Md Mushfiqur Rahman
commited on
Commit
•
a58a899
1
Parent(s):
89b9668
Upload with huggingface_hub
Browse files- README.md +15 -0
- all_results.json +22 -0
- config.json +109 -0
- eval_predictions.csv +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_predictions.csv +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +945 -0
- training_args.bin +3 -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": 294.87,
|
| 3 |
+
"eval_las": 69.00867976244861,
|
| 4 |
+
"eval_loss": 5.695150852203369,
|
| 5 |
+
"eval_runtime": 2.5102,
|
| 6 |
+
"eval_samples": 381,
|
| 7 |
+
"eval_samples_per_second": 151.781,
|
| 8 |
+
"eval_steps_per_second": 19.122,
|
| 9 |
+
"eval_uas": 76.09867519415258,
|
| 10 |
+
"test_las": 69.7063369397218,
|
| 11 |
+
"test_loss": 5.427152633666992,
|
| 12 |
+
"test_runtime": 2.5595,
|
| 13 |
+
"test_samples": 403,
|
| 14 |
+
"test_samples_per_second": 157.454,
|
| 15 |
+
"test_steps_per_second": 19.926,
|
| 16 |
+
"test_uas": 75.97565687789799,
|
| 17 |
+
"train_loss": 0.10975235502227493,
|
| 18 |
+
"train_runtime": 5024.1647,
|
| 19 |
+
"train_samples": 1227,
|
| 20 |
+
"train_samples_per_second": 95.538,
|
| 21 |
+
"train_steps_per_second": 2.986
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/canine-s",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CanineForBiaffineParsing"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 57344,
|
| 8 |
+
"downsampling_rate": 4,
|
| 9 |
+
"eos_token_id": 57345,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "_",
|
| 15 |
+
"1": "acl",
|
| 16 |
+
"2": "advcl",
|
| 17 |
+
"3": "advmod",
|
| 18 |
+
"4": "amod",
|
| 19 |
+
"5": "appos",
|
| 20 |
+
"6": "aux",
|
| 21 |
+
"7": "case",
|
| 22 |
+
"8": "cc",
|
| 23 |
+
"9": "ccomp",
|
| 24 |
+
"10": "clf",
|
| 25 |
+
"11": "compound",
|
| 26 |
+
"12": "conj",
|
| 27 |
+
"13": "cop",
|
| 28 |
+
"14": "csubj",
|
| 29 |
+
"15": "dep",
|
| 30 |
+
"16": "det",
|
| 31 |
+
"17": "discourse",
|
| 32 |
+
"18": "dislocated",
|
| 33 |
+
"19": "expl",
|
| 34 |
+
"20": "fixed",
|
| 35 |
+
"21": "flat",
|
| 36 |
+
"22": "goeswith",
|
| 37 |
+
"23": "iobj",
|
| 38 |
+
"24": "list",
|
| 39 |
+
"25": "mark",
|
| 40 |
+
"26": "nmod",
|
| 41 |
+
"27": "nsubj",
|
| 42 |
+
"28": "nummod",
|
| 43 |
+
"29": "obj",
|
| 44 |
+
"30": "obl",
|
| 45 |
+
"31": "orphan",
|
| 46 |
+
"32": "parataxis",
|
| 47 |
+
"33": "punct",
|
| 48 |
+
"34": "reparandum",
|
| 49 |
+
"35": "root",
|
| 50 |
+
"36": "vocative",
|
| 51 |
+
"37": "xcomp"
|
| 52 |
+
},
|
| 53 |
+
"initializer_range": 0.02,
|
| 54 |
+
"intermediate_size": 3072,
|
| 55 |
+
"label2id": {
|
| 56 |
+
"_": 0,
|
| 57 |
+
"acl": 1,
|
| 58 |
+
"advcl": 2,
|
| 59 |
+
"advmod": 3,
|
| 60 |
+
"amod": 4,
|
| 61 |
+
"appos": 5,
|
| 62 |
+
"aux": 6,
|
| 63 |
+
"case": 7,
|
| 64 |
+
"cc": 8,
|
| 65 |
+
"ccomp": 9,
|
| 66 |
+
"clf": 10,
|
| 67 |
+
"compound": 11,
|
| 68 |
+
"conj": 12,
|
| 69 |
+
"cop": 13,
|
| 70 |
+
"csubj": 14,
|
| 71 |
+
"dep": 15,
|
| 72 |
+
"det": 16,
|
| 73 |
+
"discourse": 17,
|
| 74 |
+
"dislocated": 18,
|
| 75 |
+
"expl": 19,
|
| 76 |
+
"fixed": 20,
|
| 77 |
+
"flat": 21,
|
| 78 |
+
"goeswith": 22,
|
| 79 |
+
"iobj": 23,
|
| 80 |
+
"list": 24,
|
| 81 |
+
"mark": 25,
|
| 82 |
+
"nmod": 26,
|
| 83 |
+
"nsubj": 27,
|
| 84 |
+
"nummod": 28,
|
| 85 |
+
"obj": 29,
|
| 86 |
+
"obl": 30,
|
| 87 |
+
"orphan": 31,
|
| 88 |
+
"parataxis": 32,
|
| 89 |
+
"punct": 33,
|
| 90 |
+
"reparandum": 34,
|
| 91 |
+
"root": 35,
|
| 92 |
+
"vocative": 36,
|
| 93 |
+
"xcomp": 37
|
| 94 |
+
},
|
| 95 |
+
"layer_norm_eps": 1e-12,
|
| 96 |
+
"local_transformer_stride": 128,
|
| 97 |
+
"max_position_embeddings": 16384,
|
| 98 |
+
"model_type": "canine",
|
| 99 |
+
"num_attention_heads": 12,
|
| 100 |
+
"num_hash_buckets": 16384,
|
| 101 |
+
"num_hash_functions": 8,
|
| 102 |
+
"num_hidden_layers": 12,
|
| 103 |
+
"pad_token_id": -100,
|
| 104 |
+
"torch_dtype": "float32",
|
| 105 |
+
"transformers_version": "4.17.0",
|
| 106 |
+
"type_vocab_size": 16,
|
| 107 |
+
"upsampling_kernel_size": 4,
|
| 108 |
+
"use_cache": true
