Md Mushfiqur Rahman
commited on
Commit
•
3ec1803
1
Parent(s):
a0aac2c
Upload with huggingface_hub
Browse files- README.md +15 -0
- all_results.json +26 -0
- config.json +51 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_predictions.txt +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +601 -0
- training_args.bin +3 -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": 119.4,
|
3 |
+
"eval_accuracy_score": 0.9705493924986793,
|
4 |
+
"eval_f1": 0.7951020408163265,
|
5 |
+
"eval_loss": 0.23545745015144348,
|
6 |
+
"eval_precision": 0.7867528271405493,
|
7 |
+
"eval_recall": 0.8036303630363036,
|
8 |
+
"eval_runtime": 2.4256,
|
9 |
+
"eval_samples": 306,
|
10 |
+
"eval_samples_per_second": 126.153,
|
11 |
+
"eval_steps_per_second": 16.078,
|
12 |
+
"test_accuracy_score": 0.9540281045336046,
|
13 |
+
"test_f1": 0.6339193381592555,
|
14 |
+
"test_loss": 0.36486369371414185,
|
15 |
+
"test_precision": 0.6039408866995074,
|
16 |
+
"test_recall": 0.6670293797606094,
|
17 |
+
"test_runtime": 4.735,
|
18 |
+
"test_samples": 600,
|
19 |
+
"test_samples_per_second": 126.716,
|
20 |
+
"test_steps_per_second": 15.84,
|
21 |
+
"train_loss": 0.029139109283685686,
|
22 |
+
"train_runtime": 3971.1585,
|
23 |
+
"train_samples": 2124,
|
24 |
+
"train_samples_per_second": 120.872,
|
25 |
+
"train_steps_per_second": 3.777
|
26 |
+
}
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/canine-c",
|
3 |
+
"architectures": [
|
4 |
+
"CanineForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 57344,
|
8 |
+
"downsampling_rate": 4,
|
9 |
+
"eos_token_id": 57345,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-DATE",
|
16 |
+
"2": "I-DATE",
|
17 |
+
"3": "B-PER",
|
18 |
+
"4": "I-PER",
|
19 |
+
"5": "B-ORG",
|
20 |
+
"6": "I-ORG",
|
21 |
+
"7": "B-LOC",
|
22 |
+
"8": "I-LOC"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"B-DATE": 1,
|
28 |
+
"B-LOC": 7,
|
29 |
+
"B-ORG": 5,
|
30 |
+
"B-PER": 3,
|
31 |
+
"I-DATE": 2,
|
32 |
+
"I-LOC": 8,
|
33 |
+
"I-ORG": 6,
|
34 |
+
"I-PER": 4,
|
35 |
+
"O": 0
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-12,
|
38 |
+
"local_transformer_stride": 128,
|
39 |
+
"max_position_embeddings": 16384,
|
40 |
+
"model_type": "canine",
|
41 |
+
"num_attention_heads": 12,
|
42 |
+
"num_hash_buckets": 16384,
|
43 |
+
"num_hash_functions": 8,
|
44 |
+
"num_hidden_layers": 12,
|
45 |
+
"pad_token_id": 0,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.17.0",
|
48 |
+
"type_vocab_size": 16,
|
49 |
+
"upsampling_kernel_size": 4,
|
50 |
+
"use_cache": true
|
51 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e8e0f0bc0f664d5f26447001c02b7e1092befcc5a6725d8fc51545c82da8e70
|
3 |
+
size 528594737
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
test_predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": "/home/mrahma45/.cache/huggingface/transformers/f8be97736b4765e3e8d559b4e7d4f1f531b1621150e5344b600684a27bc84e38.ab71f530366fe02e2834427e7b90198bfd0d573bc4279bfafdb2b95fe2b46dde", "name_or_path": "google/canine-c", "tokenizer_class": "CanineTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,601 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7951020408163265,
|
3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-pcm/checkpoint-7000",
|
4 |
+
"epoch": 119.40298507462687,
|
5 |
+
"global_step": 8000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.99,
|
12 |
+
