Md Mushfiqur Rahman
commited on
Commit
•
3bf4c69
1
Parent(s):
8d1f200
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 +1225 -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": 36.06,
|
3 |
+
"eval_las": 74.99219127126105,
|
4 |
+
"eval_loss": 3.1982181072235107,
|
5 |
+
"eval_runtime": 11.8527,
|
6 |
+
"eval_samples": 1659,
|
7 |
+
"eval_samples_per_second": 139.968,
|
8 |
+
"eval_steps_per_second": 17.549,
|
9 |
+
"eval_uas": 83.58747195956498,
|
10 |
+
"test_las": 76.7880327406153,
|
11 |
+
"test_loss": 2.911848306655884,
|
12 |
+
"test_runtime": 12.0083,
|
13 |
+
"test_samples": 1684,
|
14 |
+
"test_samples_per_second": 140.237,
|
15 |
+
"test_steps_per_second": 17.571,
|
16 |
+
"test_uas": 84.92802709568163,
|
17 |
+
"train_loss": 0.2272949548403422,
|
18 |
+
"train_runtime": 8371.5337,
|
19 |
+
"train_samples": 13304,
|
20 |
+
"train_samples_per_second": 57.337,
|
21 |
+
"train_steps_per_second": 1.792
|
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 sha256:82cb80917a99ca6d051f030cd8f7d525139bdc7568959e5ff7735f9788f497da
|
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 +1,1225 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 74.99219127126105,
|
3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Hindi-HDTB/checkpoint-15000",
|
4 |
+
"epoch": 36.05769230769231,
|
5 |
+
"global_step": 15000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.24,
|
12 |
+
"learning_rate": 7.52e-05,
|
13 |
+
"loss": 4.0483,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.48,
|
18 |
+
"learning_rate": 7.949530201342283e-05,
|
19 |
+
"loss": 1.7391,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.72,
|
24 |
+
"learning_rate": 7.895838926174497e-05,
|
25 |
+
"loss": 1.4589,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.96,
|
30 |
+
"learning_rate": 7.842147651006712e-05,
|
31 |
+
"loss": 1.2986,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.2,
|
36 |
+
"learning_rate": 7.788456375838927e-05,
|
37 |
+
"loss": 1.1463,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.2,
|
42 |
+
"eval_las": 68.06655876423319,
|
43 |
+
"eval_loss": 1.2132718563079834,
|
44 |
+
"eval_runtime": 11.8598,
|
45 |
+
"eval_samples_per_second": 139.885,
|
46 |
+
"eval_steps_per_second": 17.538,
|
47 |
+
"eval_uas": 77.91691512621746,
|
48 |
+
"step": 500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.44,
|
52 |
+
"learning_rate": 7.734765100671142e-05,
|
53 |
+
"loss": 1.1162,
|
54 |
+
"step": 600
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.68,
|
58 |
+
"learning_rate": 7.681073825503357e-05,
|
59 |
+
"loss": 1.0738,
|
60 |
+
"step": 700
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.92,
|
64 |
+
"learning_rate": 7.627382550335572e-05,
|
65 |
+
"loss": 1.0485,
|
66 |
+
"step": 800
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 2.16,
|
70 |
+
"learning_rate": 7.573691275167786e-05,
|
71 |
+
"loss": 0.9272,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.4,
|
76 |
+
"learning_rate": 7.52e-05,
|
77 |
+
"loss": 0.901,
|
78 |
+
"step": 1000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 2.4,
|
82 |
+
"eval_las": 71.78635318170203,
|
83 |
+
"eval_loss": 1.053443193435669,
|
84 |
+
"eval_runtime": 11.8478,
|
85 |
+
"eval_samples_per_second": 140.026,
|
86 |
+
"eval_steps_per_second": 17.556,
|
87 |
+
"eval_uas": 80.90410881108555,
|
88 |
+
"step": 1000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 2.64,
|
92 |
+
"learning_rate": 7.466308724832215e-05,
|
93 |
+
"loss": 0.8841,
|
94 |
+
"step": 1100
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 2.88,
|
98 |
+
"learning_rate": 7.41261744966443e-05,
|
99 |
+
"loss": 0.8871,
|
100 |
+
"step": 1200
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 3.12,
|
104 |
+
"learning_rate": 7.358926174496644e-05,
|
105 |
+
"loss": 0.7905,
|
106 |
+
"step": 1300
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 3.37,
|
110 |
+
"learning_rate": 7.305234899328859e-05,
|
111 |
+
"loss": 0.7284,
|
112 |
+
"step": 1400
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 3.61,
|
116 |
+
"learning_rate": 7.251543624161074e-05,
|
117 |
+
"loss": 0.7392,
|
118 |
+
"step": 1500
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 3.61,
|
122 |
+
"eval_las": 73.2231592696709,
|
123 |
+
"eval_loss": 1.0388336181640625,
|
124 |
+
"eval_runtime": 11.8527,
|
125 |
+
"eval_samples_per_second": 139.968,
|
126 |
+
"eval_steps_per_second": 17.549,
|
127 |
+
"eval_uas": 81.9320214669052,
|
128 |
+
