Md Mushfiqur Rahman
commited on
Commit
•
c59cbbe
1
Parent(s):
b769246
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": 340.91,
|
| 3 |
+
"eval_las": 50.781657113079724,
|
| 4 |
+
"eval_loss": 9.509201049804688,
|
| 5 |
+
"eval_runtime": 5.2013,
|
| 6 |
+
"eval_samples": 800,
|
| 7 |
+
"eval_samples_per_second": 153.806,
|
| 8 |
+
"eval_steps_per_second": 19.226,
|
| 9 |
+
"eval_uas": 61.53378495744312,
|
| 10 |
+
"test_las": 49.008782936010036,
|
| 11 |
+
"test_loss": 9.438948631286621,
|
| 12 |
+
"test_runtime": 5.237,
|
| 13 |
+
"test_samples": 800,
|
| 14 |
+
"test_samples_per_second": 152.76,
|
| 15 |
+
"test_steps_per_second": 19.095,
|
| 16 |
+
"test_uas": 59.72396486825596,
|
| 17 |
+
"train_loss": 0.06309178725369274,
|
| 18 |
+
"train_runtime": 7782.9093,
|
| 19 |
+
"train_samples": 1400,
|
| 20 |
+
"train_samples_per_second": 61.674,
|
| 21 |
+
"train_steps_per_second": 1.927
|
| 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 sha256:52ab5b5375eef27198dfbcd838cdc434a510f9d5e2caaf71c9cf0c657583e85a
|
| 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": 50.781657113079724,
|
| 3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Vietnamese-VTB/checkpoint-15000",
|
| 4 |
+
"epoch": 340.90909090909093,
|
| 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": 2.27,
|
| 12 |
+
"learning_rate": 7.52e-05,
|
| 13 |
+
"loss": 4.4887,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 4.55,
|
| 18 |
+
"learning_rate": 7.949530201342283e-05,
|
| 19 |
+
"loss": 1.7443,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 6.82,
|
| 24 |
+
"learning_rate": 7.895838926174497e-05,
|
| 25 |
+
"loss": 0.8269,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 9.09,
|
| 30 |
+
"learning_rate": 7.842147651006712e-05,
|
| 31 |
+
"loss": 0.4089,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 11.36,
|
| 36 |
+
"learning_rate": 7.788456375838927e-05,
|
| 37 |
+
"loss": 0.2343,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 11.36,
|
| 42 |
+
"eval_las": 48.28903943025882,
|
| 43 |
+
"eval_loss": 3.7556207180023193,
|
| 44 |
+
"eval_runtime": 5.1839,
|
| 45 |
+
"eval_samples_per_second": 154.325,
|
| 46 |
+
"eval_steps_per_second": 19.291,
|
| 47 |
+
"eval_uas": 59.15407330206705,
|
| 48 |
+
"step": 500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 13.64,
|
| 52 |
+
"learning_rate": 7.734765100671142e-05,
|
| 53 |
+
"loss": 0.1547,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 15.91,
|
| 58 |
+
"learning_rate": 7.681073825503357e-05,
|
| 59 |
+
"loss": 0.1145,
|
| 60 |
+
"step": 700
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 18.18,
|
| 64 |
+
"learning_rate": 7.627382550335572e-05,
|
| 65 |
+
"loss": 0.089,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 20.45,
|
| 70 |
+
"learning_rate": 7.573691275167786e-05,
|
| 71 |
+
"loss": 0.0777,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 22.73,
|
| 76 |
+
"learning_rate": 7.52e-05,
|
| 77 |
+
"loss": 0.0697,
|
| 78 |
+
"step": 1000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 22.73,
|
| 82 |
+
"eval_las": 47.168664234844535,
|
| 83 |
+
"eval_loss": 5.077505588531494,
|
| 84 |
+
"eval_runtime": 5.1923,
|
| 85 |
+
"eval_samples_per_second": 154.073,
|
| 86 |
+
"eval_steps_per_second": 19.259,
|
| 87 |
+
"eval_uas": 57.755775577557756,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 25.0,
|
| 92 |
+
"learning_rate": 7.466308724832215e-05,
|
| 93 |
+
"loss": 0.0611,
|
| 94 |
+
"step": 1100
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 27.27,
|
| 98 |
+
"learning_rate": 7.41261744966443e-05,
|
| 99 |
+
"loss": 0.0498,
|
| 100 |
+
"step": 1200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 29.55,
|
| 104 |
+
"learning_rate": 7.358926174496644e-05,
|
| 105 |
+
"loss": 0.049,
|
| 106 |
+
"step": 1300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 31.82,
|
| 110 |
+
"learning_rate": 7.305234899328859e-05,
|
| 111 |
+
"loss": 0.0443,
|
| 112 |
+
"step": 1400
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 34.09,
|
| 116 |
+
"learning_rate": 7.251543624161074e-05,
|
| 117 |
+
"loss": 0.04,
|
| 118 |
+
"step": 1500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 34.09,
|
| 122 |
+
"eval_las": 48.20218863991662,
|
| 123 |
+
"eval_loss": 5.622523307800293,
|
| 124 |
+
"eval_runtime": 5.1912,
|
| 125 |
+
"eval_samples_per_second": 154.107,
|
| 126 |
+
"eval_steps_per_second": 19.263,
|
| 127 |
+
"eval_uas": 58.580858085808586,
|
| 128 |
+
"step": 1500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 36.36,
|
| 132 |
+
"learning_rate": 7.197852348993289e-05,
|
| 133 |
+
"loss": 0.0428,
|
| 134 |
+