|
| 109 |
+
}
|
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 sha256:88f75e8f2dc63b985df64f3301e61a5d3944f11a2ea5bdb87d86cdf44c09b172
|
| 3 |
+
size 620816369
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
test_predictions.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": "/home/mrahma45/.cache/huggingface/transformers/00ffef2919c64d09945b6c06b1c03c4d18bf55f88013390d4443a1eb8c4f8a10.ab71f530366fe02e2834427e7b90198bfd0d573bc4279bfafdb2b95fe2b46dde", "name_or_path": "google/canine-s", "tokenizer_class": "CanineTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 69.00867976244861,
|
| 3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/bert-base-finetuned-parsing-ud-Coptic-Scriptorium/checkpoint-9000",
|
| 4 |
+
"epoch": 294.87179487179486,
|
| 5 |
+
"global_step": 11500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.56,
|
| 12 |
+
"learning_rate": 7.680000000000001e-05,
|
| 13 |
+
"loss": 4.7843,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 5.13,
|
| 18 |
+
"learning_rate": 7.948456375838927e-05,
|
| 19 |
+
"loss": 2.0692,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 7.69,
|
| 24 |
+
"learning_rate": 7.894765100671142e-05,
|
| 25 |
+
"loss": 1.2357,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 10.26,
|
| 30 |
+
"learning_rate": 7.841073825503357e-05,
|
| 31 |
+
"loss": 0.8102,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 12.82,
|
| 36 |
+
"learning_rate": 7.78738255033557e-05,
|
| 37 |
+
"loss": 0.5577,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 12.82,
|
| 42 |
+
"eval_las": 61.26998629511192,
|
| 43 |
+
"eval_loss": 2.625490188598633,
|
| 44 |
+
"eval_runtime": 2.5145,
|
| 45 |
+
"eval_samples_per_second": 151.518,
|
| 46 |
+
"eval_steps_per_second": 19.089,
|
| 47 |
+
"eval_uas": 69.51119232526267,
|
| 48 |
+
"step": 500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 15.38,
|
| 52 |
+
"learning_rate": 7.733691275167786e-05,
|
| 53 |
+
"loss": 0.4067,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 17.95,
|
| 58 |
+
"learning_rate": 7.680000000000001e-05,
|
| 59 |
+
"loss": 0.31,
|
| 60 |
+
"step": 700
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 20.51,
|
| 64 |
+
"learning_rate": 7.626308724832216e-05,
|
| 65 |
+
"loss": 0.2329,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 23.08,
|
| 70 |
+
"learning_rate": 7.57261744966443e-05,
|
| 71 |
+
"loss": 0.2022,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 25.64,
|
| 76 |
+
"learning_rate": 7.518926174496645e-05,
|
| 77 |
+
"loss": 0.1537,
|
| 78 |
+
"step": 1000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 25.64,
|
| 82 |
+
"eval_las": 64.12060301507537,
|
| 83 |
+
"eval_loss": 3.8098294734954834,
|
| 84 |
+
"eval_runtime": 2.5064,
|
| 85 |
+
"eval_samples_per_second": 152.01,
|
| 86 |
+
"eval_steps_per_second": 19.151,
|
| 87 |
+
"eval_uas": 72.4988579259936,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 28.21,
|
| 92 |
+
"learning_rate": 7.46523489932886e-05,
|
| 93 |
+
"loss": 0.1318,
|
| 94 |
+
"step": 1100
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 30.77,
|
| 98 |
+
"learning_rate": 7.411543624161075e-05,
|
| 99 |
+
"loss": 0.1154,
|
| 100 |
+
"step": 1200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 33.33,
|
| 104 |
+
"learning_rate": 7.35785234899329e-05,
|
| 105 |
+
"loss": 0.0959,
|
| 106 |
+
"step": 1300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 35.9,
|
| 110 |
+
"learning_rate": 7.304161073825505e-05,
|
| 111 |
+
"loss": 0.09,
|
| 112 |
+
"step": 1400
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 38.46,
|
| 116 |
+
"learning_rate": 7.25046979865772e-05,
|
| 117 |
+
"loss": 0.08,
|
| 118 |
+
"step": 1500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 38.46,
|
| 122 |
+
"eval_las": 65.40886249428964,
|
| 123 |
+
"eval_loss": 4.147989273071289,
|
| 124 |
+
"eval_runtime": 2.512,
|
| 125 |
+
"eval_samples_per_second": 151.674,
|
| 126 |
+
"eval_steps_per_second": 19.108,
|
| 127 |
+
"eval_uas": 73.27546825034263,
|
| 128 |
+