"eval_accuracy_score": 0.8950079239302694,
|
13 |
+
"eval_f1": 0.4056413700470114,
|
14 |
+
"eval_loss": 0.31147781014442444,
|
15 |
+
"eval_precision": 0.3420158550396376,
|
16 |
+
"eval_recall": 0.49834983498349833,
|
17 |
+
"eval_runtime": 2.4074,
|
18 |
+
"eval_samples_per_second": 127.107,
|
19 |
+
"eval_steps_per_second": 16.2,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 5.97,
|
24 |
+
"eval_accuracy_score": 0.9330427892234548,
|
25 |
+
"eval_f1": 0.541019955654102,
|
26 |
+
"eval_loss": 0.22155305743217468,
|
27 |
+
"eval_precision": 0.4899598393574297,
|
28 |
+
"eval_recall": 0.6039603960396039,
|
29 |
+
"eval_runtime": 2.4071,
|
30 |
+
"eval_samples_per_second": 127.125,
|
31 |
+
"eval_steps_per_second": 16.202,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 7.46,
|
36 |
+
"learning_rate": 4.865771812080537e-05,
|
37 |
+
"loss": 0.3727,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 8.96,
|
42 |
+
"eval_accuracy_score": 0.9498151082937136,
|
43 |
+
"eval_f1": 0.6552238805970149,
|
44 |
+
"eval_loss": 0.18555797636508942,
|
45 |
+
"eval_precision": 0.5980926430517711,
|
46 |
+
"eval_recall": 0.7244224422442245,
|
47 |
+
"eval_runtime": 2.4132,
|
48 |
+
"eval_samples_per_second": 126.802,
|
49 |
+
"eval_steps_per_second": 16.161,
|
50 |
+
"step": 600
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 11.94,
|
54 |
+
"eval_accuracy_score": 0.95932382461701,
|
55 |
+
"eval_f1": 0.7168627450980393,
|
56 |
+
"eval_loss": 0.1749705672264099,
|
57 |
+
"eval_precision": 0.6831091180866966,
|
58 |
+
"eval_recall": 0.7541254125412541,
|
59 |
+
"eval_runtime": 2.408,
|
60 |
+
"eval_samples_per_second": 127.076,
|
61 |
+
"eval_steps_per_second": 16.196,
|
62 |
+
"step": 800
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 14.93,
|
66 |
+
"learning_rate": 4.697986577181208e-05,
|
67 |
+
"loss": 0.0555,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 14.93,
|
72 |
+
"eval_accuracy_score": 0.9578711040676176,
|
73 |
+
"eval_f1": 0.7334360554699538,
|
74 |
+
"eval_loss": 0.1944570541381836,
|
75 |
+
"eval_precision": 0.6878612716763006,
|
76 |
+
"eval_recall": 0.7854785478547854,
|
77 |
+
"eval_runtime": 2.4095,
|
78 |
+
"eval_samples_per_second": 127.0,
|
79 |
+
"eval_steps_per_second": 16.186,
|
80 |
+
"step": 1000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 17.91,
|
84 |
+
"eval_accuracy_score": 0.9647385103011094,
|
85 |
+
"eval_f1": 0.7670364500792393,
|
86 |
+
"eval_loss": 0.18250040709972382,
|
87 |
+
"eval_precision": 0.7378048780487805,
|
88 |
+
"eval_recall": 0.7986798679867987,
|
89 |
+
"eval_runtime": 2.4111,
|
90 |
+
"eval_samples_per_second": 126.911,
|
91 |
+
"eval_steps_per_second": 16.175,
|
92 |
+
"step": 1200
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 20.9,
|
96 |
+
"eval_accuracy_score": 0.9630216587427364,
|
97 |
+
"eval_f1": 0.7384615384615385,
|
98 |
+
"eval_loss": 0.19533774256706238,
|
99 |
+
"eval_precision": 0.724960254372019,
|
100 |
+
"eval_recall": 0.7524752475247525,
|
101 |
+
"eval_runtime": 2.4014,
|
102 |
+
"eval_samples_per_second": 127.425,
|
103 |
+
"eval_steps_per_second": 16.24,
|
104 |
+
"step": 1400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 22.39,
|
108 |
+
"learning_rate": 4.530201342281879e-05,
|
109 |
+
"loss": 0.0105,
|
110 |
+
"step": 1500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 23.88,
|
114 |
+
"eval_accuracy_score": 0.9644743792921289,
