Md Mushfiqur Rahman
commited on
Commit
•
1c0e3c4
1
Parent(s):
b4d0e69
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 +529 -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": 155.56,
|
3 |
+
"eval_accuracy_score": 0.9596923892866613,
|
4 |
+
"eval_f1": 0.7548387096774194,
|
5 |
+
"eval_loss": 0.35259804129600525,
|
6 |
+
"eval_precision": 0.7048192771084337,
|
7 |
+
"eval_recall": 0.8125,
|
8 |
+
"eval_runtime": 2.7613,
|
9 |
+
"eval_samples": 200,
|
10 |
+
"eval_samples_per_second": 72.431,
|
11 |
+
"eval_steps_per_second": 9.054,
|
12 |
+
"test_accuracy_score": 0.9636215831724418,
|
13 |
+
"test_f1": 0.7854710556186153,
|
14 |
+
"test_loss": 0.3192311227321625,
|
15 |
+
"test_precision": 0.762114537444934,
|
16 |
+
"test_recall": 0.810304449648712,
|
17 |
+
"test_runtime": 5.626,
|
18 |
+
"test_samples": 407,
|
19 |
+
"test_samples_per_second": 72.343,
|
20 |
+
"test_steps_per_second": 9.065,
|
21 |
+
"train_loss": 0.011920496485063008,
|
22 |
+
"train_runtime": 10148.142,
|
23 |
+
"train_samples": 1428,
|
24 |
+
"train_samples_per_second": 47.299,
|
25 |
+
"train_steps_per_second": 1.478
|
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 sha256:0627e325a8bcc8f7640cc9281068e0df9877d55e6655c2d4c61a31add51c6502
|
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 +1,529 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7548387096774194,
|
3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-lug/checkpoint-6000",
|
4 |
+
"epoch": 155.55555555555554,
|
5 |
+
"global_step": 7000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 4.44,
|
12 |
+
"eval_accuracy_score": 0.949085123309467,
|
13 |
+
"eval_f1": 0.7053435114503817,
|
14 |
+
"eval_loss": 0.200306236743927,
|
15 |
+
"eval_precision": 0.6294277929155313,
|
16 |
+
"eval_recall": 0.8020833333333334,
|
17 |
+
"eval_runtime": 2.7824,
|
18 |
+
"eval_samples_per_second": 71.881,
|
19 |
+
"eval_steps_per_second": 8.985,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 8.89,
|
24 |
+
"eval_accuracy_score": 0.9461681251657386,
|
25 |
+
"eval_f1": 0.6605783866057838,
|
26 |
+
"eval_loss": 0.2998030185699463,
|
27 |
+
"eval_precision": 0.5880758807588076,
|
28 |
+
"eval_recall": 0.7534722222222222,
|
29 |
+
"eval_runtime": 2.7782,
|
30 |
+
"eval_samples_per_second": 71.989,
|
31 |
+
"eval_steps_per_second": 8.999,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 11.11,
|
36 |
+
"learning_rate": 4.865771812080537e-05,
|
37 |
+
"loss": 0.1417,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 13.33,
|
42 |
+
"eval_accuracy_score": 0.9543887562980642,
|
43 |
+
"eval_f1": 0.7278382581648523,
|
44 |
+
"eval_loss": 0.2749716639518738,
|
45 |
+
"eval_precision": 0.6591549295774648,
|
46 |
+
"eval_recall": 0.8125,
|
47 |
+
"eval_runtime": 2.7787,
|
48 |
+
"eval_samples_per_second": 71.975,
|
49 |
+
"eval_steps_per_second": 8.997,
|
50 |
+
"step": 600
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 17.78,
|
54 |
+
"eval_accuracy_score": 0.9517369398037656,
|
55 |
+
"eval_f1": 0.6957878315132605,
|
56 |
+
"eval_loss": 0.30419987440109253,
|
57 |
+
"eval_precision": 0.6317280453257791,
|
58 |
+
"eval_recall": 0.7743055555555556,
|
59 |
+
"eval_runtime": 2.7786,
|
60 |
+
"eval_samples_per_second": 71.978,
