Md Mushfiqur Rahman
commited on
Commit
•
ac080d4
1
Parent(s):
e916d76
Upload with huggingface_hub
Browse files- README.md +15 -0
- all_results.json +22 -0
- config.json +111 -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 +625 -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": 19.13,
|
| 3 |
+
"eval_las": 89.27591554336156,
|
| 4 |
+
"eval_loss": 0.9186694025993347,
|
| 5 |
+
"eval_runtime": 12.8763,
|
| 6 |
+
"eval_samples": 2001,
|
| 7 |
+
"eval_samples_per_second": 155.402,
|
| 8 |
+
"eval_steps_per_second": 19.493,
|
| 9 |
+
"eval_uas": 91.59409916895304,
|
| 10 |
+
"test_las": 89.08105523232646,
|
| 11 |
+
"test_loss": 0.9234644770622253,
|
| 12 |
+
"test_runtime": 13.2736,
|
| 13 |
+
"test_samples": 2077,
|
| 14 |
+
"test_samples_per_second": 156.476,
|
| 15 |
+
"test_steps_per_second": 19.588,
|
| 16 |
+
"test_uas": 91.39236470869531,
|
| 17 |
+
"train_loss": 0.15542098660469056,
|
| 18 |
+
"train_runtime": 4224.7831,
|
| 19 |
+
"train_samples": 12543,
|
| 20 |
+
"train_samples_per_second": 113.615,
|
| 21 |
+
"train_steps_per_second": 3.55
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForBiaffineParsing"
|
| 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": "_",
|
| 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 |
+
"pooler_fc_size": 768,
|
| 101 |
+
"pooler_num_attention_heads": 12,
|
| 102 |
+
"pooler_num_fc_layers": 3,
|
| 103 |
+
"pooler_size_per_head": 128,
|
| 104 |
+
"pooler_type": "first_token_transform",
|
| 105 |
+
"position_embedding_type": "absolute",
|
| 106 |
+
"torch_dtype": "float32",
|
| 107 |
+
"transformers_version": "4.17.0",
|
| 108 |
+
"type_vocab_size": 2,
|
| 109 |
+
"use_cache": true,
|
| 110 |
+
"vocab_size": 119547
|
| 111 |
+
}
|
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:f7f5382e75dfe109e5d924619066c0023d532a558a1d8be14df42e3a0d7ba147
|
| 3 |
+
size 803749941
|
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-multilingual-cased", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,625 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 89.27591554336156,
|
| 3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-parsing-ud-English-EWT/checkpoint-5000",
|
| 4 |
+
"epoch": 19.132653061224488,
|
| 5 |
+
"global_step": 7500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.26,
|
| 12 |
+
"learning_rate": 7.840000000000001e-05,
|
| 13 |
+
"loss": 3.0745,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.51,
|
| 18 |
+
"learning_rate": 7.947382550335571e-05,
|
| 19 |
+
"loss": 0.8754,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.77,
|
| 24 |
+
"learning_rate": 7.893691275167786e-05,
|
| 25 |
+
"loss": 0.6847,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.02,
|
| 30 |
+
"learning_rate": 7.840000000000001e-05,
|
| 31 |
+
"loss": 0.5794,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.28,
|
| 36 |
+
"learning_rate": 7.786308724832216e-05,
|
| 37 |
+
"loss": 0.424,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.28,
|
| 42 |
+
"eval_las": 86.52033878086604,
|
| 43 |
+
"eval_loss": 0.5685478448867798,
|
| 44 |
+
"eval_runtime": 12.8416,
|
| 45 |
+
"eval_samples_per_second": 155.822,
|
| 46 |
+
"eval_steps_per_second": 19.546,
|
| 47 |
+
"eval_uas": 89.4031571831882,
|
| 48 |
+
"step": 500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.53,
|
| 52 |
+
"learning_rate": 7.73261744966443e-05,
