elisanchez-beep
commited on
Commit
•
a4b98bb
1
Parent(s):
89584cc
Upload 8 files
Browse files- .gitattributes +1 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +21 -0
- trainer_state.json +97 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": "ner",
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "LABEL_0",
|
16 |
+
"1": "LABEL_1",
|
17 |
+
"2": "LABEL_2"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 4096,
|
21 |
+
"label2id": {
|
22 |
+
"LABEL_0": 0,
|
23 |
+
"LABEL_1": 1,
|
24 |
+
"LABEL_2": 2
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "xlm-roberta",
|
29 |
+
"num_attention_heads": 16,
|
30 |
+
"num_hidden_layers": 24,
|
31 |
+
"output_past": true,
|
32 |
+
"pad_token_id": 1,
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.20.0",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 250002
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:554c5538acc9772548f6755c26e33b772b7b3abd67bdd22183199104eaf43eb0
|
3 |
+
size 2235512177
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 512,
|
15 |
+
"name_or_path": "xlm-roberta-large",
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"special_tokens_map_file": null,
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7399236317352567,
|
3 |
+
"best_model_checkpoint": "./outputs/xlm-roberta-large-output/vua_metaphor_32_0.1_0.00003_07-19-22_17-18/checkpoint-903",
|
4 |
+
"epoch": 3.998341625207297,
|
5 |
+
"global_step": 1204,
|
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 |
+
"learning_rate": 2.3952254641909816e-05,
|
13 |
+
"loss": 0.2302,
|
14 |
+
"step": 301
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.9587389893370422,
|
19 |
+
"eval_f1": 0.6235381935804927,
|
20 |
+
"eval_loss": 0.1028517335653305,
|
21 |
+
"eval_precision": 0.7607771706132362,
|
22 |
+
"eval_recall": 0.5282462057335582,
|
23 |
+
"eval_runtime": 10.4111,
|
24 |
+
"eval_samples_per_second": 231.484,
|
25 |
+
"eval_steps_per_second": 29.008,
|
26 |
+
"step": 301
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"learning_rate": 1.596816976127321e-05,
|
31 |
+
"loss": 0.0825,
|
32 |
+
"step": 602
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.9657749052333033,
|
37 |
+
"eval_f1": 0.7058823529411765,
|
38 |
+
"eval_loss": 0.08832709491252899,
|
39 |
+
"eval_precision": 0.7947229551451187,
|
40 |
+
"eval_recall": 0.6349072512647554,
|
41 |
+
"eval_runtime": 10.4364,
|
42 |
+
"eval_samples_per_second": 230.922,
|
43 |
+
"eval_steps_per_second": 28.937,
|
44 |
+
"step": 602
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"learning_rate": 7.984084880636604e-06,
|
49 |
+
"loss": 0.053,
|
50 |
+
"step": 903
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.0,
|
54 |
+
"eval_accuracy": 0.9665657639968366,
|
55 |
+
"eval_f1": 0.7399236317352567,
|
56 |
+
"eval_loss": 0.09772537648677826,
|
57 |
+
"eval_precision": 0.7446626814688301,
|
58 |
+
"eval_recall": 0.7352445193929174,
|
59 |
+
"eval_runtime": 10.4481,
|
60 |
+
"eval_samples_per_second": 230.664,
|
61 |
+
"eval_steps_per_second": 28.905,
|
62 |
+
"step": 903
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.0,
|
66 |
+
"learning_rate": 0.0,
|
67 |
+
"loss": 0.0302,
|
68 |
+
"step": 1204
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 4.0,
|
72 |
+
"eval_accuracy": 0.9673838937522158,
|
73 |
+
"eval_f1": 0.7341040462427745,
|
74 |
+
"eval_loss": 0.11126415431499481,
|
75 |
+
"eval_precision": 0.7765757290686736,
|
76 |
+
"eval_recall": 0.6960370994940978,
|
77 |
+
"eval_runtime": 10.506,
|
78 |
+
"eval_samples_per_second": 229.394,
|
79 |
+
"eval_steps_per_second": 28.746,
|
80 |
+
"step": 1204
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.0,
|
84 |
+
"step": 1204,
|
85 |
+
"total_flos": 4407052490588292.0,
|
86 |
+
"train_loss": 0.0989648171041495,
|
87 |
+
"train_runtime": 907.5206,
|
88 |
+
"train_samples_per_second": 42.459,
|
89 |
+
"train_steps_per_second": 1.327
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"max_steps": 1204,
|
93 |
+
"num_train_epochs": 4,
|
94 |
+
"total_flos": 4407052490588292.0,
|
95 |
+
"trial_name": null,
|
96 |
+
"trial_params": null
|
97 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9bf497afbb89a829244609804a72cf2acc6b079da90fc77cf53eb4c66cfd685
|
3 |
+
size 3311
|