|
115 |
+
"eval_f1": 0.7389937106918238,
|
116 |
+
"eval_loss": 0.19444848597049713,
|
117 |
+
"eval_precision": 0.7057057057057057,
|
118 |
+
"eval_recall": 0.7755775577557755,
|
119 |
+
"eval_runtime": 2.4134,
|
120 |
+
"eval_samples_per_second": 126.79,
|
121 |
+
"eval_steps_per_second": 16.16,
|
122 |
+
"step": 1600
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 26.87,
|
126 |
+
"eval_accuracy_score": 0.963946117274168,
|
127 |
+
"eval_f1": 0.7565424266455195,
|
128 |
+
"eval_loss": 0.211569145321846,
|
129 |
+
"eval_precision": 0.7282442748091603,
|
130 |
+
"eval_recall": 0.7871287128712872,
|
131 |
+
"eval_runtime": 2.4076,
|
132 |
+
"eval_samples_per_second": 127.097,
|
133 |
+
"eval_steps_per_second": 16.199,
|
134 |
+
"step": 1800
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 29.85,
|
138 |
+
"learning_rate": 4.36241610738255e-05,
|
139 |
+
"loss": 0.0055,
|
140 |
+
"step": 2000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 29.85,
|
144 |
+
"eval_accuracy_score": 0.9611727416798732,
|
145 |
+
"eval_f1": 0.7248979591836734,
|
146 |
+
"eval_loss": 0.23255787789821625,
|
147 |
+
"eval_precision": 0.7172859450726979,
|
148 |
+
"eval_recall": 0.7326732673267327,
|
149 |
+
"eval_runtime": 2.4063,
|
150 |
+
"eval_samples_per_second": 127.167,
|
151 |
+
"eval_steps_per_second": 16.208,
|
152 |
+
"step": 2000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 32.84,
|
156 |
+
"eval_accuracy_score": 0.9650026413100898,
|
157 |
+
"eval_f1": 0.7594339622641509,
|
158 |
+
"eval_loss": 0.21984447538852692,
|
159 |
+
"eval_precision": 0.7252252252252253,
|
160 |
+
"eval_recall": 0.7970297029702971,
|
161 |
+
"eval_runtime": 2.4107,
|
162 |
+
"eval_samples_per_second": 126.936,
|
163 |
+
"eval_steps_per_second": 16.178,
|
164 |
+
"step": 2200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 35.82,
|
168 |
+
"eval_accuracy_score": 0.963946117274168,
|
169 |
+
"eval_f1": 0.7598736176935229,
|
170 |
+
"eval_loss": 0.2293044477701187,
|
171 |
+
"eval_precision": 0.7287878787878788,
|
172 |
+
"eval_recall": 0.7937293729372937,
|
173 |
+
"eval_runtime": 2.4114,
|
174 |
+
"eval_samples_per_second": 126.899,
|
175 |
+
"eval_steps_per_second": 16.173,
|
176 |
+
"step": 2400
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 37.31,
|
180 |
+
"learning_rate": 4.194630872483222e-05,
|
181 |
+
"loss": 0.0038,
|
182 |
+
"step": 2500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 38.81,
|
186 |
+
"eval_accuracy_score": 0.9643423137876387,
|
187 |
+
"eval_f1": 0.7497975708502024,
|
188 |
+
"eval_loss": 0.23353905975818634,
|
189 |
+
"eval_precision": 0.7360890302066773,
|
190 |
+
"eval_recall": 0.764026402640264,
|
191 |
+
"eval_runtime": 2.4071,
|
192 |
+
"eval_samples_per_second": 127.125,
|
193 |
+
"eval_steps_per_second": 16.202,
|
194 |
+
"step": 2600
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 41.79,
|
198 |
+
"eval_accuracy_score": 0.9655309033280507,
|
199 |
+
"eval_f1": 0.7648,
|
200 |
+
"eval_loss": 0.224817156791687,
|
201 |
+
"eval_precision": 0.7422360248447205,
|
202 |
+
"eval_recall": 0.7887788778877888,
|
203 |
+
"eval_runtime": 2.4046,
|
204 |
+
"eval_samples_per_second": 127.255,
|
205 |
+
"eval_steps_per_second": 16.219,
|
206 |
+
"step": 2800
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 44.78,
|
210 |
+
"learning_rate": 4.026845637583892e-05,
|
211 |
+