|
| 53 |
+
"loss": 0.4108,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.79,
|
| 58 |
+
"learning_rate": 7.678926174496645e-05,
|
| 59 |
+
"loss": 0.4139,
|
| 60 |
+
"step": 700
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 2.04,
|
| 64 |
+
"learning_rate": 7.62523489932886e-05,
|
| 65 |
+
"loss": 0.3663,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.3,
|
| 70 |
+
"learning_rate": 7.571543624161075e-05,
|
| 71 |
+
"loss": 0.2592,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.55,
|
| 76 |
+
"learning_rate": 7.51785234899329e-05,
|
| 77 |
+
"loss": 0.2636,
|
| 78 |
+
"step": 1000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.55,
|
| 82 |
+
"eval_las": 87.8523996978011,
|
| 83 |
+
"eval_loss": 0.5544716715812683,
|
| 84 |
+
"eval_runtime": 12.834,
|
| 85 |
+
"eval_samples_per_second": 155.914,
|
| 86 |
+
"eval_steps_per_second": 19.557,
|
| 87 |
+
"eval_uas": 90.59604755656288,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.81,
|
| 92 |
+
"learning_rate": 7.464161073825505e-05,
|
| 93 |
+
"loss": 0.2582,
|
| 94 |
+
"step": 1100
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.06,
|
| 98 |
+
"learning_rate": 7.410469798657718e-05,
|
| 99 |
+
"loss": 0.2466,
|
| 100 |
+
"step": 1200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.32,
|
| 104 |
+
"learning_rate": 7.357315436241611e-05,
|
| 105 |
+
"loss": 0.1731,
|
| 106 |
+
"step": 1300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.57,
|
| 110 |
+
"learning_rate": 7.303624161073826e-05,
|
| 111 |
+
"loss": 0.1932,
|
| 112 |
+
"step": 1400
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 3.83,
|
| 116 |
+
"learning_rate": 7.249932885906041e-05,
|
| 117 |
+
"loss": 0.1935,
|
| 118 |
+
"step": 1500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 3.83,
|
| 122 |
+
"eval_las": 88.85045131019126,
|
| 123 |
+
"eval_loss": 0.5856050252914429,
|
| 124 |
+
"eval_runtime": 12.8153,
|
| 125 |
+
"eval_samples_per_second": 156.141,
|
| 126 |
+
"eval_steps_per_second": 19.586,
|
| 127 |
+
"eval_uas": 91.49469163783849,
|
| 128 |
+
"step": 1500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.08,
|
| 132 |
+
"learning_rate": 7.196241610738256e-05,
|
| 133 |
+
"loss": 0.1652,
|
| 134 |
+
"step": 1600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.34,
|
| 138 |
+
"learning_rate": 7.142550335570471e-05,
|
| 139 |
+
"loss": 0.1374,
|
| 140 |
+
"step": 1700
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.59,
|
| 144 |
+
"learning_rate": 7.088859060402686e-05,
|
| 145 |
+
"loss": 0.1356,
|
| 146 |
+
"step": 1800
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.85,
|
| 150 |
+
"learning_rate": 7.0351677852349e-05,
|
| 151 |
+
"loss": 0.1431,
|
| 152 |
+
"step": 1900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 5.1,
|
| 156 |
+
"learning_rate": 6.981476510067114e-05,
|
| 157 |
+
"loss": 0.1221,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 5.1,
|
| 162 |
+
"eval_las": 88.68742295916338,
|
| 163 |
+
"eval_loss": 0.7061353325843811,
|
| 164 |
+
"eval_runtime": 12.9124,
|
| 165 |
+
"eval_samples_per_second": 154.967,
|
| 166 |
+
"eval_steps_per_second": 19.439,
|
| 167 |
+
"eval_uas": 91.10103781462485,
|
| 168 |
+
"step": 2000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.36,
|
| 172 |
+
"learning_rate": 6.927785234899329e-05,
|
| 173 |
+
"loss": 0.1071,
|
| 174 |
+