|
61 |
+
"eval_steps_per_second": 8.997,
|
62 |
+
"step": 800
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 22.22,
|
66 |
+
"learning_rate": 4.697986577181208e-05,
|
67 |
+
"loss": 0.0049,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 22.22,
|
72 |
+
"eval_accuracy_score": 0.9498806682577565,
|
73 |
+
"eval_f1": 0.7075471698113208,
|
74 |
+
"eval_loss": 0.36269524693489075,
|
75 |
+
"eval_precision": 0.646551724137931,
|
76 |
+
"eval_recall": 0.78125,
|
77 |
+
"eval_runtime": 2.7801,
|
78 |
+
"eval_samples_per_second": 71.941,
|
79 |
+
"eval_steps_per_second": 8.993,
|
80 |
+
"step": 1000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 26.67,
|
84 |
+
"eval_accuracy_score": 0.9533280297003447,
|
85 |
+
"eval_f1": 0.7145135566188199,
|
86 |
+
"eval_loss": 0.36558207869529724,
|
87 |
+
"eval_precision": 0.6607669616519174,
|
88 |
+
"eval_recall": 0.7777777777777778,
|
89 |
+
"eval_runtime": 2.7791,
|
90 |
+
"eval_samples_per_second": 71.966,
|
91 |
+
"eval_steps_per_second": 8.996,
|
92 |
+
"step": 1200
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 31.11,
|
96 |
+
"eval_accuracy_score": 0.9557146645452135,
|
97 |
+
"eval_f1": 0.7142857142857142,
|
98 |
+
"eval_loss": 0.2809523344039917,
|
99 |
+
"eval_precision": 0.6847133757961783,
|
100 |
+
"eval_recall": 0.7465277777777778,
|
101 |
+
"eval_runtime": 2.7804,
|
102 |
+
"eval_samples_per_second": 71.931,
|
103 |
+
"eval_steps_per_second": 8.991,
|
104 |
+
"step": 1400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 33.33,
|
108 |
+
"learning_rate": 4.530201342281879e-05,
|
109 |
+
"loss": 0.0036,
|
110 |
+
"step": 1500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 35.56,
|
114 |
+
"eval_accuracy_score": 0.9517369398037656,
|
115 |
+
"eval_f1": 0.6644951140065147,
|
116 |
+
"eval_loss": 0.32650795578956604,
|
117 |
+
"eval_precision": 0.6257668711656442,
|
118 |
+
"eval_recall": 0.7083333333333334,
|
119 |
+
"eval_runtime": 2.7784,
|
120 |
+
"eval_samples_per_second": 71.985,
|
121 |
+
"eval_steps_per_second": 8.998,
|
122 |
+
"step": 1600
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 40.0,
|
126 |
+
"eval_accuracy_score": 0.952797666401485,
|
127 |
+
"eval_f1": 0.6910828025477705,
|
128 |
+
"eval_loss": 0.3485059440135956,
|
129 |
+
"eval_precision": 0.638235294117647,
|
130 |
+
"eval_recall": 0.7534722222222222,
|
131 |
+
"eval_runtime": 2.7769,
|
132 |
+
"eval_samples_per_second": 72.023,
|
133 |
+
"eval_steps_per_second": 9.003,
|
134 |
+
"step": 1800
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 44.44,
|
138 |
+
"learning_rate": 4.36241610738255e-05,
|
139 |
+
"loss": 0.0028,
|
140 |
+
"step": 2000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 44.44,
|
144 |
+
"eval_accuracy_score": 0.9512065765049058,
|
145 |
+
"eval_f1": 0.6754530477759474,
|
146 |
+
"eval_loss": 0.3388746678829193,
|
147 |
+
"eval_precision": 0.6426332288401254,
|
148 |
+
"eval_recall": 0.7118055555555556,
|
149 |
+
"eval_runtime": 2.7758,
|
150 |
+
"eval_samples_per_second": 72.052,
|
151 |
+
"eval_steps_per_second": 9.007,
|
152 |
+
"step": 2000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 48.89,
|
156 |
+
"eval_accuracy_score": 0.9549191195969239,
|
157 |
+
"eval_f1": 0.7112561174551387,
