bikashpatra
commited on
Commit
•
5dfa342
1
Parent(s):
36e76d0
Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-64/config.json +105 -0
- checkpoint-64/model.safetensors +3 -0
- checkpoint-64/optimizer.pt +3 -0
- checkpoint-64/rng_state.pth +3 -0
- checkpoint-64/scheduler.pt +3 -0
- checkpoint-64/trainer_state.json +201 -0
- checkpoint-64/training_args.bin +3 -0
- config.json +105 -0
- model.safetensors +3 -0
- runs/Jul25_05-11-33_r-bikashpatra-argilla-ds-train-iqtz0wo5-25785-ytq5e/events.out.tfevents.1721884294.r-bikashpatra-argilla-ds-train-iqtz0wo5-25785-ytq5e.75.0 +2 -2
- runs/Jul25_05-11-33_r-bikashpatra-argilla-ds-train-iqtz0wo5-25785-ytq5e/events.out.tfevents.1721884321.r-bikashpatra-argilla-ds-train-iqtz0wo5-25785-ytq5e.75.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- token-classification
|
6 |
+
base_model: google-bert/bert-base-uncased
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
datasets:
|
10 |
+
- bikashpatra/claims_token_classification
|
11 |
+
---
|
12 |
+
|
13 |
+
# Model Trained Using AutoTrain
|
14 |
+
|
15 |
+
- Problem type: Token Classification
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
loss: 5.530978679656982
|
19 |
+
|
20 |
+
precision: 0.0
|
21 |
+
|
22 |
+
recall: 0.0
|
23 |
+
|
24 |
+
f1: 0.0
|
25 |
+
|
26 |
+
accuracy: 0.0026870229007633587
|
checkpoint-64/config.json
ADDED
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 37,
|
4 |
+
"architectures": [
|
5 |
+
"BertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B-Apparatus",
|
15 |
+
"1": "B-Chemical Compound",
|
16 |
+
"2": "I-Algorithm",
|
17 |
+
"3": "B-Product",
|
18 |
+
"4": "B-Composition of Matter",
|
19 |
+
"5": "B-Machine",
|
20 |
+
"6": "B-Algorithm",
|
21 |
+
"7": "B-Biotechnology",
|
22 |
+
"8": "B-Process",
|
23 |
+
"9": "I-Electrical Circuit",
|
24 |
+
"10": "I-Manufacture",
|
25 |
+
"11": "B-Electrical Circuit",
|
26 |
+
"12": "O",
|
27 |
+
"13": "I-Software",
|
28 |
+
"14": "I-Composition of Matter",
|
29 |
+
"15": "I-Pharmaceutical Formulation",
|
30 |
+
"16": "I-System",
|
31 |
+
"17": "I-Hardware",
|
32 |
+
"18": "I-Biotechnology",
|
33 |
+
"19": "B-Device",
|
34 |
+
"20": "B-Pharmaceutical Formulation",
|
35 |
+
"21": "I-Product",
|
36 |
+
"22": "I-Machine",
|
37 |
+
"23": "B-Hardware",
|
38 |
+
"24": "B-System",
|
39 |
+
"25": "B-Software",
|
40 |
+
"26": "I-Device",
|
41 |
+
"27": "B-Design",
|
42 |
+
"28": "I-Design",
|
43 |
+
"29": "I-Process",
|
44 |
+
"30": "I-Chemical Compound",
|
45 |
+
"31": "B-Method of Use",
|
46 |
+
"32": "I-Apparatus",
|
47 |
+
"33": "I-Method of Use",
|
48 |
+
"34": "B-Method",
|
49 |
+
"35": "B-Manufacture",
|
50 |
+
"36": "I-Method"
|
51 |
+
},
|
52 |
+
"initializer_range": 0.02,
|
53 |
+
"intermediate_size": 3072,
|
54 |
+
"label2id": {
|
55 |
+
"B-Algorithm": 6,
|
56 |
+
"B-Apparatus": 0,
|
57 |
+
"B-Biotechnology": 7,
|
58 |
+
"B-Chemical Compound": 1,
|
59 |
+
"B-Composition of Matter": 4,
|
60 |
+
"B-Design": 27,
|
61 |
+
"B-Device": 19,
|
62 |
+