"step": 1600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 38.64,
|
| 138 |
+
"learning_rate": 7.144161073825504e-05,
|
| 139 |
+
"loss": 0.0402,
|
| 140 |
+
"step": 1700
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 40.91,
|
| 144 |
+
"learning_rate": 7.090469798657718e-05,
|
| 145 |
+
"loss": 0.0353,
|
| 146 |
+
"step": 1800
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 43.18,
|
| 150 |
+
"learning_rate": 7.036778523489933e-05,
|
| 151 |
+
"loss": 0.0292,
|
| 152 |
+
"step": 1900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 45.45,
|
| 156 |
+
"learning_rate": 6.983087248322148e-05,
|
| 157 |
+
"loss": 0.0363,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 45.45,
|
| 162 |
+
"eval_las": 48.53222164321696,
|
| 163 |
+
"eval_loss": 6.002054214477539,
|
| 164 |
+
"eval_runtime": 5.1905,
|
| 165 |
+
"eval_samples_per_second": 154.128,
|
| 166 |
+
"eval_steps_per_second": 19.266,
|
| 167 |
+
"eval_uas": 59.37988535695675,
|
| 168 |
+
"step": 2000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 47.73,
|
| 172 |
+
"learning_rate": 6.929395973154363e-05,
|
| 173 |
+
"loss": 0.0321,
|
| 174 |
+
"step": 2100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 50.0,
|
| 178 |
+
"learning_rate": 6.875704697986578e-05,
|
| 179 |
+
"loss": 0.031,
|
| 180 |
+
"step": 2200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 52.27,
|
| 184 |
+
"learning_rate": 6.822013422818793e-05,
|
| 185 |
+
"loss": 0.0282,
|
| 186 |
+
"step": 2300
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 54.55,
|
| 190 |
+
"learning_rate": 6.768322147651007e-05,
|
| 191 |
+
"loss": 0.0237,
|
| 192 |
+
"step": 2400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 56.82,
|
| 196 |
+
"learning_rate": 6.714630872483222e-05,
|
| 197 |
+
"loss": 0.0238,
|
| 198 |
+
"step": 2500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 56.82,
|
| 202 |
+
"eval_las": 48.27166927219038,
|
| 203 |
+
"eval_loss": 6.428050994873047,
|
| 204 |
+
"eval_runtime": 5.1921,
|
| 205 |
+
"eval_samples_per_second": 154.079,
|
| 206 |
+
"eval_steps_per_second": 19.26,
|
| 207 |
+
"eval_uas": 59.05853743269064,
|
| 208 |
+
"step": 2500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 59.09,
|
| 212 |
+
"learning_rate": 6.660939597315437e-05,
|
| 213 |
+
"loss": 0.0246,
|
| 214 |
+
"step": 2600
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 61.36,
|
| 218 |
+
"learning_rate": 6.607248322147652e-05,
|
| 219 |
+
"loss": 0.0224,
|
| 220 |
+
"step": 2700
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 63.64,
|
| 224 |
+
"learning_rate": 6.553557046979867e-05,
|
| 225 |
+
"loss": 0.0231,
|
| 226 |
+
"step": 2800
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 65.91,
|
| 230 |
+
"learning_rate": 6.499865771812081e-05,
|
| 231 |
+
"loss": 0.0224,
|
| 232 |
+
"step": 2900
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 68.18,
|
| 236 |
+
"learning_rate": 6.446174496644296e-05,
|
| 237 |
+
"loss": 0.0184,
|
| 238 |
+
"step": 3000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 68.18,
|
| 242 |
+
"eval_las": 48.966475594927914,
|
| 243 |
+
"eval_loss": 7.119157791137695,
|
| 244 |
+
"eval_runtime": 5.1953,
|
| 245 |
+
"eval_samples_per_second": 153.986,
|
| 246 |
+
"eval_steps_per_second": 19.248,
|
| 247 |
+
"eval_uas": 59.47542122633316,
|
| 248 |
+
"step": 3000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 70.45,
|
| 252 |
+
"learning_rate": 6.392483221476511e-05,
|
| 253 |
+
"loss": 0.02,
|
| 254 |
+
"step": 3100
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 72.73,
|
| 258 |
+
"learning_rate": 6.338791946308726e-05,
|
| 259 |
+
"loss": 0.0198,
|
| 260 |
+
"step": 3200
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 75.0,
|
| 264 |
+
"learning_rate": 6.28510067114094e-05,
|
| 265 |
+
"loss": 0.0196,
|
| 266 |
+
"step": 3300
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 77.27,
|
| 270 |
+
"learning_rate": 6.231409395973154e-05,
|
| 271 |
+
"loss": 0.0177,
|
| 272 |
+
"step": 3400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 79.55,
|
| 276 |
+
"learning_rate": 6.177718120805369e-05,
|
| 277 |
+
"loss": 0.0149,
|
| 278 |
+
"step": 3500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 79.55,
|
| 282 |
+
"eval_las": 48.75803369810665,
|
| 283 |
+
"eval_loss": 7.0862298011779785,
|
| 284 |
+
"eval_runtime": 5.1933,
|
| 285 |
+
"eval_samples_per_second": 154.044,
|
| 286 |
+
"eval_steps_per_second": 19.256,
|
| 287 |
+
"eval_uas": 59.44936598923051,
|
| 288 |
+
"step": 3500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 81.82,
|
| 292 |
+
"learning_rate": 6.124026845637584e-05,
|
| 293 |
+
"loss": 0.0138,
|
| 294 |
+