"step": 2100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.61,
|
| 178 |
+
"learning_rate": 6.874093959731543e-05,
|
| 179 |
+
"loss": 0.1046,
|
| 180 |
+
"step": 2200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.87,
|
| 184 |
+
"learning_rate": 6.820402684563758e-05,
|
| 185 |
+
"loss": 0.1113,
|
| 186 |
+
"step": 2300
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 6.12,
|
| 190 |
+
"learning_rate": 6.766711409395973e-05,
|
| 191 |
+
"loss": 0.103,
|
| 192 |
+
"step": 2400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 6.38,
|
| 196 |
+
"learning_rate": 6.713020134228188e-05,
|
| 197 |
+
"loss": 0.0852,
|
| 198 |
+
"step": 2500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.38,
|
| 202 |
+
"eval_las": 88.96974034752873,
|
| 203 |
+
"eval_loss": 0.775122344493866,
|
| 204 |
+
"eval_runtime": 12.9063,
|
| 205 |
+
"eval_samples_per_second": 155.04,
|
| 206 |
+
"eval_steps_per_second": 19.448,
|
| 207 |
+
"eval_uas": 91.53047834903973,
|
| 208 |
+
"step": 2500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 6.63,
|
| 212 |
+
"learning_rate": 6.659328859060403e-05,
|
| 213 |
+
"loss": 0.0804,
|
| 214 |
+
"step": 2600
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 6.89,
|
| 218 |
+
"learning_rate": 6.605637583892618e-05,
|
| 219 |
+
"loss": 0.0855,
|
| 220 |
+
"step": 2700
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 7.14,
|
| 224 |
+
"learning_rate": 6.551946308724832e-05,
|
| 225 |
+
"loss": 0.0762,
|
| 226 |
+
"step": 2800
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.4,
|
| 230 |
+
"learning_rate": 6.498255033557047e-05,
|
| 231 |
+
"loss": 0.0682,
|
| 232 |
+
"step": 2900
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 7.65,
|
| 236 |
+
"learning_rate": 6.444563758389262e-05,
|
| 237 |
+
"loss": 0.0739,
|
| 238 |
+
"step": 3000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 7.65,
|
| 242 |
+
"eval_las": 88.96576404628415,
|
| 243 |
+
"eval_loss": 0.8953888416290283,
|
| 244 |
+
"eval_runtime": 12.8724,
|
| 245 |
+
"eval_samples_per_second": 155.449,
|
| 246 |
+
"eval_steps_per_second": 19.499,
|
| 247 |
+
"eval_uas": 91.44299972165891,
|
| 248 |
+
"step": 3000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.91,
|
| 252 |
+
"learning_rate": 6.390872483221477e-05,
|
| 253 |
+
"loss": 0.0693,
|
| 254 |
+
"step": 3100
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.16,
|
| 258 |
+
"learning_rate": 6.337181208053692e-05,
|
| 259 |
+
"loss": 0.0661,
|
| 260 |
+
"step": 3200
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 8.42,
|
| 264 |
+
"learning_rate": 6.283489932885907e-05,
|
| 265 |
+
"loss": 0.0642,
|
| 266 |
+
"step": 3300
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 8.67,
|
| 270 |
+
"learning_rate": 6.229798657718121e-05,
|
| 271 |
+
"loss": 0.0607,
|
| 272 |
+
"step": 3400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 8.93,
|
| 276 |
+
"learning_rate": 6.176644295302013e-05,
|
| 277 |
+
"loss": 0.0668,
|
| 278 |
+
"step": 3500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 8.93,
|
| 282 |
+
"eval_las": 88.93792993757206,
|
| 283 |
+
"eval_loss": 0.8302858471870422,
|
| 284 |
+
"eval_runtime": 12.9054,
|
| 285 |
+
"eval_samples_per_second": 155.052,
|
| 286 |
+
"eval_steps_per_second": 19.449,
|
| 287 |
+
"eval_uas": 91.45890492663725,
|
| 288 |
+
"step": 3500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 9.18,
