Md Mushfiqur Rahman
commited on
Commit
•
f2eaef7
1
Parent(s):
0dd11a7
Upload with huggingface_hub
Browse files- README.md +15 -0
- all_results.json +22 -0
- config.json +106 -0
- eval_predictions.csv +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_predictions.csv +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +345 -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 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 28.99,
|
3 |
+
"eval_las": 29.294196353905335,
|
4 |
+
"eval_loss": 3.0349910259246826,
|
5 |
+
"eval_runtime": 6.1778,
|
6 |
+
"eval_samples": 950,
|
7 |
+
"eval_samples_per_second": 153.776,
|
8 |
+
"eval_steps_per_second": 19.262,
|
9 |
+
"eval_uas": 47.00618832580699,
|
10 |
+
"test_las": 30.110473580542944,
|
11 |
+
"test_loss": 2.873572587966919,
|
12 |
+
"test_runtime": 6.3685,
|
13 |
+
"test_samples": 989,
|
14 |
+
"test_samples_per_second": 155.297,
|
15 |
+
"test_steps_per_second": 19.471,
|
16 |
+
"test_uas": 48.87385458593817,
|
17 |
+
"train_loss": 2.234064235687256,
|
18 |
+
"train_runtime": 2087.3588,
|
19 |
+
"train_samples": 4400,
|
20 |
+
"train_samples_per_second": 229.956,
|
21 |
+
"train_steps_per_second": 7.186
|
22 |
+
}
|
config.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForBiaffineParsing"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "_",
|
14 |
+
"1": "acl",
|
15 |
+
"2": "advcl",
|
16 |
+
"3": "advmod",
|
17 |
+
"4": "amod",
|
18 |
+
"5": "appos",
|
19 |
+
"6": "aux",
|
20 |
+
"7": "case",
|
21 |
+
"8": "cc",
|
22 |
+
"9": "ccomp",
|
23 |
+
"10": "clf",
|
24 |
+
"11": "compound",
|
25 |
+
"12": "conj",
|
26 |
+
"13": "cop",
|
27 |
+
"14": "csubj",
|
28 |
+
"15": "dep",
|
29 |
+
"16": "det",
|
30 |
+
"17": "discourse",
|
31 |
+
"18": "dislocated",
|
32 |
+
"19": "expl",
|
33 |
+
"20": "fixed",
|
34 |
+
"21": "flat",
|
35 |
+
"22": "goeswith",
|
36 |
+
"23": "iobj",
|
37 |
+
"24": "list",
|
38 |
+
"25": "mark",
|
39 |
+
"26": "nmod",
|
40 |
+
"27": "nsubj",
|
41 |
+
"28": "nummod",
|
42 |
+
"29": "obj",
|
43 |
+
"30": "obl",
|
44 |
+
"31": "orphan",
|
45 |
+
"32": "parataxis",
|
46 |
+
"33": "punct",
|
47 |
+
"34": "reparandum",
|
48 |
+
"35": "root",
|
49 |
+
"36": "vocative",
|
50 |
+
"37": "xcomp"
|
51 |
+
},
|
52 |
+
"initializer_range": 0.02,
|
53 |
+
"intermediate_size": 3072,
|
54 |
+
"label2id": {
|
55 |
+
"_": 0,
|
56 |
+
"acl": 1,
|
57 |
+
"advcl": 2,
|
58 |
+
"advmod": 3,
|
59 |
+
"amod": 4,
|
60 |
+
"appos": 5,
|
61 |
+
"aux": 6,
|
62 |
+
"case": 7,
|
63 |
+
"cc": 8,
|
64 |
+
"ccomp": 9,
|
65 |
+
"clf": 10,
|
66 |
+
"compound": 11,
|
67 |
+
"conj": 12,
|
68 |
+
"cop": 13,
|
69 |
+
"csubj": 14,
|
70 |
+
"dep": 15,
|
71 |
+
"det": 16,
|
72 |
+
"discourse": 17,
|
73 |
+
"dislocated": 18,
|
74 |
+
"expl": 19,
|
75 |
+
"fixed": 20,
|
76 |
+
"flat": 21,
|
77 |
+
"goeswith": 22,
|
78 |
+
"iobj": 23,
|
79 |
+
"list": 24,
|
80 |
+
"mark": 25,
|
81 |
+
"nmod": 26,
|
82 |
+
"nsubj": 27,
|
83 |
+
"nummod": 28,
|
84 |
+
"obj": 29,
|
85 |
+
"obl": 30,
|
86 |
+
"orphan": 31,
|
87 |
+
"parataxis": 32,
|
88 |
+
"punct": 33,
|
89 |
+
"reparandum": 34,
|
90 |
+
"root": 35,
|
91 |
+
"vocative": 36,
|
92 |
+
"xcomp": 37
|
93 |
+
},
|
94 |
+
"layer_norm_eps": 1e-12,
|
95 |
+
"max_position_embeddings": 512,
|
96 |
+
"model_type": "bert",
|
97 |
+
"num_attention_heads": 12,
|
98 |
+
"num_hidden_layers": 12,
|
99 |
+
"pad_token_id": -100,
|
100 |
+
"position_embedding_type": "absolute",
|
