Md Mushfiqur Rahman
commited on
Commit
·
7589aa5
1
Parent(s):
e6cbdde
Upload with huggingface_hub
Browse files- README.md +15 -0
- all_results.json +20 -0
- config.json +64 -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 +1195 -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 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 78.95,
|
| 3 |
+
"eval_accuracy": 0.9574718836285272,
|
| 4 |
+
"eval_loss": 0.36283352971076965,
|
| 5 |
+
"eval_runtime": 4.632,
|
| 6 |
+
"eval_samples": 909,
|
| 7 |
+
"eval_samples_per_second": 196.244,
|
| 8 |
+
"eval_steps_per_second": 24.611,
|
| 9 |
+
"test_accuracy": 0.9551404853128991,
|
| 10 |
+
"test_loss": 0.38531413674354553,
|
| 11 |
+
"test_runtime": 3.482,
|
| 12 |
+
"test_samples": 680,
|
| 13 |
+
"test_samples_per_second": 195.29,
|
| 14 |
+
"test_steps_per_second": 24.411,
|
| 15 |
+
"train_loss": 0.028036758323883016,
|
| 16 |
+
"train_runtime": 3937.3195,
|
| 17 |
+
"train_samples": 6075,
|
| 18 |
+
"train_samples_per_second": 121.91,
|
| 19 |
+
"train_steps_per_second": 3.81
|
| 20 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 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": "ADJ",
|
| 14 |
+
"1": "ADP",
|
| 15 |
+
"2": "ADV",
|
| 16 |
+
"3": "AUX",
|
| 17 |
+
"4": "CCONJ",
|
| 18 |
+
"5": "DET",
|
| 19 |
+
"6": "INTJ",
|
| 20 |
+
"7": "NOUN",
|
| 21 |
+
"8": "NUM",
|
| 22 |
+
"9": "PART",
|
| 23 |
+
"10": "PRON",
|
| 24 |
+
"11": "PROPN",
|
| 25 |
+
"12": "PUNCT",
|
| 26 |
+
"13": "SCONJ",
|
| 27 |
+
"14": "SYM",
|
| 28 |
+
"15": "VERB",
|
| 29 |
+
"16": "X"
|
| 30 |
+
},
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 3072,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"ADJ": 0,
|
| 35 |
+
"ADP": 1,
|
| 36 |
+
"ADV": 2,
|
| 37 |
+
"AUX": 3,
|
| 38 |
+
"CCONJ": 4,
|
| 39 |
+
"DET": 5,
|
| 40 |
+
"INTJ": 6,
|
| 41 |
+
"NOUN": 7,
|
| 42 |
+
"NUM": 8,
|
| 43 |
+
"PART": 9,
|
| 44 |
+
"PRON": 10,
|
| 45 |
+
"PROPN": 11,
|
| 46 |
+
"PUNCT": 12,
|
| 47 |
+
"SCONJ": 13,
|
| 48 |
+
"SYM": 14,
|
| 49 |
+
"VERB": 15,
|
| 50 |
+
"X": 16
|
| 51 |
+
},
|
| 52 |
+
"layer_norm_eps": 1e-12,
|
| 53 |
+
"max_position_embeddings": 512,
|
| 54 |
+
"model_type": "bert",
|
| 55 |
+
"num_attention_heads": 12,
|
| 56 |
+
"num_hidden_layers": 12,
|
| 57 |
+
"pad_token_id": 0,
|
| 58 |
+
"position_embedding_type": "absolute",
|
| 59 |
+
"torch_dtype": "float32",
|
| 60 |
+
"transformers_version": "4.17.0",
|
| 61 |
+
"type_vocab_size": 2,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 28996
|
| 64 |
+
}
|
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:cf0b3671f5a1083e42ff2d7aa1647576bacb5a651f8185d98c44d0fa120a5d83
|
| 3 |
+
size 431017069
|
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 +1,1195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9574718836285272,
|
| 3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-pos-ud-Arabic-PADT/checkpoint-13000",
|
| 4 |
+
"epoch": 78.94736842105263,
|
| 5 |
+
"global_step": 15000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.53,
|
| 12 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 13 |
+
"loss": 1.2456,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.05,
|
| 18 |
+
"learning_rate": 4.966778523489933e-05,
|
| 19 |
+
"loss": 0.3317,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.58,
|
| 24 |
+
"learning_rate": 4.933221476510068e-05,
|
| 25 |
+
"loss": 0.2403,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.11,
|
| 30 |
+
"learning_rate": 4.8996644295302016e-05,
|
| 31 |
+
"loss": 0.2052,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.63,
|
| 36 |
+
"learning_rate": 4.8661073825503355e-05,
|
| 37 |
+
"loss": 0.171,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.63,
|
| 42 |
+
"eval_accuracy": 0.9443396861741531,
|
| 43 |
+
"eval_loss": 0.18388177454471588,
|
| 44 |
+
"eval_runtime": 4.6604,
|
| 45 |
+
"eval_samples_per_second": 195.048,
|
| 46 |
+
"eval_steps_per_second": 24.461,
|
| 47 |
+
"step": 500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.16,
|
| 51 |
+
"learning_rate": 4.83255033557047e-05,
|
| 52 |
+
"loss": 0.1527,
|
| 53 |
+
"step": 600
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.68,
|
| 57 |
+
"learning_rate": 4.798993288590604e-05,
|
| 58 |
+
"loss": 0.1387,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.21,
|
| 63 |
+
"learning_rate": 4.765436241610739e-05,
|
| 64 |
+
"loss": 0.1234,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.74,
|
| 69 |
+
"learning_rate": 4.7318791946308726e-05,
|
| 70 |
+
"loss": 0.1116,
|
| 71 |
+
"step": 900
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.26,
|
| 75 |
+
"learning_rate": 4.698322147651007e-05,
|
| 76 |
+