|
| 292 |
+
"learning_rate": 6.122953020134228e-05,
|
| 293 |
+
"loss": 0.0553,
|
| 294 |
+
"step": 3600
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 9.44,
|
| 298 |
+
"learning_rate": 6.069261744966444e-05,
|
| 299 |
+
"loss": 0.0546,
|
| 300 |
+
"step": 3700
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 9.69,
|
| 304 |
+
"learning_rate": 6.0155704697986585e-05,
|
| 305 |
+
"loss": 0.0554,
|
| 306 |
+
"step": 3800
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 9.95,
|
| 310 |
+
"learning_rate": 5.9618791946308734e-05,
|
| 311 |
+
"loss": 0.0552,
|
| 312 |
+
"step": 3900
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 10.2,
|
| 316 |
+
"learning_rate": 5.9081879194630875e-05,
|
| 317 |
+
"loss": 0.0512,
|
| 318 |
+
"step": 4000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 10.2,
|
| 322 |
+
"eval_las": 88.94985884130581,
|
| 323 |
+
"eval_loss": 0.9160601496696472,
|
| 324 |
+
"eval_runtime": 12.8984,
|
| 325 |
+
"eval_samples_per_second": 155.135,
|
| 326 |
+
"eval_steps_per_second": 19.46,
|
| 327 |
+
"eval_uas": 91.40721301045768,
|
| 328 |
+
"step": 4000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 10.46,
|
| 332 |
+
"learning_rate": 5.854496644295302e-05,
|
| 333 |
+
"loss": 0.0504,
|
| 334 |
+
"step": 4100
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 10.71,
|
| 338 |
+
"learning_rate": 5.800805369127517e-05,
|
| 339 |
+
"loss": 0.0495,
|
| 340 |
+
"step": 4200
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 10.97,
|
| 344 |
+
"learning_rate": 5.747114093959732e-05,
|
| 345 |
+
"loss": 0.044,
|
| 346 |
+
"step": 4300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 11.22,
|
| 350 |
+
"learning_rate": 5.693422818791947e-05,
|
| 351 |
+
"loss": 0.0402,
|
| 352 |
+
"step": 4400
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 11.48,
|
| 356 |
+
"learning_rate": 5.6397315436241616e-05,
|
| 357 |
+
"loss": 0.0378,
|
| 358 |
+
"step": 4500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 11.48,
|
| 362 |
+
"eval_las": 89.11686349357826,
|
| 363 |
+
"eval_loss": 1.0157352685928345,
|
| 364 |
+
"eval_runtime": 12.8902,
|
| 365 |
+
"eval_samples_per_second": 155.234,
|
| 366 |
+
"eval_steps_per_second": 19.472,
|
| 367 |
+
"eval_uas": 91.51854944530598,
|
| 368 |
+
"step": 4500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 11.73,
|
| 372 |
+
"learning_rate": 5.5860402684563764e-05,
|
| 373 |
+
"loss": 0.044,
|
| 374 |
+
"step": 4600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 11.99,
|
| 378 |
+
"learning_rate": 5.532348993288591e-05,
|
| 379 |
+
"loss": 0.0423,
|
| 380 |
+
"step": 4700
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 12.24,
|
| 384 |
+
"learning_rate": 5.478657718120806e-05,
|
| 385 |
+
"loss": 0.0372,
|
| 386 |
+
"step": 4800
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 12.5,
|
| 390 |
+
"learning_rate": 5.424966442953021e-05,
|
| 391 |
+
"loss": 0.0367,
|
| 392 |
+
"step": 4900
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 12.76,
|
| 396 |
+
"learning_rate": 5.371275167785236e-05,
|
| 397 |
+
"loss": 0.0354,
|
| 398 |
+
"step": 5000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 12.76,
|
| 402 |
+
"eval_las": 89.27591554336156,
|
| 403 |
+
"eval_loss": 0.9186694025993347,
|
| 404 |
+
"eval_runtime": 12.8914,
|
| 405 |
+
"eval_samples_per_second": 155.22,