"step": 3600
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 84.09,
|
| 298 |
+
"learning_rate": 6.070335570469799e-05,
|
| 299 |
+
"loss": 0.0173,
|
| 300 |
+
"step": 3700
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 86.36,
|
| 304 |
+
"learning_rate": 6.0166442953020136e-05,
|
| 305 |
+
"loss": 0.0165,
|
| 306 |
+
"step": 3800
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 88.64,
|
| 310 |
+
"learning_rate": 5.962953020134229e-05,
|
| 311 |
+
"loss": 0.015,
|
| 312 |
+
"step": 3900
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 90.91,
|
| 316 |
+
"learning_rate": 5.909261744966444e-05,
|
| 317 |
+
"loss": 0.0132,
|
| 318 |
+
"step": 4000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 90.91,
|
| 322 |
+
"eval_las": 49.035956227201666,
|
| 323 |
+
"eval_loss": 7.622977256774902,
|
| 324 |
+
"eval_runtime": 5.1898,
|
| 325 |
+
"eval_samples_per_second": 154.148,
|
| 326 |
+
"eval_steps_per_second": 19.268,
|
| 327 |
+
"eval_uas": 59.31908980371722,
|
| 328 |
+
"step": 4000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 93.18,
|
| 332 |
+
"learning_rate": 5.855570469798659e-05,
|
| 333 |
+
"loss": 0.0154,
|
| 334 |
+
"step": 4100
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 95.45,
|
| 338 |
+
"learning_rate": 5.8018791946308735e-05,
|
| 339 |
+
"loss": 0.0131,
|
| 340 |
+
"step": 4200
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 97.73,
|
| 344 |
+
"learning_rate": 5.7481879194630884e-05,
|
| 345 |
+
"loss": 0.0124,
|
| 346 |
+
"step": 4300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 100.0,
|
| 350 |
+
"learning_rate": 5.694496644295303e-05,
|
| 351 |
+
"loss": 0.0125,
|
| 352 |
+
"step": 4400
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 102.27,
|
| 356 |
+
"learning_rate": 5.6408053691275166e-05,
|
| 357 |
+
"loss": 0.0142,
|
| 358 |
+
"step": 4500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 102.27,
|
| 362 |
+
"eval_las": 49.27045336112559,
|
| 363 |
+
"eval_loss": 7.618669509887695,
|
| 364 |
+
"eval_runtime": 5.1961,
|
| 365 |
+
"eval_samples_per_second": 153.962,
|
| 366 |
+
"eval_steps_per_second": 19.245,
|
| 367 |
+
"eval_uas": 59.47542122633316,
|
| 368 |
+
"step": 4500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 104.55,
|
| 372 |
+
"learning_rate": 5.5871140939597315e-05,
|
| 373 |
+
"loss": 0.0131,
|
| 374 |
+
"step": 4600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 106.82,
|
| 378 |
+
"learning_rate": 5.533422818791946e-05,
|
| 379 |
+
"loss": 0.0126,
|
| 380 |
+
"step": 4700
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 109.09,
|
| 384 |
+
"learning_rate": 5.479731543624161e-05,
|
| 385 |
+
"loss": 0.0101,
|
| 386 |
+
"step": 4800
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 111.36,
|
| 390 |
+
"learning_rate": 5.426040268456376e-05,
|
| 391 |
+
"loss": 0.0094,
|
| 392 |
+
"step": 4900
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 113.64,
|
| 396 |
+
"learning_rate": 5.372348993288591e-05,
|
| 397 |
+
"loss": 0.0098,
|
| 398 |
+
"step": 5000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 113.64,
|
| 402 |
+
"eval_las": 49.678652075733886,
|
| 403 |
+
"eval_loss": 7.6977925300598145,
|
| 404 |
+
"eval_runtime": 5.1957,
|
| 405 |
+
"eval_samples_per_second": 153.974,
|
| 406 |
+
"eval_steps_per_second": 19.247,
|
| 407 |
+
"eval_uas": 59.82282438770192,
|
| 408 |
+
"step": 5000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 115.91,
|
| 412 |
+
"learning_rate": 5.3186577181208056e-05,
|
| 413 |
+
"loss": 0.0096,
|
| 414 |
+
"step": 5100
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 118.18,
|
| 418 |
+
"learning_rate": 5.2649664429530204e-05,
|
| 419 |
+
"loss": 0.009,
|
| 420 |
+
"step": 5200
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 120.45,
|
| 424 |
+
"learning_rate": 5.211275167785235e-05,
|
| 425 |
+
"loss": 0.0104,
|
| 426 |
+
"step": 5300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 122.73,
|
| 430 |
+
"learning_rate": 5.15758389261745e-05,
|
| 431 |
+
"loss": 0.0111,
|
| 432 |
+
"step": 5400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 125.0,
|
| 436 |
+
"learning_rate": 5.1038926174496656e-05,
|
| 437 |
+
"loss": 0.0095,
|
| 438 |
+
"step": 5500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 125.0,
|
| 442 |
+
"eval_las": 49.17491749174918,
|
| 443 |
+
"eval_loss": 7.922099590301514,
|
| 444 |
+
"eval_runtime": 5.1917,
|
| 445 |
+
"eval_samples_per_second": 154.091,
|
| 446 |
+
"eval_steps_per_second": 19.261,
|
| 447 |
+
"eval_uas": 59.80545422963349,
|
| 448 |
+
"step": 5500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 127.27,
|
| 452 |
+