"loss": 0.1049,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.26,
|
| 81 |
+
"eval_accuracy": 0.9493231867465822,
|
| 82 |
+
"eval_loss": 0.18382076919078827,
|
| 83 |
+
"eval_runtime": 4.6662,
|
| 84 |
+
"eval_samples_per_second": 194.805,
|
| 85 |
+
"eval_steps_per_second": 24.431,
|
| 86 |
+
"step": 1000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.79,
|
| 90 |
+
"learning_rate": 4.664765100671141e-05,
|
| 91 |
+
"loss": 0.0932,
|
| 92 |
+
"step": 1100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.32,
|
| 96 |
+
"learning_rate": 4.631208053691276e-05,
|
| 97 |
+
"loss": 0.0843,
|
| 98 |
+
"step": 1200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.84,
|
| 102 |
+
"learning_rate": 4.5976510067114097e-05,
|
| 103 |
+
"loss": 0.0773,
|
| 104 |
+
"step": 1300
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.37,
|
| 108 |
+
"learning_rate": 4.564093959731544e-05,
|
| 109 |
+
"loss": 0.0664,
|
| 110 |
+
"step": 1400
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.89,
|
| 114 |
+
"learning_rate": 4.5305369127516775e-05,
|
| 115 |
+
"loss": 0.0678,
|
| 116 |
+
"step": 1500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.89,
|
| 120 |
+
"eval_accuracy": 0.9527914337665836,
|
| 121 |
+
"eval_loss": 0.18106327950954437,
|
| 122 |
+
"eval_runtime": 4.676,
|
| 123 |
+
"eval_samples_per_second": 194.398,
|
| 124 |
+
"eval_steps_per_second": 24.38,
|
| 125 |
+
"step": 1500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 8.42,
|
| 129 |
+
"learning_rate": 4.496979865771812e-05,
|
| 130 |
+
"loss": 0.0566,
|
| 131 |
+
"step": 1600
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 8.95,
|
| 135 |
+
"learning_rate": 4.463422818791946e-05,
|
| 136 |
+
"loss": 0.0567,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.47,
|
| 141 |
+
"learning_rate": 4.4298657718120806e-05,
|
| 142 |
+
"loss": 0.0443,
|
| 143 |
+
"step": 1800
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 10.0,
|
| 147 |
+
"learning_rate": 4.3963087248322146e-05,
|
| 148 |
+
"loss": 0.0465,
|
| 149 |
+
"step": 1900
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 10.53,
|
| 153 |
+
"learning_rate": 4.362751677852349e-05,
|
| 154 |
+
"loss": 0.0359,
|
| 155 |
+
"step": 2000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 10.53,
|
| 159 |
+
"eval_accuracy": 0.9525893999595932,
|
| 160 |
+
"eval_loss": 0.21346914768218994,
|
| 161 |
+
"eval_runtime": 4.6791,
|
| 162 |
+
"eval_samples_per_second": 194.267,
|
| 163 |
+
"eval_steps_per_second": 24.364,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 11.05,
|
| 168 |
+
"learning_rate": 4.329194630872484e-05,
|
| 169 |
+
"loss": 0.0388,
|
| 170 |
+
"step": 2100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 11.58,
|
| 174 |
+
"learning_rate": 4.295637583892618e-05,
|
| 175 |
+
"loss": 0.0327,
|
| 176 |
+
"step": 2200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 12.11,
|
| 180 |
+
"learning_rate": 4.262080536912752e-05,
|
| 181 |
+
"loss": 0.0319,
|
| 182 |
+
"step": 2300
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 12.63,
|
| 186 |
+
"learning_rate": 4.228523489932886e-05,
|
| 187 |
+
"loss": 0.028,
|
| 188 |
+
"step": 2400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 13.16,
|
| 192 |
+
"learning_rate": 4.194966442953021e-05,
|
| 193 |
+
"loss": 0.0275,
|
| 194 |
+
"step": 2500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 13.16,
|
| 198 |
+
"eval_accuracy": 0.9520843154421174,
|
| 199 |
+
"eval_loss": 0.2462630569934845,
|
| 200 |
+
"eval_runtime": 4.6736,
|
| 201 |
+
"eval_samples_per_second": 194.499,
|
| 202 |
+
"eval_steps_per_second": 24.393,
|
| 203 |
+
"step": 2500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 13.68,
|
| 207 |
+
"learning_rate": 4.161409395973155e-05,
|
| 208 |
+
"loss": 0.023,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 14.21,
|
| 213 |
+
"learning_rate": 4.127852348993289e-05,
|
| 214 |
+
"loss": 0.0241,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 14.74,
|
| 219 |
+
"learning_rate": 4.0942953020134226e-05,
|
| 220 |
+
"loss": 0.0214,
|
| 221 |
+
"step": 2800
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 15.26,
|
| 225 |
+
"learning_rate": 4.060738255033557e-05,
|
| 226 |
+
"loss": 0.0191,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 15.79,
|
| 231 |
+
"learning_rate": 4.027181208053691e-05,
|
| 232 |
+
"loss": 0.0188,
|
| 233 |
+
"step": 3000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.79,
|
| 237 |
+
"eval_accuracy": 0.9528587783689138,
|
| 238 |
+
"eval_loss": 0.24228344857692719,
|
| 239 |
+
"eval_runtime": 4.6621,
|
| 240 |
+
"eval_samples_per_second": 194.978,
|
| 241 |
+
"eval_steps_per_second": 24.453,
|
| 242 |
+