"step": 1500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.85,
|
132 |
+
"learning_rate": 7.197852348993289e-05,
|
133 |
+
"loss": 0.7587,
|
134 |
+
"step": 1600
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 4.09,
|
138 |
+
"learning_rate": 7.144161073825504e-05,
|
139 |
+
"loss": 0.6997,
|
140 |
+
"step": 1700
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 4.33,
|
144 |
+
"learning_rate": 7.090469798657718e-05,
|
145 |
+
"loss": 0.5892,
|
146 |
+
"step": 1800
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 4.57,
|
150 |
+
"learning_rate": 7.036778523489933e-05,
|
151 |
+
"loss": 0.6111,
|
152 |
+
"step": 1900
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 4.81,
|
156 |
+
"learning_rate": 6.983087248322148e-05,
|
157 |
+
"loss": 0.6103,
|
158 |
+
"step": 2000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 4.81,
|
162 |
+
"eval_las": 73.0783428457847,
|
163 |
+
"eval_loss": 1.0303574800491333,
|
164 |
+
"eval_runtime": 11.8592,
|
165 |
+
"eval_samples_per_second": 139.892,
|
166 |
+
"eval_steps_per_second": 17.539,
|
167 |
+
"eval_uas": 81.92350285373541,
|
168 |
+
"step": 2000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 5.05,
|
172 |
+
"learning_rate": 6.929395973154363e-05,
|
173 |
+
"loss": 0.6054,
|
174 |
+
"step": 2100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 5.29,
|
178 |
+
"learning_rate": 6.875704697986578e-05,
|
179 |
+
"loss": 0.4648,
|
180 |
+
"step": 2200
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 5.53,
|
184 |
+
"learning_rate": 6.822013422818793e-05,
|
185 |
+
"loss": 0.4894,
|
186 |
+
"step": 2300
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 5.77,
|
190 |
+
"learning_rate": 6.768322147651007e-05,
|
191 |
+
"loss": 0.5087,
|
192 |
+
"step": 2400
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 6.01,
|
196 |
+
"learning_rate": 6.714630872483222e-05,
|
197 |
+
"loss": 0.5131,
|
198 |
+
"step": 2500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 6.01,
|
202 |
+
"eval_las": 73.69452253173183,
|
203 |
+
"eval_loss": 1.1480714082717896,
|
204 |
+
"eval_runtime": 11.8558,
|
205 |
+
"eval_samples_per_second": 139.932,
|
206 |
+
"eval_steps_per_second": 17.544,
|
207 |
+
"eval_uas": 82.44881733253825,
|
208 |
+
"step": 2500
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 6.25,
|
212 |
+
"learning_rate": 6.660939597315437e-05,
|
213 |
+
"loss": 0.3686,
|
214 |
+
"step": 2600
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 6.49,
|
218 |
+
"learning_rate": 6.607248322147652e-05,
|
219 |
+
"loss": 0.381,
|
220 |
+
"step": 2700
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 6.73,
|
224 |
+
"learning_rate": 6.553557046979867e-05,
|
225 |
+
"loss": 0.408,
|
226 |
+
"step": 2800
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 6.97,
|
230 |
+
"learning_rate": 6.499865771812081e-05,
|
231 |
+
"loss": 0.4176,
|
232 |
+
"step": 2900
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 7.21,
|
236 |
+
"learning_rate": 6.446174496644296e-05,
|
237 |
+
"loss": 0.3048,
|
238 |
+
"step": 3000
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 7.21,
|
242 |
+
"eval_las": 73.29698725047562,
|
243 |
+
"eval_loss": 1.3656591176986694,
|
244 |
+
"eval_runtime": 11.8603,
|
245 |
+
"eval_samples_per_second": 139.878,
|
246 |
+
"eval_steps_per_second": 17.537,
|
247 |
+
"eval_uas": 82.40338472896612,
|
248 |
+
"step": 3000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 7.45,
|
252 |
+
"learning_rate": 6.392483221476511e-05,
|
253 |
+
"loss": 0.2996,
|
254 |
+
"step": 3100
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.69,
|
258 |
+
"learning_rate": 6.338791946308726e-05,
|
259 |
+
"loss": 0.3191,
|
260 |
+
"step": 3200
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 7.93,
|
264 |
+
"learning_rate": 6.28510067114094e-05,
|
265 |
+
"loss": 0.3222,
|
266 |
+
"step": 3300
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 8.17,
|
270 |
+
"learning_rate": 6.231409395973154e-05,
|
271 |
+
"loss": 0.2624,
|
272 |
+
"step": 3400
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 8.41,
|
276 |
+
"learning_rate": 6.177718120805369e-05,
|
277 |
+
"loss": 0.2485,
|
278 |
+
"step": 3500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 8.41,
|
282 |
+
"eval_las": 73.33106170315473,
|
283 |
+
"eval_loss": 1.4516910314559937,
|
284 |
+
"eval_runtime": 11.8613,
|
285 |
+
"eval_samples_per_second": 139.867,
|
286 |
+
"eval_steps_per_second": 17.536,
|
287 |
+
"eval_uas": 82.43461964392196,
|
288 |
+
"step": 3500