"learning_rate": 5.050201342281879e-05,
|
| 453 |
+
"loss": 0.0104,
|
| 454 |
+
"step": 5600
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 129.55,
|
| 458 |
+
"learning_rate": 4.996510067114094e-05,
|
| 459 |
+
"loss": 0.0103,
|
| 460 |
+
"step": 5700
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 131.82,
|
| 464 |
+
"learning_rate": 4.942818791946309e-05,
|
| 465 |
+
"loss": 0.0104,
|
| 466 |
+
"step": 5800
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 134.09,
|
| 470 |
+
"learning_rate": 4.8891275167785235e-05,
|
| 471 |
+
"loss": 0.0073,
|
| 472 |
+
"step": 5900
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 136.36,
|
| 476 |
+
"learning_rate": 4.835436241610738e-05,
|
| 477 |
+
"loss": 0.0085,
|
| 478 |
+
"step": 6000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 136.36,
|
| 482 |
+
"eval_las": 49.504950495049506,
|
| 483 |
+
"eval_loss": 8.327244758605957,
|
| 484 |
+
"eval_runtime": 5.1925,
|
| 485 |
+
"eval_samples_per_second": 154.068,
|
| 486 |
+
"eval_steps_per_second": 19.258,
|
| 487 |
+
"eval_uas": 59.73597359735974,
|
| 488 |
+
"step": 6000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 138.64,
|
| 492 |
+
"learning_rate": 4.781744966442953e-05,
|
| 493 |
+
"loss": 0.0076,
|
| 494 |
+
"step": 6100
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 140.91,
|
| 498 |
+
"learning_rate": 4.728053691275168e-05,
|
| 499 |
+
"loss": 0.0078,
|
| 500 |
+
"step": 6200
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 143.18,
|
| 504 |
+
"learning_rate": 4.674362416107383e-05,
|
| 505 |
+
"loss": 0.007,
|
| 506 |
+
"step": 6300
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 145.45,
|
| 510 |
+
"learning_rate": 4.6206711409395976e-05,
|
| 511 |
+
"loss": 0.005,
|
| 512 |
+
"step": 6400
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 147.73,
|
| 516 |
+
"learning_rate": 4.5669798657718125e-05,
|
| 517 |
+
"loss": 0.005,
|
| 518 |
+
"step": 6500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 147.73,
|
| 522 |
+
"eval_las": 49.71339239187076,
|
| 523 |
+
"eval_loss": 8.44931697845459,
|
| 524 |
+
"eval_runtime": 5.1924,
|
| 525 |
+
"eval_samples_per_second": 154.072,
|
| 526 |
+
"eval_steps_per_second": 19.259,
|
| 527 |
+
"eval_uas": 59.96178565224943,
|
| 528 |
+
"step": 6500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 150.0,
|
| 532 |
+
"learning_rate": 4.513288590604027e-05,
|
| 533 |
+
"loss": 0.0064,
|
| 534 |
+
"step": 6600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 152.27,
|
| 538 |
+
"learning_rate": 4.459597315436242e-05,
|
| 539 |
+
"loss": 0.0049,
|
| 540 |
+
"step": 6700
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 154.55,
|
| 544 |
+
"learning_rate": 4.405906040268456e-05,
|
| 545 |
+
"loss": 0.0039,
|
| 546 |
+
"step": 6800
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 156.82,
|
| 550 |
+
"learning_rate": 4.352214765100671e-05,
|
| 551 |
+
"loss": 0.0044,
|
| 552 |
+
"step": 6900
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 159.09,
|
| 556 |
+
"learning_rate": 4.298523489932886e-05,
|
| 557 |
+
"loss": 0.0052,
|
| 558 |
+
"step": 7000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 159.09,
|
| 562 |
+
"eval_las": 49.70470731283655,
|
| 563 |
+
"eval_loss": 8.672440528869629,
|
| 564 |
+
"eval_runtime": 5.1898,
|
| 565 |
+
"eval_samples_per_second": 154.15,
|
| 566 |
+
"eval_steps_per_second": 19.269,
|
| 567 |
+
"eval_uas": 60.36998436685774,
|
| 568 |
+
"step": 7000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 161.36,
|
| 572 |
+
"learning_rate": 4.244832214765101e-05,
|
| 573 |
+
"loss": 0.0049,
|
| 574 |
+
"step": 7100
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 163.64,
|
| 578 |
+
"learning_rate": 4.1911409395973156e-05,
|
| 579 |
+
"loss": 0.0089,
|
| 580 |
+
"step": 7200
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 165.91,
|
| 584 |
+
"learning_rate": 4.1374496644295304e-05,
|
| 585 |
+
"loss": 0.0036,
|
| 586 |
+
"step": 7300
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 168.18,
|
| 590 |
+
"learning_rate": 4.083758389261745e-05,
|
| 591 |
+
"loss": 0.0056,
|
| 592 |
+
"step": 7400
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 170.45,
|
| 596 |
+
"learning_rate": 4.03006711409396e-05,
|
| 597 |
+
"loss": 0.0038,
|
| 598 |
+
"step": 7500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 170.45,
|
| 602 |
+
"eval_las": 49.58311620635748,
|
| 603 |
+
"eval_loss": 8.693171501159668,
|
| 604 |
+
"eval_runtime": 5.1886,
|
| 605 |
+
"eval_samples_per_second": 154.183,
|
| 606 |
+
"eval_steps_per_second": 19.273,
|
| 607 |
+
"eval_uas": 60.700017370158065,
|
| 608 |
+