"loss": 0.0032,
|
212 |
+
"step": 3000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 44.78,
|
216 |
+
"eval_accuracy_score": 0.95932382461701,
|
217 |
+
"eval_f1": 0.7264076130055511,
|
218 |
+
"eval_loss": 0.26162534952163696,
|
219 |
+
"eval_precision": 0.6992366412213741,
|
220 |
+
"eval_recall": 0.7557755775577558,
|
221 |
+
"eval_runtime": 2.3994,
|
222 |
+
"eval_samples_per_second": 127.53,
|
223 |
+
"eval_steps_per_second": 16.254,
|
224 |
+
"step": 3000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 47.76,
|
228 |
+
"eval_accuracy_score": 0.9638140517696777,
|
229 |
+
"eval_f1": 0.7374392220421394,
|
230 |
+
"eval_loss": 0.2429530769586563,
|
231 |
+
"eval_precision": 0.7245222929936306,
|
232 |
+
"eval_recall": 0.7508250825082509,
|
233 |
+
"eval_runtime": 2.4056,
|
234 |
+
"eval_samples_per_second": 127.201,
|
235 |
+
"eval_steps_per_second": 16.212,
|
236 |
+
"step": 3200
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 50.75,
|
240 |
+
"eval_accuracy_score": 0.9646064447966192,
|
241 |
+
"eval_f1": 0.7631578947368421,
|
242 |
+
"eval_loss": 0.2461545169353485,
|
243 |
+
"eval_precision": 0.760655737704918,
|
244 |
+
"eval_recall": 0.7656765676567657,
|
245 |
+
"eval_runtime": 2.4169,
|
246 |
+
"eval_samples_per_second": 126.61,
|
247 |
+
"eval_steps_per_second": 16.137,
|
248 |
+
"step": 3400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 52.24,
|
252 |
+
"learning_rate": 3.859060402684564e-05,
|
253 |
+
"loss": 0.0027,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 53.73,
|
258 |
+
"eval_accuracy_score": 0.9615689381933439,
|
259 |
+
"eval_f1": 0.7359870024370431,
|
260 |
+
"eval_loss": 0.25643840432167053,
|
261 |
+
"eval_precision": 0.7248,
|
262 |
+
"eval_recall": 0.7475247524752475,
|
263 |
+
"eval_runtime": 2.402,
|
264 |
+
"eval_samples_per_second": 127.392,
|
265 |
+
"eval_steps_per_second": 16.236,
|
266 |
+
"step": 3600
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 56.72,
|
270 |
+
"eval_accuracy_score": 0.96513470681458,
|
271 |
+
"eval_f1": 0.7636932707355242,
|
272 |
+
"eval_loss": 0.24773868918418884,
|
273 |
+
"eval_precision": 0.7261904761904762,
|
274 |
+
"eval_recall": 0.8052805280528053,
|
275 |
+
"eval_runtime": 2.406,
|
276 |
+
"eval_samples_per_second": 127.183,
|
277 |
+
"eval_steps_per_second": 16.21,
|
278 |
+
"step": 3800
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 59.7,
|
282 |
+
"learning_rate": 3.6912751677852356e-05,
|
283 |
+
"loss": 0.0019,
|
284 |
+
"step": 4000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 59.7,
|
288 |
+
"eval_accuracy_score": 0.9615689381933439,
|
289 |
+
"eval_f1": 0.7295796986518637,
|
290 |
+
"eval_loss": 0.27105194330215454,
|
291 |
+
"eval_precision": 0.7022900763358778,
|
292 |
+
"eval_recall": 0.759075907590759,
|
293 |
+
"eval_runtime": 2.4067,
|
294 |
+
"eval_samples_per_second": 127.143,
|
295 |
+
"eval_steps_per_second": 16.204,
|
296 |
+
"step": 4000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 62.69,
|
300 |
+
"eval_accuracy_score": 0.9620972002113048,
|
301 |
+
"eval_f1": 0.7459807073954984,
|
302 |
+
"eval_loss": 0.2745388150215149,
|
303 |
+
"eval_precision": 0.7272727272727273,
|
304 |
+
"eval_recall": 0.7656765676567657,
|
305 |
+
"eval_runtime": 2.4067,
|
306 |
+
"eval_samples_per_second": 127.143,
|
307 |
+
"eval_steps_per_second": 16.205,
|
308 |
+
"step": 4200