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 8.65,
|
292 |
+
"learning_rate": 6.124026845637584e-05,
|
293 |
+
"loss": 0.247,
|
294 |
+
"step": 3600
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 8.89,
|
298 |
+
"learning_rate": 6.070335570469799e-05,
|
299 |
+
"loss": 0.269,
|
300 |
+
"step": 3700
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 9.13,
|
304 |
+
"learning_rate": 6.0166442953020136e-05,
|
305 |
+
"loss": 0.2213,
|
306 |
+
"step": 3800
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 9.38,
|
310 |
+
"learning_rate": 5.962953020134229e-05,
|
311 |
+
"loss": 0.1917,
|
312 |
+
"step": 3900
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 9.62,
|
316 |
+
"learning_rate": 5.909261744966444e-05,
|
317 |
+
"loss": 0.2013,
|
318 |
+
"step": 4000
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 9.62,
|
322 |
+
"eval_las": 73.58945963597127,
|
323 |
+
"eval_loss": 1.5729166269302368,
|
324 |
+
"eval_runtime": 11.8551,
|
325 |
+
"eval_samples_per_second": 139.94,
|
326 |
+
"eval_steps_per_second": 17.545,
|
327 |
+
"eval_uas": 82.28980322003578,
|
328 |
+
"step": 4000
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 9.86,
|
332 |
+
"learning_rate": 5.855570469798659e-05,
|
333 |
+
"loss": 0.2064,
|
334 |
+
"step": 4100
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 10.1,
|
338 |
+
"learning_rate": 5.8018791946308735e-05,
|
339 |
+
"loss": 0.1845,
|
340 |
+
"step": 4200
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 10.34,
|
344 |
+
"learning_rate": 5.7481879194630884e-05,
|
345 |
+
"loss": 0.1576,
|
346 |
+
"step": 4300
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 10.58,
|
350 |
+
"learning_rate": 5.694496644295303e-05,
|
351 |
+
"loss": 0.1647,
|
352 |
+
"step": 4400
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 10.82,
|
356 |
+
"learning_rate": 5.6408053691275166e-05,
|
357 |
+
"loss": 0.17,
|
358 |
+
"step": 4500
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 10.82,
|
362 |
+
"eval_las": 73.72859698441094,
|
363 |
+
"eval_loss": 1.6659384965896606,
|
364 |
+
"eval_runtime": 11.8486,
|
365 |
+
"eval_samples_per_second": 140.016,
|
366 |
+
"eval_steps_per_second": 17.555,
|
367 |
+
"eval_uas": 82.71289434080131,
|
368 |
+
"step": 4500
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 11.06,
|
372 |
+
"learning_rate": 5.5871140939597315e-05,
|
373 |
+
"loss": 0.1642,
|
374 |
+
"step": 4600
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 11.3,
|
378 |
+
"learning_rate": 5.533422818791946e-05,
|
379 |
+
"loss": 0.1259,
|
380 |
+
"step": 4700
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 11.54,
|
384 |
+
"learning_rate": 5.479731543624161e-05,
|
385 |
+
"loss": 0.1365,
|
386 |
+
"step": 4800
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 11.78,
|
390 |
+
"learning_rate": 5.426040268456376e-05,
|
391 |
+
"loss": 0.1398,
|
392 |
+
"step": 4900
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 12.02,
|
396 |
+
"learning_rate": 5.372348993288591e-05,
|
397 |
+
"loss": 0.1447,
|
398 |
+
"step": 5000
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 12.02,
|
402 |
+
"eval_las": 74.01539029446006,
|
403 |
+
"eval_loss": 1.8783390522003174,
|
404 |
+
"eval_runtime": 11.8594,
|
405 |
+
"eval_samples_per_second": 139.889,
|
406 |
+
"eval_steps_per_second": 17.539,
|
407 |
+
"eval_uas": 82.87474799102706,
|
408 |
+
"step": 5000
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 12.26,
|
412 |
+
"learning_rate": 5.3186577181208056e-05,
|
413 |
+
"loss": 0.1091,
|
414 |
+
"step": 5100
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 12.5,
|
418 |
+
"learning_rate": 5.2649664429530204e-05,
|
419 |
+
"loss": 0.1146,
|
420 |
+
"step": 5200
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 12.74,
|
424 |
+
"learning_rate": 5.211275167785235e-05,
|
425 |
+
"loss": 0.1186,
|
426 |
+
"step": 5300
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 12.98,
|
430 |
+
"learning_rate": 5.15758389261745e-05,
|
431 |
+
"loss": 0.1171,
|
432 |
+
"step": 5400
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 13.22,
|
436 |
+
"learning_rate": 5.1038926174496656e-05,
|
437 |
+
"loss": 0.0908,
|
438 |
+
"step": 5500
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 13.22,
|
442 |
+
"eval_las": 73.81094357838543,
|
443 |
+
"eval_loss": 2.0186927318573,
|
444 |
+
"eval_runtime": 11.8461,
|
445 |
+
"eval_samples_per_second": 140.046,
|
446 |
+
"eval_steps_per_second": 17.558,
|
447 |
+
"eval_uas": 82.64758497316636,