"step": 7500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 172.73,
|
| 612 |
+
"learning_rate": 3.976375838926175e-05,
|
| 613 |
+
"loss": 0.0039,
|
| 614 |
+
"step": 7600
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 175.0,
|
| 618 |
+
"learning_rate": 3.92268456375839e-05,
|
| 619 |
+
"loss": 0.003,
|
| 620 |
+
"step": 7700
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 177.27,
|
| 624 |
+
"learning_rate": 3.8689932885906045e-05,
|
| 625 |
+
"loss": 0.0025,
|
| 626 |
+
"step": 7800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 179.55,
|
| 630 |
+
"learning_rate": 3.815302013422819e-05,
|
| 631 |
+
"loss": 0.003,
|
| 632 |
+
"step": 7900
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 181.82,
|
| 636 |
+
"learning_rate": 3.761610738255034e-05,
|
| 637 |
+
"loss": 0.0035,
|
| 638 |
+
"step": 8000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 181.82,
|
| 642 |
+
"eval_las": 50.20844189682126,
|
| 643 |
+
"eval_loss": 8.397028923034668,
|
| 644 |
+
"eval_runtime": 5.1807,
|
| 645 |
+
"eval_samples_per_second": 154.42,
|
| 646 |
+
"eval_steps_per_second": 19.303,
|
| 647 |
+
"eval_uas": 60.552371026576346,
|
| 648 |
+
"step": 8000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 184.09,
|
| 652 |
+
"learning_rate": 3.707919463087249e-05,
|
| 653 |
+
"loss": 0.0034,
|
| 654 |
+
"step": 8100
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 186.36,
|
| 658 |
+
"learning_rate": 3.654228187919463e-05,
|
| 659 |
+
"loss": 0.0023,
|
| 660 |
+
"step": 8200
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 188.64,
|
| 664 |
+
"learning_rate": 3.600536912751678e-05,
|
| 665 |
+
"loss": 0.004,
|
| 666 |
+
"step": 8300
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 190.91,
|
| 670 |
+
"learning_rate": 3.546845637583893e-05,
|
| 671 |
+
"loss": 0.0031,
|
| 672 |
+
"step": 8400
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 193.18,
|
| 676 |
+
"learning_rate": 3.4931543624161076e-05,
|
| 677 |
+
"loss": 0.0037,
|
| 678 |
+
"step": 8500
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 193.18,
|
| 682 |
+
"eval_las": 49.7741879451103,
|
| 683 |
+
"eval_loss": 8.718303680419922,
|
| 684 |
+
"eval_runtime": 5.1796,
|
| 685 |
+
"eval_samples_per_second": 154.452,
|
| 686 |
+
"eval_steps_per_second": 19.306,
|
| 687 |
+
"eval_uas": 60.54368594754212,
|
| 688 |
+
"step": 8500
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 195.45,
|
| 692 |
+
"learning_rate": 3.4394630872483224e-05,
|
| 693 |
+
"loss": 0.003,
|
| 694 |
+
"step": 8600
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 197.73,
|
| 698 |
+
"learning_rate": 3.385771812080537e-05,
|
| 699 |
+
"loss": 0.004,
|
| 700 |
+
"step": 8700
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 200.0,
|
| 704 |
+
"learning_rate": 3.332080536912752e-05,
|
| 705 |
+
"loss": 0.004,
|
| 706 |
+
"step": 8800
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 202.27,
|
| 710 |
+
"learning_rate": 3.278389261744967e-05,
|
| 711 |
+
"loss": 0.0023,
|
| 712 |
+
"step": 8900
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 204.55,
|
| 716 |
+
"learning_rate": 3.224697986577182e-05,
|
| 717 |
+
"loss": 0.0029,
|
| 718 |
+
"step": 9000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 204.55,
|
| 722 |
+
"eval_las": 49.73944762897342,
|
| 723 |
+
"eval_loss": 8.950847625732422,
|
| 724 |
+
"eval_runtime": 5.1787,
|
| 725 |
+
"eval_samples_per_second": 154.478,
|
| 726 |
+
"eval_steps_per_second": 19.31,
|
| 727 |
+
"eval_uas": 60.40472468299461,
|
| 728 |
+
"step": 9000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 206.82,
|
| 732 |
+
"learning_rate": 3.1710067114093965e-05,
|
| 733 |
+
"loss": 0.0023,
|
| 734 |
+
"step": 9100
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 209.09,
|
| 738 |
+
"learning_rate": 3.1173154362416114e-05,
|
| 739 |
+
"loss": 0.004,
|
| 740 |
+
"step": 9200
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 211.36,
|
| 744 |
+
"learning_rate": 3.0636241610738255e-05,
|
| 745 |
+
"loss": 0.0023,
|
| 746 |
+
"step": 9300
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 213.64,
|
| 750 |
+
"learning_rate": 3.0099328859060403e-05,
|
| 751 |
+
"loss": 0.0056,
|
| 752 |
+
"step": 9400
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 215.91,
|
| 756 |
+
"learning_rate": 2.956241610738255e-05,
|
| 757 |
+
"loss": 0.0022,
|
| 758 |
+
"step": 9500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 215.91,
|
| 762 |
+
"eval_las": 49.75681778704186,
|
| 763 |
+
"eval_loss": 8.873396873474121,
|
| 764 |
+
"eval_runtime": 5.1795,
|
| 765 |
+
"eval_samples_per_second": 154.455,
|
| 766 |
+
"eval_steps_per_second": 19.307,