"step": 3000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 16.32,
|
| 246 |
+
"learning_rate": 3.993624161073826e-05,
|
| 247 |
+
"loss": 0.0166,
|
| 248 |
+
"step": 3100
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.84,
|
| 252 |
+
"learning_rate": 3.96006711409396e-05,
|
| 253 |
+
"loss": 0.0183,
|
| 254 |
+
"step": 3200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 17.37,
|
| 258 |
+
"learning_rate": 3.926510067114094e-05,
|
| 259 |
+
"loss": 0.0155,
|
| 260 |
+
"step": 3300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 17.89,
|
| 264 |
+
"learning_rate": 3.892953020134228e-05,
|
| 265 |
+
"loss": 0.0156,
|
| 266 |
+
"step": 3400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 18.42,
|
| 270 |
+
"learning_rate": 3.859395973154363e-05,
|
| 271 |
+
"loss": 0.0133,
|
| 272 |
+
"step": 3500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 18.42,
|
| 276 |
+
"eval_accuracy": 0.95349855209105,
|
| 277 |
+
"eval_loss": 0.26400476694107056,
|
| 278 |
+
"eval_runtime": 4.6713,
|
| 279 |
+
"eval_samples_per_second": 194.593,
|
| 280 |
+
"eval_steps_per_second": 24.404,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 18.95,
|
| 285 |
+
"learning_rate": 3.825838926174497e-05,
|
| 286 |
+
"loss": 0.0142,
|
| 287 |
+
"step": 3600
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 19.47,
|
| 291 |
+
"learning_rate": 3.7922818791946313e-05,
|
| 292 |
+
"loss": 0.0122,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 20.0,
|
| 297 |
+
"learning_rate": 3.758724832214765e-05,
|
| 298 |
+
"loss": 0.0131,
|
| 299 |
+
"step": 3800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 20.53,
|
| 303 |
+
"learning_rate": 3.725167785234899e-05,
|
| 304 |
+
"loss": 0.0115,
|
| 305 |
+
"step": 3900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 21.05,
|
| 309 |
+
"learning_rate": 3.691610738255034e-05,
|
| 310 |
+
"loss": 0.0127,
|
| 311 |
+
"step": 4000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 21.05,
|
| 315 |
+
"eval_accuracy": 0.9521853323456125,
|
| 316 |
+
"eval_loss": 0.27901268005371094,
|
| 317 |
+
"eval_runtime": 4.6772,
|
| 318 |
+
"eval_samples_per_second": 194.348,
|
| 319 |
+
"eval_steps_per_second": 24.374,
|
| 320 |
+
"step": 4000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 21.58,
|
| 324 |
+
"learning_rate": 3.658053691275168e-05,
|
| 325 |
+
"loss": 0.0107,
|
| 326 |
+
"step": 4100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 22.11,
|
| 330 |
+
"learning_rate": 3.624496644295302e-05,
|
| 331 |
+
"loss": 0.0112,
|
| 332 |
+
"step": 4200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 22.63,
|
| 336 |
+
"learning_rate": 3.590939597315436e-05,
|
| 337 |
+
"loss": 0.0097,
|
| 338 |
+
"step": 4300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 23.16,
|
| 342 |
+
"learning_rate": 3.557382550335571e-05,
|
| 343 |
+
"loss": 0.0101,
|
| 344 |
+
"step": 4400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 23.68,
|
| 348 |
+
"learning_rate": 3.523825503355705e-05,
|
| 349 |
+
"loss": 0.0091,
|
| 350 |
+
"step": 4500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 23.68,
|
| 354 |
+
"eval_accuracy": 0.9530608121759041,
|
| 355 |
+
"eval_loss": 0.2944227457046509,
|
| 356 |
+
"eval_runtime": 4.6644,
|
| 357 |
+
"eval_samples_per_second": 194.881,
|
| 358 |
+
"eval_steps_per_second": 24.44,
|
| 359 |
+
"step": 4500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 24.21,
|
| 363 |
+
"learning_rate": 3.4902684563758394e-05,
|
| 364 |
+
"loss": 0.0097,
|
| 365 |
+
"step": 4600
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 24.74,
|
| 369 |
+
"learning_rate": 3.456711409395973e-05,
|
| 370 |
+
"loss": 0.0075,
|
| 371 |
+
"step": 4700
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 25.26,
|
| 375 |
+
"learning_rate": 3.423154362416108e-05,
|
| 376 |
+
"loss": 0.0086,
|
| 377 |
+
"step": 4800
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 25.79,
|
| 381 |
+
"learning_rate": 3.389597315436242e-05,
|
| 382 |
+
"loss": 0.0075,
|
| 383 |
+
"step": 4900
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 26.32,
|
| 387 |
+
"learning_rate": 3.356040268456376e-05,
|
| 388 |
+
"loss": 0.0082,
|
| 389 |
+
"step": 5000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 26.32,
|
| 393 |
+
"eval_accuracy": 0.9545087211260017,
|
| 394 |
+
"eval_loss": 0.28701817989349365,
|
| 395 |
+
"eval_runtime": 4.6855,
|
| 396 |
+
"eval_samples_per_second": 194.002,
|
| 397 |
+
"eval_steps_per_second": 24.33,
|
| 398 |
+
"step": 5000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 26.84,
|
| 402 |
+
"learning_rate": 3.32248322147651e-05,
|
| 403 |
+
"loss": 0.008,
|
| 404 |
+
"step": 5100
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 27.37,