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 65.67,
|
312 |
+
"eval_accuracy_score": 0.9632857897517169,
|
313 |
+
"eval_f1": 0.7472353870458136,
|
314 |
+
"eval_loss": 0.26222512125968933,
|
315 |
+
"eval_precision": 0.7166666666666667,
|
316 |
+
"eval_recall": 0.7805280528052805,
|
317 |
+
"eval_runtime": 2.4079,
|
318 |
+
"eval_samples_per_second": 127.079,
|
319 |
+
"eval_steps_per_second": 16.196,
|
320 |
+
"step": 4400
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 67.16,
|
324 |
+
"learning_rate": 3.523489932885906e-05,
|
325 |
+
"loss": 0.0019,
|
326 |
+
"step": 4500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 68.66,
|
330 |
+
"eval_accuracy_score": 0.9644743792921289,
|
331 |
+
"eval_f1": 0.7557677008750995,
|
332 |
+
"eval_loss": 0.25255098938941956,
|
333 |
+
"eval_precision": 0.7296466973886329,
|
334 |
+
"eval_recall": 0.7838283828382838,
|
335 |
+
"eval_runtime": 2.4095,
|
336 |
+
"eval_samples_per_second": 126.996,
|
337 |
+
"eval_steps_per_second": 16.186,
|
338 |
+
"step": 4600
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 71.64,
|
342 |
+
"eval_accuracy_score": 0.9657950343370312,
|
343 |
+
"eval_f1": 0.765079365079365,
|
344 |
+
"eval_loss": 0.2474120408296585,
|
345 |
+
"eval_precision": 0.7370030581039755,
|
346 |
+
"eval_recall": 0.7953795379537953,
|
347 |
+
"eval_runtime": 2.4085,
|
348 |
+
"eval_samples_per_second": 127.049,
|
349 |
+
"eval_steps_per_second": 16.192,
|
350 |
+
"step": 4800
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 74.63,
|
354 |
+
"learning_rate": 3.3557046979865775e-05,
|
355 |
+
"loss": 0.0018,
|
356 |
+
"step": 5000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 74.63,
|
360 |
+
"eval_accuracy_score": 0.9653988378235605,
|
361 |
+
"eval_f1": 0.7618296529968455,
|
362 |
+
"eval_loss": 0.2491973489522934,
|
363 |
+
"eval_precision": 0.729607250755287,
|
364 |
+
"eval_recall": 0.7970297029702971,
|
365 |
+
"eval_runtime": 2.4082,
|
366 |
+
"eval_samples_per_second": 127.066,
|
367 |
+
"eval_steps_per_second": 16.195,
|
368 |
+
"step": 5000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 77.61,
|
372 |
+
"eval_accuracy_score": 0.963946117274168,
|
373 |
+
"eval_f1": 0.7564604541895067,
|
374 |
+
"eval_loss": 0.2652634084224701,
|
375 |
+
"eval_precision": 0.7198211624441133,
|
376 |
+
"eval_recall": 0.7970297029702971,
|
377 |
+
"eval_runtime": 2.4091,
|
378 |
+
"eval_samples_per_second": 127.02,
|
379 |
+
"eval_steps_per_second": 16.189,
|
380 |
+
"step": 5200
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 80.6,
|
384 |
+
"eval_accuracy_score": 0.963946117274168,
|
385 |
+
"eval_f1": 0.7577235772357722,
|
386 |
+
"eval_loss": 0.2766047418117523,
|
387 |
+
"eval_precision": 0.7467948717948718,
|
388 |
+
"eval_recall": 0.768976897689769,
|
389 |
+
"eval_runtime": 2.4127,
|
390 |
+
"eval_samples_per_second": 126.83,
|
391 |
+
"eval_steps_per_second": 16.165,
|
392 |
+
"step": 5400
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 82.09,
|
396 |
+
"learning_rate": 3.1879194630872485e-05,
|
397 |
+
"loss": 0.0012,
|
398 |
+
"step": 5500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 83.58,
|
402 |
+
"eval_accuracy_score": 0.9627575277337559,
|
403 |
+
"eval_f1": 0.7384855581576891,
|
404 |
+
"eval_loss": 0.2791267931461334,
|
405 |
+
"eval_precision": 0.7007407407407408,
|
406 |
+
"eval_recall": 0.7805280528052805,
|
407 |
+
"eval_runtime": 2.4092,
