Md Mushfiqur Rahman
commited on
Commit
•
86337d0
1
Parent(s):
0b36fb9
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 +1025 -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": 56.56,
|
| 3 |
+
"eval_las": 94.51452754944249,
|
| 4 |
+
"eval_loss": 0.7882774472236633,
|
| 5 |
+
"eval_runtime": 3.7372,
|
| 6 |
+
"eval_samples": 507,
|
| 7 |
+
"eval_samples_per_second": 135.662,
|
| 8 |
+
"eval_steps_per_second": 17.125,
|
| 9 |
+
"eval_uas": 95.56441767721982,
|
| 10 |
+
"test_las": 92.99524321006598,
|
| 11 |
+
"test_loss": 0.9460740089416504,
|
| 12 |
+
"test_runtime": 3.9916,
|
| 13 |
+
"test_samples": 543,
|
| 14 |
+
"test_samples_per_second": 136.034,
|
| 15 |
+
"test_steps_per_second": 17.036,
|
| 16 |
+
"test_uas": 94.38391898112629,
|
| 17 |
+
"train_loss": 0.05763526131868362,
|
| 18 |
+
"train_runtime": 7165.6139,
|
| 19 |
+
"train_samples": 7050,
|
| 20 |
+
"train_samples_per_second": 66.987,
|
| 21 |
+
"train_steps_per_second": 2.093
|
| 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 sha256:8cec60b8fd48a1c3daaadc6d7429913dad6cc14edee1f838e668259f5b5c41e6
|
| 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 +1,1025 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 94.51452754944249,
|
| 3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-parsing-ud-Japanese-GSD/checkpoint-10000",
|
| 4 |
+
"epoch": 56.56108597285068,
|
| 5 |
+
"global_step": 12500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.45,
|
| 12 |
+
"learning_rate": 7.76e-05,
|
| 13 |
+
"loss": 2.8808,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.9,
|
| 18 |
+
"learning_rate": 7.947919463087248e-05,
|
| 19 |
+
"loss": 0.5888,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.36,
|
| 24 |
+
"learning_rate": 7.894228187919463e-05,
|
| 25 |
+
"loss": 0.387,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.81,
|
| 30 |
+
"learning_rate": 7.840536912751678e-05,
|
| 31 |
+
"loss": 0.3305,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.26,
|
| 36 |
+
"learning_rate": 7.786845637583893e-05,
|
| 37 |
+
"loss": 0.2643,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.26,
|
| 42 |
+
"eval_las": 92.13803206641165,
|
| 43 |
+
"eval_loss": 0.37336885929107666,
|
| 44 |
+
"eval_runtime": 3.7431,
|
| 45 |
+
"eval_samples_per_second": 135.449,
|
| 46 |
+
"eval_steps_per_second": 17.098,
|
| 47 |
+
"eval_uas": 94.02620655977863,
|
| 48 |
+
"step": 500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.71,
|
| 52 |
+
"learning_rate": 7.733154362416108e-05,
|
| 53 |
+
"loss": 0.22,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.17,
|
| 58 |
+
"learning_rate": 7.679463087248322e-05,
|
| 59 |
+
"loss": 0.1981,
|
| 60 |
+
"step": 700
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.62,
|
| 64 |
+
"learning_rate": 7.625771812080537e-05,
|
| 65 |
+
"loss": 0.1498,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.07,
|
| 70 |
+
"learning_rate": 7.572080536912752e-05,
|
| 71 |
+
"loss": 0.1522,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.52,
|
| 76 |
+
"learning_rate": 7.518389261744967e-05,
|
| 77 |
+
"loss": 0.1105,
|
| 78 |
+
"step": 1000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 4.52,
|
| 82 |
+
"eval_las": 93.34255717424921,
|
| 83 |
+
"eval_loss": 0.3645283281803131,
|
| 84 |
+
"eval_runtime": 3.7438,
|
| 85 |
+
"eval_samples_per_second": 135.422,
|
| 86 |
+
"eval_steps_per_second": 17.095,
|
| 87 |
+
"eval_uas": 94.83193619272402,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 4.98,
|
| 92 |
+
"learning_rate": 7.464697986577182e-05,
|
| 93 |
+
"loss": 0.1191,
|
| 94 |
+
"step": 1100
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 5.43,
|
| 98 |
+
"learning_rate": 7.411006711409397e-05,
|
| 99 |
+
"loss": 0.0871,
|
| 100 |
+
"step": 1200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 5.88,
|
| 104 |
+
"learning_rate": 7.357315436241611e-05,
|
| 105 |
+
"loss": 0.09,