"step": 1500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 41.03,
|
| 132 |
+
"learning_rate": 7.196778523489934e-05,
|
| 133 |
+
"loss": 0.0696,
|
| 134 |
+
"step": 1600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 43.59,
|
| 138 |
+
"learning_rate": 7.143087248322148e-05,
|
| 139 |
+
"loss": 0.0632,
|
| 140 |
+
"step": 1700
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 46.15,
|
| 144 |
+
"learning_rate": 7.089395973154363e-05,
|
| 145 |
+
"loss": 0.0566,
|
| 146 |
+
"step": 1800
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 48.72,
|
| 150 |
+
"learning_rate": 7.035704697986578e-05,
|
| 151 |
+
"loss": 0.0528,
|
| 152 |
+
"step": 1900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 51.28,
|
| 156 |
+
"learning_rate": 6.982013422818792e-05,
|
| 157 |
+
"loss": 0.0523,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 51.28,
|
| 162 |
+
"eval_las": 66.48698035632708,
|
| 163 |
+
"eval_loss": 4.477940559387207,
|
| 164 |
+
"eval_runtime": 2.5091,
|
| 165 |
+
"eval_samples_per_second": 151.846,
|
| 166 |
+
"eval_steps_per_second": 19.13,
|
| 167 |
+
"eval_uas": 74.16171767930561,
|
| 168 |
+
"step": 2000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 53.85,
|
| 172 |
+
"learning_rate": 6.928322147651007e-05,
|
| 173 |
+
"loss": 0.0455,
|
| 174 |
+
"step": 2100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 56.41,
|
| 178 |
+
"learning_rate": 6.874630872483222e-05,
|
| 179 |
+
"loss": 0.0436,
|
| 180 |
+
"step": 2200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 58.97,
|
| 184 |
+
"learning_rate": 6.820939597315437e-05,
|
| 185 |
+
"loss": 0.042,
|
| 186 |
+
"step": 2300
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 61.54,
|
| 190 |
+
"learning_rate": 6.767248322147652e-05,
|
| 191 |
+
"loss": 0.0379,
|
| 192 |
+
"step": 2400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 64.1,
|
| 196 |
+
"learning_rate": 6.713557046979866e-05,
|
| 197 |
+
"loss": 0.0374,
|
| 198 |
+
"step": 2500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 64.1,
|
| 202 |
+
"eval_las": 66.45043398812243,
|
| 203 |
+
"eval_loss": 4.416062831878662,
|
| 204 |
+
"eval_runtime": 2.5116,
|
| 205 |
+
"eval_samples_per_second": 151.694,
|
| 206 |
+
"eval_steps_per_second": 19.111,
|
| 207 |
+
"eval_uas": 74.2439470077661,
|
| 208 |
+
"step": 2500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 66.67,
|
| 212 |
+
"learning_rate": 6.659865771812081e-05,
|
| 213 |
+
"loss": 0.0337,
|
| 214 |
+
"step": 2600
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 69.23,
|
| 218 |
+
"learning_rate": 6.606174496644296e-05,
|
| 219 |
+
"loss": 0.0321,
|
| 220 |
+
"step": 2700
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 71.79,
|
| 224 |
+
"learning_rate": 6.55248322147651e-05,
|
| 225 |
+
"loss": 0.0283,
|
| 226 |
+
"step": 2800
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 74.36,
|
| 230 |
+
"learning_rate": 6.498791946308724e-05,
|
| 231 |
+
"loss": 0.0292,
|
| 232 |
+
"step": 2900
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 76.92,
|
| 236 |
+
"learning_rate": 6.445100671140939e-05,
|
| 237 |
+
"loss": 0.0259,
|
| 238 |
+
"step": 3000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 76.92,
|
| 242 |
+
"eval_las": 66.7976244860667,
|
| 243 |
+
"eval_loss": 4.949475288391113,
|
| 244 |
+
"eval_runtime": 2.5044,
|
| 245 |
+
"eval_samples_per_second": 152.134,
|
| 246 |
+
"eval_steps_per_second": 19.166,
|
| 247 |
+
"eval_uas": 74.59113750571036,
|
| 248 |
+
"step": 3000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 79.49,
|
| 252 |
+
"learning_rate": 6.391409395973154e-05,
|
| 253 |
+
"loss": 0.0247,
|
| 254 |
+
"step": 3100
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 82.05,
|
| 258 |
+
"learning_rate": 6.337718120805369e-05,
|
| 259 |
+
"loss": 0.0259,
|
| 260 |
+
"step": 3200
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 84.62,
|
| 264 |
+
"learning_rate": 6.284026845637584e-05,
|
| 265 |
+
"loss": 0.0226,
|
| 266 |
+
"step": 3300
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 87.18,