101 |
+
"torch_dtype": "float32",
|
102 |
+
"transformers_version": "4.17.0",
|
103 |
+
"type_vocab_size": 2,
|
104 |
+
"use_cache": true,
|
105 |
+
"vocab_size": 28996
|
106 |
+
}
|
eval_predictions.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58a563970c986ca0f12e1cccbc6e1d7ff8a926399c131ef52c977205ca5e0b3b
|
3 |
+
size 525577269
|
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.csv
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-cased", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,345 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 29.294196353905335,
|
3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Korean-GSD/checkpoint-1500",
|
4 |
+
"epoch": 28.985507246376812,
|
5 |
+
"global_step": 4000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.72,
|
12 |
+
"learning_rate": 7.52e-05,
|
13 |
+
"loss": 4.639,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.45,
|
18 |
+
"learning_rate": 7.949530201342283e-05,
|
19 |
+
"loss": 3.2377,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.17,
|
24 |
+
"learning_rate": 7.895838926174497e-05,
|
25 |
+
"loss": 3.0918,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.9,
|
30 |
+
"learning_rate": 7.842147651006712e-05,
|
31 |
+
"loss": 2.9885,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.62,
|
36 |
+
"learning_rate": 7.788456375838927e-05,
|
37 |
+
"loss": 2.9165,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.62,
|
42 |
+
"eval_las": 27.86419133634387,
|
43 |
+
"eval_loss": 2.9203531742095947,
|
44 |
+
"eval_runtime": 6.1866,
|
45 |
+
"eval_samples_per_second": 153.558,
|
46 |
+
"eval_steps_per_second": 19.235,
|
47 |
+
"eval_uas": 44.94062552266265,
|
48 |
+
"step": 500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 4.35,
|
52 |
+
"learning_rate": 7.734765100671142e-05,
|
53 |
+
"loss": 2.8823,
|
54 |
+
"step": 600
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 5.07,
|
58 |
+
"learning_rate": 7.681073825503357e-05,
|
59 |
+
"loss": 2.8323,
|
60 |
+
"step": 700
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 5.8,
|
64 |
+
"learning_rate": 7.627382550335572e-05,
|
65 |
+
"loss": 2.7932,
|
66 |
+
"step": 800
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 6.52,
|
70 |
+
"learning_rate": 7.573691275167786e-05,
|
71 |
+
"loss": 2.753,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 7.25,
|
76 |
+
"learning_rate": 7.52e-05,
|
77 |
+
"loss": 2.7026,
|
78 |
+
"step": 1000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 7.25,
|
82 |
+
"eval_las": 29.118581702625857,
|
83 |
+
"eval_loss": 2.91562819480896,
|
84 |
+
"eval_runtime": 6.1737,
|
85 |
+
"eval_samples_per_second": 153.878,
|
86 |
+
"eval_steps_per_second": 19.275,
|
87 |
+
"eval_uas": 46.52115738417796,
|
88 |
+
"step": 1000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 7.97,
|
92 |
+
"learning_rate": 7.466308724832215e-05,
|
93 |
+
"loss": 2.6742,
|
94 |
+
"step": 1100
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 8.7,
|
98 |
+
"learning_rate": 7.41261744966443e-05,
|
99 |
+
"loss": 2.5757,
|
100 |
+
"step": 1200
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 9.42,
|
104 |
+
"learning_rate": 7.358926174496644e-05,
|
105 |
+
"loss": 2.5635,
|
106 |
+
"step": 1300
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 10.14,
|
110 |
+
"learning_rate": 7.305234899328859e-05,
|
111 |
+
"loss": 2.5617,
|
112 |
+
"step": 1400