|
| 406 |
+
"eval_steps_per_second": 19.47,
|
| 407 |
+
"eval_uas": 91.59409916895304,
|
| 408 |
+
"step": 5000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 13.01,
|
| 412 |
+
"learning_rate": 5.31758389261745e-05,
|
| 413 |
+
"loss": 0.0379,
|
| 414 |
+
"step": 5100
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 13.27,
|
| 418 |
+
"learning_rate": 5.263892617449665e-05,
|
| 419 |
+
"loss": 0.0299,
|
| 420 |
+
"step": 5200
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 13.52,
|
| 424 |
+
"learning_rate": 5.2102013422818795e-05,
|
| 425 |
+
"loss": 0.0329,
|
| 426 |
+
"step": 5300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 13.78,
|
| 430 |
+
"learning_rate": 5.1565100671140944e-05,
|
| 431 |
+
"loss": 0.032,
|
| 432 |
+
"step": 5400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 14.03,
|
| 436 |
+
"learning_rate": 5.102818791946309e-05,
|
| 437 |
+
"loss": 0.0287,
|
| 438 |
+
"step": 5500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 14.03,
|
| 442 |
+
"eval_las": 88.96178774503957,
|
| 443 |
+
"eval_loss": 1.0049980878829956,
|
| 444 |
+
"eval_runtime": 12.88,
|
| 445 |
+
"eval_samples_per_second": 155.357,
|
| 446 |
+
"eval_steps_per_second": 19.488,
|
| 447 |
+
"eval_uas": 91.26406616565271,
|
| 448 |
+
"step": 5500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 14.29,
|
| 452 |
+
"learning_rate": 5.049127516778524e-05,
|
| 453 |
+
"loss": 0.0271,
|
| 454 |
+
"step": 5600
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 14.54,
|
| 458 |
+
"learning_rate": 4.995436241610739e-05,
|
| 459 |
+
"loss": 0.0268,
|
| 460 |
+
"step": 5700
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 14.8,
|
| 464 |
+
"learning_rate": 4.941744966442954e-05,
|
| 465 |
+
"loss": 0.0305,
|
| 466 |
+
"step": 5800
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 15.05,
|
| 470 |
+
"learning_rate": 4.8880536912751685e-05,
|
| 471 |
+
"loss": 0.026,
|
| 472 |
+
"step": 5900
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 15.31,
|
| 476 |
+
"learning_rate": 4.834362416107383e-05,
|
| 477 |
+
"loss": 0.0211,
|
| 478 |
+
"step": 6000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 15.31,
|
| 482 |
+
"eval_las": 89.10891089108911,
|
| 483 |
+
"eval_loss": 1.1387187242507935,
|
| 484 |
+
"eval_runtime": 12.8891,
|
| 485 |
+
"eval_samples_per_second": 155.247,
|
| 486 |
+
"eval_steps_per_second": 19.474,
|
| 487 |
+
"eval_uas": 91.48276273410474,
|
| 488 |
+
"step": 6000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 15.56,
|
| 492 |
+
"learning_rate": 4.780671140939598e-05,
|
| 493 |
+
"loss": 0.0252,
|
| 494 |
+
"step": 6100
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 15.82,
|
| 498 |
+
"learning_rate": 4.726979865771813e-05,
|
| 499 |
+
"loss": 0.0259,
|
| 500 |
+
"step": 6200
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 16.07,
|
| 504 |
+
"learning_rate": 4.673288590604027e-05,
|
| 505 |
+
"loss": 0.0277,
|
| 506 |
+
"step": 6300
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 16.33,
|
| 510 |
+
"learning_rate": 4.619597315436242e-05,
|
| 511 |
+
"loss": 0.0205,
|
| 512 |
+
"step": 6400
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 16.58,
|
| 516 |
+
"learning_rate": 4.565906040268457e-05,
|
| 517 |
+
"loss": 0.0248,
|
| 518 |
+
"step": 6500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 16.58,