|
| 270 |
+
"learning_rate": 6.230335570469799e-05,
|
| 271 |
+
"loss": 0.0247,
|
| 272 |
+
"step": 3400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 89.74,
|
| 276 |
+
"learning_rate": 6.176644295302013e-05,
|
| 277 |
+
"loss": 0.0191,
|
| 278 |
+
"step": 3500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 89.74,
|
| 282 |
+
"eval_las": 66.78848789401553,
|
| 283 |
+
"eval_loss": 5.227412700653076,
|
| 284 |
+
"eval_runtime": 2.5046,
|
| 285 |
+
"eval_samples_per_second": 152.118,
|
| 286 |
+
"eval_steps_per_second": 19.164,
|
| 287 |
+
"eval_uas": 74.36272270443125,
|
| 288 |
+
"step": 3500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 92.31,
|
| 292 |
+
"learning_rate": 6.122953020134228e-05,
|
| 293 |
+
"loss": 0.0206,
|
| 294 |
+
"step": 3600
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 94.87,
|
| 298 |
+
"learning_rate": 6.069261744966444e-05,
|
| 299 |
+
"loss": 0.0203,
|
| 300 |
+
"step": 3700
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 97.44,
|
| 304 |
+
"learning_rate": 6.0155704697986585e-05,
|
| 305 |
+
"loss": 0.0196,
|
| 306 |
+
"step": 3800
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 100.0,
|
| 310 |
+
"learning_rate": 5.9618791946308734e-05,
|
| 311 |
+
"loss": 0.0176,
|
| 312 |
+
"step": 3900
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 102.56,
|
| 316 |
+
"learning_rate": 5.9081879194630875e-05,
|
| 317 |
+
"loss": 0.0181,
|
| 318 |
+
"step": 4000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 102.56,
|
| 322 |
+
"eval_las": 67.46459570580173,
|
| 323 |
+
"eval_loss": 5.025106906890869,
|
| 324 |
+
"eval_runtime": 2.5067,
|
| 325 |
+
"eval_samples_per_second": 151.992,
|
| 326 |
+
"eval_steps_per_second": 19.149,
|
| 327 |
+
"eval_uas": 74.9200548195523,
|
| 328 |
+
"step": 4000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 105.13,
|
| 332 |
+
"learning_rate": 5.854496644295302e-05,
|
| 333 |
+
"loss": 0.0164,
|
| 334 |
+
"step": 4100
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 107.69,
|
| 338 |
+
"learning_rate": 5.800805369127517e-05,
|
| 339 |
+
"loss": 0.0177,
|
| 340 |
+
"step": 4200
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 110.26,
|
| 344 |
+
"learning_rate": 5.747114093959732e-05,
|
| 345 |
+
"loss": 0.0151,
|
| 346 |
+
"step": 4300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 112.82,
|
| 350 |
+
"learning_rate": 5.693422818791947e-05,
|
| 351 |
+
"loss": 0.0159,
|
| 352 |
+
"step": 4400
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 115.38,
|
| 356 |
+
"learning_rate": 5.6397315436241616e-05,
|
| 357 |
+
"loss": 0.0148,
|
| 358 |
+
"step": 4500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 115.38,
|
| 362 |
+
"eval_las": 67.21790772042027,
|
| 363 |
+
"eval_loss": 5.194654941558838,
|
| 364 |
+
"eval_runtime": 2.5047,
|
| 365 |
+
"eval_samples_per_second": 152.112,
|
| 366 |
+
"eval_steps_per_second": 19.164,
|
| 367 |
+
"eval_uas": 74.71904979442668,
|
| 368 |
+
"step": 4500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 117.95,
|
| 372 |
+
"learning_rate": 5.5860402684563764e-05,
|
| 373 |
+
"loss": 0.0158,
|
| 374 |
+
"step": 4600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 120.51,
|
| 378 |
+
"learning_rate": 5.532348993288591e-05,
|
| 379 |
+
"loss": 0.0127,
|
| 380 |
+
"step": 4700
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 123.08,
|
| 384 |
+
"learning_rate": 5.478657718120806e-05,
|
| 385 |
+
"loss": 0.0141,
|
| 386 |
+
"step": 4800
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 125.64,
|
| 390 |
+
"learning_rate": 5.424966442953021e-05,
|
| 391 |
+
"loss": 0.012,
|
| 392 |
+
"step": 4900
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 128.21,
|
| 396 |
+
"learning_rate": 5.371275167785236e-05,
|
| 397 |
+
"loss": 0.012,
|
| 398 |
+
"step": 5000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 128.21,
|
| 402 |
+
"eval_las": 67.5011420740064,
|
| 403 |
+
"eval_loss": 5.243346214294434,
|
| 404 |
+
"eval_runtime": 2.5045,
|
| 405 |
+
"eval_samples_per_second": 152.124,
|