|
| 106 |
+
"step": 1300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 6.33,
|
| 110 |
+
"learning_rate": 7.303624161073826e-05,
|
| 111 |
+
"loss": 0.0724,
|
| 112 |
+
"step": 1400
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.79,
|
| 116 |
+
"learning_rate": 7.249932885906041e-05,
|
| 117 |
+
"loss": 0.0729,
|
| 118 |
+
"step": 1500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 6.79,
|
| 122 |
+
"eval_las": 93.60299503540327,
|
| 123 |
+
"eval_loss": 0.42577120661735535,
|
| 124 |
+
"eval_runtime": 3.7422,
|
| 125 |
+
"eval_samples_per_second": 135.482,
|
| 126 |
+
"eval_steps_per_second": 17.102,
|
| 127 |
+
"eval_uas": 94.98657117278424,
|
| 128 |
+
"step": 1500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.24,
|
| 132 |
+
"learning_rate": 7.196241610738256e-05,
|
| 133 |
+
"loss": 0.069,
|
| 134 |
+
"step": 1600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 7.69,
|
| 138 |
+
"learning_rate": 7.142550335570471e-05,
|
| 139 |
+
"loss": 0.0616,
|
| 140 |
+
"step": 1700
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 8.14,
|
| 144 |
+
"learning_rate": 7.088859060402686e-05,
|
| 145 |
+
"loss": 0.0579,
|
| 146 |
+
"step": 1800
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 8.6,
|
| 150 |
+
"learning_rate": 7.0351677852349e-05,
|
| 151 |
+
"loss": 0.0512,
|
| 152 |
+
"step": 1900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 9.05,
|
| 156 |
+
"learning_rate": 6.981476510067114e-05,
|
| 157 |
+
"loss": 0.05,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 9.05,
|
| 162 |
+
"eval_las": 93.67624318385285,
|
| 163 |
+
"eval_loss": 0.5269723534584045,
|
| 164 |
+
"eval_runtime": 3.7443,
|
| 165 |
+
"eval_samples_per_second": 135.405,
|
| 166 |
+
"eval_steps_per_second": 17.093,
|
| 167 |
+
"eval_uas": 95.07609668755596,
|
| 168 |
+
"step": 2000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.5,
|
| 172 |
+
"learning_rate": 6.927785234899329e-05,
|
| 173 |
+
"loss": 0.0453,
|
| 174 |
+
"step": 2100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.95,
|
| 178 |
+
"learning_rate": 6.874093959731543e-05,
|
| 179 |
+
"loss": 0.0459,
|
| 180 |
+
"step": 2200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.41,
|
| 184 |
+
"learning_rate": 6.820402684563758e-05,
|
| 185 |
+
"loss": 0.0399,
|
| 186 |
+
"step": 2300
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 10.86,
|
| 190 |
+
"learning_rate": 6.766711409395973e-05,
|
| 191 |
+
"loss": 0.04,
|
| 192 |
+
"step": 2400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 11.31,
|
| 196 |
+
"learning_rate": 6.713020134228188e-05,
|
| 197 |
+
"loss": 0.0353,
|
| 198 |
+
"step": 2500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 11.31,
|
| 202 |
+
"eval_las": 93.99365182713437,
|
| 203 |
+
"eval_loss": 0.5733376145362854,
|
| 204 |
+
"eval_runtime": 3.7349,
|
| 205 |
+
"eval_samples_per_second": 135.745,
|
| 206 |
+
"eval_steps_per_second": 17.136,
|
| 207 |
+
"eval_uas": 95.26328640026044,
|
| 208 |
+
"step": 2500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 11.76,
|
| 212 |
+
"learning_rate": 6.659328859060403e-05,
|
| 213 |
+
"loss": 0.0378,
|
| 214 |
+
"step": 2600
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 12.22,
|
| 218 |
+
"learning_rate": 6.605637583892618e-05,
|
| 219 |
+
"loss": 0.0355,
|
| 220 |
+
"step": 2700
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 12.67,
|
| 224 |
+
"learning_rate": 6.551946308724832e-05,
|
| 225 |
+
"loss": 0.0324,
|
| 226 |
+
"step": 2800
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 13.12,
|
| 230 |
+
"learning_rate": 6.498255033557047e-05,
|
| 231 |
+
"loss": 0.0316,
|
| 232 |
+
"step": 2900
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 13.57,
|
| 236 |
+
"learning_rate": 6.444563758389262e-05,
|
| 237 |
+
"loss": 0.0307,
|
| 238 |
+
"step": 3000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 13.57,
|
| 242 |