|
| 408 |
+
"learning_rate": 3.288926174496644e-05,
|
| 409 |
+
"loss": 0.0066,
|
| 410 |
+
"step": 5200
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 27.89,
|
| 414 |
+
"learning_rate": 3.255369127516779e-05,
|
| 415 |
+
"loss": 0.007,
|
| 416 |
+
"step": 5300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 28.42,
|
| 420 |
+
"learning_rate": 3.221812080536913e-05,
|
| 421 |
+
"loss": 0.0065,
|
| 422 |
+
"step": 5400
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 28.95,
|
| 426 |
+
"learning_rate": 3.1882550335570474e-05,
|
| 427 |
+
"loss": 0.0071,
|
| 428 |
+
"step": 5500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 28.95,
|
| 432 |
+
"eval_accuracy": 0.9537005858980403,
|
| 433 |
+
"eval_loss": 0.2949673533439636,
|
| 434 |
+
"eval_runtime": 4.6645,
|
| 435 |
+
"eval_samples_per_second": 194.878,
|
| 436 |
+
"eval_steps_per_second": 24.44,
|
| 437 |
+
"step": 5500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 29.47,
|
| 441 |
+
"learning_rate": 3.1546979865771814e-05,
|
| 442 |
+
"loss": 0.0058,
|
| 443 |
+
"step": 5600
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 30.0,
|
| 447 |
+
"learning_rate": 3.121140939597316e-05,
|
| 448 |
+
"loss": 0.0069,
|
| 449 |
+
"step": 5700
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 30.53,
|
| 453 |
+
"learning_rate": 3.08758389261745e-05,
|
| 454 |
+
"loss": 0.0057,
|
| 455 |
+
"step": 5800
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 31.05,
|
| 459 |
+
"learning_rate": 3.0540268456375845e-05,
|
| 460 |
+
"loss": 0.0062,
|
| 461 |
+
"step": 5900
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 31.58,
|
| 465 |
+
"learning_rate": 3.0204697986577184e-05,
|
| 466 |
+
"loss": 0.0059,
|
| 467 |
+
"step": 6000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 31.58,
|
| 471 |
+
"eval_accuracy": 0.9539699643073608,
|
| 472 |
+
"eval_loss": 0.30248409509658813,
|
| 473 |
+
"eval_runtime": 4.6764,
|
| 474 |
+
"eval_samples_per_second": 194.38,
|
| 475 |
+
"eval_steps_per_second": 24.378,
|
| 476 |
+
"step": 6000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 32.11,
|
| 480 |
+
"learning_rate": 2.9869127516778524e-05,
|
| 481 |
+
"loss": 0.0066,
|
| 482 |
+
"step": 6100
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 32.63,
|
| 486 |
+
"learning_rate": 2.9533557046979866e-05,
|
| 487 |
+
"loss": 0.0055,
|
| 488 |
+
"step": 6200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 33.16,
|
| 492 |
+
"learning_rate": 2.919798657718121e-05,
|
| 493 |
+
"loss": 0.0058,
|
| 494 |
+
"step": 6300
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 33.68,
|
| 498 |
+
"learning_rate": 2.886241610738255e-05,
|
| 499 |
+
"loss": 0.0054,
|
| 500 |
+
"step": 6400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 34.21,
|
| 504 |
+
"learning_rate": 2.8526845637583894e-05,
|
| 505 |
+
"loss": 0.0054,
|
| 506 |
+
"step": 6500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 34.21,
|
| 510 |
+
"eval_accuracy": 0.95349855209105,
|
| 511 |
+
"eval_loss": 0.3090747594833374,
|
| 512 |
+
"eval_runtime": 4.706,
|
| 513 |
+
"eval_samples_per_second": 193.157,
|
| 514 |
+
"eval_steps_per_second": 24.224,
|
| 515 |
+
"step": 6500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 34.74,
|
| 519 |
+
"learning_rate": 2.8191275167785237e-05,
|
| 520 |
+
"loss": 0.0045,
|
| 521 |
+
"step": 6600
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 35.26,
|
| 525 |
+
"learning_rate": 2.785570469798658e-05,
|
| 526 |
+
"loss": 0.0048,
|
| 527 |
+
"step": 6700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 35.79,
|
| 531 |
+
"learning_rate": 2.7520134228187922e-05,
|
| 532 |
+
"loss": 0.0051,
|
| 533 |
+
"step": 6800
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 36.32,
|
| 537 |
+
"learning_rate": 2.7184563758389265e-05,
|
| 538 |
+
"loss": 0.0041,
|
| 539 |
+
"step": 6900
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 36.84,
|
| 543 |
+
"learning_rate": 2.6848993288590607e-05,
|
| 544 |
+
"loss": 0.0043,
|
| 545 |
+
"step": 7000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 36.84,
|
| 549 |
+
"eval_accuracy": 0.9523873661526029,
|
| 550 |
+
"eval_loss": 0.3119761049747467,
|
| 551 |
+
"eval_runtime": 4.6767,
|
| 552 |
+
"eval_samples_per_second": 194.369,
|
| 553 |
+
"eval_steps_per_second": 24.376,
|
| 554 |
+
"step": 7000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 37.37,
|
| 558 |
+
"learning_rate": 2.651342281879195e-05,
|
| 559 |
+
"loss": 0.0043,
|
| 560 |
+
"step": 7100
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 37.89,
|
| 564 |
+
"learning_rate": 2.6177852348993293e-05,
|
| 565 |
+
"loss": 0.0035,
|
| 566 |
+
"step": 7200
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 38.42,