| 406 |
+
"eval_steps_per_second": 19.165,
|
| 407 |
+
"eval_uas": 75.23983554134308,
|
| 408 |
+
"step": 5000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 130.77,
|
| 412 |
+
"learning_rate": 5.31758389261745e-05,
|
| 413 |
+
"loss": 0.0118,
|
| 414 |
+
"step": 5100
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 133.33,
|
| 418 |
+
"learning_rate": 5.263892617449665e-05,
|
| 419 |
+
"loss": 0.0112,
|
| 420 |
+
"step": 5200
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 135.9,
|
| 424 |
+
"learning_rate": 5.2102013422818795e-05,
|
| 425 |
+
"loss": 0.0094,
|
| 426 |
+
"step": 5300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 138.46,
|
| 430 |
+
"learning_rate": 5.1565100671140944e-05,
|
| 431 |
+
"loss": 0.0133,
|
| 432 |
+
"step": 5400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 141.03,
|
| 436 |
+
"learning_rate": 5.102818791946309e-05,
|
| 437 |
+
"loss": 0.0098,
|
| 438 |
+
"step": 5500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 141.03,
|
| 442 |
+
"eval_las": 67.54682503426223,
|
| 443 |
+
"eval_loss": 5.314740180969238,
|
| 444 |
+
"eval_runtime": 2.5216,
|
| 445 |
+
"eval_samples_per_second": 151.093,
|
| 446 |
+
"eval_steps_per_second": 19.035,
|
| 447 |
+
"eval_uas": 74.99314755596163,
|
| 448 |
+
"step": 5500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 143.59,
|
| 452 |
+
"learning_rate": 5.049127516778524e-05,
|
| 453 |
+
"loss": 0.0096,
|
| 454 |
+
"step": 5600
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 146.15,
|
| 458 |
+
"learning_rate": 4.995436241610739e-05,
|
| 459 |
+
"loss": 0.0104,
|
| 460 |
+
"step": 5700
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 148.72,
|
| 464 |
+
"learning_rate": 4.941744966442954e-05,
|
| 465 |
+
"loss": 0.0095,
|
| 466 |
+
"step": 5800
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 151.28,
|
| 470 |
+
"learning_rate": 4.8880536912751685e-05,
|
| 471 |
+
"loss": 0.0078,
|
| 472 |
+
"step": 5900
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 153.85,
|
| 476 |
+
"learning_rate": 4.834362416107383e-05,
|
| 477 |
+
"loss": 0.0083,
|
| 478 |
+
"step": 6000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 153.85,
|
| 482 |
+
"eval_las": 67.90315212425764,
|
| 483 |
+
"eval_loss": 5.257903575897217,
|
| 484 |
+
"eval_runtime": 2.5051,
|
| 485 |
+
"eval_samples_per_second": 152.089,
|
| 486 |
+
"eval_steps_per_second": 19.161,
|
| 487 |
+
"eval_uas": 75.16674280493376,
|
| 488 |
+
"step": 6000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 156.41,
|
| 492 |
+
"learning_rate": 4.780671140939598e-05,
|
| 493 |
+
"loss": 0.0086,
|
| 494 |
+
"step": 6100
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 158.97,
|
| 498 |
+
"learning_rate": 4.726979865771813e-05,
|
| 499 |
+
"loss": 0.0088,
|
| 500 |
+
"step": 6200
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 161.54,
|
| 504 |
+
"learning_rate": 4.673288590604027e-05,
|
| 505 |
+
"loss": 0.0073,
|
| 506 |
+
"step": 6300
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 164.1,
|
| 510 |
+
"learning_rate": 4.619597315436242e-05,
|
| 511 |
+
"loss": 0.0075,
|
| 512 |
+
"step": 6400
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 166.67,
|
| 516 |
+
"learning_rate": 4.565906040268457e-05,
|
| 517 |
+
"loss": 0.0075,
|
| 518 |
+
"step": 6500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 166.67,
|
| 522 |
+
"eval_las": 67.38236637734126,
|
| 523 |
+
"eval_loss": 5.439788818359375,
|
| 524 |
+
"eval_runtime": 2.5045,
|
| 525 |
+
"eval_samples_per_second": 152.128,
|
| 526 |
+
"eval_steps_per_second": 19.166,
|
| 527 |
+
"eval_uas": 74.9200548195523,
|
| 528 |
+
"step": 6500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 169.23,
|
| 532 |
+
"learning_rate": 4.5122147651006716e-05,
|
| 533 |
+
"loss": 0.0063,
|
| 534 |
+
"step": 6600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 171.79,
|
| 538 |
+
"learning_rate": 4.4585234899328864e-05,
|
| 539 |
+
"loss": 0.0072,
|
| 540 |
+
"step": 6700
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 174.36,