+
"eval_las": 93.83901684707413,
|
| 243 |
+
"eval_loss": 0.5204811096191406,
|
| 244 |
+
"eval_runtime": 3.7373,
|
| 245 |
+
"eval_samples_per_second": 135.659,
|
| 246 |
+
"eval_steps_per_second": 17.125,
|
| 247 |
+
"eval_uas": 95.23073166761617,
|
| 248 |
+
"step": 3000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 14.03,
|
| 252 |
+
"learning_rate": 6.390872483221477e-05,
|
| 253 |
+
"loss": 0.0293,
|
| 254 |
+
"step": 3100
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 14.48,
|
| 258 |
+
"learning_rate": 6.337181208053692e-05,
|
| 259 |
+
"loss": 0.0271,
|
| 260 |
+
"step": 3200
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 14.93,
|
| 264 |
+
"learning_rate": 6.283489932885907e-05,
|
| 265 |
+
"loss": 0.0286,
|
| 266 |
+
"step": 3300
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 15.38,
|
| 270 |
+
"learning_rate": 6.229798657718121e-05,
|
| 271 |
+
"loss": 0.0232,
|
| 272 |
+
"step": 3400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 15.84,
|
| 276 |
+
"learning_rate": 6.176107382550336e-05,
|
| 277 |
+
"loss": 0.0251,
|
| 278 |
+
"step": 3500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 15.84,
|
| 282 |
+
"eval_las": 93.86343289655734,
|
| 283 |
+
"eval_loss": 0.58524090051651,
|
| 284 |
+
"eval_runtime": 3.7398,
|
| 285 |
+
"eval_samples_per_second": 135.568,
|
| 286 |
+
"eval_steps_per_second": 17.113,
|
| 287 |
+
"eval_uas": 95.19817693497193,
|
| 288 |
+
"step": 3500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 16.29,
|
| 292 |
+
"learning_rate": 6.122416107382551e-05,
|
| 293 |
+
"loss": 0.023,
|
| 294 |
+
"step": 3600
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.74,
|
| 298 |
+
"learning_rate": 6.068724832214766e-05,
|
| 299 |
+
"loss": 0.0224,
|
| 300 |
+
"step": 3700
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 17.19,
|
| 304 |
+
"learning_rate": 6.015033557046981e-05,
|
| 305 |
+
"loss": 0.0202,
|
| 306 |
+
"step": 3800
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 17.65,
|
| 310 |
+
"learning_rate": 5.9613422818791955e-05,
|
| 311 |
+
"loss": 0.0223,
|
| 312 |
+
"step": 3900
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 18.1,
|
| 316 |
+
"learning_rate": 5.90765100671141e-05,
|
| 317 |
+
"loss": 0.0208,
|
| 318 |
+
"step": 4000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 18.1,
|
| 322 |
+
"eval_las": 93.76576869862457,
|
| 323 |
+
"eval_loss": 0.6501343250274658,
|
| 324 |
+
"eval_runtime": 3.7407,
|
| 325 |
+
"eval_samples_per_second": 135.537,
|
| 326 |
+
"eval_steps_per_second": 17.109,
|
| 327 |
+
"eval_uas": 95.01912590542851,
|
| 328 |
+
"step": 4000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 18.55,
|
| 332 |
+
"learning_rate": 5.853959731543625e-05,
|
| 333 |
+
"loss": 0.019,
|
| 334 |
+
"step": 4100
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 19.0,
|
| 338 |
+
"learning_rate": 5.80026845637584e-05,
|
| 339 |
+
"loss": 0.0191,
|
| 340 |
+
"step": 4200
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 19.46,
|
| 344 |
+
"learning_rate": 5.7465771812080534e-05,
|
| 345 |
+
"loss": 0.0166,
|
| 346 |
+
"step": 4300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 19.91,
|
| 350 |
+
"learning_rate": 5.692885906040268e-05,
|
| 351 |
+
"loss": 0.0175,
|
| 352 |
+
"step": 4400
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 20.36,
|
| 356 |
+
"learning_rate": 5.639194630872483e-05,
|
| 357 |
+
"loss": 0.0183,
|
| 358 |
+
"step": 4500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 20.36,
|
| 362 |
+
"eval_las": 94.2378123219663,
|
| 363 |
+
"eval_loss": 0.5928093194961548,
|
| 364 |
+
"eval_runtime": 3.7386,
|
| 365 |
+
"eval_samples_per_second": 135.611,
|
| 366 |
+
"eval_steps_per_second": 17.119,
|
| 367 |
+
"eval_uas": 95.46675347928705,
|
| 368 |
+
"step": 4500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 20.81,
|
| 372 |
+
"learning_rate": 5.5855033557046986e-05,
