Spaces:
Runtime error
Runtime error
first time
Browse files- app.py +26 -0
- checkpoint-final/config.json +28 -0
- checkpoint-final/merges.txt +0 -0
- checkpoint-final/optimizer.pt +3 -0
- checkpoint-final/pytorch_model.bin +3 -0
- checkpoint-final/rng_state.pth +3 -0
- checkpoint-final/scaler.pt +3 -0
- checkpoint-final/scheduler.pt +3 -0
- checkpoint-final/special_tokens_map.json +1 -0
- checkpoint-final/trainer_state.json +1064 -0
- checkpoint-final/training_args.bin +3 -0
- checkpoint-final/vocab.json +1 -0
- checkpoint-final/vocab.txt +1 -0
- requirements.txt +3 -0
app.py
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
from transformers import AutoModel, AutoTokenizer, AutoModelForTokenClassification
|
| 3 |
+
import torch
|
| 4 |
+
import numpy as np
|
| 5 |
+
import torch.nn.functional as F
|
| 6 |
+
|
| 7 |
+
tokenizer = AutoTokenizer.from_pretrained("./checkpoint-final/")
|
| 8 |
+
model = AutoModelForTokenClassification.from_pretrained("./checkpoint-final/")
|
| 9 |
+
model = model.eval()
|
| 10 |
+
|
| 11 |
+
def get_out(sent):
|
| 12 |
+
encoded = tokenizer.encode_plus(sent, return_tensors="pt")
|
| 13 |
+
with torch.no_grad():
|
| 14 |
+
output = model(**encoded)
|
| 15 |
+
output = F.softmax(torch.squeeze(output['logits']))[1:-1,1].detach().numpy()
|
| 16 |
+
output = np.array2string(output, precision=4, separator=',',
|
| 17 |
+
suppress_small=True)
|
| 18 |
+
return output
|
| 19 |
+
|
| 20 |
+
gr.Interface(
|
| 21 |
+
get_out,
|
| 22 |
+
[
|
| 23 |
+
gr.components.Textbox(label="Input Amino Acid Sequence", placeholder = " Amino acid sequence here ...")
|
| 24 |
+
],
|
| 25 |
+
["text"],
|
| 26 |
+
).launch()
|
checkpoint-final/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./Models/ST-PRoBERTa/Checkpoints/checkpoint-3560000",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"max_position_embeddings": 1026,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 6,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.16.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 35
|
| 28 |
+
}
|
checkpoint-final/merges.txt
ADDED
|
File without changes
|
checkpoint-final/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22cc075cff31ab2bd9272f28c5dc01cdc6d2f79eb01ee2bbb4985e4875dbce81
|
| 3 |
+
size 346830453
|
checkpoint-final/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad4b68eb568e4f55b3e8d2891eb7f9409746e11a43a2184a8568b81a7404bac9
|
| 3 |
+
size 173435447
|
checkpoint-final/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5523d3fda330aa9b075ea20710439bc7ba67010d79ce0e5a3dc4bcce7871d362
|
| 3 |
+
size 14649
|
checkpoint-final/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eba87ee474597760c3889fee7265223c103205478e8ac6cd81e0f758f77f898
|
| 3 |
+
size 559
|
checkpoint-final/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad38eaeabb992906e2169cc6f14ef0a0fb33da0274fccf9bc55cc26cd8c9543
|
| 3 |
+
size 623
|
checkpoint-final/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-final/trainer_state.json
ADDED
|
@@ -0,0 +1,1064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.40570268034935,
|
| 3 |
+
"best_model_checkpoint": "./Models/DR-BERT/Checkpoints/checkpoint-3138",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 15690,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 3.98e-07,
|
| 13 |
+
"loss": 0.6674,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.25,
|
| 18 |
+
"learning_rate": 7.98e-07,
|
| 19 |
+
"loss": 0.6492,
|
| 20 |
+
"step": 400
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.38,
|
| 24 |
+
"learning_rate": 1.1979999999999998e-06,
|
| 25 |
+
"loss": 0.6435,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.51,
|
| 30 |
+
"learning_rate": 1.598e-06,
|
| 31 |
+
"loss": 0.5972,
|
| 32 |
+
"step": 800
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.64,
|
| 36 |
+
"learning_rate": 1.9979999999999998e-06,
|
| 37 |
+
"loss": 0.5761,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.76,
|
| 42 |
+
"learning_rate": 1.9991036210569223e-06,
|
| 43 |
+
"loss": 0.5303,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.89,
|
| 48 |
+
"learning_rate": 1.9963798206157456e-06,
|
| 49 |
+
"loss": 0.5456,
|
| 50 |
+
"step": 1400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0,
|
| 54 |
+
"eval_f1_linear15": 0.005990586221651691,
|
| 55 |
+
"eval_f1_linear5": 0.006721662083715246,
|
| 56 |
+
"eval_f1_linear9": 0.006478029701155044,
|
| 57 |
+
"eval_f1_normal": 0.009390243902439022,
|
| 58 |
+
"eval_f1_quad15": 0.007208748243631254,