|
158 |
+
"eval_loss": 0.3353417217731476,
|
159 |
+
"eval_precision": 0.6707692307692308,
|
160 |
+
"eval_recall": 0.7569444444444444,
|
161 |
+
"eval_runtime": 2.7837,
|
162 |
+
"eval_samples_per_second": 71.847,
|
163 |
+
"eval_steps_per_second": 8.981,
|
164 |
+
"step": 2200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 53.33,
|
168 |
+
"eval_accuracy_score": 0.9541235746486343,
|
169 |
+
"eval_f1": 0.701095461658842,
|
170 |
+
"eval_loss": 0.3772818446159363,
|
171 |
+
"eval_precision": 0.6381766381766382,
|
172 |
+
"eval_recall": 0.7777777777777778,
|
173 |
+
"eval_runtime": 2.7767,
|
174 |
+
"eval_samples_per_second": 72.029,
|
175 |
+
"eval_steps_per_second": 9.004,
|
176 |
+
"step": 2400
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 55.56,
|
180 |
+
"learning_rate": 4.194630872483222e-05,
|
181 |
+
"loss": 0.0024,
|
182 |
+
"step": 2500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 57.78,
|
186 |
+
"eval_accuracy_score": 0.9581012993900823,
|
187 |
+
"eval_f1": 0.7302100161550888,
|
188 |
+
"eval_loss": 0.3589210510253906,
|
189 |
+
"eval_precision": 0.6827794561933535,
|
190 |
+
"eval_recall": 0.7847222222222222,
|
191 |
+
"eval_runtime": 2.7851,
|
192 |
+
"eval_samples_per_second": 71.809,
|
193 |
+
"eval_steps_per_second": 8.976,
|
194 |
+
"step": 2600
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 62.22,
|
198 |
+
"eval_accuracy_score": 0.9498806682577565,
|
199 |
+
"eval_f1": 0.7086614173228347,
|
200 |
+
"eval_loss": 0.384027361869812,
|
201 |
+
"eval_precision": 0.6484149855907781,
|
202 |
+
"eval_recall": 0.78125,
|
203 |
+
"eval_runtime": 2.7806,
|
204 |
+
"eval_samples_per_second": 71.928,
|
205 |
+
"eval_steps_per_second": 8.991,
|
206 |
+
"step": 2800
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 66.67,
|
210 |
+
"learning_rate": 4.026845637583892e-05,
|
211 |
+
"loss": 0.0018,
|
212 |
+
"step": 3000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 66.67,
|
216 |
+
"eval_accuracy_score": 0.9533280297003447,
|
217 |
+
"eval_f1": 0.7140600315955765,
|
218 |
+
"eval_loss": 0.3608270287513733,
|
219 |
+
"eval_precision": 0.6550724637681159,
|
220 |
+
"eval_recall": 0.7847222222222222,
|
221 |
+
"eval_runtime": 2.7702,
|
222 |
+
"eval_samples_per_second": 72.197,
|
223 |
+
"eval_steps_per_second": 9.025,
|
224 |
+
"step": 3000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 71.11,
|
228 |
+
"eval_accuracy_score": 0.9504110315566163,
|
229 |
+
"eval_f1": 0.6666666666666666,
|
230 |
+
"eval_loss": 0.33889251947402954,
|
231 |
+
"eval_precision": 0.6091954022988506,
|
232 |
+
"eval_recall": 0.7361111111111112,
|
233 |
+
"eval_runtime": 2.7756,
|
234 |
+
"eval_samples_per_second": 72.058,
|
235 |
+
"eval_steps_per_second": 9.007,
|
236 |
+
"step": 3200
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 75.56,
|
240 |
+
"eval_accuracy_score": 0.9559798461946434,
|
241 |
+
"eval_f1": 0.7193548387096774,
|
242 |
+
"eval_loss": 0.325101763010025,
|
243 |
+
"eval_precision": 0.6716867469879518,
|
244 |
+
"eval_recall": 0.7743055555555556,
|
245 |
+
"eval_runtime": 2.7793,
|
246 |
+
"eval_samples_per_second": 71.96,
|
247 |
+
"eval_steps_per_second": 8.995,
|
248 |
+
"step": 3400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 77.78,