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 10.87,
|
116 |
+
"learning_rate": 7.251543624161074e-05,
|
117 |
+
"loss": 2.4701,
|
118 |
+
"step": 1500
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 10.87,
|
122 |
+
"eval_las": 29.294196353905335,
|
123 |
+
"eval_loss": 3.0349910259246826,
|
124 |
+
"eval_runtime": 6.1916,
|
125 |
+
"eval_samples_per_second": 153.433,
|
126 |
+
"eval_steps_per_second": 19.219,
|
127 |
+
"eval_uas": 47.00618832580699,
|
128 |
+
"step": 1500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 11.59,
|
132 |
+
"learning_rate": 7.197852348993289e-05,
|
133 |
+
"loss": 2.3668,
|
134 |
+
"step": 1600
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 12.32,
|
138 |
+
"learning_rate": 7.144161073825504e-05,
|
139 |
+
"loss": 2.3771,
|
140 |
+
"step": 1700
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 13.04,
|
144 |
+
"learning_rate": 7.090469798657718e-05,
|
145 |
+
"loss": 2.3208,
|
146 |
+
"step": 1800
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 13.77,
|
150 |
+
"learning_rate": 7.036778523489933e-05,
|
151 |
+
"loss": 2.2402,
|
152 |
+
"step": 1900
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 14.49,
|
156 |
+
"learning_rate": 6.983087248322148e-05,
|
157 |
+
"loss": 2.1529,
|
158 |
+
"step": 2000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 14.49,
|
162 |
+
"eval_las": 29.0600434855327,
|
163 |
+
"eval_loss": 3.292515277862549,
|
164 |
+
"eval_runtime": 6.1874,
|
165 |
+
"eval_samples_per_second": 153.538,
|
166 |
+
"eval_steps_per_second": 19.233,
|
167 |
+
"eval_uas": 47.09817695266767,
|
168 |
+
"step": 2000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 15.22,
|
172 |
+
"learning_rate": 6.929395973154363e-05,
|
173 |
+
"loss": 2.1538,
|
174 |
+
"step": 2100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 15.94,
|
178 |
+
"learning_rate": 6.875704697986578e-05,
|
179 |
+
"loss": 2.0934,
|
180 |
+
"step": 2200
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 16.67,
|
184 |
+
"learning_rate": 6.822013422818793e-05,
|
185 |
+
"loss": 1.9925,
|
186 |
+
"step": 2300
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 17.39,
|
190 |
+
"learning_rate": 6.768322147651007e-05,
|
191 |
+
"loss": 1.9471,
|
192 |
+
"step": 2400
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 18.12,
|
196 |
+
"learning_rate": 6.714630872483222e-05,
|
197 |
+
"loss": 1.9399,
|
198 |
+
"step": 2500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 18.12,
|
202 |
+
"eval_las": 28.85934102692758,
|
203 |
+
"eval_loss": 3.839879274368286,
|
204 |
+
"eval_runtime": 6.1995,
|
205 |
+
"eval_samples_per_second": 153.237,
|
206 |
+
"eval_steps_per_second": 19.195,
|
207 |
+
"eval_uas": 46.28700451580532,
|
208 |
+
"step": 2500
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 18.84,
|
212 |
+
"learning_rate": 6.660939597315437e-05,
|
213 |
+
"loss": 1.8651,
|
214 |
+
"step": 2600
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 19.57,
|
218 |
+
"learning_rate": 6.607248322147652e-05,
|
219 |
+
"loss": 1.7929,
|
220 |
+
"step": 2700
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 20.29,
|
224 |
+
"learning_rate": 6.553557046979867e-05,
|
225 |
+
"loss": 1.7378,
|
226 |
+
"step": 2800
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 21.01,
|
230 |
+
"learning_rate": 6.499865771812081e-05,
|
231 |
+
"loss": 1.7862,
|
232 |
+
"step": 2900
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 21.74,