|
| 767 |
+
"eval_uas": 60.23102310231023,
|
| 768 |
+
"step": 9500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 218.18,
|
| 772 |
+
"learning_rate": 2.90255033557047e-05,
|
| 773 |
+
"loss": 0.0024,
|
| 774 |
+
"step": 9600
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 220.45,
|
| 778 |
+
"learning_rate": 2.8488590604026848e-05,
|
| 779 |
+
"loss": 0.0018,
|
| 780 |
+
"step": 9700
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 222.73,
|
| 784 |
+
"learning_rate": 2.7951677852348996e-05,
|
| 785 |
+
"loss": 0.0013,
|
| 786 |
+
"step": 9800
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 225.0,
|
| 790 |
+
"learning_rate": 2.741476510067114e-05,
|
| 791 |
+
"loss": 0.0016,
|
| 792 |
+
"step": 9900
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 227.27,
|
| 796 |
+
"learning_rate": 2.687785234899329e-05,
|
| 797 |
+
"loss": 0.0015,
|
| 798 |
+
"step": 10000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 227.27,
|
| 802 |
+
"eval_las": 50.225812054889694,
|
| 803 |
+
"eval_loss": 9.140296936035156,
|
| 804 |
+
"eval_runtime": 5.1821,
|
| 805 |
+
"eval_samples_per_second": 154.379,
|
| 806 |
+
"eval_steps_per_second": 19.297,
|
| 807 |
+
"eval_uas": 60.70870244919229,
|
| 808 |
+
"step": 10000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 229.55,
|
| 812 |
+
"learning_rate": 2.6340939597315438e-05,
|
| 813 |
+
"loss": 0.0013,
|
| 814 |
+
"step": 10100
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 231.82,
|
| 818 |
+
"learning_rate": 2.5804026845637586e-05,
|
| 819 |
+
"loss": 0.0013,
|
| 820 |
+
"step": 10200
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 234.09,
|
| 824 |
+
"learning_rate": 2.5267114093959734e-05,
|
| 825 |
+
"loss": 0.0031,
|
| 826 |
+
"step": 10300
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 236.36,
|
| 830 |
+
"learning_rate": 2.4730201342281882e-05,
|
| 831 |
+
"loss": 0.0018,
|
| 832 |
+
"step": 10400
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 238.64,
|
| 836 |
+
"learning_rate": 2.4193288590604027e-05,
|
| 837 |
+
"loss": 0.0015,
|
| 838 |
+
"step": 10500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 238.64,
|
| 842 |
+
"eval_las": 49.86972381448671,
|
| 843 |
+
"eval_loss": 9.165424346923828,
|
| 844 |
+
"eval_runtime": 5.1856,
|
| 845 |
+
"eval_samples_per_second": 154.274,
|
| 846 |
+
"eval_steps_per_second": 19.284,
|
| 847 |
+
"eval_uas": 60.63922181691853,
|
| 848 |
+
"step": 10500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 240.91,
|
| 852 |
+
"learning_rate": 2.3656375838926175e-05,
|
| 853 |
+
"loss": 0.0019,
|
| 854 |
+
"step": 10600
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 243.18,
|
| 858 |
+
"learning_rate": 2.3119463087248324e-05,
|
| 859 |
+
"loss": 0.0012,
|
| 860 |
+
"step": 10700
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 245.45,
|
| 864 |
+
"learning_rate": 2.2582550335570472e-05,
|
| 865 |
+
"loss": 0.0016,
|
| 866 |
+
"step": 10800
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 247.73,
|
| 870 |
+
"learning_rate": 2.204563758389262e-05,
|
| 871 |
+
"loss": 0.0005,
|
| 872 |
+
"step": 10900
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 250.0,
|
| 876 |
+
"learning_rate": 2.150872483221477e-05,
|
| 877 |
+
"loss": 0.0007,
|
| 878 |
+
"step": 11000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 250.0,
|
| 882 |
+
"eval_las": 50.48636442591628,
|
| 883 |
+
"eval_loss": 8.970284461975098,
|
| 884 |
+
"eval_runtime": 5.2059,
|
| 885 |
+
"eval_samples_per_second": 153.671,
|
| 886 |
+
"eval_steps_per_second": 19.209,
|
| 887 |
+
"eval_uas": 61.09953100573215,
|
| 888 |
+
"step": 11000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 252.27,
|
| 892 |
+
"learning_rate": 2.0971812080536913e-05,
|
| 893 |
+
"loss": 0.0005,
|
| 894 |
+
"step": 11100
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 254.55,
|
| 898 |
+
"learning_rate": 2.043489932885906e-05,
|
| 899 |
+
"loss": 0.0004,
|
| 900 |
+
"step": 11200
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 256.82,
|
| 904 |
+
"learning_rate": 1.989798657718121e-05,
|
| 905 |
+
"loss": 0.0004,
|
| 906 |
+
"step": 11300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 259.09,
|
| 910 |
+
"learning_rate": 1.9361073825503358e-05,
|
| 911 |
+
"loss": 0.0009,
|
| 912 |
+
"step": 11400
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 261.36,
|
| 916 |
+
"learning_rate": 1.8824161073825503e-05,
|
| 917 |
+
"loss": 0.0009,
|
| 918 |
+
"step": 11500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 261.36,
|
| 922 |
+
"eval_las": 50.13027618551329,
|
| 923 |
+
"eval_loss": 9.078216552734375,
|
| 924 |
+
