Md Mushfiqur Rahman
commited on
Commit
•
5402c14
1
Parent(s):
05002ad
Upload with huggingface_hub
Browse files- README.md +15 -0
- all_results.json +26 -0
- config.json +53 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_predictions.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +409 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- canine
|
5 |
+
- pretrained-on-english-language
|
6 |
+
---
|
7 |
+
|
8 |
+
### How to use
|
9 |
+
|
10 |
+
Here is how to use this model:
|
11 |
+
|
12 |
+
```python
|
13 |
+
from transformers import CanineModel
|
14 |
+
model = CanineModel.from_pretrained('mushfiqur11/<repo name>')
|
15 |
+
```
|
all_results.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 81.82,
|
3 |
+
"eval_accuracy_score": 0.9655789618614897,
|
4 |
+
"eval_f1": 0.8729121278140886,
|
5 |
+
"eval_loss": 0.2113661915063858,
|
6 |
+
"eval_precision": 0.8549075391180654,
|
7 |
+
"eval_recall": 0.8916913946587537,
|
8 |
+
"eval_runtime": 4.2063,
|
9 |
+
"eval_samples": 300,
|
10 |
+
"eval_samples_per_second": 71.322,
|
11 |
+
"eval_steps_per_second": 9.034,
|
12 |
+
"test_accuracy_score": 0.9729378934388994,
|
13 |
+
"test_f1": 0.8639598158225199,
|
14 |
+
"test_loss": 0.20872025191783905,
|
15 |
+
"test_precision": 0.8528925619834711,
|
16 |
+
"test_recall": 0.8753180661577609,
|
17 |
+
"test_runtime": 8.4194,
|
18 |
+
"test_samples": 604,
|
19 |
+
"test_samples_per_second": 71.739,
|
20 |
+
"test_steps_per_second": 9.027,
|
21 |
+
"train_loss": 0.015092053589997469,
|
22 |
+
"train_runtime": 8361.8493,
|
23 |
+
"train_samples": 2109,
|
24 |
+
"train_samples_per_second": 57.404,
|
25 |
+
"train_steps_per_second": 1.794
|
26 |
+
}
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-DATE",
|
15 |
+
"2": "I-DATE",
|
16 |
+
"3": "B-PER",
|
17 |
+
"4": "I-PER",
|
18 |
+
"5": "B-ORG",
|
19 |
+
"6": "I-ORG",
|
20 |
+
"7": "B-LOC",
|
21 |
+
"8": "I-LOC"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"B-DATE": 1,
|
27 |
+
"B-LOC": 7,
|
28 |
+
"B-ORG": 5,
|
29 |
+
"B-PER": 3,
|
30 |
+
"I-DATE": 2,
|
31 |
+
"I-LOC": 8,
|
32 |
+
"I-ORG": 6,
|
33 |
+
"I-PER": 4,
|
34 |
+
"O": 0
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"max_position_embeddings": 512,
|
38 |
+
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"pooler_fc_size": 768,
|
43 |
+
"pooler_num_attention_heads": 12,
|
44 |
+
"pooler_num_fc_layers": 3,
|
45 |
+
"pooler_size_per_head": 128,
|
46 |
+
"pooler_type": "first_token_transform",
|
47 |
+
"position_embedding_type": "absolute",
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.17.0",
|
50 |
+
"type_vocab_size": 2,
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 119547
|
53 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05ba4e271a8ad529bc9516fd1fcadd43b9f90e92fc6e1f2d06e4f83ec3b2c7e3
|
3 |
+
size 709165101
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
test_predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_prefix_space": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,409 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8729121278140886,
|
3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-swa/checkpoint-4000",
|
4 |
+
"epoch": 81.81818181818181,
|
5 |
+
"global_step": 5400,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 3.03,
|
12 |
+
"eval_accuracy_score": 0.969571802285557,
|
13 |
+
"eval_f1": 0.8581610833927299,
|
14 |
+
"eval_loss": 0.11472320556640625,
|