"B-Electrical Circuit": 11,
|
63 |
+
"B-Hardware": 23,
|
64 |
+
"B-Machine": 5,
|
65 |
+
"B-Manufacture": 35,
|
66 |
+
"B-Method": 34,
|
67 |
+
"B-Method of Use": 31,
|
68 |
+
"B-Pharmaceutical Formulation": 20,
|
69 |
+
"B-Process": 8,
|
70 |
+
"B-Product": 3,
|
71 |
+
"B-Software": 25,
|
72 |
+
"B-System": 24,
|
73 |
+
"I-Algorithm": 2,
|
74 |
+
"I-Apparatus": 32,
|
75 |
+
"I-Biotechnology": 18,
|
76 |
+
"I-Chemical Compound": 30,
|
77 |
+
"I-Composition of Matter": 14,
|
78 |
+
"I-Design": 28,
|
79 |
+
"I-Device": 26,
|
80 |
+
"I-Electrical Circuit": 9,
|
81 |
+
"I-Hardware": 17,
|
82 |
+
"I-Machine": 22,
|
83 |
+
"I-Manufacture": 10,
|
84 |
+
"I-Method": 36,
|
85 |
+
"I-Method of Use": 33,
|
86 |
+
"I-Pharmaceutical Formulation": 15,
|
87 |
+
"I-Process": 29,
|
88 |
+
"I-Product": 21,
|
89 |
+
"I-Software": 13,
|
90 |
+
"I-System": 16,
|
91 |
+
"O": 12
|
92 |
+
},
|
93 |
+
"layer_norm_eps": 1e-12,
|
94 |
+
"max_position_embeddings": 512,
|
95 |
+
"model_type": "bert",
|
96 |
+
"num_attention_heads": 12,
|
97 |
+
"num_hidden_layers": 12,
|
98 |
+
"pad_token_id": 0,
|
99 |
+
"position_embedding_type": "absolute",
|
100 |
+
"torch_dtype": "float32",
|
101 |
+
"transformers_version": "4.43.1",
|
102 |
+
"type_vocab_size": 2,
|
103 |
+
"use_cache": true,
|
104 |
+
"vocab_size": 30522
|
105 |
+
}
|
checkpoint-64/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:529da2609ef1b81aad84e36c60f9f930350c2b4e8c00c313e854345480df6dcf
|
3 |
+
size 435703748
|
checkpoint-64/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:061b98b34abdd41730ae03d2edb482822112d86fc8e83e37baa894157122f107
|
3 |
+
size 871527226
|
checkpoint-64/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c21a74bdfd38d8b7666387a0f90a7e511f9b4a7d3dc76d66c8167e372f0106d2
|
3 |
+
size 14244
|
checkpoint-64/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85a8006e7634cff31754bd13b32eede2d71c85280f7942cea6b29f79d9ae354c
|
3 |
+
size 1064
|
checkpoint-64/trainer_state.json
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 5.530978679656982,
|
3 |
+
"best_model_checkpoint": "autotrain-r8zdq-nww6o/checkpoint-64",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 64,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.046875,
|
13 |
+
"grad_norm": 15.872576713562012,
|
14 |
+
"learning_rate": 2.5e-06,
|
15 |
+
"loss": 4.0459,
|
16 |
+
"step": 3
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09375,
|
20 |
+
"grad_norm": 14.468564987182617,
|
21 |
+
"learning_rate": 1e-05,
|
22 |
+
"loss": 3.8906,
|
23 |
+
"step": 6
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.140625,
|
27 |
+
"grad_norm": 12.806556701660156,
|
28 |
+
"learning_rate": 1.75e-05,
|
29 |
+
"loss": 3.1036,
|
30 |
+
"step": 9
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1875,
|
34 |
+
"grad_norm": 7.326994895935059,
|
35 |
+
"learning_rate": 2.5e-05,
|
36 |
+
"loss": 2.1466,
|
37 |
+
"step": 12
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.234375,
|
41 |
+
