |
+
"21": "r2:root",
|
36 |
+
"22": "r3:arg0",
|
37 |
+
"23": "r3:arg1",
|
38 |
+
"24": "r3:arg2",
|
39 |
+
"25": "r3:root",
|
40 |
+
"26": "r4:arg0",
|
41 |
+
"27": "r4:arg1",
|
42 |
+
"28": "r4:arg2",
|
43 |
+
"29": "r4:root",
|
44 |
+
"30": "r5:arg0",
|
45 |
+
"31": "r5:arg1",
|
46 |
+
"32": "r5:arg2",
|
47 |
+
"33": "r5:root",
|
48 |
+
"34": "r6:arg0",
|
49 |
+
"35": "r6:arg1",
|
50 |
+
"36": "r6:arg2",
|
51 |
+
"37": "r6:root",
|
52 |
+
"38": "r7:arg0",
|
53 |
+
"39": "r7:arg1",
|
54 |
+
"40": "r7:arg2",
|
55 |
+
"41": "r7:root",
|
56 |
+
"42": "r8:arg0",
|
57 |
+
"43": "r8:arg1",
|
58 |
+
"44": "r8:arg2",
|
59 |
+
"45": "r8:root",
|
60 |
+
"46": "r9:arg0",
|
61 |
+
"47": "r9:arg1",
|
62 |
+
"48": "r9:arg2",
|
63 |
+
"49": "r9:root"
|
64 |
+
},
|
65 |
+
"initializer_range": 0.02,
|
66 |
+
"intermediate_size": 3072,
|
67 |
+
"label2id": {
|
68 |
+
"O": 0,
|
69 |
+
"r0:arg0": 1,
|
70 |
+
"r0:arg1": 2,
|
71 |
+
"r0:arg2": 3,
|
72 |
+
"r0:root": 4,
|
73 |
+
"r10:arg0": 5,
|
74 |
+
"r10:arg1": 6,
|
75 |
+
"r10:root": 7,
|
76 |
+
"r11:arg0": 8,
|
77 |
+
"r11:root": 9,
|
78 |
+
"r12:arg1": 10,
|
79 |
+
"r12:root": 11,
|
80 |
+
"r13:arg1": 12,
|
81 |
+
"r13:root": 13,
|
82 |
+
"r1:arg0": 14,
|
83 |
+
"r1:arg1": 15,
|
84 |
+
"r1:arg2": 16,
|
85 |
+
"r1:root": 17,
|
86 |
+
"r2:arg0": 18,
|
87 |
+
"r2:arg1": 19,
|
88 |
+
"r2:arg2": 20,
|
89 |
+
"r2:root": 21,
|
90 |
+
"r3:arg0": 22,
|
91 |
+
"r3:arg1": 23,
|
92 |
+
"r3:arg2": 24,
|
93 |
+
"r3:root": 25,
|
94 |
+
"r4:arg0": 26,
|
95 |
+
"r4:arg1": 27,
|
96 |
+
"r4:arg2": 28,
|
97 |
+
"r4:root": 29,
|
98 |
+
"r5:arg0": 30,
|
99 |
+
"r5:arg1": 31,
|
100 |
+
"r5:arg2": 32,
|
101 |
+
"r5:root": 33,
|
102 |
+
"r6:arg0": 34,
|
103 |
+
"r6:arg1": 35,
|
104 |
+
"r6:arg2": 36,
|
105 |
+
"r6:root": 37,
|
106 |
+
"r7:arg0": 38,
|
107 |
+
"r7:arg1": 39,
|
108 |
+
"r7:arg2": 40,
|
109 |
+
"r7:root": 41,
|
110 |
+
"r8:arg0": 42,
|
111 |
+
"r8:arg1": 43,
|
112 |
+
"r8:arg2": 44,
|
113 |
+
"r8:root": 45,
|
114 |
+
"r9:arg0": 46,
|
115 |
+
"r9:arg1": 47,
|
116 |
+
"r9:arg2": 48,
|
117 |
+
"r9:root": 49
|
118 |
+
},
|
119 |
+
"layer_norm_eps": 1e-05,
|
120 |
+
"max_position_embeddings": 514,
|
121 |
+
"model_type": "xlm-roberta",
|
122 |
+
"num_attention_heads": 12,
|
123 |
+
"num_hidden_layers": 12,
|
124 |
+
"output_past": true,
|
125 |
+
"pad_token_id": 1,
|
126 |
+
"position_embedding_type": "absolute",
|
127 |
+
"torch_dtype": "float32",
|
128 |
+
"transformers_version": "4.27.4",
|
129 |
+
"type_vocab_size": 2,
|
130 |
+
"use_cache": true,
|
131 |
+
"vocab_size": 250002
|
132 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3ec50b331c87a2c313f2c88e22bcd8a351c9521b7c8bcbb6c50f6c481f156b2
|
3 |
+
size 2220053605
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c3ed27f27193763719bfd990291d0a0424ffb5a0457f5f535c3d9607ce5cdb4
|
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 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pad_token": "<pad>",
|
15 |
+
"sep_token": "</s>",
|
16 |
+
"sp_model_kwargs": {},
|
17 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--liaad--srl-enpt_xlmr-base/snapshots/da8cf09e9d7ec9758e2531387b3003114cf9cd9b/special_tokens_map.json",