|
448 |
+
"step": 5500
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 13.46,
|
452 |
+
"learning_rate": 5.050201342281879e-05,
|
453 |
+
"loss": 0.0969,
|
454 |
+
"step": 5600
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 13.7,
|
458 |
+
"learning_rate": 4.996510067114094e-05,
|
459 |
+
"loss": 0.099,
|
460 |
+
"step": 5700
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 13.94,
|
464 |
+
"learning_rate": 4.942818791946309e-05,
|
465 |
+
"loss": 0.0998,
|
466 |
+
"step": 5800
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 14.18,
|
470 |
+
"learning_rate": 4.8891275167785235e-05,
|
471 |
+
"loss": 0.078,
|
472 |
+
"step": 5900
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 14.42,
|
476 |
+
"learning_rate": 4.835436241610738e-05,
|
477 |
+
"loss": 0.0827,
|
478 |
+
"step": 6000
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 14.42,
|
482 |
+
"eval_las": 74.11761365249737,
|
483 |
+
"eval_loss": 2.0184013843536377,
|
484 |
+
"eval_runtime": 11.8521,
|
485 |
+
"eval_samples_per_second": 139.975,
|
486 |
+
"eval_steps_per_second": 17.55,
|
487 |
+
"eval_uas": 82.9343782832155,
|
488 |
+
"step": 6000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 14.66,
|
492 |
+
"learning_rate": 4.781744966442953e-05,
|
493 |
+
"loss": 0.084,
|
494 |
+
"step": 6100
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 14.9,
|
498 |
+
"learning_rate": 4.728053691275168e-05,
|
499 |
+
"loss": 0.0891,
|
500 |
+
"step": 6200
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 15.14,
|
504 |
+
"learning_rate": 4.674362416107383e-05,
|
505 |
+
"loss": 0.076,
|
506 |
+
"step": 6300
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 15.38,
|
510 |
+
"learning_rate": 4.6206711409395976e-05,
|
511 |
+
"loss": 0.0747,
|
512 |
+
"step": 6400
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 15.62,
|
516 |
+
"learning_rate": 4.5669798657718125e-05,
|
517 |
+
"loss": 0.0738,
|
518 |
+
"step": 6500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 15.62,
|
522 |
+
"eval_las": 74.12045319022063,
|
523 |
+
"eval_loss": 2.130760431289673,
|
524 |
+
"eval_runtime": 11.8527,
|
525 |
+
"eval_samples_per_second": 139.968,
|
526 |
+
"eval_steps_per_second": 17.549,
|
527 |
+
"eval_uas": 82.88042706647359,
|
528 |
+
"step": 6500
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 15.87,
|
532 |
+
"learning_rate": 4.513288590604027e-05,
|
533 |
+
"loss": 0.0725,
|
534 |
+
"step": 6600
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 16.11,
|
538 |
+
"learning_rate": 4.459597315436242e-05,
|
539 |
+
"loss": 0.0669,
|
540 |
+
"step": 6700
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 16.35,
|
544 |
+
"learning_rate": 4.405906040268456e-05,
|
545 |
+
"loss": 0.0632,
|
546 |
+
"step": 6800
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 16.59,
|
550 |
+
"learning_rate": 4.352214765100671e-05,
|
551 |
+
"loss": 0.0649,
|
552 |
+
"step": 6900
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 16.83,
|
556 |
+
"learning_rate": 4.298523489932886e-05,
|
557 |
+
"loss": 0.0667,
|
558 |
+
"step": 7000
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 16.83,
|
562 |
+
"eval_las": 74.06650197347872,
|
563 |
+
"eval_loss": 2.201524019241333,
|
564 |
+
"eval_runtime": 11.8493,
|
565 |
+
"eval_samples_per_second": 140.008,
|
566 |
+
"eval_steps_per_second": 17.554,
|
567 |
+
"eval_uas": 82.75548740665019,
|
568 |
+
"step": 7000
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 17.07,
|
572 |
+
"learning_rate": 4.244832214765101e-05,
|
573 |
+
"loss": 0.0607,
|
574 |
+
"step": 7100
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 17.31,
|
578 |
+
"learning_rate": 4.1911409395973156e-05,
|
579 |
+
"loss": 0.0532,
|
580 |
+
"step": 7200
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 17.55,
|
584 |
+
"learning_rate": 4.1374496644295304e-05,
|
585 |
+
"loss": 0.0544,
|
586 |
+
"step": 7300
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 17.79,
|
590 |
+
"learning_rate": 4.083758389261745e-05,
|
591 |
+
"loss": 0.0558,
|
592 |
+
"step": 7400
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 18.03,
|
596 |
+
"learning_rate": 4.03006711409396e-05,
|
597 |
+
"loss": 0.0537,
|
598 |
+
"step": 7500
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 18.03,
|
602 |
+
"eval_las": 74.13465087883692,
|
603 |
+
"eval_loss": 2.413492202758789,
|
604 |
+
"eval_runtime": 11.8547,
|
605 |
+
"eval_samples_per_second": 139.944,
|
606 |
+
"eval_steps_per_second": 17.546,