15 |
+
"eval_precision": 0.8257887517146777,
|
16 |
+
"eval_recall": 0.8931750741839762,
|
17 |
+
"eval_runtime": 4.1914,
|
18 |
+
"eval_samples_per_second": 71.574,
|
19 |
+
"eval_steps_per_second": 9.066,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 6.06,
|
24 |
+
"eval_accuracy_score": 0.9607600165220983,
|
25 |
+
"eval_f1": 0.8493342676944637,
|
26 |
+
"eval_loss": 0.14969909191131592,
|
27 |
+
"eval_precision": 0.8047808764940239,
|
28 |
+
"eval_recall": 0.8991097922848664,
|
29 |
+
"eval_runtime": 4.1964,
|
30 |
+
"eval_samples_per_second": 71.491,
|
31 |
+
"eval_steps_per_second": 9.055,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 7.58,
|
36 |
+
"learning_rate": 4.865771812080537e-05,
|
37 |
+
"loss": 0.1339,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 9.09,
|
42 |
+
"eval_accuracy_score": 0.9611730689797604,
|
43 |
+
"eval_f1": 0.8616039744499645,
|
44 |
+
"eval_loss": 0.16909180581569672,
|
45 |
+
"eval_precision": 0.8258503401360544,
|
46 |
+
"eval_recall": 0.900593471810089,
|
47 |
+
"eval_runtime": 4.1879,
|
48 |
+
"eval_samples_per_second": 71.635,
|
49 |
+
"eval_steps_per_second": 9.074,
|
50 |
+
"step": 600
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 12.12,
|
54 |
+
"eval_accuracy_score": 0.9651659094038276,
|
55 |
+
"eval_f1": 0.8659058487874465,
|
56 |
+
"eval_loss": 0.16794395446777344,
|
57 |
+
"eval_precision": 0.8337912087912088,
|
58 |
+
"eval_recall": 0.900593471810089,
|
59 |
+
"eval_runtime": 4.1904,
|
60 |
+
"eval_samples_per_second": 71.593,
|
61 |
+
"eval_steps_per_second": 9.068,
|
62 |
+
"step": 800
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 15.15,
|
66 |
+
"learning_rate": 4.697986577181208e-05,
|
67 |
+
"loss": 0.0084,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 15.15,
|
72 |
+
"eval_accuracy_score": 0.9653035935563816,
|
73 |
+
"eval_f1": 0.8672817601135557,
|
74 |
+
"eval_loss": 0.1805761158466339,
|
75 |
+
"eval_precision": 0.8312925170068027,
|
76 |
+
"eval_recall": 0.9065281899109793,
|
77 |
+
"eval_runtime": 4.1859,
|
78 |
+
"eval_samples_per_second": 71.669,
|
79 |
+
"eval_steps_per_second": 9.078,
|
80 |
+
"step": 1000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 18.18,
|
84 |
+
"eval_accuracy_score": 0.9566294919454771,
|
85 |
+
"eval_f1": 0.8536931818181818,
|
86 |
+
"eval_loss": 0.2617969214916229,
|
87 |
+
"eval_precision": 0.8188010899182562,
|
88 |
+
"eval_recall": 0.8916913946587537,
|
89 |
+
"eval_runtime": 4.1909,
|
90 |
+
"eval_samples_per_second": 71.583,
|
91 |
+
"eval_steps_per_second": 9.067,
|
92 |
+
"step": 1200
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 21.21,
|
96 |
+
"eval_accuracy_score": 0.9686080132176786,
|
97 |
+
"eval_f1": 0.873661670235546,
|
98 |
+
"eval_loss": 0.17235662043094635,
|
99 |
+
"eval_precision": 0.8418156808803301,
|
100 |
+
"eval_recall": 0.9080118694362018,
|
101 |
+
"eval_runtime": 4.1851,
|
102 |
+
"eval_samples_per_second": 71.683,
|
103 |
+
"eval_steps_per_second": 9.08,
|
104 |
+
"step": 1400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 22.73,
|
108 |
+
"learning_rate": 4.530201342281879e-05,
|
109 |
+
"loss": 0.0044,
|
110 |
+
"step": 1500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 24.24,
|
114 |
+
"eval_accuracy_score": 0.9637890678782872,
|
115 |
+
"eval_f1": 0.875629043853343,
|
116 |
+
"eval_loss": 0.21507766842842102,
|
117 |
+
"eval_precision": 0.8493723849372385,