|
408 |
+
"eval_samples_per_second": 127.015,
|
409 |
+
"eval_steps_per_second": 16.188,
|
410 |
+
"step": 5600
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 86.57,
|
414 |
+
"eval_accuracy_score": 0.9672477548864237,
|
415 |
+
"eval_f1": 0.7776000000000001,
|
416 |
+
"eval_loss": 0.24720582365989685,
|
417 |
+
"eval_precision": 0.7546583850931677,
|
418 |
+
"eval_recall": 0.801980198019802,
|
419 |
+
"eval_runtime": 2.4153,
|
420 |
+
"eval_samples_per_second": 126.694,
|
421 |
+
"eval_steps_per_second": 16.147,
|
422 |
+
"step": 5800
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 89.55,
|
426 |
+
"learning_rate": 3.02013422818792e-05,
|
427 |
+
"loss": 0.0013,
|
428 |
+
"step": 6000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 89.55,
|
432 |
+
"eval_accuracy_score": 0.9664553618594823,
|
433 |
+
"eval_f1": 0.7794707297514034,
|
434 |
+
"eval_loss": 0.25364401936531067,
|
435 |
+
"eval_precision": 0.7581903276131046,
|
436 |
+
"eval_recall": 0.801980198019802,
|
437 |
+
"eval_runtime": 2.4087,
|
438 |
+
"eval_samples_per_second": 127.037,
|
439 |
+
"eval_steps_per_second": 16.191,
|
440 |
+
"step": 6000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 92.54,
|
444 |
+
"eval_accuracy_score": 0.9676439513998943,
|
445 |
+
"eval_f1": 0.7832393231265109,
|
446 |
+
"eval_loss": 0.25377386808395386,
|
447 |
+
"eval_precision": 0.7653543307086614,
|
448 |
+
"eval_recall": 0.801980198019802,
|
449 |
+
"eval_runtime": 2.4146,
|
450 |
+
"eval_samples_per_second": 126.731,
|
451 |
+
"eval_steps_per_second": 16.152,
|
452 |
+
"step": 6200
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 95.52,
|
456 |
+
"eval_accuracy_score": 0.9689646064447967,
|
457 |
+
"eval_f1": 0.7859424920127794,
|
458 |
+
"eval_loss": 0.23607416450977325,
|
459 |
+
"eval_precision": 0.7616099071207431,
|
460 |
+
"eval_recall": 0.8118811881188119,
|
461 |
+
"eval_runtime": 2.4167,
|
462 |
+
"eval_samples_per_second": 126.62,
|
463 |
+
"eval_steps_per_second": 16.138,
|
464 |
+
"step": 6400
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 97.01,
|
468 |
+
"learning_rate": 2.8523489932885905e-05,
|
469 |
+
"loss": 0.0014,
|
470 |
+
"step": 6500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 98.51,
|
474 |
+
"eval_accuracy_score": 0.9696249339672478,
|
475 |
+
"eval_f1": 0.784155214227971,
|
476 |
+
"eval_loss": 0.22985981404781342,
|
477 |
+
"eval_precision": 0.768621236133122,
|
478 |
+
"eval_recall": 0.8003300330033003,
|
479 |
+
"eval_runtime": 2.4152,
|
480 |
+
"eval_samples_per_second": 126.699,
|
481 |
+
"eval_steps_per_second": 16.148,
|
482 |
+
"step": 6600
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 101.49,
|
486 |
+
"eval_accuracy_score": 0.969228737453777,
|
487 |
+
"eval_f1": 0.7798537774167345,
|
488 |
+
"eval_loss": 0.2279633730649948,
|
489 |
+
"eval_precision": 0.768,
|
490 |
+
"eval_recall": 0.7920792079207921,
|
491 |
+
"eval_runtime": 2.4192,
|
492 |
+
"eval_samples_per_second": 126.488,
|
493 |
+
"eval_steps_per_second": 16.121,
|
494 |
+
"step": 6800
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 104.48,
|
498 |
+
"learning_rate": 2.6845637583892618e-05,
|
499 |
+
"loss": 0.001,
|
500 |
+
"step": 7000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 104.48,
|
504 |
+
"eval_accuracy_score": 0.9705493924986793,
|
505 |
+
"eval_f1": 0.7951020408163265,
|
506 |
+
"eval_loss": 0.23545745015144348,