|
| 544 |
+
"learning_rate": 4.404832214765101e-05,
|
| 545 |
+
"loss": 0.0062,
|
| 546 |
+
"step": 6800
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 176.92,
|
| 550 |
+
"learning_rate": 4.351140939597316e-05,
|
| 551 |
+
"loss": 0.0063,
|
| 552 |
+
"step": 6900
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 179.49,
|
| 556 |
+
"learning_rate": 4.297449664429531e-05,
|
| 557 |
+
"loss": 0.008,
|
| 558 |
+
"step": 7000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 179.49,
|
| 562 |
+
"eval_las": 67.61078117862037,
|
| 563 |
+
"eval_loss": 5.429704189300537,
|
| 564 |
+
"eval_runtime": 2.5048,
|
| 565 |
+
"eval_samples_per_second": 152.105,
|
| 566 |
+
"eval_steps_per_second": 19.163,
|
| 567 |
+
"eval_uas": 75.58702603928734,
|
| 568 |
+
"step": 7000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 182.05,
|
| 572 |
+
"learning_rate": 4.243758389261746e-05,
|
| 573 |
+
"loss": 0.0064,
|
| 574 |
+
"step": 7100
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 184.62,
|
| 578 |
+
"learning_rate": 4.1900671140939605e-05,
|
| 579 |
+
"loss": 0.0056,
|
| 580 |
+
"step": 7200
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 187.18,
|
| 584 |
+
"learning_rate": 4.1363758389261754e-05,
|
| 585 |
+
"loss": 0.0058,
|
| 586 |
+
"step": 7300
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 189.74,
|
| 590 |
+
"learning_rate": 4.0826845637583895e-05,
|
| 591 |
+
"loss": 0.0058,
|
| 592 |
+
"step": 7400
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 192.31,
|
| 596 |
+
"learning_rate": 4.028993288590604e-05,
|
| 597 |
+
"loss": 0.0064,
|
| 598 |
+
"step": 7500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 192.31,
|
| 602 |
+
"eval_las": 68.15897670169026,
|
| 603 |
+
"eval_loss": 5.503659725189209,
|
| 604 |
+
"eval_runtime": 2.5084,
|
| 605 |
+
"eval_samples_per_second": 151.887,
|
| 606 |
+
"eval_steps_per_second": 19.135,
|
| 607 |
+
"eval_uas": 75.56875285518501,
|
| 608 |
+
"step": 7500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 194.87,
|
| 612 |
+
"learning_rate": 3.975302013422819e-05,
|
| 613 |
+
"loss": 0.0067,
|
| 614 |
+
"step": 7600
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 197.44,
|
| 618 |
+
"learning_rate": 3.921610738255034e-05,
|
| 619 |
+
"loss": 0.0046,
|
| 620 |
+
"step": 7700
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 200.0,
|
| 624 |
+
"learning_rate": 3.867919463087249e-05,
|
| 625 |
+
"loss": 0.0045,
|
| 626 |
+
"step": 7800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 202.56,
|
| 630 |
+
"learning_rate": 3.8142281879194636e-05,
|
| 631 |
+
"loss": 0.005,
|
| 632 |
+
"step": 7900
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 205.13,
|
| 636 |
+
"learning_rate": 3.7605369127516784e-05,
|
| 637 |
+
"loss": 0.0049,
|
| 638 |
+
"step": 8000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 205.13,
|
| 642 |
+
"eval_las": 67.86660575605299,
|
| 643 |
+
"eval_loss": 5.539348125457764,
|
| 644 |
+
"eval_runtime": 2.5096,
|
| 645 |
+
"eval_samples_per_second": 151.815,
|
| 646 |
+
"eval_steps_per_second": 19.126,
|
| 647 |
+
"eval_uas": 75.4682503426222,
|
| 648 |
+
"step": 8000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 207.69,
|
| 652 |
+
"learning_rate": 3.706845637583893e-05,
|
| 653 |
+
"loss": 0.0052,
|
| 654 |
+
"step": 8100
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 210.26,
|
| 658 |
+
"learning_rate": 3.653154362416108e-05,
|
| 659 |
+
"loss": 0.0043,
|
| 660 |
+
"step": 8200
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 212.82,
|
| 664 |
+
"learning_rate": 3.599463087248322e-05,
|
| 665 |
+
"loss": 0.0043,
|
| 666 |
+
"step": 8300
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 215.38,
|
| 670 |
+
"learning_rate": 3.545771812080537e-05,
|
| 671 |
+
"loss": 0.0041,
|
| 672 |
+
"step": 8400
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 217.95,
|
| 676 |
+
"learning_rate": 3.492080536912752e-05,
|
| 677 |
+
"loss": 0.0053,
|
| 678 |
+
"step": 8500
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 217.95,