"grad_norm": 2.5583295822143555,
|
42 |
+
"learning_rate": 3.2500000000000004e-05,
|
43 |
+
"loss": 1.7102,
|
44 |
+
"step": 15
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.28125,
|
48 |
+
"grad_norm": 3.5812530517578125,
|
49 |
+
"learning_rate": 4e-05,
|
50 |
+
"loss": 1.5867,
|
51 |
+
"step": 18
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.328125,
|
55 |
+
"grad_norm": 1.4613455533981323,
|
56 |
+
"learning_rate": 4.75e-05,
|
57 |
+
"loss": 1.3785,
|
58 |
+
"step": 21
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.375,
|
62 |
+
"grad_norm": 3.1722567081451416,
|
63 |
+
"learning_rate": 4.941860465116279e-05,
|
64 |
+
"loss": 1.4526,
|
65 |
+
"step": 24
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.421875,
|
69 |
+
"grad_norm": 3.3172366619110107,
|
70 |
+
"learning_rate": 4.854651162790698e-05,
|
71 |
+
"loss": 1.3307,
|
72 |
+
"step": 27
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.46875,
|
76 |
+
"grad_norm": 2.2563154697418213,
|
77 |
+
"learning_rate": 4.7674418604651164e-05,
|
78 |
+
"loss": 1.4428,
|
79 |
+
"step": 30
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.515625,
|
83 |
+
"grad_norm": 2.1187117099761963,
|
84 |
+
"learning_rate": 4.680232558139535e-05,
|
85 |
+
"loss": 1.4933,
|
86 |
+
"step": 33
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5625,
|
90 |
+
"grad_norm": 3.107919931411743,
|
91 |
+
"learning_rate": 4.593023255813954e-05,
|
92 |
+
"loss": 1.3909,
|
93 |
+
"step": 36
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.609375,
|
97 |
+
"grad_norm": 2.8481452465057373,
|
98 |
+
"learning_rate": 4.505813953488372e-05,
|
99 |
+
"loss": 1.4789,
|
100 |
+
"step": 39
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.65625,
|
104 |
+
"grad_norm": 1.2975138425827026,
|
105 |
+
"learning_rate": 4.418604651162791e-05,
|
106 |
+
"loss": 1.3402,
|
107 |
+
"step": 42
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.703125,
|
111 |
+
"grad_norm": 2.2250919342041016,
|
112 |
+
"learning_rate": 4.3313953488372096e-05,
|
113 |
+
"loss": 1.5143,
|
114 |
+
"step": 45
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.75,
|
118 |
+
"grad_norm": 1.7821475267410278,
|
119 |
+
"learning_rate": 4.2441860465116276e-05,
|
120 |
+
"loss": 1.2815,
|
121 |
+
"step": 48
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.796875,
|
125 |
+
"grad_norm": 1.3603293895721436,
|
126 |
+
"learning_rate": 4.156976744186047e-05,
|
127 |
+
"loss": 1.2912,
|
128 |
+
"step": 51
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.84375,
|
132 |
+
"grad_norm": 1.1273295879364014,
|
133 |
+
"learning_rate": 4.0697674418604655e-05,
|
134 |
+
"loss": 1.3891,
|
135 |
+
"step": 54
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.890625,
|
139 |
+
"grad_norm": 1.2710983753204346,
|
140 |
+
"learning_rate": 3.9825581395348835e-05,
|
141 |
+
"loss": 1.4103,
|
142 |
+
"step": 57
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.9375,
|
146 |
+
"grad_norm": 1.6584129333496094,
|