|
| 373 |
+
"loss": 0.0162,
|
| 374 |
+
"step": 4600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 21.27,
|
| 378 |
+
"learning_rate": 5.5318120805369134e-05,
|
| 379 |
+
"loss": 0.0158,
|
| 380 |
+
"step": 4700
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 21.72,
|
| 384 |
+
"learning_rate": 5.478120805369128e-05,
|
| 385 |
+
"loss": 0.0176,
|
| 386 |
+
"step": 4800
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 22.17,
|
| 390 |
+
"learning_rate": 5.424429530201343e-05,
|
| 391 |
+
"loss": 0.0136,
|
| 392 |
+
"step": 4900
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 22.62,
|
| 396 |
+
"learning_rate": 5.370738255033558e-05,
|
| 397 |
+
"loss": 0.0146,
|
| 398 |
+
"step": 5000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 22.62,
|
| 402 |
+
"eval_las": 93.96109709449011,
|
| 403 |
+
"eval_loss": 0.6554161906242371,
|
| 404 |
+
"eval_runtime": 3.737,
|
| 405 |
+
"eval_samples_per_second": 135.671,
|
| 406 |
+
"eval_steps_per_second": 17.126,
|
| 407 |
+
"eval_uas": 95.27956376658257,
|
| 408 |
+
"step": 5000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 23.08,
|
| 412 |
+
"learning_rate": 5.317046979865773e-05,
|
| 413 |
+
"loss": 0.0132,
|
| 414 |
+
"step": 5100
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 23.53,
|
| 418 |
+
"learning_rate": 5.2633557046979875e-05,
|
| 419 |
+
"loss": 0.0137,
|
| 420 |
+
"step": 5200
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 23.98,
|
| 424 |
+
"learning_rate": 5.2096644295302024e-05,
|
| 425 |
+
"loss": 0.0163,
|
| 426 |
+
"step": 5300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 24.43,
|
| 430 |
+
"learning_rate": 5.155973154362417e-05,
|
| 431 |
+
"loss": 0.0115,
|
| 432 |
+
"step": 5400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 24.89,
|
| 436 |
+
"learning_rate": 5.1022818791946307e-05,
|
| 437 |
+
"loss": 0.0129,
|
| 438 |
+
"step": 5500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 24.89,
|
| 442 |
+
"eval_las": 94.2622283714495,
|
| 443 |
+
"eval_loss": 0.657804548740387,
|
| 444 |
+
"eval_runtime": 3.7329,
|
| 445 |
+
"eval_samples_per_second": 135.821,
|
| 446 |
+
"eval_steps_per_second": 17.145,
|
| 447 |
+
"eval_uas": 95.51558557825344,
|
| 448 |
+
"step": 5500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 25.34,
|
| 452 |
+
"learning_rate": 5.0485906040268455e-05,
|
| 453 |
+
"loss": 0.0133,
|
| 454 |
+
"step": 5600
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 25.79,
|
| 458 |
+
"learning_rate": 4.99489932885906e-05,
|
| 459 |
+
"loss": 0.0118,
|
| 460 |
+
"step": 5700
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 26.24,
|
| 464 |
+
"learning_rate": 4.941208053691275e-05,
|
| 465 |
+
"loss": 0.0123,
|
| 466 |
+
"step": 5800
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 26.7,
|
| 470 |
+
"learning_rate": 4.88751677852349e-05,
|
| 471 |
+
"loss": 0.0094,
|
| 472 |
+
"step": 5900
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 27.15,
|
| 476 |
+
"learning_rate": 4.833825503355705e-05,
|
| 477 |
+
"loss": 0.0099,
|
| 478 |
+
"step": 6000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 27.15,
|
| 482 |
+
"eval_las": 94.1238707577114,
|
| 483 |
+
"eval_loss": 0.6814541220664978,
|
| 484 |
+
"eval_runtime": 3.7329,
|
| 485 |
+
"eval_samples_per_second": 135.82,
|
| 486 |
+
"eval_steps_per_second": 17.145,
|
| 487 |
+
"eval_uas": 95.31211849922683,
|
| 488 |
+
"step": 6000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 27.6,
|
| 492 |
+
"learning_rate": 4.7801342281879196e-05,
|
| 493 |
+
"loss": 0.0112,
|
| 494 |
+
"step": 6100
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 28.05,
|
| 498 |
+
"learning_rate": 4.726442953020135e-05,
|
| 499 |
+
"loss": 0.01,
|
| 500 |
+
"step": 6200
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 28.51,
|
| 504 |
+
"learning_rate": 4.67275167785235e-05,
|
| 505 |
+
"loss": 0.0096,
|
| 506 |