|
| 570 |
+
"learning_rate": 2.584228187919463e-05,
|
| 571 |
+
"loss": 0.0035,
|
| 572 |
+
"step": 7300
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 38.95,
|
| 576 |
+
"learning_rate": 2.551006711409396e-05,
|
| 577 |
+
"loss": 0.0039,
|
| 578 |
+
"step": 7400
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 39.47,
|
| 582 |
+
"learning_rate": 2.5174496644295303e-05,
|
| 583 |
+
"loss": 0.0036,
|
| 584 |
+
"step": 7500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 39.47,
|
| 588 |
+
"eval_accuracy": 0.9550138056434777,
|
| 589 |
+
"eval_loss": 0.317449688911438,
|
| 590 |
+
"eval_runtime": 4.671,
|
| 591 |
+
"eval_samples_per_second": 194.604,
|
| 592 |
+
"eval_steps_per_second": 24.406,
|
| 593 |
+
"step": 7500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 40.0,
|
| 597 |
+
"learning_rate": 2.4838926174496646e-05,
|
| 598 |
+
"loss": 0.0034,
|
| 599 |
+
"step": 7600
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 40.53,
|
| 603 |
+
"learning_rate": 2.4506711409395974e-05,
|
| 604 |
+
"loss": 0.0041,
|
| 605 |
+
"step": 7700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 41.05,
|
| 609 |
+
"learning_rate": 2.4171140939597317e-05,
|
| 610 |
+
"loss": 0.0044,
|
| 611 |
+
"step": 7800
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 41.58,
|
| 615 |
+
"learning_rate": 2.383557046979866e-05,
|
| 616 |
+
"loss": 0.0039,
|
| 617 |
+
"step": 7900
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 42.11,
|
| 621 |
+
"learning_rate": 2.35e-05,
|
| 622 |
+
"loss": 0.0032,
|
| 623 |
+
"step": 8000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 42.11,
|
| 627 |
+
"eval_accuracy": 0.9548791164388174,
|
| 628 |
+
"eval_loss": 0.32017943263053894,
|
| 629 |
+
"eval_runtime": 4.682,
|
| 630 |
+
"eval_samples_per_second": 194.147,
|
| 631 |
+
"eval_steps_per_second": 24.348,
|
| 632 |
+
"step": 8000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 42.63,
|
| 636 |
+
"learning_rate": 2.316442953020134e-05,
|
| 637 |
+
"loss": 0.0032,
|
| 638 |
+
"step": 8100
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 43.16,
|
| 642 |
+
"learning_rate": 2.2828859060402684e-05,
|
| 643 |
+
"loss": 0.0038,
|
| 644 |
+
"step": 8200
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 43.68,
|
| 648 |
+
"learning_rate": 2.2493288590604027e-05,
|
| 649 |
+
"loss": 0.0029,
|
| 650 |
+
"step": 8300
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 44.21,
|
| 654 |
+
"learning_rate": 2.215771812080537e-05,
|
| 655 |
+
"loss": 0.003,
|
| 656 |
+
"step": 8400
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 44.74,
|
| 660 |
+
"learning_rate": 2.1822147651006712e-05,
|
| 661 |
+
"loss": 0.0037,
|
| 662 |
+
"step": 8500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 44.74,
|
| 666 |
+
"eval_accuracy": 0.9536332412957101,
|
| 667 |
+
"eval_loss": 0.3339065611362457,
|
| 668 |
+
"eval_runtime": 4.676,
|
| 669 |
+
"eval_samples_per_second": 194.396,
|
| 670 |
+
"eval_steps_per_second": 24.38,
|
| 671 |
+
"step": 8500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 45.26,
|
| 675 |
+
"learning_rate": 2.1486577181208055e-05,
|
| 676 |
+
"loss": 0.0033,
|
| 677 |
+
"step": 8600
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 45.79,
|
| 681 |
+
"learning_rate": 2.1151006711409397e-05,
|
| 682 |
+
"loss": 0.0038,
|
| 683 |
+
"step": 8700
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 46.32,
|
| 687 |
+
"learning_rate": 2.081543624161074e-05,
|
| 688 |
+
"loss": 0.0027,
|
| 689 |
+
"step": 8800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 46.84,
|
| 693 |
+
"learning_rate": 2.0479865771812082e-05,
|
| 694 |
+
"loss": 0.0029,
|
| 695 |
+
"step": 8900
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 47.37,
|
| 699 |
+
"learning_rate": 2.0144295302013425e-05,
|
| 700 |
+
"loss": 0.0022,
|
| 701 |
+
"step": 9000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 47.37,
|
| 705 |
+
"eval_accuracy": 0.9552495117516331,
|
| 706 |
+
"eval_loss": 0.3310903012752533,
|
| 707 |
+
"eval_runtime": 4.6747,
|
| 708 |
+
"eval_samples_per_second": 194.451,
|
| 709 |
+
"eval_steps_per_second": 24.387,
|
| 710 |
+
"step": 9000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 47.89,
|
| 714 |
+
"learning_rate": 1.9808724832214768e-05,
|
| 715 |
+
"loss": 0.002,
|
| 716 |
+
"step": 9100
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 48.42,
|
| 720 |
+
"learning_rate": 1.9473154362416107e-05,
|
| 721 |
+
"loss": 0.0023,
|
| 722 |
+
"step": 9200
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 48.95,
|
| 726 |
+
"learning_rate": 1.913758389261745e-05,
|
| 727 |
+
"loss": 0.0024,
|
| 728 |
+
"step": 9300