147 |
+
"learning_rate": 3.895348837209303e-05,
|
148 |
+
"loss": 1.4676,
|
149 |
+
"step": 60
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.984375,
|
153 |
+
"grad_norm": 1.8036679029464722,
|
154 |
+
"learning_rate": 3.8081395348837215e-05,
|
155 |
+
"loss": 1.3896,
|
156 |
+
"step": 63
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.0,
|
160 |
+
"eval_accuracy": 0.0026870229007633587,
|
161 |
+
"eval_f1": 0.0,
|
162 |
+
"eval_loss": 5.530978679656982,
|
163 |
+
"eval_precision": 0.0,
|
164 |
+
"eval_recall": 0.0,
|
165 |
+
"eval_runtime": 0.3581,
|
166 |
+
"eval_samples_per_second": 388.142,
|
167 |
+
"eval_steps_per_second": 25.132,
|
168 |
+
"step": 64
|
169 |
+
}
|
170 |
+
],
|
171 |
+
"logging_steps": 3,
|
172 |
+
"max_steps": 192,
|
173 |
+
"num_input_tokens_seen": 0,
|
174 |
+
"num_train_epochs": 3,
|
175 |
+
"save_steps": 500,
|
176 |
+
"stateful_callbacks": {
|
177 |
+
"EarlyStoppingCallback": {
|
178 |
+
"args": {
|
179 |
+
"early_stopping_patience": 5,
|
180 |
+
"early_stopping_threshold": 0.01
|
181 |
+
},
|
182 |
+
"attributes": {
|
183 |
+
"early_stopping_patience_counter": 0
|
184 |
+
}
|
185 |
+
},
|
186 |
+
"TrainerControl": {
|
187 |
+
"args": {
|
188 |
+
"should_epoch_stop": false,
|
189 |
+
"should_evaluate": false,
|
190 |
+
"should_log": false,
|
191 |
+
"should_save": true,
|
192 |
+
"should_training_stop": false
|
193 |
+
},
|
194 |
+
"attributes": {}
|
195 |
+
}
|
196 |
+
},
|
197 |
+
"total_flos": 33260533691136.0,
|
198 |
+
"train_batch_size": 8,
|
199 |
+
"trial_name": null,
|
200 |
+
"trial_params": null
|
201 |
+
}
|
checkpoint-64/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8a5084cd13493a32e16d73cc0a3e059a4dfed355ffd86c4aaef5c6776a156d
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 37,
|
4 |
+
"architectures": [
|
5 |
+
"BertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B-Apparatus",
|
15 |
+
"1": "B-Chemical Compound",
|
16 |
+
"2": "I-Algorithm",
|
17 |
+
"3": "B-Product",
|
18 |
+
"4": "B-Composition of Matter",
|
19 |
+
"5": "B-Machine",
|
20 |
+
"6": "B-Algorithm",
|
21 |
+
"7": "B-Biotechnology",
|
22 |
+
"8": "B-Process",
|
23 |
+
"9": "I-Electrical Circuit",
|
24 |
+
"10": "I-Manufacture",
|
25 |
+
"11": "B-Electrical Circuit",
|
26 |
+
"12": "O",
|
27 |
+
"13": "I-Software",
|
28 |
+
"14": "I-Composition of Matter",
|
29 |
+
"15": "I-Pharmaceutical Formulation",
|
30 |
+
"16": "I-System",
|
31 |
+
"17": "I-Hardware",
|
32 |
+
"18": "I-Biotechnology",
|
33 |
+
"19": "B-Device",
|
34 |
+
"20": "B-Pharmaceutical Formulation",
|
35 |
+
"21": "I-Product",
|
36 |
+
"22": "I-Machine",
|
37 |
+
"23": "B-Hardware",
|
38 |
+
"24": "B-System",
|
39 |
+
"25": "B-Software",
|
40 |
+
"26": "I-Device",
|
41 |
+
"27": "B-Design",
|
42 |
+
"28": "I-Design",
|
43 |
+
"29": "I-Process",
|
44 |
+
"30": "I-Chemical Compound",
|
45 |
+
"31": "B-Method of Use",
|
46 |
+
"32": "I-Apparatus",
|
47 |
+
"33": "I-Method of Use",
|
48 |
+
"34": "B-Method",
|
49 |
+
"35": "B-Manufacture",