|
| 682 |
+
"eval_las": 68.07674737322978,
|
| 683 |
+
"eval_loss": 5.689121246337891,
|
| 684 |
+
"eval_runtime": 2.5046,
|
| 685 |
+
"eval_samples_per_second": 152.121,
|
| 686 |
+
"eval_steps_per_second": 19.165,
|
| 687 |
+
"eval_uas": 75.678391959799,
|
| 688 |
+
"step": 8500
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 220.51,
|
| 692 |
+
"learning_rate": 3.438389261744967e-05,
|
| 693 |
+
"loss": 0.0039,
|
| 694 |
+
"step": 8600
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 223.08,
|
| 698 |
+
"learning_rate": 3.3846979865771815e-05,
|
| 699 |
+
"loss": 0.004,
|
| 700 |
+
"step": 8700
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 225.64,
|
| 704 |
+
"learning_rate": 3.3310067114093964e-05,
|
| 705 |
+
"loss": 0.0038,
|
| 706 |
+
"step": 8800
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 228.21,
|
| 710 |
+
"learning_rate": 3.277315436241611e-05,
|
| 711 |
+
"loss": 0.0038,
|
| 712 |
+
"step": 8900
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 230.77,
|
| 716 |
+
"learning_rate": 3.223624161073826e-05,
|
| 717 |
+
"loss": 0.0033,
|
| 718 |
+
"step": 9000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 230.77,
|
| 722 |
+
"eval_las": 69.00867976244861,
|
| 723 |
+
"eval_loss": 5.695150852203369,
|
| 724 |
+
"eval_runtime": 2.503,
|
| 725 |
+
"eval_samples_per_second": 152.215,
|
| 726 |
+
"eval_steps_per_second": 19.177,
|
| 727 |
+
"eval_uas": 76.09867519415258,
|
| 728 |
+
"step": 9000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 233.33,
|
| 732 |
+
"learning_rate": 3.169932885906041e-05,
|
| 733 |
+
"loss": 0.0038,
|
| 734 |
+
"step": 9100
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 235.9,
|
| 738 |
+
"learning_rate": 3.1162416107382557e-05,
|
| 739 |
+
"loss": 0.0034,
|
| 740 |
+
"step": 9200
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 238.46,
|
| 744 |
+
"learning_rate": 3.0625503355704705e-05,
|
| 745 |
+
"loss": 0.0036,
|
| 746 |
+
"step": 9300
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 241.03,
|
| 750 |
+
"learning_rate": 3.0088590604026846e-05,
|
| 751 |
+
"loss": 0.0037,
|
| 752 |
+
"step": 9400
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 243.59,
|
| 756 |
+
"learning_rate": 2.9551677852348995e-05,
|
| 757 |
+
"loss": 0.0033,
|
| 758 |
+
"step": 9500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 243.59,
|
| 762 |
+
"eval_las": 68.76199177706715,
|
| 763 |
+
"eval_loss": 5.625730037689209,
|
| 764 |
+
"eval_runtime": 2.5076,
|
| 765 |
+
"eval_samples_per_second": 151.938,
|
| 766 |
+
"eval_steps_per_second": 19.142,
|
| 767 |
+
"eval_uas": 75.96162631338511,
|
| 768 |
+
"step": 9500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 246.15,
|
| 772 |
+
"learning_rate": 2.9014765100671143e-05,
|
| 773 |
+
"loss": 0.0025,
|
| 774 |
+
"step": 9600
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 248.72,
|
| 778 |
+
"learning_rate": 2.847785234899329e-05,
|
| 779 |
+
"loss": 0.0029,
|
| 780 |
+
"step": 9700
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 251.28,
|
| 784 |
+
"learning_rate": 2.794093959731544e-05,
|
| 785 |
+
"loss": 0.0036,
|
| 786 |
+
"step": 9800
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 253.85,
|
| 790 |
+
"learning_rate": 2.7404026845637588e-05,
|
| 791 |
+
"loss": 0.0034,
|
| 792 |
+
"step": 9900
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 256.41,
|
| 796 |
+
"learning_rate": 2.6867114093959732e-05,
|
| 797 |
+
"loss": 0.0032,
|
| 798 |
+
"step": 10000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 256.41,
|
| 802 |
+
"eval_las": 68.68889904065783,
|
| 803 |
+
"eval_loss": 5.689762115478516,
|
| 804 |
+
"eval_runtime": 2.5074,
|
| 805 |
+
"eval_samples_per_second": 151.949,
|
| 806 |
+
"eval_steps_per_second": 19.143,
|
| 807 |
+
"eval_uas": 75.68752855185016,
|
| 808 |
+
"step": 10000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 258.97,
|
| 812 |
+
"learning_rate": 2.633020134228188e-05,
|
| 813 |
+
"loss": 0.0028,
|
| 814 |
+
"step": 10100