|
507 |
+
"eval_precision": 0.7867528271405493,
|
508 |
+
"eval_recall": 0.8036303630363036,
|
509 |
+
"eval_runtime": 2.41,
|
510 |
+
"eval_samples_per_second": 126.97,
|
511 |
+
"eval_steps_per_second": 16.182,
|
512 |
+
"step": 7000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 107.46,
|
516 |
+
"eval_accuracy_score": 0.9688325409403064,
|
517 |
+
"eval_f1": 0.7739340305711988,
|
518 |
+
"eval_loss": 0.23859038949012756,
|
519 |
+
"eval_precision": 0.7551020408163265,
|
520 |
+
"eval_recall": 0.7937293729372937,
|
521 |
+
"eval_runtime": 2.4059,
|
522 |
+
"eval_samples_per_second": 127.189,
|
523 |
+
"eval_steps_per_second": 16.21,
|
524 |
+
"step": 7200
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 110.45,
|
528 |
+
"eval_accuracy_score": 0.9684363444268357,
|
529 |
+
"eval_f1": 0.7909967845659165,
|
530 |
+
"eval_loss": 0.2557569444179535,
|
531 |
+
"eval_precision": 0.7711598746081505,
|
532 |
+
"eval_recall": 0.8118811881188119,
|
533 |
+
"eval_runtime": 2.4083,
|
534 |
+
"eval_samples_per_second": 127.062,
|
535 |
+
"eval_steps_per_second": 16.194,
|
536 |
+
"step": 7400
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 111.94,
|
540 |
+
"learning_rate": 2.516778523489933e-05,
|
541 |
+
"loss": 0.0008,
|
542 |
+
"step": 7500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 113.43,
|
546 |
+
"eval_accuracy_score": 0.9683042789223455,
|
547 |
+
"eval_f1": 0.7780429594272077,
|
548 |
+
"eval_loss": 0.2508944869041443,
|
549 |
+
"eval_precision": 0.7511520737327189,
|
550 |
+
"eval_recall": 0.806930693069307,
|
551 |
+
"eval_runtime": 2.4124,
|
552 |
+
"eval_samples_per_second": 126.846,
|
553 |
+
"eval_steps_per_second": 16.167,
|
554 |
+
"step": 7600
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 116.42,
|
558 |
+
"eval_accuracy_score": 0.9681722134178553,
|
559 |
+
"eval_f1": 0.7712206952303962,
|
560 |
+
"eval_loss": 0.2467135787010193,
|
561 |
+
"eval_precision": 0.7559429477020603,
|
562 |
+
"eval_recall": 0.7871287128712872,
|
563 |
+
"eval_runtime": 2.4114,
|
564 |
+
"eval_samples_per_second": 126.896,
|
565 |
+
"eval_steps_per_second": 16.173,
|
566 |
+
"step": 7800
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 119.4,
|
570 |
+
"learning_rate": 2.348993288590604e-05,
|
571 |
+
"loss": 0.0011,
|
572 |
+
"step": 8000
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 119.4,
|
576 |
+
"eval_accuracy_score": 0.966323296354992,
|
577 |
+
"eval_f1": 0.7704654895666132,
|
578 |
+
"eval_loss": 0.24946843087673187,
|
579 |
+
"eval_precision": 0.75,
|
580 |
+
"eval_recall": 0.7920792079207921,
|
581 |
+
"eval_runtime": 2.4125,
|
582 |
+
"eval_samples_per_second": 126.837,
|
583 |
+
"eval_steps_per_second": 16.166,
|
584 |
+
"step": 8000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 119.4,
|
588 |
+
"step": 8000,
|
589 |
+
"total_flos": 4.164857671044096e+16,
|
590 |
+
"train_loss": 0.029139109283685686,
|
591 |
+
"train_runtime": 3971.1585,
|
592 |
+
"train_samples_per_second": 120.872,
|
593 |
+
"train_steps_per_second": 3.777
|
594 |
+
}
|
595 |
+
],
|
596 |
+
"max_steps": 15000,
|
597 |
+
"num_train_epochs": 224,
|
598 |
+
"total_flos": 4.164857671044096e+16,
|
599 |
+
"trial_name": null,
|
600 |
+
"trial_params": null
|
601 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:075bec07a6e14a0842c0efec93e592b23ca2d2f567dc848c4f855ee52696c7c5
|
3 |
+
size 3259
|