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 49.47,
|
| 732 |
+
"learning_rate": 1.8802013422818792e-05,
|
| 733 |
+
"loss": 0.0017,
|
| 734 |
+
"step": 9400
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 50.0,
|
| 738 |
+
"learning_rate": 1.8466442953020135e-05,
|
| 739 |
+
"loss": 0.0019,
|
| 740 |
+
"step": 9500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 50.0,
|
| 744 |
+
"eval_accuracy": 0.9556535793656138,
|
| 745 |
+
"eval_loss": 0.3342548906803131,
|
| 746 |
+
"eval_runtime": 4.6676,
|
| 747 |
+
"eval_samples_per_second": 194.747,
|
| 748 |
+
"eval_steps_per_second": 24.424,
|
| 749 |
+
"step": 9500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 50.53,
|
| 753 |
+
"learning_rate": 1.8130872483221478e-05,
|
| 754 |
+
"loss": 0.002,
|
| 755 |
+
"step": 9600
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 51.05,
|
| 759 |
+
"learning_rate": 1.779530201342282e-05,
|
| 760 |
+
"loss": 0.0018,
|
| 761 |
+
"step": 9700
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 51.58,
|
| 765 |
+
"learning_rate": 1.745973154362416e-05,
|
| 766 |
+
"loss": 0.0019,
|
| 767 |
+
"step": 9800
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 52.11,
|
| 771 |
+
"learning_rate": 1.7124161073825502e-05,
|
| 772 |
+
"loss": 0.0019,
|
| 773 |
+
"step": 9900
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 52.63,
|
| 777 |
+
"learning_rate": 1.6788590604026845e-05,
|
| 778 |
+
"loss": 0.0018,
|
| 779 |
+
"step": 10000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 52.63,
|
| 783 |
+
"eval_accuracy": 0.955720923967944,
|
| 784 |
+
"eval_loss": 0.34407833218574524,
|
| 785 |
+
"eval_runtime": 4.6926,
|
| 786 |
+
"eval_samples_per_second": 193.709,
|
| 787 |
+
"eval_steps_per_second": 24.294,
|
| 788 |
+
"step": 10000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 53.16,
|
| 792 |
+
"learning_rate": 1.6453020134228188e-05,
|
| 793 |
+
"loss": 0.0021,
|
| 794 |
+
"step": 10100
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 53.68,
|
| 798 |
+
"learning_rate": 1.6117449664429534e-05,
|
| 799 |
+
"loss": 0.0018,
|
| 800 |
+
"step": 10200
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 54.21,
|
| 804 |
+
"learning_rate": 1.5781879194630873e-05,
|
| 805 |
+
"loss": 0.0017,
|
| 806 |
+
"step": 10300
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 54.74,
|
| 810 |
+
"learning_rate": 1.5446308724832215e-05,
|
| 811 |
+
"loss": 0.0015,
|
| 812 |
+
"step": 10400
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 55.26,
|
| 816 |
+
"learning_rate": 1.5110738255033558e-05,
|
| 817 |
+
"loss": 0.0018,
|
| 818 |
+
"step": 10500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 55.26,
|
| 822 |
+
"eval_accuracy": 0.9560913192807596,
|
| 823 |
+
"eval_loss": 0.3533622622489929,
|
| 824 |
+
"eval_runtime": 4.6805,
|
| 825 |
+
"eval_samples_per_second": 194.209,
|
| 826 |
+
"eval_steps_per_second": 24.356,
|
| 827 |
+
"step": 10500
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 55.79,
|
| 831 |
+
"learning_rate": 1.47751677852349e-05,
|
| 832 |
+
"loss": 0.0017,
|
| 833 |
+
"step": 10600
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 56.32,
|
| 837 |
+
"learning_rate": 1.4439597315436243e-05,
|
| 838 |
+
"loss": 0.0019,
|
| 839 |
+
"step": 10700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 56.84,
|
| 843 |
+
"learning_rate": 1.4104026845637586e-05,
|
| 844 |
+
"loss": 0.001,
|
| 845 |
+
"step": 10800
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 57.37,
|
| 849 |
+
"learning_rate": 1.3768456375838925e-05,
|
| 850 |
+
"loss": 0.0011,
|
| 851 |
+
"step": 10900
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 57.89,
|
| 855 |
+
"learning_rate": 1.3432885906040268e-05,
|
| 856 |
+
"loss": 0.0013,
|
| 857 |
+
"step": 11000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 57.89,
|
| 861 |
+
"eval_accuracy": 0.9553505286551283,
|
| 862 |
+
"eval_loss": 0.3556341230869293,
|
| 863 |
+
"eval_runtime": 4.6828,
|
| 864 |
+
"eval_samples_per_second": 194.116,
|
| 865 |
+
"eval_steps_per_second": 24.345,
|
| 866 |
+
"step": 11000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 58.42,
|
| 870 |
+
"learning_rate": 1.309731543624161e-05,
|
| 871 |
+
"loss": 0.0013,
|
| 872 |
+
"step": 11100
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 58.95,
|
| 876 |
+
"learning_rate": 1.2761744966442953e-05,
|
| 877 |
+
"loss": 0.0012,
|
| 878 |
+
"step": 11200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 59.47,
|
| 882 |
+
"learning_rate": 1.2426174496644296e-05,
|
| 883 |
+
"loss": 0.001,
|
| 884 |
+
"step": 11300
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 60.0,
|
| 888 |
+
"learning_rate": 1.2090604026845639e-05,
|
| 889 |
+