|
607 |
+
"eval_uas": 82.8719084533038,
|
608 |
+
"step": 7500
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 18.27,
|
612 |
+
"learning_rate": 3.976375838926175e-05,
|
613 |
+
"loss": 0.0462,
|
614 |
+
"step": 7600
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 18.51,
|
618 |
+
"learning_rate": 3.92268456375839e-05,
|
619 |
+
"loss": 0.0484,
|
620 |
+
"step": 7700
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 18.75,
|
624 |
+
"learning_rate": 3.8689932885906045e-05,
|
625 |
+
"loss": 0.0477,
|
626 |
+
"step": 7800
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 18.99,
|
630 |
+
"learning_rate": 3.815302013422819e-05,
|
631 |
+
"loss": 0.0527,
|
632 |
+
"step": 7900
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 19.23,
|
636 |
+
"learning_rate": 3.761610738255034e-05,
|
637 |
+
"loss": 0.0394,
|
638 |
+
"step": 8000
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 19.23,
|
642 |
+
"eval_las": 74.10625550160434,
|
643 |
+
"eval_loss": 2.4247446060180664,
|
644 |
+
"eval_runtime": 11.8548,
|
645 |
+
"eval_samples_per_second": 139.943,
|
646 |
+
"eval_steps_per_second": 17.546,
|
647 |
+
"eval_uas": 82.85203168924099,
|
648 |
+
"step": 8000
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 19.47,
|
652 |
+
"learning_rate": 3.707919463087249e-05,
|
653 |
+
"loss": 0.0407,
|
654 |
+
"step": 8100
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 19.71,
|
658 |
+
"learning_rate": 3.654228187919463e-05,
|
659 |
+
"loss": 0.045,
|
660 |
+
"step": 8200
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 19.95,
|
664 |
+
"learning_rate": 3.600536912751678e-05,
|
665 |
+
"loss": 0.044,
|
666 |
+
"step": 8300
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 20.19,
|
670 |
+
"learning_rate": 3.546845637583893e-05,
|
671 |
+
"loss": 0.0336,
|
672 |
+
"step": 8400
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 20.43,
|
676 |
+
"learning_rate": 3.4931543624161076e-05,
|
677 |
+
"loss": 0.0358,
|
678 |
+
"step": 8500
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 20.43,
|
682 |
+
"eval_las": 74.19996024647187,
|
683 |
+
"eval_loss": 2.439199209213257,
|
684 |
+
"eval_runtime": 11.8496,
|
685 |
+
"eval_samples_per_second": 140.005,
|
686 |
+
"eval_steps_per_second": 17.553,
|
687 |
+
"eval_uas": 83.01672487719,
|
688 |
+
"step": 8500
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 20.67,
|
692 |
+
"learning_rate": 3.4394630872483224e-05,
|
693 |
+
"loss": 0.0352,
|
694 |
+
"step": 8600
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 20.91,
|
698 |
+
"learning_rate": 3.385771812080537e-05,
|
699 |
+
"loss": 0.038,
|
700 |
+
"step": 8700
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 21.15,
|
704 |
+
"learning_rate": 3.332080536912752e-05,
|
705 |
+
"loss": 0.0314,
|
706 |
+
"step": 8800
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 21.39,
|
710 |
+
"learning_rate": 3.278389261744967e-05,
|
711 |
+
"loss": 0.0323,
|
712 |
+
"step": 8900
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 21.63,
|
716 |
+
"learning_rate": 3.224697986577182e-05,
|
717 |
+
"loss": 0.0293,
|
718 |
+
"step": 9000
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 21.63,
|
722 |
+
"eval_las": 74.28230684044638,
|
723 |
+
"eval_loss": 2.6793813705444336,
|
724 |
+
"eval_runtime": 11.8495,
|
725 |
+
"eval_samples_per_second": 140.006,
|
726 |
+
"eval_steps_per_second": 17.553,
|
727 |
+
"eval_uas": 82.96277366044808,
|
728 |
+
"step": 9000
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 21.88,
|
732 |
+
"learning_rate": 3.1710067114093965e-05,
|
733 |
+
"loss": 0.0332,
|
734 |
+
"step": 9100
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 22.12,
|
738 |
+
"learning_rate": 3.1173154362416114e-05,
|
739 |
+
"loss": 0.0302,
|
740 |
+
"step": 9200
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 22.36,
|
744 |
+
"learning_rate": 3.0636241610738255e-05,
|
745 |
+
"loss": 0.0268,
|
746 |
+
"step": 9300
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 22.6,
|
750 |
+
"learning_rate": 3.0099328859060403e-05,
|
751 |
+
"loss": 0.0273,
|
752 |
+
"step": 9400
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 22.84,
|
756 |
+
"learning_rate": 2.956241610738255e-05,
|
757 |
+
"loss": 0.0275,
|
758 |
+
"step": 9500
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 22.84,
|
762 |
+
"eval_las": 74.25391146321378,
|
763 |
+
"eval_loss": 2.634089231491089,
|
764 |
+
"eval_runtime": 11.8524,
|
765 |
+
"eval_samples_per_second": 139.972,