|
118 |
+
"eval_recall": 0.9035608308605341,
|
119 |
+
"eval_runtime": 4.1889,
|
120 |
+
"eval_samples_per_second": 71.619,
|
121 |
+
"eval_steps_per_second": 9.072,
|
122 |
+
"step": 1600
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 27.27,
|
126 |
+
"eval_accuracy_score": 0.9574555968608013,
|
127 |
+
"eval_f1": 0.8459900638750887,
|
128 |
+
"eval_loss": 0.24175740778446198,
|
129 |
+
"eval_precision": 0.8108843537414966,
|
130 |
+
"eval_recall": 0.884272997032641,
|
131 |
+
"eval_runtime": 4.1899,
|
132 |
+
"eval_samples_per_second": 71.601,
|
133 |
+
"eval_steps_per_second": 9.07,
|
134 |
+
"step": 1800
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 30.3,
|
138 |
+
"learning_rate": 4.36241610738255e-05,
|
139 |
+
"loss": 0.003,
|
140 |
+
"step": 2000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 30.3,
|
144 |
+
"eval_accuracy_score": 0.9582817017761256,
|
145 |
+
"eval_f1": 0.8468085106382979,
|
146 |
+
"eval_loss": 0.25091126561164856,
|
147 |
+
"eval_precision": 0.811141304347826,
|
148 |
+
"eval_recall": 0.8857566765578635,
|
149 |
+
"eval_runtime": 4.1982,
|
150 |
+
"eval_samples_per_second": 71.459,
|
151 |
+
"eval_steps_per_second": 9.051,
|
152 |
+
"step": 2000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 33.33,
|
156 |
+
"eval_accuracy_score": 0.9658543301665978,
|
157 |
+
"eval_f1": 0.8738284066330209,
|
158 |
+
"eval_loss": 0.225422665476799,
|
159 |
+
"eval_precision": 0.8499298737727911,
|
160 |
+
"eval_recall": 0.8991097922848664,
|
161 |
+
"eval_runtime": 4.2016,
|
162 |
+
"eval_samples_per_second": 71.402,
|
163 |
+
"eval_steps_per_second": 9.044,
|
164 |
+
"step": 2200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 36.36,
|
168 |
+
"eval_accuracy_score": 0.9669558033870301,
|
169 |
+
"eval_f1": 0.8775216138328531,
|
170 |
+
"eval_loss": 0.22372400760650635,
|
171 |
+
"eval_precision": 0.8529411764705882,
|
172 |
+
"eval_recall": 0.9035608308605341,
|
173 |
+
"eval_runtime": 4.1974,
|
174 |
+
"eval_samples_per_second": 71.472,
|
175 |
+
"eval_steps_per_second": 9.053,
|
176 |
+
"step": 2400
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 37.88,
|
180 |
+
"learning_rate": 4.194630872483222e-05,
|
181 |
+
"loss": 0.0024,
|
182 |
+
"step": 2500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 39.39,
|
186 |
+
"eval_accuracy_score": 0.9611730689797604,
|
187 |
+
"eval_f1": 0.8640915593705293,
|
188 |
+
"eval_loss": 0.23863321542739868,
|
189 |
+
"eval_precision": 0.8342541436464088,
|
190 |
+
"eval_recall": 0.8961424332344213,
|
191 |
+
"eval_runtime": 4.1973,
|
192 |
+
"eval_samples_per_second": 71.474,
|
193 |
+
"eval_steps_per_second": 9.053,
|
194 |
+
"step": 2600
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 42.42,
|
198 |
+
"eval_accuracy_score": 0.9684703290651246,
|
199 |
+
"eval_f1": 0.8781542898341744,
|
200 |
+
"eval_loss": 0.1946461945772171,
|
201 |
+
"eval_precision": 0.8541374474053296,
|
202 |
+
"eval_recall": 0.9035608308605341,
|
203 |
+
"eval_runtime": 4.1975,
|
204 |
+
"eval_samples_per_second": 71.471,
|
205 |
+
"eval_steps_per_second": 9.053,
|
206 |
+
"step": 2800
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 45.45,
|
210 |
+
"learning_rate": 4.026845637583892e-05,
|
211 |
+
"loss": 0.003,
|
212 |
+
"step": 3000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 45.45,
|
216 |
+
"eval_accuracy_score": 0.956354123640369,
|
217 |
+