"loss": 0.0014,
|
| 890 |
+
"step": 11400
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 60.53,
|
| 894 |
+
"learning_rate": 1.1755033557046981e-05,
|
| 895 |
+
"loss": 0.0017,
|
| 896 |
+
"step": 11500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 60.53,
|
| 900 |
+
"eval_accuracy": 0.9556872516667789,
|
| 901 |
+
"eval_loss": 0.3435748815536499,
|
| 902 |
+
"eval_runtime": 4.6824,
|
| 903 |
+
"eval_samples_per_second": 194.129,
|
| 904 |
+
"eval_steps_per_second": 24.346,
|
| 905 |
+
"step": 11500
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 61.05,
|
| 909 |
+
"learning_rate": 1.1419463087248322e-05,
|
| 910 |
+
"loss": 0.0013,
|
| 911 |
+
"step": 11600
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 61.58,
|
| 915 |
+
"learning_rate": 1.1083892617449665e-05,
|
| 916 |
+
"loss": 0.0008,
|
| 917 |
+
"step": 11700
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 62.11,
|
| 921 |
+
"learning_rate": 1.0748322147651008e-05,
|
| 922 |
+
"loss": 0.0012,
|
| 923 |
+
"step": 11800
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 62.63,
|
| 927 |
+
"learning_rate": 1.0412751677852349e-05,
|
| 928 |
+
"loss": 0.0009,
|
| 929 |
+
"step": 11900
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 63.16,
|
| 933 |
+
"learning_rate": 1.0077181208053691e-05,
|
| 934 |
+
"loss": 0.0011,
|
| 935 |
+
"step": 12000
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 63.16,
|
| 939 |
+
"eval_accuracy": 0.9564617145935753,
|
| 940 |
+
"eval_loss": 0.3513157069683075,
|
| 941 |
+
"eval_runtime": 4.6776,
|
| 942 |
+
"eval_samples_per_second": 194.332,
|
| 943 |
+
"eval_steps_per_second": 24.372,
|
| 944 |
+
"step": 12000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 63.68,
|
| 948 |
+
"learning_rate": 9.741610738255034e-06,
|
| 949 |
+
"loss": 0.0009,
|
| 950 |
+
"step": 12100
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 64.21,
|
| 954 |
+
"learning_rate": 9.406040268456376e-06,
|
| 955 |
+
"loss": 0.0008,
|
| 956 |
+
"step": 12200
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 64.74,
|
| 960 |
+
"learning_rate": 9.070469798657719e-06,
|
| 961 |
+
"loss": 0.0009,
|
| 962 |
+
"step": 12300
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 65.26,
|
| 966 |
+
"learning_rate": 8.734899328859062e-06,
|
| 967 |
+
"loss": 0.0009,
|
| 968 |
+
"step": 12400
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 65.79,
|
| 972 |
+
"learning_rate": 8.40268456375839e-06,
|
| 973 |
+
"loss": 0.0009,
|
| 974 |
+
"step": 12500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 65.79,
|
| 978 |
+
"eval_accuracy": 0.9567647653040608,
|
| 979 |
+
"eval_loss": 0.35964664816856384,
|
| 980 |
+
"eval_runtime": 4.6795,
|
| 981 |
+
"eval_samples_per_second": 194.25,
|
| 982 |
+
"eval_steps_per_second": 24.361,
|
| 983 |
+
"step": 12500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 66.32,
|
| 987 |
+
"learning_rate": 8.067114093959733e-06,
|
| 988 |
+
"loss": 0.0008,
|
| 989 |
+
"step": 12600
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 66.84,
|
| 993 |
+
"learning_rate": 7.731543624161074e-06,
|
| 994 |
+
"loss": 0.0007,
|
| 995 |
+
"step": 12700
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 67.37,
|
| 999 |
+
"learning_rate": 7.395973154362416e-06,
|
| 1000 |
+
"loss": 0.0007,
|
| 1001 |
+
"step": 12800
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 67.89,
|
| 1005 |
+
"learning_rate": 7.060402684563759e-06,
|
| 1006 |
+
"loss": 0.0008,
|
| 1007 |
+
"step": 12900
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 68.42,
|
| 1011 |
+
"learning_rate": 6.724832214765101e-06,
|
| 1012 |
+
"loss": 0.0006,
|
| 1013 |
+
"step": 13000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 68.42,
|
| 1017 |
+
"eval_accuracy": 0.9574718836285272,
|
| 1018 |
+
"eval_loss": 0.36283352971076965,
|
| 1019 |
+
"eval_runtime": 4.6706,
|
| 1020 |
+
"eval_samples_per_second": 194.621,
|
| 1021 |
+
"eval_steps_per_second": 24.408,
|
| 1022 |
+
"step": 13000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 68.95,
|
| 1026 |
+
"learning_rate": 6.3892617449664435e-06,
|
| 1027 |
+
"loss": 0.0007,
|
| 1028 |
+
"step": 13100
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 69.47,
|
| 1032 |
+
"learning_rate": 6.053691275167785e-06,
|
| 1033 |
+
"loss": 0.0004,
|
| 1034 |
+
"step": 13200
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 70.0,
|
| 1038 |
+
"learning_rate": 5.718120805369128e-06,
|
| 1039 |
+
"loss": 0.0007,
|
| 1040 |
+
"step": 13300
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 70.53,
|
| 1044 |
+
"learning_rate": 5.38255033557047e-06,
|
| 1045 |
+
"loss": 0.0004,
|
| 1046 |
+
"step": 13400
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 71.05,