|
50 |
+
"36": "I-Method"
|
51 |
+
},
|
52 |
+
"initializer_range": 0.02,
|
53 |
+
"intermediate_size": 3072,
|
54 |
+
"label2id": {
|
55 |
+
"B-Algorithm": 6,
|
56 |
+
"B-Apparatus": 0,
|
57 |
+
"B-Biotechnology": 7,
|
58 |
+
"B-Chemical Compound": 1,
|
59 |
+
"B-Composition of Matter": 4,
|
60 |
+
"B-Design": 27,
|
61 |
+
"B-Device": 19,
|
62 |
+
"B-Electrical Circuit": 11,
|
63 |
+
"B-Hardware": 23,
|
64 |
+
"B-Machine": 5,
|
65 |
+
"B-Manufacture": 35,
|
66 |
+
"B-Method": 34,
|
67 |
+
"B-Method of Use": 31,
|
68 |
+
"B-Pharmaceutical Formulation": 20,
|
69 |
+
"B-Process": 8,
|
70 |
+
"B-Product": 3,
|
71 |
+
"B-Software": 25,
|
72 |
+
"B-System": 24,
|
73 |
+
"I-Algorithm": 2,
|
74 |
+
"I-Apparatus": 32,
|
75 |
+
"I-Biotechnology": 18,
|
76 |
+
"I-Chemical Compound": 30,
|
77 |
+
"I-Composition of Matter": 14,
|
78 |
+
"I-Design": 28,
|
79 |
+
"I-Device": 26,
|
80 |
+
"I-Electrical Circuit": 9,
|
81 |
+
"I-Hardware": 17,
|
82 |
+
"I-Machine": 22,
|
83 |
+
"I-Manufacture": 10,
|
84 |
+
"I-Method": 36,
|
85 |
+
"I-Method of Use": 33,
|
86 |
+
"I-Pharmaceutical Formulation": 15,
|
87 |
+
"I-Process": 29,
|
88 |
+
"I-Product": 21,
|
89 |
+
"I-Software": 13,
|
90 |
+
"I-System": 16,
|
91 |
+
"O": 12
|
92 |
+
},
|
93 |
+
"layer_norm_eps": 1e-12,
|
94 |
+
"max_position_embeddings": 512,
|
95 |
+
"model_type": "bert",
|
96 |
+
"num_attention_heads": 12,
|
97 |
+
"num_hidden_layers": 12,
|
98 |
+
"pad_token_id": 0,
|
99 |
+
"position_embedding_type": "absolute",
|
100 |
+
"torch_dtype": "float32",
|
101 |
+
"transformers_version": "4.43.1",
|
102 |
+
"type_vocab_size": 2,
|
103 |
+
"use_cache": true,
|
104 |
+
"vocab_size": 30522
|
105 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:529da2609ef1b81aad84e36c60f9f930350c2b4e8c00c313e854345480df6dcf
|
3 |
+
size 435703748
|
runs/Jul25_05-11-33_r-bikashpatra-argilla-ds-train-iqtz0wo5-25785-ytq5e/events.out.tfevents.1721884294.r-bikashpatra-argilla-ds-train-iqtz0wo5-25785-ytq5e.75.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7328bf4912fd18ae51dae8ced5ac6203e3c32a8bfd5c483e66aa5fae130aff61
|
3 |
+
size 21994
|
runs/Jul25_05-11-33_r-bikashpatra-argilla-ds-train-iqtz0wo5-25785-ytq5e/events.out.tfevents.1721884321.r-bikashpatra-argilla-ds-train-iqtz0wo5-25785-ytq5e.75.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cda4e03a9ba0ca0e9caad42cab05e03e3acd5bbc0eef328738357fe63826b4b5
|
3 |
+
size 560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8a5084cd13493a32e16d73cc0a3e059a4dfed355ffd86c4aaef5c6776a156d
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "bikashpatra/claims_token_classification",
|
3 |
+
"model": "google-bert/bert-base-uncased",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"tokens_column": "tokens",
|
18 |
+
"tags_column": "ner_tags",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "autotrain-r8zdq-nww6o",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "bikashpatra",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|