"eval_f1": 0.845993031358885,
|
218 |
+
"eval_loss": 0.2664543688297272,
|
219 |
+
"eval_precision": 0.797634691195795,
|
220 |
+
"eval_recall": 0.900593471810089,
|
221 |
+
"eval_runtime": 4.1956,
|
222 |
+
"eval_samples_per_second": 71.503,
|
223 |
+
"eval_steps_per_second": 9.057,
|
224 |
+
"step": 3000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 48.48,
|
228 |
+
"eval_accuracy_score": 0.9624122263527468,
|
229 |
+
"eval_f1": 0.8711303095752341,
|
230 |
+
"eval_loss": 0.2241496741771698,
|
231 |
+
"eval_precision": 0.8461538461538461,
|
232 |
+
"eval_recall": 0.8976261127596439,
|
233 |
+
"eval_runtime": 4.2045,
|
234 |
+
"eval_samples_per_second": 71.353,
|
235 |
+
"eval_steps_per_second": 9.038,
|
236 |
+
"step": 3200
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 51.52,
|
240 |
+
"eval_accuracy_score": 0.9617238055899766,
|
241 |
+
"eval_f1": 0.8640569395017793,
|
242 |
+
"eval_loss": 0.26432353258132935,
|
243 |
+
"eval_precision": 0.8303693570451436,
|
244 |
+
"eval_recall": 0.900593471810089,
|
245 |
+
"eval_runtime": 4.2012,
|
246 |
+
"eval_samples_per_second": 71.409,
|
247 |
+
"eval_steps_per_second": 9.045,
|
248 |
+
"step": 3400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 53.03,
|
252 |
+
"learning_rate": 3.859060402684564e-05,
|
253 |
+
"loss": 0.0017,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 54.55,
|
258 |
+
"eval_accuracy_score": 0.9681949607600165,
|
259 |
+
"eval_f1": 0.8776249094858798,
|
260 |
+
"eval_loss": 0.1974426507949829,
|
261 |
+
"eval_precision": 0.8571428571428571,
|
262 |
+
"eval_recall": 0.8991097922848664,
|
263 |
+
"eval_runtime": 4.1963,
|
264 |
+
"eval_samples_per_second": 71.491,
|
265 |
+
"eval_steps_per_second": 9.056,
|
266 |
+
"step": 3600
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 57.58,
|
270 |
+
"eval_accuracy_score": 0.9624122263527468,
|
271 |
+
"eval_f1": 0.8690563277249451,
|
272 |
+
"eval_loss": 0.25220534205436707,
|
273 |
+
"eval_precision": 0.8571428571428571,
|
274 |
+
"eval_recall": 0.8813056379821959,
|
275 |
+
"eval_runtime": 4.205,
|
276 |
+
"eval_samples_per_second": 71.343,
|
277 |
+
"eval_steps_per_second": 9.037,
|
278 |
+
"step": 3800
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 60.61,
|
282 |
+
"learning_rate": 3.6912751677852356e-05,
|
283 |
+
"loss": 0.001,
|
284 |
+
"step": 4000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 60.61,
|
288 |
+
"eval_accuracy_score": 0.9655789618614897,
|
289 |
+
"eval_f1": 0.8729121278140886,
|
290 |
+
"eval_loss": 0.2113661915063858,
|
291 |
+
"eval_precision": 0.8549075391180654,
|
292 |
+
"eval_recall": 0.8916913946587537,
|
293 |
+
"eval_runtime": 4.1875,
|
294 |
+
"eval_samples_per_second": 71.642,
|
295 |
+
"eval_steps_per_second": 9.075,
|
296 |
+
"step": 4000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 63.64,
|
300 |
+
"eval_accuracy_score": 0.9625499105053008,
|
301 |
+
"eval_f1": 0.8552821997105645,
|
302 |
+
"eval_loss": 0.2266554832458496,
|
303 |
+
"eval_precision": 0.8347457627118644,
|
304 |
+
"eval_recall": 0.8768545994065282,
|
305 |
+
"eval_runtime": 4.1917,
|
306 |
+
"eval_samples_per_second": 71.57,
|
307 |
+
"eval_steps_per_second": 9.066,
|
308 |
+
"step": 4200
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 66.67,
|
312 |
+
"eval_accuracy_score": 0.969984854743219,
|
313 |
+
"eval_f1": 0.8743718592964824,
|
314 |
+
"eval_loss": 0.18208536505699158,
|
315 |
+