|
236 |
+
"learning_rate": 6.446174496644296e-05,
|
237 |
+
"loss": 1.6585,
|
238 |
+
"step": 3000
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 21.74,
|
242 |
+
"eval_las": 28.349222277972906,
|
243 |
+
"eval_loss": 4.253769397735596,
|
244 |
+
"eval_runtime": 6.1742,
|
245 |
+
"eval_samples_per_second": 153.865,
|
246 |
+
"eval_steps_per_second": 19.274,
|
247 |
+
"eval_uas": 45.63472152533868,
|
248 |
+
"step": 3000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 22.46,
|
252 |
+
"learning_rate": 6.392483221476511e-05,
|
253 |
+
"loss": 1.6568,
|
254 |
+
"step": 3100
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 23.19,
|
258 |
+
"learning_rate": 6.338791946308726e-05,
|
259 |
+
"loss": 1.625,
|
260 |
+
"step": 3200
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 23.91,
|
264 |
+
"learning_rate": 6.28510067114094e-05,
|
265 |
+
"loss": 1.628,
|
266 |
+
"step": 3300
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 24.64,
|
270 |
+
"learning_rate": 6.231409395973154e-05,
|
271 |
+
"loss": 1.5299,
|
272 |
+
"step": 3400
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 25.36,
|
276 |
+
"learning_rate": 6.177718120805369e-05,
|
277 |
+
"loss": 1.5284,
|
278 |
+
"step": 3500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 25.36,
|
282 |
+
"eval_las": 28.6001003512293,
|
283 |
+
"eval_loss": 4.6269941329956055,
|
284 |
+
"eval_runtime": 6.1796,
|
285 |
+
"eval_samples_per_second": 153.733,
|
286 |
+
"eval_steps_per_second": 19.257,
|
287 |
+
"eval_uas": 45.37548084964041,
|
288 |
+
"step": 3500
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 26.09,
|
292 |
+
"learning_rate": 6.124026845637584e-05,
|
293 |
+
"loss": 1.5192,
|
294 |
+
"step": 3600
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 26.81,
|
298 |
+
"learning_rate": 6.070335570469799e-05,
|
299 |
+
"loss": 1.4848,
|
300 |
+
"step": 3700
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 27.54,
|
304 |
+
"learning_rate": 6.0166442953020136e-05,
|
305 |
+
"loss": 1.4342,
|
306 |
+
"step": 3800
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 28.26,
|
310 |
+
"learning_rate": 5.962953020134229e-05,
|
311 |
+
"loss": 1.418,
|
312 |
+
"step": 3900
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 28.99,
|
316 |
+
"learning_rate": 5.909261744966444e-05,
|
317 |
+
"loss": 1.4311,
|
318 |
+
"step": 4000
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 28.99,
|
322 |
+
"eval_las": 28.299046663321626,
|
323 |
+
"eval_loss": 4.774014472961426,
|
324 |
+
"eval_runtime": 6.1783,
|
325 |
+
"eval_samples_per_second": 153.765,
|
326 |
+
"eval_steps_per_second": 19.261,
|
327 |
+
"eval_uas": 45.16641578859341,
|
328 |
+
"step": 4000
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 28.99,
|
332 |
+
"step": 4000,
|
333 |
+
"total_flos": 2.1298234165100544e+16,
|
334 |
+
"train_loss": 2.234064235687256,
|
335 |
+
"train_runtime": 2087.3588,
|
336 |
+
"train_samples_per_second": 229.956,
|
337 |
+
"train_steps_per_second": 7.186
|
338 |
+
}
|
339 |
+
],
|
340 |
+
"max_steps": 15000,
|
341 |
+
"num_train_epochs": 109,
|
342 |
+
"total_flos": 2.1298234165100544e+16,
|
343 |
+
"trial_name": null,
|
344 |
+
"trial_params": null
|
345 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a8b845c9911c1d4335a76e4d288d4dcad253b59902b2d6654f5f08019455c5b
|
3 |
+
size 3387
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|