|
766 |
+
"eval_steps_per_second": 17.549,
|
767 |
+
"eval_uas": 82.99400857540392,
|
768 |
+
"step": 9500
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 23.08,
|
772 |
+
"learning_rate": 2.90255033557047e-05,
|
773 |
+
"loss": 0.0277,
|
774 |
+
"step": 9600
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 23.32,
|
778 |
+
"learning_rate": 2.8488590604026848e-05,
|
779 |
+
"loss": 0.0245,
|
780 |
+
"step": 9700
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 23.56,
|
784 |
+
"learning_rate": 2.7951677852348996e-05,
|
785 |
+
"loss": 0.0228,
|
786 |
+
"step": 9800
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 23.8,
|
790 |
+
"learning_rate": 2.741476510067114e-05,
|
791 |
+
"loss": 0.0242,
|
792 |
+
"step": 9900
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 24.04,
|
796 |
+
"learning_rate": 2.687785234899329e-05,
|
797 |
+
"loss": 0.0235,
|
798 |
+
"step": 10000
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 24.04,
|
802 |
+
"eval_las": 74.29366499133941,
|
803 |
+
"eval_loss": 2.7188923358917236,
|
804 |
+
"eval_runtime": 11.8499,
|
805 |
+
"eval_samples_per_second": 140.001,
|
806 |
+
"eval_steps_per_second": 17.553,
|
807 |
+
"eval_uas": 83.09339239571798,
|
808 |
+
"step": 10000
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 24.28,
|
812 |
+
"learning_rate": 2.6340939597315438e-05,
|
813 |
+
"loss": 0.0207,
|
814 |
+
"step": 10100
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 24.52,
|
818 |
+
"learning_rate": 2.5804026845637586e-05,
|
819 |
+
"loss": 0.0204,
|
820 |
+
"step": 10200
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 24.76,
|
824 |
+
"learning_rate": 2.5267114093959734e-05,
|
825 |
+
"loss": 0.0239,
|
826 |
+
"step": 10300
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 25.0,
|
830 |
+
"learning_rate": 2.4730201342281882e-05,
|
831 |
+
"loss": 0.0218,
|
832 |
+
"step": 10400
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 25.24,
|
836 |
+
"learning_rate": 2.4193288590604027e-05,
|
837 |
+
"loss": 0.0167,
|
838 |
+
"step": 10500
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 25.24,
|
842 |
+
"eval_las": 74.49243263196752,
|
843 |
+
"eval_loss": 2.821323871612549,
|
844 |
+
"eval_runtime": 11.852,
|
845 |
+
"eval_samples_per_second": 139.976,
|
846 |
+
"eval_steps_per_second": 17.55,
|
847 |
+
"eval_uas": 83.17005991424597,
|
848 |
+
"step": 10500
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 25.48,
|
852 |
+
"learning_rate": 2.3656375838926175e-05,
|
853 |
+
"loss": 0.0189,
|
854 |
+
"step": 10600
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 25.72,
|
858 |
+
"learning_rate": 2.3119463087248324e-05,
|
859 |
+
"loss": 0.0189,
|
860 |
+
"step": 10700
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 25.96,
|
864 |
+
"learning_rate": 2.2582550335570472e-05,
|
865 |
+
"loss": 0.0202,
|
866 |
+
"step": 10800
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 26.2,
|
870 |
+
"learning_rate": 2.204563758389262e-05,
|
871 |
+
"loss": 0.0161,
|
872 |
+
"step": 10900
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 26.44,
|
876 |
+
"learning_rate": 2.150872483221477e-05,
|
877 |
+
"loss": 0.0157,
|
878 |
+
"step": 11000
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 26.44,
|
882 |
+
"eval_las": 74.57193968821876,
|
883 |
+
"eval_loss": 2.849531650543213,
|
884 |
+
"eval_runtime": 11.8513,
|
885 |
+
"eval_samples_per_second": 139.985,
|
886 |
+
"eval_steps_per_second": 17.551,
|
887 |
+
"eval_uas": 83.22117159326461,
|
888 |
+
"step": 11000
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 26.68,
|
892 |
+
"learning_rate": 2.0971812080536913e-05,
|
893 |
+
"loss": 0.0166,
|
894 |
+
"step": 11100
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 26.92,
|
898 |
+
"learning_rate": 2.043489932885906e-05,
|
899 |
+
"loss": 0.0156,
|
900 |
+
"step": 11200
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 27.16,
|
904 |
+
"learning_rate": 1.989798657718121e-05,
|
905 |
+
"loss": 0.0143,
|
906 |
+
"step": 11300
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 27.4,
|
910 |
+
"learning_rate": 1.9361073825503358e-05,
|
911 |
+
"loss": 0.0141,
|
912 |
+
"step": 11400
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 27.64,
|
916 |
+
"learning_rate": 1.8824161073825503e-05,
|
917 |
+
"loss": 0.014,
|
918 |
+
"step": 11500
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 27.64,
|
922 |
+
"eval_las": 74.45267910384189,
|
923 |
+
"eval_loss": 2.8970541954040527,
|