"eval_precision": 0.847009735744089,
|
316 |
+
"eval_recall": 0.9035608308605341,
|
317 |
+
"eval_runtime": 4.1915,
|
318 |
+
"eval_samples_per_second": 71.573,
|
319 |
+
"eval_steps_per_second": 9.066,
|
320 |
+
"step": 4400
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 68.18,
|
324 |
+
"learning_rate": 3.523489932885906e-05,
|
325 |
+
"loss": 0.0021,
|
326 |
+
"step": 4500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 69.7,
|
330 |
+
"eval_accuracy_score": 0.9551149662673826,
|
331 |
+
"eval_f1": 0.8406633020908435,
|
332 |
+
"eval_loss": 0.2883528769016266,
|
333 |
+
"eval_precision": 0.8176718092566619,
|
334 |
+
"eval_recall": 0.8649851632047477,
|
335 |
+
"eval_runtime": 4.1939,
|
336 |
+
"eval_samples_per_second": 71.533,
|
337 |
+
"eval_steps_per_second": 9.061,
|
338 |
+
"step": 4600
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 72.73,
|
342 |
+
"eval_accuracy_score": 0.9581440176235715,
|
343 |
+
"eval_f1": 0.8530050687907313,
|
344 |
+
"eval_loss": 0.2784726023674011,
|
345 |
+
"eval_precision": 0.8330975954738331,
|
346 |
+
"eval_recall": 0.8738872403560831,
|
347 |
+
"eval_runtime": 4.1999,
|
348 |
+
"eval_samples_per_second": 71.43,
|
349 |
+
"eval_steps_per_second": 9.048,
|
350 |
+
"step": 4800
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 75.76,
|
354 |
+
"learning_rate": 3.3557046979865775e-05,
|
355 |
+
"loss": 0.0017,
|
356 |
+
"step": 5000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 75.76,
|
360 |
+
"eval_accuracy_score": 0.9633760154206251,
|
361 |
+
"eval_f1": 0.8614501076812634,
|
362 |
+
"eval_loss": 0.22903957962989807,
|
363 |
+
"eval_precision": 0.8344923504867872,
|
364 |
+
"eval_recall": 0.8902077151335311,
|
365 |
+
"eval_runtime": 59.3501,
|
366 |
+
"eval_samples_per_second": 5.055,
|
367 |
+
"eval_steps_per_second": 0.64,
|
368 |
+
"step": 5000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 78.79,
|
372 |
+
"eval_accuracy_score": 0.9639267520308412,
|
373 |
+
"eval_f1": 0.8656499636891795,
|
374 |
+
"eval_loss": 0.24257344007492065,
|
375 |
+
"eval_precision": 0.8477951635846372,
|
376 |
+
"eval_recall": 0.884272997032641,
|
377 |
+
"eval_runtime": 4.1775,
|
378 |
+
"eval_samples_per_second": 71.814,
|
379 |
+
"eval_steps_per_second": 9.096,
|
380 |
+
"step": 5200
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 81.82,
|
384 |
+
"eval_accuracy_score": 0.9650282252512736,
|
385 |
+
"eval_f1": 0.868804664723032,
|
386 |
+
"eval_loss": 0.23794998228549957,
|
387 |
+
"eval_precision": 0.8538681948424068,
|
388 |
+
"eval_recall": 0.884272997032641,
|
389 |
+
"eval_runtime": 4.1803,
|
390 |
+
"eval_samples_per_second": 71.765,
|
391 |
+
"eval_steps_per_second": 9.09,
|
392 |
+
"step": 5400
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 81.82,
|
396 |
+
"step": 5400,
|
397 |
+
"total_flos": 2.254571897701939e+16,
|
398 |
+
"train_loss": 0.015092053589997469,
|
399 |
+
"train_runtime": 8361.8493,
|
400 |
+
"train_samples_per_second": 57.404,
|
401 |
+
"train_steps_per_second": 1.794
|
402 |
+
}
|
403 |
+
],
|
404 |
+
"max_steps": 15000,
|
405 |
+
"num_train_epochs": 228,
|
406 |
+
"total_flos": 2.254571897701939e+16,
|
407 |
+
"trial_name": null,
|
408 |
+
"trial_params": null
|
409 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59ac6480402076c1686db3ef506cb31193ee138ab5a30c4309b85e194607585a
|
3 |
+
size 3259
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|