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 261.54,
|
| 818 |
+
"learning_rate": 2.579328859060403e-05,
|
| 819 |
+
"loss": 0.0027,
|
| 820 |
+
"step": 10200
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 264.1,
|
| 824 |
+
"learning_rate": 2.5256375838926177e-05,
|
| 825 |
+
"loss": 0.002,
|
| 826 |
+
"step": 10300
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 266.67,
|
| 830 |
+
"learning_rate": 2.4719463087248325e-05,
|
| 831 |
+
"loss": 0.0023,
|
| 832 |
+
"step": 10400
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 269.23,
|
| 836 |
+
"learning_rate": 2.4182550335570474e-05,
|
| 837 |
+
"loss": 0.002,
|
| 838 |
+
"step": 10500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 269.23,
|
| 842 |
+
"eval_las": 68.93558702603929,
|
| 843 |
+
"eval_loss": 6.083931922912598,
|
| 844 |
+
"eval_runtime": 2.511,
|
| 845 |
+
"eval_samples_per_second": 151.731,
|
| 846 |
+
"eval_steps_per_second": 19.116,
|
| 847 |
+
"eval_uas": 76.0438556418456,
|
| 848 |
+
"step": 10500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 271.79,
|
| 852 |
+
"learning_rate": 2.364563758389262e-05,
|
| 853 |
+
"loss": 0.0016,
|
| 854 |
+
"step": 10600
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 274.36,
|
| 858 |
+
"learning_rate": 2.3108724832214767e-05,
|
| 859 |
+
"loss": 0.0016,
|
| 860 |
+
"step": 10700
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 276.92,
|
| 864 |
+
"learning_rate": 2.2571812080536915e-05,
|
| 865 |
+
"loss": 0.0021,
|
| 866 |
+
"step": 10800
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 279.49,
|
| 870 |
+
"learning_rate": 2.2034899328859063e-05,
|
| 871 |
+
"loss": 0.0021,
|
| 872 |
+
"step": 10900
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 282.05,
|
| 876 |
+
"learning_rate": 2.149798657718121e-05,
|
| 877 |
+
"loss": 0.0019,
|
| 878 |
+
"step": 11000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 282.05,
|
| 882 |
+
"eval_las": 68.63407948835084,
|
| 883 |
+
"eval_loss": 6.047039031982422,
|
| 884 |
+
"eval_runtime": 2.5036,
|
| 885 |
+
"eval_samples_per_second": 152.181,
|
| 886 |
+
"eval_steps_per_second": 19.172,
|
| 887 |
+
"eval_uas": 75.85198720877113,
|
| 888 |
+
"step": 11000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 284.62,
|
| 892 |
+
"learning_rate": 2.0961073825503356e-05,
|
| 893 |
+
"loss": 0.0016,
|
| 894 |
+
"step": 11100
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 287.18,
|
| 898 |
+
"learning_rate": 2.0424161073825505e-05,
|
| 899 |
+
"loss": 0.0021,
|
| 900 |
+
"step": 11200
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 289.74,
|
| 904 |
+
"learning_rate": 1.9887248322147653e-05,
|
| 905 |
+
"loss": 0.0024,
|
| 906 |
+
"step": 11300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 292.31,
|
| 910 |
+
"learning_rate": 1.93503355704698e-05,
|
| 911 |
+
"loss": 0.0017,
|
| 912 |
+
"step": 11400
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 294.87,
|
| 916 |
+
"learning_rate": 1.881342281879195e-05,
|
| 917 |
+
"loss": 0.0019,
|
| 918 |
+
"step": 11500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 294.87,
|
| 922 |
+
"eval_las": 68.79853814527182,
|
| 923 |
+
"eval_loss": 6.113554000854492,
|
| 924 |
+
"eval_runtime": 2.505,
|
| 925 |
+
"eval_samples_per_second": 152.095,
|
| 926 |
+
"eval_steps_per_second": 19.162,
|
| 927 |
+
"eval_uas": 76.23572407492006,
|
| 928 |
+
"step": 11500
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 294.87,
|
| 932 |
+
"step": 11500,
|
| 933 |
+
"total_flos": 7.223115436230451e+16,
|
| 934 |
+
"train_loss": 0.10975235502227493,
|
| 935 |
+
"train_runtime": 5024.1647,
|
| 936 |
+
"train_samples_per_second": 95.538,
|
| 937 |
+
"train_steps_per_second": 2.986
|
| 938 |
+
}
|
| 939 |
+
],
|
| 940 |
+
"max_steps": 15000,
|
| 941 |
+
"num_train_epochs": 385,
|
| 942 |
+
"total_flos": 7.223115436230451e+16,
|
| 943 |
+
"trial_name": null,
|
| 944 |
+
"trial_params": null
|
| 945 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab0ac43ad804f8ef985420eb2aefa3d58506b88edf8f2b7736dde5aa9938e8b7
|
| 3 |
+
size 3451
|