+
"step": 6300
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 28.96,
|
| 510 |
+
"learning_rate": 4.619060402684565e-05,
|
| 511 |
+
"loss": 0.0116,
|
| 512 |
+
"step": 6400
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 29.41,
|
| 516 |
+
"learning_rate": 4.5653691275167796e-05,
|
| 517 |
+
"loss": 0.0081,
|
| 518 |
+
"step": 6500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 29.41,
|
| 522 |
+
"eval_las": 94.34361520306015,
|
| 523 |
+
"eval_loss": 0.6585590839385986,
|
| 524 |
+
"eval_runtime": 3.7358,
|
| 525 |
+
"eval_samples_per_second": 135.713,
|
| 526 |
+
"eval_steps_per_second": 17.131,
|
| 527 |
+
"eval_uas": 95.5969724098641,
|
| 528 |
+
"step": 6500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 29.86,
|
| 532 |
+
"learning_rate": 4.511677852348993e-05,
|
| 533 |
+
"loss": 0.0082,
|
| 534 |
+
"step": 6600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 30.32,
|
| 538 |
+
"learning_rate": 4.4585234899328864e-05,
|
| 539 |
+
"loss": 0.0081,
|
| 540 |
+
"step": 6700
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 30.77,
|
| 544 |
+
"learning_rate": 4.404832214765101e-05,
|
| 545 |
+
"loss": 0.0088,
|
| 546 |
+
"step": 6800
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 31.22,
|
| 550 |
+
"learning_rate": 4.351140939597316e-05,
|
| 551 |
+
"loss": 0.009,
|
| 552 |
+
"step": 6900
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 31.67,
|
| 556 |
+
"learning_rate": 4.297449664429531e-05,
|
| 557 |
+
"loss": 0.0088,
|
| 558 |
+
"step": 7000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 31.67,
|
| 562 |
+
"eval_las": 94.32733783673801,
|
| 563 |
+
"eval_loss": 0.6393760442733765,
|
| 564 |
+
"eval_runtime": 3.7286,
|
| 565 |
+
"eval_samples_per_second": 135.974,
|
| 566 |
+
"eval_steps_per_second": 17.164,
|
| 567 |
+
"eval_uas": 95.46675347928705,
|
| 568 |
+
"step": 7000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 32.13,
|
| 572 |
+
"learning_rate": 4.243758389261746e-05,
|
| 573 |
+
"loss": 0.008,
|
| 574 |
+
"step": 7100
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 32.58,
|
| 578 |
+
"learning_rate": 4.1900671140939605e-05,
|
| 579 |
+
"loss": 0.0065,
|
| 580 |
+
"step": 7200
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 33.03,
|
| 584 |
+
"learning_rate": 4.1363758389261754e-05,
|
| 585 |
+
"loss": 0.0066,
|
| 586 |
+
"step": 7300
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 33.48,
|
| 590 |
+
"learning_rate": 4.0826845637583895e-05,
|
| 591 |
+
"loss": 0.0052,
|
| 592 |
+
"step": 7400
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 33.94,
|
| 596 |
+
"learning_rate": 4.028993288590604e-05,
|
| 597 |
+
"loss": 0.0057,
|
| 598 |
+
"step": 7500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 33.94,
|
| 602 |
+
"eval_las": 94.34361520306015,
|
| 603 |
+
"eval_loss": 0.7660797834396362,
|
| 604 |
+
"eval_runtime": 3.7339,
|
| 605 |
+
"eval_samples_per_second": 135.781,
|
| 606 |
+
"eval_steps_per_second": 17.14,
|
| 607 |
+
"eval_uas": 95.51558557825344,
|
| 608 |
+
"step": 7500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 34.39,
|
| 612 |
+
"learning_rate": 3.975302013422819e-05,
|
| 613 |
+
"loss": 0.0065,
|
| 614 |
+
"step": 7600
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 34.84,
|
| 618 |
+
"learning_rate": 3.921610738255034e-05,
|
| 619 |
+
"loss": 0.0067,
|
| 620 |
+
"step": 7700
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 35.29,
|
| 624 |
+
"learning_rate": 3.867919463087249e-05,
|
| 625 |
+
"loss": 0.0064,
|
| 626 |
+
"step": 7800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 35.75,
|
| 630 |
+
"learning_rate": 3.8142281879194636e-05,
|
| 631 |
+
"loss": 0.0077,
|
| 632 |
+
"step": 7900
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 36.2,
|
| 636 |
+
"learning_rate": 3.7605369127516784e-05,
|
| 637 |
+
"loss": 0.0054,
|
| 638 |
+