"eval_runtime": 5.2191,
|
| 925 |
+
"eval_samples_per_second": 153.282,
|
| 926 |
+
"eval_steps_per_second": 19.16,
|
| 927 |
+
"eval_uas": 60.769498002431824,
|
| 928 |
+
"step": 11500
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 263.64,
|
| 932 |
+
"learning_rate": 1.828724832214765e-05,
|
| 933 |
+
"loss": 0.0005,
|
| 934 |
+
"step": 11600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 265.91,
|
| 938 |
+
"learning_rate": 1.77503355704698e-05,
|
| 939 |
+
"loss": 0.0004,
|
| 940 |
+
"step": 11700
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 268.18,
|
| 944 |
+
"learning_rate": 1.7213422818791948e-05,
|
| 945 |
+
"loss": 0.0004,
|
| 946 |
+
"step": 11800
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 270.45,
|
| 950 |
+
"learning_rate": 1.6676510067114096e-05,
|
| 951 |
+
"loss": 0.0003,
|
| 952 |
+
"step": 11900
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 272.73,
|
| 956 |
+
"learning_rate": 1.6139597315436244e-05,
|
| 957 |
+
"loss": 0.0022,
|
| 958 |
+
"step": 12000
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 272.73,
|
| 962 |
+
"eval_las": 50.13896126454751,
|
| 963 |
+
"eval_loss": 8.995458602905273,
|
| 964 |
+
"eval_runtime": 5.1822,
|
| 965 |
+
"eval_samples_per_second": 154.375,
|
| 966 |
+
"eval_steps_per_second": 19.297,
|
| 967 |
+
"eval_uas": 60.61316657981588,
|
| 968 |
+
"step": 12000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 275.0,
|
| 972 |
+
"learning_rate": 1.560268456375839e-05,
|
| 973 |
+
"loss": 0.0007,
|
| 974 |
+
"step": 12100
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 277.27,
|
| 978 |
+
"learning_rate": 1.5065771812080539e-05,
|
| 979 |
+
"loss": 0.0006,
|
| 980 |
+
"step": 12200
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 279.55,
|
| 984 |
+
"learning_rate": 1.4528859060402685e-05,
|
| 985 |
+
"loss": 0.0011,
|
| 986 |
+
"step": 12300
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 281.82,
|
| 990 |
+
"learning_rate": 1.3991946308724834e-05,
|
| 991 |
+
"loss": 0.0007,
|
| 992 |
+
"step": 12400
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 284.09,
|
| 996 |
+
"learning_rate": 1.3455033557046982e-05,
|
| 997 |
+
"loss": 0.0008,
|
| 998 |
+
"step": 12500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 284.09,
|
| 1002 |
+
"eval_las": 50.23449713392392,
|
| 1003 |
+
"eval_loss": 9.353437423706055,
|
| 1004 |
+
"eval_runtime": 5.1815,
|
| 1005 |
+
"eval_samples_per_second": 154.397,
|
| 1006 |
+
"eval_steps_per_second": 19.3,
|
| 1007 |
+
"eval_uas": 60.969254820218865,
|
| 1008 |
+
"step": 12500
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 286.36,
|
| 1012 |
+
"learning_rate": 1.2918120805369127e-05,
|
| 1013 |
+
"loss": 0.0004,
|
| 1014 |
+
"step": 12600
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 288.64,
|
| 1018 |
+
"learning_rate": 1.2381208053691277e-05,
|
| 1019 |
+
"loss": 0.0005,
|
| 1020 |
+
"step": 12700
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 290.91,
|
| 1024 |
+
"learning_rate": 1.1844295302013425e-05,
|
| 1025 |
+
"loss": 0.0004,
|
| 1026 |
+
"step": 12800
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 293.18,
|
| 1030 |
+
"learning_rate": 1.130738255033557e-05,
|
| 1031 |
+
"loss": 0.0005,
|
| 1032 |
+
"step": 12900
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 295.45,
|
| 1036 |
+
"learning_rate": 1.0770469798657718e-05,
|
| 1037 |
+
"loss": 0.0006,
|
| 1038 |
+
"step": 13000
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 295.45,
|
| 1042 |
+
"eval_las": 50.62532569046378,
|
| 1043 |
+
"eval_loss": 9.346752166748047,
|
| 1044 |
+
"eval_runtime": 5.1837,
|
| 1045 |
+
"eval_samples_per_second": 154.331,
|
| 1046 |
+
"eval_steps_per_second": 19.291,
|
| 1047 |
+
"eval_uas": 61.54247003647734,
|
| 1048 |
+
"step": 13000
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 297.73,
|
| 1052 |
+
"learning_rate": 1.0233557046979868e-05,
|
| 1053 |
+
"loss": 0.0004,
|
| 1054 |
+
"step": 13100
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 300.0,
|
| 1058 |
+
"learning_rate": 9.696644295302015e-06,
|
| 1059 |
+
"loss": 0.0004,
|
| 1060 |
+
"step": 13200
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 302.27,
|
| 1064 |
+
"learning_rate": 9.159731543624161e-06,
|
| 1065 |
+
"loss": 0.0003,
|
| 1066 |
+
"step": 13300
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 304.55,
|
| 1070 |
+
"learning_rate": 8.62281879194631e-06,
|
| 1071 |
+
"loss": 0.0003,
|
| 1072 |
+
"step": 13400
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 306.82,
|
| 1076 |
+
"learning_rate": 8.085906040268458e-06,
|
| 1077 |
+
"loss": 0.0003,
|
| 1078 |
+
"step": 13500