924 |
+
"eval_runtime": 11.8508,
|
925 |
+
"eval_samples_per_second": 139.991,
|
926 |
+
"eval_steps_per_second": 17.552,
|
927 |
+
"eval_uas": 83.05931794303886,
|
928 |
+
"step": 11500
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 27.88,
|
932 |
+
"learning_rate": 1.828724832214765e-05,
|
933 |
+
"loss": 0.0135,
|
934 |
+
"step": 11600
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 28.12,
|
938 |
+
"learning_rate": 1.77503355704698e-05,
|
939 |
+
"loss": 0.0124,
|
940 |
+
"step": 11700
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 28.37,
|
944 |
+
"learning_rate": 1.7213422818791948e-05,
|
945 |
+
"loss": 0.0112,
|
946 |
+
"step": 11800
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 28.61,
|
950 |
+
"learning_rate": 1.6676510067114096e-05,
|
951 |
+
"loss": 0.0115,
|
952 |
+
"step": 11900
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 28.85,
|
956 |
+
"learning_rate": 1.6139597315436244e-05,
|
957 |
+
"loss": 0.0104,
|
958 |
+
"step": 12000
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 28.85,
|
962 |
+
"eval_las": 74.57761876366527,
|
963 |
+
"eval_loss": 2.9912426471710205,
|
964 |
+
"eval_runtime": 11.851,
|
965 |
+
"eval_samples_per_second": 139.988,
|
966 |
+
"eval_steps_per_second": 17.551,
|
967 |
+
"eval_uas": 83.14734361245989,
|
968 |
+
"step": 12000
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 29.09,
|
972 |
+
"learning_rate": 1.560268456375839e-05,
|
973 |
+
"loss": 0.0106,
|
974 |
+
"step": 12100
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 29.33,
|
978 |
+
"learning_rate": 1.5071140939597317e-05,
|
979 |
+
"loss": 0.0101,
|
980 |
+
"step": 12200
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 29.57,
|
984 |
+
"learning_rate": 1.4534228187919464e-05,
|
985 |
+
"loss": 0.0096,
|
986 |
+
"step": 12300
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 29.81,
|
990 |
+
"learning_rate": 1.3997315436241612e-05,
|
991 |
+
"loss": 0.0093,
|
992 |
+
"step": 12400
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 30.05,
|
996 |
+
"learning_rate": 1.346040268456376e-05,
|
997 |
+
"loss": 0.0093,
|
998 |
+
"step": 12500
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 30.05,
|
1002 |
+
"eval_las": 74.54922338643269,
|
1003 |
+
"eval_loss": 3.005786418914795,
|
1004 |
+
"eval_runtime": 11.8568,
|
1005 |
+
"eval_samples_per_second": 139.92,
|
1006 |
+
"eval_steps_per_second": 17.543,
|
1007 |
+
"eval_uas": 83.15586222562966,
|
1008 |
+
"step": 12500
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 30.29,
|
1012 |
+
"learning_rate": 1.2923489932885907e-05,
|
1013 |
+
"loss": 0.0084,
|
1014 |
+
"step": 12600
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 30.53,
|
1018 |
+
"learning_rate": 1.2386577181208055e-05,
|
1019 |
+
"loss": 0.0088,
|
1020 |
+
"step": 12700
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 30.77,
|
1024 |
+
"learning_rate": 1.1849664429530204e-05,
|
1025 |
+
"loss": 0.0075,
|
1026 |
+
"step": 12800
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 31.01,
|
1030 |
+
"learning_rate": 1.131275167785235e-05,
|
1031 |
+
"loss": 0.0094,
|
1032 |
+
"step": 12900
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 31.25,
|
1036 |
+
"learning_rate": 1.0775838926174498e-05,
|
1037 |
+
"loss": 0.0071,
|
1038 |
+
"step": 13000
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 31.25,
|
1042 |
+
"eval_las": 74.84453530965159,
|
1043 |
+
"eval_loss": 3.0800094604492188,
|
1044 |
+
"eval_runtime": 11.8601,
|
1045 |
+
"eval_samples_per_second": 139.881,
|
1046 |
+
"eval_steps_per_second": 17.538,
|
1047 |
+
"eval_uas": 83.40574154527643,
|
1048 |
+
"step": 13000
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 31.49,
|
1052 |
+
"learning_rate": 1.0238926174496647e-05,
|
1053 |
+
"loss": 0.0065,
|
1054 |
+
"step": 13100
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 31.73,
|
1058 |
+
"learning_rate": 9.702013422818793e-06,
|
1059 |
+
"loss": 0.0067,
|
1060 |
+
"step": 13200
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 31.97,
|
1064 |
+
"learning_rate": 9.165100671140941e-06,
|
1065 |
+
"loss": 0.0069,
|
1066 |
+
"step": 13300
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 32.21,
|
1070 |
+
"learning_rate": 8.628187919463088e-06,
|
1071 |
+
"loss": 0.0056,
|
1072 |
+
"step": 13400
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 32.45,
|
1076 |
+
"learning_rate": 8.091275167785234e-06,
|
1077 |
+
"loss": 0.0052,
|
1078 |
+
"step": 13500