"step": 8000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 36.2,
|
| 642 |
+
"eval_las": 94.29478310409377,
|
| 643 |
+
"eval_loss": 0.7726401686668396,
|
| 644 |
+
"eval_runtime": 3.7388,
|
| 645 |
+
"eval_samples_per_second": 135.605,
|
| 646 |
+
"eval_steps_per_second": 17.118,
|
| 647 |
+
"eval_uas": 95.45861479612599,
|
| 648 |
+
"step": 8000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 36.65,
|
| 652 |
+
"learning_rate": 3.706845637583893e-05,
|
| 653 |
+
"loss": 0.0064,
|
| 654 |
+
"step": 8100
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 37.1,
|
| 658 |
+
"learning_rate": 3.653154362416108e-05,
|
| 659 |
+
"loss": 0.0058,
|
| 660 |
+
"step": 8200
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 37.56,
|
| 664 |
+
"learning_rate": 3.599463087248322e-05,
|
| 665 |
+
"loss": 0.006,
|
| 666 |
+
"step": 8300
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 38.01,
|
| 670 |
+
"learning_rate": 3.545771812080537e-05,
|
| 671 |
+
"loss": 0.0061,
|
| 672 |
+
"step": 8400
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 38.46,
|
| 676 |
+
"learning_rate": 3.492080536912752e-05,
|
| 677 |
+
"loss": 0.0044,
|
| 678 |
+
"step": 8500
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 38.46,
|
| 682 |
+
"eval_las": 94.43314071783185,
|
| 683 |
+
"eval_loss": 0.7485831379890442,
|
| 684 |
+
"eval_runtime": 3.7354,
|
| 685 |
+
"eval_samples_per_second": 135.729,
|
| 686 |
+
"eval_steps_per_second": 17.133,
|
| 687 |
+
"eval_uas": 95.57255636038089,
|
| 688 |
+
"step": 8500
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 38.91,
|
| 692 |
+
"learning_rate": 3.438389261744967e-05,
|
| 693 |
+
"loss": 0.0043,
|
| 694 |
+
"step": 8600
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 39.37,
|
| 698 |
+
"learning_rate": 3.3846979865771815e-05,
|
| 699 |
+
"loss": 0.0033,
|
| 700 |
+
"step": 8700
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 39.82,
|
| 704 |
+
"learning_rate": 3.3310067114093964e-05,
|
| 705 |
+
"loss": 0.004,
|
| 706 |
+
"step": 8800
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 40.27,
|
| 710 |
+
"learning_rate": 3.277315436241611e-05,
|
| 711 |
+
"loss": 0.0049,
|
| 712 |
+
"step": 8900
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 40.72,
|
| 716 |
+
"learning_rate": 3.223624161073826e-05,
|
| 717 |
+
"loss": 0.0038,
|
| 718 |
+
"step": 9000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 40.72,
|
| 722 |
+
"eval_las": 94.30292178725482,
|
| 723 |
+
"eval_loss": 0.7324322462081909,
|
| 724 |
+
"eval_runtime": 3.7333,
|
| 725 |
+
"eval_samples_per_second": 135.804,
|
| 726 |
+
"eval_steps_per_second": 17.143,
|
| 727 |
+
"eval_uas": 95.50744689509237,
|
| 728 |
+
"step": 9000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 41.18,
|
| 732 |
+
"learning_rate": 3.169932885906041e-05,
|
| 733 |
+
"loss": 0.0042,
|
| 734 |
+
"step": 9100
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 41.63,
|
| 738 |
+
"learning_rate": 3.1162416107382557e-05,
|
| 739 |
+
"loss": 0.0042,
|
| 740 |
+
"step": 9200
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 42.08,
|
| 744 |
+
"learning_rate": 3.0625503355704705e-05,
|
| 745 |
+
"loss": 0.0033,
|
| 746 |
+
"step": 9300
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 42.53,
|
| 750 |
+
"learning_rate": 3.0088590604026846e-05,
|
| 751 |
+
"loss": 0.0031,
|
| 752 |
+
"step": 9400
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 42.99,
|
| 756 |
+
"learning_rate": 2.9551677852348995e-05,
|
| 757 |
+
"loss": 0.0035,
|
| 758 |
+
"step": 9500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 42.99,
|
| 762 |
+
"eval_las": 94.24595100512737,
|
| 763 |
+
"eval_loss": 0.8114320635795593,
|
| 764 |
+
"eval_runtime": 3.7335,
|
| 765 |
+
"eval_samples_per_second": 135.799,
|
| 766 |
+
"eval_steps_per_second": 17.142,
|
| 767 |
+
"eval_uas": 95.42606006348173,
|
| 768 |
+
"step": 9500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 43.44,