|
252 |
+
"learning_rate": 3.859060402684564e-05,
|
253 |
+
"loss": 0.0017,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 80.0,
|
258 |
+
"eval_accuracy_score": 0.9543887562980642,
|
259 |
+
"eval_f1": 0.7051070840197693,
|
260 |
+
"eval_loss": 0.3474235534667969,
|
261 |
+
"eval_precision": 0.670846394984326,
|
262 |
+
"eval_recall": 0.7430555555555556,
|
263 |
+
"eval_runtime": 2.7778,
|
264 |
+
"eval_samples_per_second": 72.0,
|
265 |
+
"eval_steps_per_second": 9.0,
|
266 |
+
"step": 3600
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 84.44,
|
270 |
+
"eval_accuracy_score": 0.9554494828957836,
|
271 |
+
"eval_f1": 0.7081339712918661,
|
272 |
+
"eval_loss": 0.3440423309803009,
|
273 |
+
"eval_precision": 0.6548672566371682,
|
274 |
+
"eval_recall": 0.7708333333333334,
|
275 |
+
"eval_runtime": 2.7746,
|
276 |
+
"eval_samples_per_second": 72.083,
|
277 |
+
"eval_steps_per_second": 9.01,
|
278 |
+
"step": 3800
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 88.89,
|
282 |
+
"learning_rate": 3.6912751677852356e-05,
|
283 |
+
"loss": 0.001,
|
284 |
+
"step": 4000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 88.89,
|
288 |
+
"eval_accuracy_score": 0.9562450278440732,
|
289 |
+
"eval_f1": 0.7081967213114755,
|
290 |
+
"eval_loss": 0.34857451915740967,
|
291 |
+
"eval_precision": 0.6708074534161491,
|
292 |
+
"eval_recall": 0.75,
|
293 |
+
"eval_runtime": 2.7573,
|
294 |
+
"eval_samples_per_second": 72.535,
|
295 |
+
"eval_steps_per_second": 9.067,
|
296 |
+
"step": 4000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 93.33,
|
300 |
+
"eval_accuracy_score": 0.9573057544417927,
|
301 |
+
"eval_f1": 0.7246376811594203,
|
302 |
+
"eval_loss": 0.3356036841869354,
|
303 |
+
"eval_precision": 0.6756756756756757,
|
304 |
+
"eval_recall": 0.78125,
|
305 |
+
"eval_runtime": 2.7694,
|
306 |
+
"eval_samples_per_second": 72.219,
|
307 |
+
"eval_steps_per_second": 9.027,
|
308 |
+
"step": 4200
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 97.78,
|
312 |
+
"eval_accuracy_score": 0.9530628480509149,
|
313 |
+
"eval_f1": 0.7017543859649124,
|
314 |
+
"eval_loss": 0.37629222869873047,
|
315 |
+
"eval_precision": 0.6489675516224189,
|
316 |
+
"eval_recall": 0.7638888888888888,
|
317 |
+
"eval_runtime": 2.7682,
|
318 |
+
"eval_samples_per_second": 72.25,
|
319 |
+
"eval_steps_per_second": 9.031,
|
320 |
+
"step": 4400
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 100.0,
|
324 |
+
"learning_rate": 3.523489932885906e-05,
|
325 |
+
"loss": 0.0015,
|
326 |
+
"step": 4500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 102.22,
|
330 |
+
"eval_accuracy_score": 0.9496154866083267,
|
331 |
+
"eval_f1": 0.673170731707317,
|
332 |
+
"eval_loss": 0.3837837874889374,
|
333 |
+
"eval_precision": 0.6330275229357798,
|
334 |
+
"eval_recall": 0.71875,
|
335 |
+
"eval_runtime": 2.7764,
|
336 |
+
"eval_samples_per_second": 72.036,
|
337 |
+
"eval_steps_per_second": 9.004,
|
338 |
+
"step": 4600
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 106.67,
|
342 |
+
"eval_accuracy_score": 0.9551843012463538,
|
343 |
+
"eval_f1": 0.7251655629139072,
|
344 |
+
"eval_loss": 0.35345935821533203,
|
345 |
+
"eval_precision": 0.6930379746835443,