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 32.45,
|
1082 |
+
"eval_las": 74.84453530965159,
|
1083 |
+
"eval_loss": 3.167156219482422,
|
1084 |
+
"eval_runtime": 11.8563,
|
1085 |
+
"eval_samples_per_second": 139.926,
|
1086 |
+
"eval_steps_per_second": 17.543,
|
1087 |
+
"eval_uas": 83.41993923389272,
|
1088 |
+
"step": 13500
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 32.69,
|
1092 |
+
"learning_rate": 7.5543624161073835e-06,
|
1093 |
+
"loss": 0.0057,
|
1094 |
+
"step": 13600
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 32.93,
|
1098 |
+
"learning_rate": 7.017449664429531e-06,
|
1099 |
+
"loss": 0.0057,
|
1100 |
+
"step": 13700
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 33.17,
|
1104 |
+
"learning_rate": 6.480536912751678e-06,
|
1105 |
+
"loss": 0.0054,
|
1106 |
+
"step": 13800
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 33.41,
|
1110 |
+
"learning_rate": 5.943624161073826e-06,
|
1111 |
+
"loss": 0.0048,
|
1112 |
+
"step": 13900
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 33.65,
|
1116 |
+
"learning_rate": 5.406711409395974e-06,
|
1117 |
+
"loss": 0.0054,
|
1118 |
+
"step": 14000
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 33.65,
|
1122 |
+
"eval_las": 74.90132606411676,
|
1123 |
+
"eval_loss": 3.178938627243042,
|
1124 |
+
"eval_runtime": 11.8514,
|
1125 |
+
"eval_samples_per_second": 139.983,
|
1126 |
+
"eval_steps_per_second": 17.551,
|
1127 |
+
"eval_uas": 83.49376721469744,
|
1128 |
+
"step": 14000
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 33.89,
|
1132 |
+
"learning_rate": 4.869798657718121e-06,
|
1133 |
+
"loss": 0.0049,
|
1134 |
+
"step": 14100
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 34.13,
|
1138 |
+
"learning_rate": 4.332885906040269e-06,
|
1139 |
+
"loss": 0.0039,
|
1140 |
+
"step": 14200
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 34.38,
|
1144 |
+
"learning_rate": 3.795973154362416e-06,
|
1145 |
+
"loss": 0.005,
|
1146 |
+
"step": 14300
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 34.62,
|
1150 |
+
"learning_rate": 3.259060402684564e-06,
|
1151 |
+
"loss": 0.004,
|
1152 |
+
"step": 14400
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 34.86,
|
1156 |
+
"learning_rate": 2.722147651006712e-06,
|
1157 |
+
"loss": 0.0042,
|
1158 |
+
"step": 14500
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 34.86,
|
1162 |
+
"eval_las": 74.9325609790726,
|
1163 |
+
"eval_loss": 3.2010536193847656,
|
1164 |
+
"eval_runtime": 11.8566,
|
1165 |
+
"eval_samples_per_second": 139.922,
|
1166 |
+
"eval_steps_per_second": 17.543,
|
1167 |
+
"eval_uas": 83.53636028054633,
|
1168 |
+
"step": 14500
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 35.1,
|
1172 |
+
"learning_rate": 2.185234899328859e-06,
|
1173 |
+
"loss": 0.0038,
|
1174 |
+
"step": 14600
|
1175 |
+
},
|
1176 |
+
{
|
1177 |
+
"epoch": 35.34,
|
1178 |
+
"learning_rate": 1.648322147651007e-06,
|
1179 |
+
"loss": 0.0045,
|
1180 |
+
"step": 14700
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 35.58,
|
1184 |
+
"learning_rate": 1.1114093959731544e-06,
|
1185 |
+
"loss": 0.0036,
|
1186 |
+
"step": 14800
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 35.82,
|
1190 |
+
"learning_rate": 5.74496644295302e-07,
|
1191 |
+
"loss": 0.0042,
|
1192 |
+
"step": 14900
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 36.06,
|
1196 |
+
"learning_rate": 3.758389261744967e-08,
|
1197 |
+
"loss": 0.0037,
|
1198 |
+
"step": 15000
|
1199 |
+
},
|
1200 |
+
{
|
1201 |
+
"epoch": 36.06,
|
1202 |
+
"eval_las": 74.99219127126105,
|
1203 |
+
"eval_loss": 3.1982181072235107,
|
1204 |
+
"eval_runtime": 11.8515,
|
1205 |
+
"eval_samples_per_second": 139.982,
|
1206 |
+
"eval_steps_per_second": 17.55,
|
1207 |
+
"eval_uas": 83.58747195956498,
|
1208 |
+
"step": 15000
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 36.06,
|
1212 |
+
"step": 15000,
|
1213 |
+
"total_flos": 8.010080992700006e+16,
|
1214 |
+
"train_loss": 0.2272949548403422,
|
1215 |
+
"train_runtime": 8371.5337,
|
1216 |
+
"train_samples_per_second": 57.337,
|
1217 |
+
"train_steps_per_second": 1.792
|
1218 |
+
}
|
1219 |
+
],
|
1220 |
+
"max_steps": 15000,
|
1221 |
+
"num_train_epochs": 37,
|
1222 |
+
"total_flos": 8.010080992700006e+16,
|
1223 |
+
"trial_name": null,
|
1224 |
+
"trial_params": null
|
1225 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22fc7168ddb495fc2dc83f71e5258a858f6d2ca7cabbdb2b4559546fac89dd39
|
3 |
+
size 3387
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|