|
| 772 |
+
"learning_rate": 2.9014765100671143e-05,
|
| 773 |
+
"loss": 0.0027,
|
| 774 |
+
"step": 9600
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 43.89,
|
| 778 |
+
"learning_rate": 2.848322147651007e-05,
|
| 779 |
+
"loss": 0.0041,
|
| 780 |
+
"step": 9700
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 44.34,
|
| 784 |
+
"learning_rate": 2.7946308724832218e-05,
|
| 785 |
+
"loss": 0.0029,
|
| 786 |
+
"step": 9800
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 44.8,
|
| 790 |
+
"learning_rate": 2.7409395973154366e-05,
|
| 791 |
+
"loss": 0.0036,
|
| 792 |
+
"step": 9900
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 45.25,
|
| 796 |
+
"learning_rate": 2.6872483221476514e-05,
|
| 797 |
+
"loss": 0.0034,
|
| 798 |
+
"step": 10000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 45.25,
|
| 802 |
+
"eval_las": 94.51452754944249,
|
| 803 |
+
"eval_loss": 0.7882774472236633,
|
| 804 |
+
"eval_runtime": 3.7243,
|
| 805 |
+
"eval_samples_per_second": 136.135,
|
| 806 |
+
"eval_steps_per_second": 17.185,
|
| 807 |
+
"eval_uas": 95.56441767721982,
|
| 808 |
+
"step": 10000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 45.7,
|
| 812 |
+
"learning_rate": 2.6335570469798663e-05,
|
| 813 |
+
"loss": 0.0035,
|
| 814 |
+
"step": 10100
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 46.15,
|
| 818 |
+
"learning_rate": 2.5798657718120804e-05,
|
| 819 |
+
"loss": 0.0027,
|
| 820 |
+
"step": 10200
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 46.61,
|
| 824 |
+
"learning_rate": 2.5261744966442952e-05,
|
| 825 |
+
"loss": 0.0023,
|
| 826 |
+
"step": 10300
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 47.06,
|
| 830 |
+
"learning_rate": 2.47248322147651e-05,
|
| 831 |
+
"loss": 0.0024,
|
| 832 |
+
"step": 10400
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 47.51,
|
| 836 |
+
"learning_rate": 2.4187919463087252e-05,
|
| 837 |
+
"loss": 0.0025,
|
| 838 |
+
"step": 10500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 47.51,
|
| 842 |
+
"eval_las": 94.44941808415398,
|
| 843 |
+
"eval_loss": 0.8562086224555969,
|
| 844 |
+
"eval_runtime": 3.7341,
|
| 845 |
+
"eval_samples_per_second": 135.776,
|
| 846 |
+
"eval_steps_per_second": 17.139,
|
| 847 |
+
"eval_uas": 95.5237242614145,
|
| 848 |
+
"step": 10500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 47.96,
|
| 852 |
+
"learning_rate": 2.36510067114094e-05,
|
| 853 |
+
"loss": 0.0032,
|
| 854 |
+
"step": 10600
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 48.42,
|
| 858 |
+
"learning_rate": 2.311409395973155e-05,
|
| 859 |
+
"loss": 0.002,
|
| 860 |
+
"step": 10700
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 48.87,
|
| 864 |
+
"learning_rate": 2.257718120805369e-05,
|
| 865 |
+
"loss": 0.0017,
|
| 866 |
+
"step": 10800
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 49.32,
|
| 870 |
+
"learning_rate": 2.204026845637584e-05,
|
| 871 |
+
"loss": 0.0015,
|
| 872 |
+
"step": 10900
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 49.77,
|
| 876 |
+
"learning_rate": 2.1503355704697987e-05,
|
| 877 |
+
"loss": 0.0013,
|
| 878 |
+
"step": 11000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 49.77,
|
| 882 |
+
"eval_las": 94.51452754944249,
|
| 883 |
+
"eval_loss": 0.8181952834129333,
|
| 884 |
+
"eval_runtime": 3.7391,
|
| 885 |
+
"eval_samples_per_second": 135.594,
|
| 886 |
+
"eval_steps_per_second": 17.116,
|
| 887 |
+
"eval_uas": 95.64580450883047,
|
| 888 |
+
"step": 11000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 50.23,
|
| 892 |
+
"learning_rate": 2.0966442953020135e-05,
|
| 893 |
+
"loss": 0.0015,
|
| 894 |
+
"step": 11100
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 50.68,
|
| 898 |
+
"learning_rate": 2.0429530201342283e-05,
|
| 899 |
+
"loss": 0.0016,
|
| 900 |
+
"step": 11200
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 51.13,