|
| 1050 |
+
"learning_rate": 5.0469798657718124e-06,
|
| 1051 |
+
"loss": 0.0006,
|
| 1052 |
+
"step": 13500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 71.05,
|
| 1056 |
+
"eval_accuracy": 0.9566300760994007,
|
| 1057 |
+
"eval_loss": 0.3649657964706421,
|
| 1058 |
+
"eval_runtime": 4.689,
|
| 1059 |
+
"eval_samples_per_second": 193.859,
|
| 1060 |
+
"eval_steps_per_second": 24.312,
|
| 1061 |
+
"step": 13500
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 71.58,
|
| 1065 |
+
"learning_rate": 4.711409395973155e-06,
|
| 1066 |
+
"loss": 0.0005,
|
| 1067 |
+
"step": 13600
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 72.11,
|
| 1071 |
+
"learning_rate": 4.375838926174497e-06,
|
| 1072 |
+
"loss": 0.0005,
|
| 1073 |
+
"step": 13700
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 72.63,
|
| 1077 |
+
"learning_rate": 4.040268456375839e-06,
|
| 1078 |
+
"loss": 0.0006,
|
| 1079 |
+
"step": 13800
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 73.16,
|
| 1083 |
+
"learning_rate": 3.704697986577181e-06,
|
| 1084 |
+
"loss": 0.0006,
|
| 1085 |
+
"step": 13900
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 73.68,
|
| 1089 |
+
"learning_rate": 3.369127516778524e-06,
|
| 1090 |
+
"loss": 0.0003,
|
| 1091 |
+
"step": 14000
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 73.68,
|
| 1095 |
+
"eval_accuracy": 0.9569331268098862,
|
| 1096 |
+
"eval_loss": 0.3655867874622345,
|
| 1097 |
+
"eval_runtime": 4.6863,
|
| 1098 |
+
"eval_samples_per_second": 193.968,
|
| 1099 |
+
"eval_steps_per_second": 24.326,
|
| 1100 |
+
"step": 14000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 74.21,
|
| 1104 |
+
"learning_rate": 3.033557046979866e-06,
|
| 1105 |
+
"loss": 0.0004,
|
| 1106 |
+
"step": 14100
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 74.74,
|
| 1110 |
+
"learning_rate": 2.6979865771812085e-06,
|
| 1111 |
+
"loss": 0.0004,
|
| 1112 |
+
"step": 14200
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 75.26,
|
| 1116 |
+
"learning_rate": 2.3624161073825503e-06,
|
| 1117 |
+
"loss": 0.0005,
|
| 1118 |
+
"step": 14300
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 75.79,
|
| 1122 |
+
"learning_rate": 2.026845637583893e-06,
|
| 1123 |
+
"loss": 0.0004,
|
| 1124 |
+
"step": 14400
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 76.32,
|
| 1128 |
+
"learning_rate": 1.6912751677852347e-06,
|
| 1129 |
+
"loss": 0.0005,
|
| 1130 |
+
"step": 14500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 76.32,
|
| 1134 |
+
"eval_accuracy": 0.9568994545087212,
|
| 1135 |
+
"eval_loss": 0.3665154278278351,
|
| 1136 |
+
"eval_runtime": 4.6825,
|
| 1137 |
+
"eval_samples_per_second": 194.127,
|
| 1138 |
+
"eval_steps_per_second": 24.346,
|
| 1139 |
+
"step": 14500
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 76.84,
|
| 1143 |
+
"learning_rate": 1.3557046979865772e-06,
|
| 1144 |
+
"loss": 0.0004,
|
| 1145 |
+
"step": 14600
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 77.37,
|
| 1149 |
+
"learning_rate": 1.0201342281879194e-06,
|
| 1150 |
+
"loss": 0.0004,
|
| 1151 |
+
"step": 14700
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 77.89,
|
| 1155 |
+
"learning_rate": 6.845637583892617e-07,
|
| 1156 |
+
"loss": 0.0004,
|
| 1157 |
+
"step": 14800
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 78.42,
|
| 1161 |
+
"learning_rate": 3.48993288590604e-07,
|
| 1162 |
+
"loss": 0.0003,
|
| 1163 |
+
"step": 14900
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 78.95,
|
| 1167 |
+
"learning_rate": 1.3422818791946309e-08,
|
| 1168 |
+
"loss": 0.0003,
|
| 1169 |
+
"step": 15000
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 78.95,
|
| 1173 |
+
"eval_accuracy": 0.9568994545087212,
|
| 1174 |
+
"eval_loss": 0.3661660850048065,
|
| 1175 |
+
"eval_runtime": 4.6775,
|
| 1176 |
+
"eval_samples_per_second": 194.335,
|
| 1177 |
+
"eval_steps_per_second": 24.372,
|
| 1178 |
+
"step": 15000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 78.95,
|
| 1182 |
+
"step": 15000,
|
| 1183 |
+
"total_flos": 6.266876636395008e+16,
|
| 1184 |
+
"train_loss": 0.028036758323883016,
|
| 1185 |
+
"train_runtime": 3937.3195,
|
| 1186 |
+
"train_samples_per_second": 121.91,
|
| 1187 |
+
"train_steps_per_second": 3.81
|
| 1188 |
+
}
|
| 1189 |
+
],
|
| 1190 |
+
"max_steps": 15000,
|
| 1191 |
+
"num_train_epochs": 79,
|
| 1192 |
+
"total_flos": 6.266876636395008e+16,
|
| 1193 |
+
"trial_name": null,
|
| 1194 |
+
"trial_params": null
|
| 1195 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:751ff3d1e6f33500f9b5bc5b32c077c8854e68a9494a4fdb9480c790573de929
|
| 3 |
+
size 3387
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|