Commit
•
9791534
1
Parent(s):
e5ca2be
system A checkpoint 4000
Browse files- config.json +93 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +163 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
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": "B-PER",
|
16 |
+
"10": "I-BIO",
|
17 |
+
"11": "B-CEL",
|
18 |
+
"12": "I-CEL",
|
19 |
+
"13": "B-DIS",
|
20 |
+
"14": "I-DIS",
|
21 |
+
"15": "B-EVE",
|
22 |
+
"16": "I-EVE",
|
23 |
+
"17": "B-FOOD",
|
24 |
+
"18": "I-FOOD",
|
25 |
+
"19": "B-INST",
|
26 |
+
"2": "I-PER",
|
27 |
+
"20": "I-INST",
|
28 |
+
"21": "B-MEDIA",
|
29 |
+
"22": "I-MEDIA",
|
30 |
+
"23": "B-MYTH",
|
31 |
+
"24": "I-MYTH",
|
32 |
+
"25": "B-PLANT",
|
33 |
+
"26": "I-PLANT",
|
34 |
+
"27": "B-TIME",
|
35 |
+
"28": "I-TIME",
|
36 |
+
"29": "B-VEHI",
|
37 |
+
"3": "B-ORG",
|
38 |
+
"30": "I-VEHI",
|
39 |
+
"4": "I-ORG",
|
40 |
+
"5": "B-LOC",
|
41 |
+
"6": "I-LOC",
|
42 |
+
"7": "B-ANIM",
|
43 |
+
"8": "I-ANIM",
|
44 |
+
"9": "B-BIO"
|
45 |
+
},
|
46 |
+
"initializer_range": 0.02,
|
47 |
+
"intermediate_size": 3072,
|
48 |
+
"label2id": {
|
49 |
+
"B-ANIM": 7,
|
50 |
+
"B-BIO": 9,
|
51 |
+
"B-CEL": 11,
|
52 |
+
"B-DIS": 13,
|
53 |
+
"B-EVE": 15,
|
54 |
+
"B-FOOD": 17,
|
55 |
+
"B-INST": 19,
|
56 |
+
"B-LOC": 5,
|
57 |
+
"B-MEDIA": 21,
|
58 |
+
"B-MYTH": 23,
|
59 |
+
"B-ORG": 3,
|
60 |
+
"B-PER": 1,
|
61 |
+
"B-PLANT": 25,
|
62 |
+
"B-TIME": 27,
|
63 |
+
"B-VEHI": 29,
|
64 |
+
"I-ANIM": 8,
|
65 |
+
"I-BIO": 10,
|
66 |
+
"I-CEL": 12,
|
67 |
+
"I-DIS": 14,
|
68 |
+
"I-EVE": 16,
|
69 |
+
"I-FOOD": 18,
|
70 |
+
"I-INST": 20,
|
71 |
+
"I-LOC": 6,
|
72 |
+
"I-MEDIA": 22,
|
73 |
+
"I-MYTH": 24,
|
74 |
+
"I-ORG": 4,
|
75 |
+
"I-PER": 2,
|
76 |
+
"I-PLANT": 26,
|
77 |
+
"I-TIME": 28,
|
78 |
+
"I-VEHI": 30,
|
79 |
+
"O": 0
|
80 |
+
},
|
81 |
+
"layer_norm_eps": 1e-05,
|
82 |
+
"max_position_embeddings": 514,
|
83 |
+
"model_type": "roberta",
|
84 |
+
"num_attention_heads": 12,
|
85 |
+
"num_hidden_layers": 12,
|
86 |
+
"pad_token_id": 1,
|
87 |
+
"position_embedding_type": "absolute",
|
88 |
+
"torch_dtype": "float32",
|
89 |
+
"transformers_version": "4.35.2",
|
90 |
+
"type_vocab_size": 1,
|
91 |
+
"use_cache": true,
|
92 |
+
"vocab_size": 50265
|
93 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:481e4627e3457b928a5e160578402025e42f50afe059ca5ea15f87664ab740bb
|
3 |
+
size 496339452
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bef93d8b7b99af7a81f742706115933b17eb2ca891f7577b9870e08b71499502
|
3 |
+
size 992797370
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef4877bb76af7155553bed487f45ed48cd16c815f1c6e4a5f3688a9aa56dccd8
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0acd1dd8634f9eb82171400dc990fc3f5742a8f7c08cbc9f0c189754ac18b98
|
3 |
+
size 1064
|
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
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9748964172556666,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.12,
|
13 |
+
"learning_rate": 4.879469122426869e-05,
|
14 |
+
"loss": 0.3842,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.12,
|
19 |
+
"eval_accuracy": 0.9771378667109926,
|
20 |
+
"eval_f1": 0.8381009137862535,
|
21 |
+
"eval_loss": 0.07010635733604431,
|
22 |
+
"eval_precision": 0.8681427219227129,
|
23 |
+
"eval_recall": 0.8100687377596867,
|
24 |
+
"eval_runtime": 73.0194,
|
25 |
+
"eval_samples_per_second": 224.735,
|
26 |
+
"eval_steps_per_second": 7.026,
|
27 |
+
"step": 500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.24,
|
31 |
+
"learning_rate": 4.202329360780065e-05,
|
32 |
+
"loss": 0.0597,
|
33 |
+
"step": 1000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.24,
|
37 |
+
"eval_accuracy": 0.9804913313861603,
|
38 |
+
"eval_f1": 0.8726274509803922,
|
39 |
+
"eval_loss": 0.05635998398065567,
|
40 |
+
"eval_precision": 0.8915421290917104,
|
41 |
+
"eval_recall": 0.8544986751660842,
|
42 |
+
"eval_runtime": 75.0428,
|
43 |
+
"eval_samples_per_second": 218.675,
|
44 |
+