|
| 522 |
+
"eval_las": 89.20831842220367,
|
| 523 |
+
"eval_loss": 1.041021704673767,
|
| 524 |
+
"eval_runtime": 12.8807,
|
| 525 |
+
"eval_samples_per_second": 155.348,
|
| 526 |
+
"eval_steps_per_second": 19.486,
|
| 527 |
+
"eval_uas": 91.59807547019763,
|
| 528 |
+
"step": 6500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 16.84,
|
| 532 |
+
"learning_rate": 4.5122147651006716e-05,
|
| 533 |
+
"loss": 0.0242,
|
| 534 |
+
"step": 6600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 17.09,
|
| 538 |
+
"learning_rate": 4.4585234899328864e-05,
|
| 539 |
+
"loss": 0.0252,
|
| 540 |
+
"step": 6700
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 17.35,
|
| 544 |
+
"learning_rate": 4.404832214765101e-05,
|
| 545 |
+
"loss": 0.0212,
|
| 546 |
+
"step": 6800
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 17.6,
|
| 550 |
+
"learning_rate": 4.351140939597316e-05,
|
| 551 |
+
"loss": 0.0221,
|
| 552 |
+
"step": 6900
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 17.86,
|
| 556 |
+
"learning_rate": 4.297986577181209e-05,
|
| 557 |
+
"loss": 0.0245,
|
| 558 |
+
"step": 7000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 17.86,
|
| 562 |
+
"eval_las": 89.0651715773987,
|
| 563 |
+
"eval_loss": 1.0336178541183472,
|
| 564 |
+
"eval_runtime": 12.8848,
|
| 565 |
+
"eval_samples_per_second": 155.299,
|
| 566 |
+
"eval_steps_per_second": 19.48,
|
| 567 |
+
"eval_uas": 91.42709451668058,
|
| 568 |
+
"step": 7000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 18.11,
|
| 572 |
+
"learning_rate": 4.244295302013423e-05,
|
| 573 |
+
"loss": 0.0169,
|
| 574 |
+
"step": 7100
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 18.37,
|
| 578 |
+
"learning_rate": 4.190604026845638e-05,
|
| 579 |
+
"loss": 0.0188,
|
| 580 |
+
"step": 7200
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 18.62,
|
| 584 |
+
"learning_rate": 4.1369127516778525e-05,
|
| 585 |
+
"loss": 0.0193,
|
| 586 |
+
"step": 7300
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 18.88,
|
| 590 |
+
"learning_rate": 4.0832214765100673e-05,
|
| 591 |
+
"loss": 0.0197,
|
| 592 |
+
"step": 7400
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 19.13,
|
| 596 |
+
"learning_rate": 4.029530201342282e-05,
|
| 597 |
+
"loss": 0.016,
|
| 598 |
+
"step": 7500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 19.13,
|
| 602 |
+
"eval_las": 89.12481609606743,
|
| 603 |
+
"eval_loss": 1.1899999380111694,
|
| 604 |
+
"eval_runtime": 12.8943,
|
| 605 |
+
"eval_samples_per_second": 155.185,
|
| 606 |
+
"eval_steps_per_second": 19.466,
|
| 607 |
+
"eval_uas": 91.38733150423477,
|
| 608 |
+
"step": 7500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 19.13,
|
| 612 |
+
"step": 7500,
|
| 613 |
+
"total_flos": 4.007127707268403e+16,
|
| 614 |
+
"train_loss": 0.15542098660469056,
|
| 615 |
+
"train_runtime": 4224.7831,
|
| 616 |
+
"train_samples_per_second": 113.615,
|
| 617 |
+
"train_steps_per_second": 3.55
|
| 618 |
+
}
|
| 619 |
+
],
|
| 620 |
+
"max_steps": 15000,
|
| 621 |
+
"num_train_epochs": 39,
|
| 622 |
+
"total_flos": 4.007127707268403e+16,
|
| 623 |
+
"trial_name": null,
|
| 624 |
+
"trial_params": null
|
| 625 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f66e5b8dad04e0e5a44da08a8877c700299023b6ccc6ab643b53038c5ff597f2
|
| 3 |
+
size 3387
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|