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 306.82,
|
| 1082 |
+
"eval_las": 50.37345839847143,
|
| 1083 |
+
"eval_loss": 9.42686653137207,
|
| 1084 |
+
"eval_runtime": 5.1835,
|
| 1085 |
+
"eval_samples_per_second": 154.335,
|
| 1086 |
+
"eval_steps_per_second": 19.292,
|
| 1087 |
+
"eval_uas": 61.281917665450756,
|
| 1088 |
+
"step": 13500
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 309.09,
|
| 1092 |
+
"learning_rate": 7.548993288590605e-06,
|
| 1093 |
+
"loss": 0.0003,
|
| 1094 |
+
"step": 13600
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 311.36,
|
| 1098 |
+
"learning_rate": 7.012080536912752e-06,
|
| 1099 |
+
"loss": 0.0003,
|
| 1100 |
+
"step": 13700
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 313.64,
|
| 1104 |
+
"learning_rate": 6.475167785234899e-06,
|
| 1105 |
+
"loss": 0.0003,
|
| 1106 |
+
"step": 13800
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 315.91,
|
| 1110 |
+
"learning_rate": 5.938255033557048e-06,
|
| 1111 |
+
"loss": 0.0002,
|
| 1112 |
+
"step": 13900
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 318.18,
|
| 1116 |
+
"learning_rate": 5.401342281879195e-06,
|
| 1117 |
+
"loss": 0.0002,
|
| 1118 |
+
"step": 14000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 318.18,
|
| 1122 |
+
"eval_las": 50.64269584853223,
|
| 1123 |
+
"eval_loss": 9.432953834533691,
|
| 1124 |
+
"eval_runtime": 5.1928,
|
| 1125 |
+
"eval_samples_per_second": 154.06,
|
| 1126 |
+
"eval_steps_per_second": 19.258,
|
| 1127 |
+
"eval_uas": 61.50772972034046,
|
| 1128 |
+
"step": 14000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 320.45,
|
| 1132 |
+
"learning_rate": 4.864429530201343e-06,
|
| 1133 |
+
"loss": 0.0002,
|
| 1134 |
+
"step": 14100
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 322.73,
|
| 1138 |
+
"learning_rate": 4.32751677852349e-06,
|
| 1139 |
+
"loss": 0.0003,
|
| 1140 |
+
"step": 14200
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 325.0,
|
| 1144 |
+
"learning_rate": 3.790604026845638e-06,
|
| 1145 |
+
"loss": 0.0002,
|
| 1146 |
+
"step": 14300
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 327.27,
|
| 1150 |
+
"learning_rate": 3.253691275167786e-06,
|
| 1151 |
+
"loss": 0.0003,
|
| 1152 |
+
"step": 14400
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 329.55,
|
| 1156 |
+
"learning_rate": 2.716778523489933e-06,
|
| 1157 |
+
"loss": 0.0002,
|
| 1158 |
+
"step": 14500
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 329.55,
|
| 1162 |
+
"eval_las": 50.73823171790863,
|
| 1163 |
+
"eval_loss": 9.487878799438477,
|
| 1164 |
+
"eval_runtime": 5.2057,
|
| 1165 |
+
"eval_samples_per_second": 153.676,
|
| 1166 |
+
"eval_steps_per_second": 19.21,
|
| 1167 |
+
"eval_uas": 61.42087892999827,
|
| 1168 |
+
"step": 14500
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 331.82,
|
| 1172 |
+
"learning_rate": 2.1798657718120807e-06,
|
| 1173 |
+
"loss": 0.0002,
|
| 1174 |
+
"step": 14600
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 334.09,
|
| 1178 |
+
"learning_rate": 1.6429530201342283e-06,
|
| 1179 |
+
"loss": 0.0002,
|
| 1180 |
+
"step": 14700
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 336.36,
|
| 1184 |
+
"learning_rate": 1.1060402684563759e-06,
|
| 1185 |
+
"loss": 0.0003,
|
| 1186 |
+
"step": 14800
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 338.64,
|
| 1190 |
+
"learning_rate": 5.691275167785235e-07,
|
| 1191 |
+
"loss": 0.0002,
|
| 1192 |
+
"step": 14900
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 340.91,
|
| 1196 |
+
"learning_rate": 3.2214765100671145e-08,
|
| 1197 |
+
"loss": 0.0002,
|
| 1198 |
+
"step": 15000
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 340.91,
|
| 1202 |
+
"eval_las": 50.781657113079724,
|
| 1203 |
+
"eval_loss": 9.509201049804688,
|
| 1204 |
+
"eval_runtime": 5.1995,
|
| 1205 |
+
"eval_samples_per_second": 153.862,
|
| 1206 |
+
"eval_steps_per_second": 19.233,
|
| 1207 |
+
"eval_uas": 61.53378495744312,
|
| 1208 |
+
"step": 15000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 340.91,
|
| 1212 |
+
"step": 15000,
|
| 1213 |
+
"total_flos": 7.969472217071616e+16,
|
| 1214 |
+
"train_loss": 0.06309178725369274,
|
| 1215 |
+
"train_runtime": 7782.9093,
|
| 1216 |
+
"train_samples_per_second": 61.674,
|
| 1217 |
+
"train_steps_per_second": 1.927
|
| 1218 |
+
}
|
| 1219 |
+
],
|
| 1220 |
+
"max_steps": 15000,
|
| 1221 |
+
"num_train_epochs": 341,
|
| 1222 |
+
"total_flos": 7.969472217071616e+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 sha256:2272a6645a901bab816582bfcdb0f12e7667d7268c4fefc5b49befd20e355cfc
|
| 3 |
+
size 3387
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|