|
| 904 |
+
"learning_rate": 1.989261744966443e-05,
|
| 905 |
+
"loss": 0.0014,
|
| 906 |
+
"step": 11300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 51.58,
|
| 910 |
+
"learning_rate": 1.935570469798658e-05,
|
| 911 |
+
"loss": 0.0012,
|
| 912 |
+
"step": 11400
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 52.04,
|
| 916 |
+
"learning_rate": 1.8818791946308724e-05,
|
| 917 |
+
"loss": 0.0013,
|
| 918 |
+
"step": 11500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 52.04,
|
| 922 |
+
"eval_las": 94.3761699357044,
|
| 923 |
+
"eval_loss": 0.8620641231536865,
|
| 924 |
+
"eval_runtime": 3.734,
|
| 925 |
+
"eval_samples_per_second": 135.778,
|
| 926 |
+
"eval_steps_per_second": 17.14,
|
| 927 |
+
"eval_uas": 95.47489216244811,
|
| 928 |
+
"step": 11500
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 52.49,
|
| 932 |
+
"learning_rate": 1.8281879194630873e-05,
|
| 933 |
+
"loss": 0.0012,
|
| 934 |
+
"step": 11600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 52.94,
|
| 938 |
+
"learning_rate": 1.774496644295302e-05,
|
| 939 |
+
"loss": 0.0014,
|
| 940 |
+
"step": 11700
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 53.39,
|
| 944 |
+
"learning_rate": 1.720805369127517e-05,
|
| 945 |
+
"loss": 0.0005,
|
| 946 |
+
"step": 11800
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 53.85,
|
| 950 |
+
"learning_rate": 1.6671140939597317e-05,
|
| 951 |
+
"loss": 0.0022,
|
| 952 |
+
"step": 11900
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 54.3,
|
| 956 |
+
"learning_rate": 1.6139597315436244e-05,
|
| 957 |
+
"loss": 0.0007,
|
| 958 |
+
"step": 12000
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 54.3,
|
| 962 |
+
"eval_las": 94.4250020346708,
|
| 963 |
+
"eval_loss": 0.891247570514679,
|
| 964 |
+
"eval_runtime": 3.7334,
|
| 965 |
+
"eval_samples_per_second": 135.801,
|
| 966 |
+
"eval_steps_per_second": 17.143,
|
| 967 |
+
"eval_uas": 95.5481403108977,
|
| 968 |
+
"step": 12000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 54.75,
|
| 972 |
+
"learning_rate": 1.560268456375839e-05,
|
| 973 |
+
"loss": 0.0009,
|
| 974 |
+
"step": 12100
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 55.2,
|
| 978 |
+
"learning_rate": 1.5065771812080539e-05,
|
| 979 |
+
"loss": 0.0008,
|
| 980 |
+
"step": 12200
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 55.66,
|
| 984 |
+
"learning_rate": 1.4528859060402685e-05,
|
| 985 |
+
"loss": 0.0005,
|
| 986 |
+
"step": 12300
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 56.11,
|
| 990 |
+
"learning_rate": 1.3991946308724834e-05,
|
| 991 |
+
"loss": 0.0007,
|
| 992 |
+
"step": 12400
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 56.56,
|
| 996 |
+
"learning_rate": 1.3455033557046982e-05,
|
| 997 |
+
"loss": 0.0009,
|
| 998 |
+
"step": 12500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 56.56,
|
| 1002 |
+
"eval_las": 94.44941808415398,
|
| 1003 |
+
"eval_loss": 0.9227140545845032,
|
| 1004 |
+
"eval_runtime": 3.7344,
|
| 1005 |
+
"eval_samples_per_second": 135.765,
|
| 1006 |
+
"eval_steps_per_second": 17.138,
|
| 1007 |
+
"eval_uas": 95.5237242614145,
|
| 1008 |
+
"step": 12500
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 56.56,
|
| 1012 |
+
"step": 12500,
|
| 1013 |
+
"total_flos": 6.65850338806825e+16,
|
| 1014 |
+
"train_loss": 0.05763526131868362,
|
| 1015 |
+
"train_runtime": 7165.6139,
|
| 1016 |
+
"train_samples_per_second": 66.987,
|
| 1017 |
+
"train_steps_per_second": 2.093
|
| 1018 |
+
}
|
| 1019 |
+
],
|
| 1020 |
+
"max_steps": 15000,
|
| 1021 |
+
"num_train_epochs": 68,
|
| 1022 |
+
"total_flos": 6.65850338806825e+16,
|
| 1023 |
+
"trial_name": null,
|
| 1024 |
+
"trial_params": null
|
| 1025 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a50f769c617e48209550a7cd5888627205741da3e985eaacdd55008cb241752f
|
| 3 |
+
size 3387
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|