"eval_steps_per_second": 6.836,
|
45 |
+
"step": 1000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.37,
|
49 |
+
"learning_rate": 3.525189599133261e-05,
|
50 |
+
"loss": 0.0524,
|
51 |
+
"step": 1500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.37,
|
55 |
+
"eval_accuracy": 0.9802354021387242,
|
56 |
+
"eval_f1": 0.8719290536491832,
|
57 |
+
"eval_loss": 0.05560198798775673,
|
58 |
+
"eval_precision": 0.9085119667013527,
|
59 |
+
"eval_recall": 0.8381782573633885,
|
60 |
+
"eval_runtime": 72.6323,
|
61 |
+
"eval_samples_per_second": 225.933,
|
62 |
+
"eval_steps_per_second": 7.063,
|
63 |
+
"step": 1500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.49,
|
67 |
+
"learning_rate": 2.8480498374864572e-05,
|
68 |
+
"loss": 0.0448,
|
69 |
+
"step": 2000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.49,
|
73 |
+
"eval_accuracy": 0.9826548569830427,
|
74 |
+
"eval_f1": 0.8893414799728445,
|
75 |
+
"eval_loss": 0.04828519746661186,
|
76 |
+
"eval_precision": 0.8985262992866662,
|
77 |
+
"eval_recall": 0.8803425367689413,
|
78 |
+
"eval_runtime": 74.6781,
|
79 |
+
"eval_samples_per_second": 219.743,
|
80 |
+
"eval_steps_per_second": 6.869,
|
81 |
+
"step": 2000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.61,
|
85 |
+
"learning_rate": 2.1709100758396535e-05,
|
86 |
+
"loss": 0.0433,
|
87 |
+
"step": 2500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.61,
|
91 |
+
"eval_accuracy": 0.9829266169055779,
|
92 |
+
"eval_f1": 0.8900519485573087,
|
93 |
+
"eval_loss": 0.046879906207323074,
|
94 |
+
"eval_precision": 0.902074459693958,
|
95 |
+
"eval_recall": 0.8783456856495526,
|
96 |
+
"eval_runtime": 75.3332,
|
97 |
+
"eval_samples_per_second": 217.832,
|
98 |
+
"eval_steps_per_second": 6.81,
|
99 |
+
"step": 2500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.73,
|
103 |
+
"learning_rate": 1.4937703141928494e-05,
|
104 |
+
"loss": 0.04,
|
105 |
+
"step": 3000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.73,
|
109 |
+
"eval_accuracy": 0.983201015273963,
|
110 |
+
"eval_f1": 0.8977493905780533,
|
111 |
+
"eval_loss": 0.04475250095129013,
|
112 |
+
"eval_precision": 0.8837711139221668,
|
113 |
+
"eval_recall": 0.9121769517299643,
|
114 |
+
"eval_runtime": 73.7339,
|
115 |
+
"eval_samples_per_second": 222.557,
|
116 |
+
"eval_steps_per_second": 6.957,
|
117 |
+
"step": 3000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.85,
|
121 |
+
"learning_rate": 8.166305525460455e-06,
|
122 |
+
"loss": 0.0365,
|
123 |
+
"step": 3500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.85,
|
127 |
+
"eval_accuracy": 0.9843672083395997,
|
128 |
+
"eval_f1": 0.9045125132863078,
|
129 |
+
"eval_loss": 0.04261544719338417,
|
130 |
+
"eval_precision": 0.9104419545596016,
|
131 |
+
"eval_recall": 0.8986598056910257,
|
132 |
+
"eval_runtime": 74.7052,
|
133 |
+
"eval_samples_per_second": 219.663,
|
134 |
+
"eval_steps_per_second": 6.867,
|
135 |
+
"step": 3500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.97,
|
139 |
+
"learning_rate": 1.394907908992416e-06,
|
140 |
+
"loss": 0.0366,
|
141 |
+
"step": 4000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.97,
|
145 |
+
"eval_accuracy": 0.9845123228613417,
|
146 |
+
"eval_f1": 0.9050084368768215,
|
147 |
+
"eval_loss": 0.041375741362571716,
|
148 |
+
"eval_precision": 0.9037953352992991,
|
149 |
+
"eval_recall": 0.9062247993548634,
|
150 |
+
"eval_runtime": 75.1389,
|
151 |
+
"eval_samples_per_second": 218.396,
|
152 |
+
"eval_steps_per_second": 6.827,
|
153 |
+
"step": 4000
|
154 |
+
}
|
155 |
+
],
|
156 |
+
"logging_steps": 500,
|
157 |
+
"max_steps": 4103,
|
158 |
+
"num_train_epochs": 1,
|
159 |
+
"save_steps": 500,
|
160 |
+
"total_flos": 4183330761475008.0,
|
161 |
+
"trial_name": null,
|
162 |
+
"trial_params": null
|
163 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9a9d7a58bc9223dee1d333461ebe1123ca065bf8f9aa6bbd0e7f5bb70632e31
|
3 |
+
size 4600
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|