|
346 |
+
"eval_recall": 0.7604166666666666,
|
347 |
+
"eval_runtime": 2.7673,
|
348 |
+
"eval_samples_per_second": 72.271,
|
349 |
+
"eval_steps_per_second": 9.034,
|
350 |
+
"step": 4800
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 111.11,
|
354 |
+
"learning_rate": 3.3557046979865775e-05,
|
355 |
+
"loss": 0.0017,
|
356 |
+
"step": 5000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 111.11,
|
360 |
+
"eval_accuracy_score": 0.9588968443383717,
|
361 |
+
"eval_f1": 0.7311072056239015,
|
362 |
+
"eval_loss": 0.3115241229534149,
|
363 |
+
"eval_precision": 0.7402135231316725,
|
364 |
+
"eval_recall": 0.7222222222222222,
|
365 |
+
"eval_runtime": 2.7806,
|
366 |
+
"eval_samples_per_second": 71.926,
|
367 |
+
"eval_steps_per_second": 8.991,
|
368 |
+
"step": 5000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 115.56,
|
372 |
+
"eval_accuracy_score": 0.9599575709360912,
|
373 |
+
"eval_f1": 0.7281879194630871,
|
374 |
+
"eval_loss": 0.29021960496902466,
|
375 |
+
"eval_precision": 0.7045454545454546,
|
376 |
+
"eval_recall": 0.7534722222222222,
|
377 |
+
"eval_runtime": 2.7637,
|
378 |
+
"eval_samples_per_second": 72.368,
|
379 |
+
"eval_steps_per_second": 9.046,
|
380 |
+
"step": 5200
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 120.0,
|
384 |
+
"eval_accuracy_score": 0.9554494828957836,
|
385 |
+
"eval_f1": 0.7348242811501597,
|
386 |
+
"eval_loss": 0.37681084871292114,
|
387 |
+
"eval_precision": 0.6804733727810651,
|
388 |
+
"eval_recall": 0.7986111111111112,
|
389 |
+
"eval_runtime": 2.7807,
|
390 |
+
"eval_samples_per_second": 71.925,
|
391 |
+
"eval_steps_per_second": 8.991,
|
392 |
+
"step": 5400
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 122.22,
|
396 |
+
"learning_rate": 3.1879194630872485e-05,
|
397 |
+
"loss": 0.0013,
|
398 |
+
"step": 5500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 124.44,
|
402 |
+
"eval_accuracy_score": 0.958631662688942,
|
403 |
+
"eval_f1": 0.745928338762215,
|
404 |
+
"eval_loss": 0.33346712589263916,
|
405 |
+
"eval_precision": 0.7024539877300614,
|
406 |
+
"eval_recall": 0.7951388888888888,
|
407 |
+
"eval_runtime": 2.7673,
|
408 |
+
"eval_samples_per_second": 72.273,
|
409 |
+
"eval_steps_per_second": 9.034,
|
410 |
+
"step": 5600
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 128.89,
|
414 |
+
"eval_accuracy_score": 0.9565102094935031,
|
415 |
+
"eval_f1": 0.7249190938511326,
|
416 |
+
"eval_loss": 0.33011287450790405,
|
417 |
+
"eval_precision": 0.6787878787878788,
|
418 |
+
"eval_recall": 0.7777777777777778,
|
419 |
+
"eval_runtime": 2.7709,
|
420 |
+
"eval_samples_per_second": 72.178,
|
421 |
+
"eval_steps_per_second": 9.022,
|
422 |
+
"step": 5800
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 133.33,
|
426 |
+
"learning_rate": 3.02013422818792e-05,
|
427 |
+
"loss": 0.0009,
|
428 |
+
"step": 6000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 133.33,
|
432 |
+
"eval_accuracy_score": 0.9596923892866613,
|
433 |
+
"eval_f1": 0.7548387096774194,
|
434 |
+
"eval_loss": 0.35259804129600525,
|
435 |
+
"eval_precision": 0.7048192771084337,
|
436 |
+
"eval_recall": 0.8125,
|
437 |
+
"eval_runtime": 2.7569,
|
438 |
+
"eval_samples_per_second": 72.544,
|
439 |
+