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.31592875719070435,
|
3 |
+
"best_model_checkpoint": "gal_enpt_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": 0.8747239941118744,
|
13 |
+
"eval_f1": 0.5165929203539823,
|
14 |
+
"eval_loss": 0.46114709973335266,
|
15 |
+
"eval_precision": 0.5705061082024433,
|
16 |
+
"eval_recall": 0.47198960438925786,
|
17 |
+
"eval_runtime": 5.1534,
|
18 |
+
"eval_samples_per_second": 193.466,
|
19 |
+
"eval_steps_per_second": 12.225,
|
20 |
+
"step": 250
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"learning_rate": 1.9600000000000002e-05,
|
25 |
+
"loss": 0.6032,
|
26 |
+
"step": 500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"eval_accuracy": 0.9003618743866536,
|
31 |
+
"eval_f1": 0.6379219210148759,
|
32 |
+
"eval_loss": 0.35644981265068054,
|
33 |
+
"eval_precision": 0.6686718378977363,
|
34 |
+
"eval_recall": 0.6098758302050246,
|
35 |
+
"eval_runtime": 5.0374,
|
36 |
+
"eval_samples_per_second": 197.92,
|
37 |
+
"eval_steps_per_second": 12.507,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"eval_accuracy": 0.8970191364082434,
|
43 |
+
"eval_f1": 0.6530527481655822,
|
44 |
+
"eval_loss": 0.3476572632789612,
|
45 |
+
"eval_precision": 0.6272606382978724,
|
46 |
+
"eval_recall": 0.6810568870921166,
|
47 |
+
"eval_runtime": 5.0473,
|
48 |
+
"eval_samples_per_second": 197.53,
|
49 |
+
"eval_steps_per_second": 12.482,
|
50 |
+
"step": 750
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"learning_rate": 1.9200000000000003e-05,
|
55 |
+
"loss": 0.295,
|
56 |
+
"step": 1000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_accuracy": 0.9082127085377821,
|
61 |
+
"eval_f1": 0.6739380022962113,
|
62 |
+
"eval_loss": 0.3241439461708069,
|
63 |
+
"eval_precision": 0.6699001426533524,
|
64 |
+
"eval_recall": 0.678024833958995,
|
65 |
+
"eval_runtime": 5.0718,
|
66 |
+
"eval_samples_per_second": 196.577,
|
67 |
+
"eval_steps_per_second": 12.422,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"eval_accuracy": 0.9141928361138371,
|
73 |
+
"eval_f1": 0.6944585663446875,
|
74 |
+
"eval_loss": 0.31592875719070435,
|
75 |
+
"eval_precision": 0.6986701739003361,
|
76 |
+
"eval_recall": 0.690297429974011,
|
77 |
+
"eval_runtime": 5.2185,
|
78 |
+
"eval_samples_per_second": 191.053,
|
79 |
+
"eval_steps_per_second": 12.073,
|
80 |
+
"step": 1250
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 6.0,
|
84 |
+
"learning_rate": 1.88e-05,
|
85 |
+
"loss": 0.2208,
|
86 |
+
"step": 1500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 6.0,
|
90 |
+
"eval_accuracy": 0.9090100588812562,
|
91 |
+
"eval_f1": 0.6787516883486174,
|
92 |
+
"eval_loss": 0.3298513889312744,
|
93 |
+
"eval_precision": 0.6685338187928862,
|
94 |
+
"eval_recall": 0.6892867455963038,
|
95 |
+
"eval_runtime": 5.1124,
|
96 |
+
"eval_samples_per_second": 195.015,
|
97 |
+
"eval_steps_per_second": 12.323,
|
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 sha256:3a18d1c254f175fc584630799625e2e6bfeec2522ef70a979ca9ff0c48c92683
|
3 |
+
size 3503
|