"eval_steps_per_second": 9.068,
|
440 |
+
"step": 6000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 137.78,
|
444 |
+
"eval_accuracy_score": 0.954653937947494,
|
445 |
+
"eval_f1": 0.6905537459283388,
|
446 |
+
"eval_loss": 0.3407050371170044,
|
447 |
+
"eval_precision": 0.6503067484662577,
|
448 |
+
"eval_recall": 0.7361111111111112,
|
449 |
+
"eval_runtime": 2.7686,
|
450 |
+
"eval_samples_per_second": 72.24,
|
451 |
+
"eval_steps_per_second": 9.03,
|
452 |
+
"step": 6200
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 142.22,
|
456 |
+
"eval_accuracy_score": 0.9578361177406524,
|
457 |
+
"eval_f1": 0.7337662337662337,
|
458 |
+
"eval_loss": 0.3645722270011902,
|
459 |
+
"eval_precision": 0.6890243902439024,
|
460 |
+
"eval_recall": 0.7847222222222222,
|
461 |
+
"eval_runtime": 2.7671,
|
462 |
+
"eval_samples_per_second": 72.277,
|
463 |
+
"eval_steps_per_second": 9.035,
|
464 |
+
"step": 6400
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 144.44,
|
468 |
+
"learning_rate": 2.8523489932885905e-05,
|
469 |
+
"loss": 0.0012,
|
470 |
+
"step": 6500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 146.67,
|
474 |
+
"eval_accuracy_score": 0.9567753911429329,
|
475 |
+
"eval_f1": 0.7427652733118972,
|
476 |
+
"eval_loss": 0.3477034866809845,
|
477 |
+
"eval_precision": 0.6916167664670658,
|
478 |
+
"eval_recall": 0.8020833333333334,
|
479 |
+
"eval_runtime": 2.7617,
|
480 |
+
"eval_samples_per_second": 72.419,
|
481 |
+
"eval_steps_per_second": 9.052,
|
482 |
+
"step": 6600
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 151.11,
|
486 |
+
"eval_accuracy_score": 0.9549191195969239,
|
487 |
+
"eval_f1": 0.7156862745098039,
|
488 |
+
"eval_loss": 0.3507363796234131,
|
489 |
+
"eval_precision": 0.6759259259259259,
|
490 |
+
"eval_recall": 0.7604166666666666,
|
491 |
+
"eval_runtime": 2.7711,
|
492 |
+
"eval_samples_per_second": 72.173,
|
493 |
+
"eval_steps_per_second": 9.022,
|
494 |
+
"step": 6800
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 155.56,
|
498 |
+
"learning_rate": 2.6845637583892618e-05,
|
499 |
+
"loss": 0.0004,
|
500 |
+
"step": 7000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 155.56,
|
504 |
+
"eval_accuracy_score": 0.9557146645452135,
|
505 |
+
"eval_f1": 0.7368421052631579,
|
506 |
+
"eval_loss": 0.40961742401123047,
|
507 |
+
"eval_precision": 0.6814159292035398,
|
508 |
+
"eval_recall": 0.8020833333333334,
|
509 |
+
"eval_runtime": 2.7599,
|
510 |
+
"eval_samples_per_second": 72.467,
|
511 |
+
"eval_steps_per_second": 9.058,
|
512 |
+
"step": 7000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 155.56,
|
516 |
+
"step": 7000,
|
517 |
+
"total_flos": 2.902406748816384e+16,
|
518 |
+
"train_loss": 0.011920496485063008,
|
519 |
+
"train_runtime": 10148.142,
|
520 |
+
"train_samples_per_second": 47.299,
|
521 |
+
"train_steps_per_second": 1.478
|
522 |
+
}
|
523 |
+
],
|
524 |
+
"max_steps": 15000,
|
525 |
+
"num_train_epochs": 334,
|
526 |
+
"total_flos": 2.902406748816384e+16,
|
527 |
+
"trial_name": null,
|
528 |
+
"trial_params": null
|
529 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd36baab522a4b93c201cf39efa567c8bde4b8e17e8c0680cb43ac1699018e1
|
3 |
+
size 3259
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|