|
| 59 |
+
"eval_f1_quad5": 0.007452202064626474,
|
| 60 |
+
"eval_f1_quad9": 0.007208748243631254,
|
| 61 |
+
"eval_f1_wa15": 0.005624847150892638,
|
| 62 |
+
"eval_f1_wa5": 0.0065998533365925205,
|
| 63 |
+
"eval_f1_wa9": 0.0065998533365925205,
|
| 64 |
+
"eval_loss": 0.4222191870212555,
|
| 65 |
+
"eval_mcc_linear15": 0.04937085998052145,
|
| 66 |
+
"eval_mcc_linear5": 0.05230812031713164,
|
| 67 |
+
"eval_mcc_linear9": 0.05134766095355671,
|
| 68 |
+
"eval_mcc_normal": 0.05500445900521522,
|
| 69 |
+
"eval_mcc_quad15": 0.05417811038948495,
|
| 70 |
+
"eval_mcc_quad5": 0.055089369887232044,
|
| 71 |
+
"eval_mcc_quad9": 0.05417811038948495,
|
| 72 |
+
"eval_mcc_wa15": 0.04783480521431672,
|
| 73 |
+
"eval_mcc_wa5": 0.051830109884810176,
|
| 74 |
+
"eval_mcc_wa9": 0.051830109884810176,
|
| 75 |
+
"eval_precision_linear15": 1.0,
|
| 76 |
+
"eval_precision_linear5": 1.0,
|
| 77 |
+
"eval_precision_linear9": 1.0,
|
| 78 |
+
"eval_precision_normal": 0.8555555555555555,
|
| 79 |
+
"eval_precision_quad15": 1.0,
|
| 80 |
+
"eval_precision_quad5": 1.0,
|
| 81 |
+
"eval_precision_quad9": 1.0,
|
| 82 |
+
"eval_precision_wa15": 1.0,
|
| 83 |
+
"eval_precision_wa5": 1.0,
|
| 84 |
+
"eval_precision_wa9": 1.0,
|
| 85 |
+
"eval_recall_linear15": 0.0030042918454935624,
|
| 86 |
+
"eval_recall_linear5": 0.003372164316370325,
|
| 87 |
+
"eval_recall_linear9": 0.003249540159411404,
|
| 88 |
+
"eval_recall_normal": 0.004721030042918455,
|
| 89 |
+
"eval_recall_quad15": 0.0036174126302881667,
|
| 90 |
+
"eval_recall_quad5": 0.003740036787247088,
|
| 91 |
+
"eval_recall_quad9": 0.0036174126302881667,
|
| 92 |
+
"eval_recall_wa15": 0.002820355610055181,
|
| 93 |
+
"eval_recall_wa5": 0.0033108522378908645,
|
| 94 |
+
"eval_recall_wa9": 0.0033108522378908645,
|
| 95 |
+
"eval_roc_auc_linear15": 0.7828390738207666,
|
| 96 |
+
"eval_roc_auc_linear5": 0.7817337422862762,
|
| 97 |
+
"eval_roc_auc_linear9": 0.7824228267267073,
|
| 98 |
+
"eval_roc_auc_normal": 0.7761193470014632,
|
| 99 |
+
"eval_roc_auc_quad15": 0.7811796591901377,
|
| 100 |
+
"eval_roc_auc_quad5": 0.7808935503319838,
|
| 101 |
+
"eval_roc_auc_quad9": 0.7811467186780047,
|
| 102 |
+
"eval_roc_auc_wa15": 0.7828482196034376,
|
| 103 |
+
"eval_roc_auc_wa5": 0.7818750385348623,
|
| 104 |
+
"eval_roc_auc_wa9": 0.7822835010606688,
|
| 105 |
+
"eval_runtime": 4.5482,
|
| 106 |
+
"eval_samples_per_second": 38.697,
|
| 107 |
+
"eval_steps_per_second": 2.419,
|
| 108 |
+
"step": 1569
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.02,
|
| 112 |
+
"learning_rate": 1.991833489451512e-06,
|
| 113 |
+
"loss": 0.5433,
|
| 114 |
+
"step": 1600
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.15,
|
| 118 |
+
"learning_rate": 1.985472943497617e-06,
|
| 119 |
+
"loss": 0.5016,
|
| 120 |
+
"step": 1800
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.27,
|
| 124 |
+
"learning_rate": 1.9773098171631238e-06,
|
| 125 |
+
"loss": 0.4998,
|
| 126 |
+
"step": 2000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.4,
|
| 130 |
+
"learning_rate": 1.9673590420516574e-06,
|
| 131 |
+
"loss": 0.4768,
|
| 132 |
+
"step": 2200
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.53,
|
| 136 |
+
"learning_rate": 1.9556388196492205e-06,
|
| 137 |
+
"loss": 0.4585,
|
| 138 |
+
"step": 2400
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.66,
|
| 142 |
+
"learning_rate": 1.942170588030901e-06,
|
| 143 |
+
"loss": 0.4774,
|
| 144 |
+
"step": 2600
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.78,
|
| 148 |
+
"learning_rate": 1.9269789826473578e-06,
|
| 149 |
+
"loss": 0.4285,
|
| 150 |
+
"step": 2800
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.91,
|
| 154 |
+
"learning_rate": 1.9100917912628272e-06,
|
| 155 |
+
"loss": 0.4874,
|
| 156 |
+
"step": 3000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.0,
|
| 160 |
+
"eval_f1_linear15": 0.37791771620486986,
|
| 161 |
+
"eval_f1_linear5": 0.38442721505866745,
|
| 162 |
+
"eval_f1_linear9": 0.3829627779165626,
|
| 163 |
+
"eval_f1_normal": 0.3845709570957096,
|
| 164 |
+
"eval_f1_quad15": 0.38500103584006623,
|
| 165 |
+
"eval_f1_quad5": 0.3853127457879703,
|
| 166 |
+
"eval_f1_quad9": 0.38540545017808336,
|
| 167 |
+
"eval_f1_wa15": 0.37510555649383553,
|
| 168 |
+
"eval_f1_wa5": 0.3827878385113806,
|
| 169 |
+
"eval_f1_wa9": 0.3822255538897218,
|
| 170 |
+
"eval_loss": 0.40570268034935,
|
| 171 |
+
"eval_mcc_linear15": 0.32352213102384086,
|
| 172 |
+
"eval_mcc_linear5": 0.3259670063637068,
|
| 173 |
+
"eval_mcc_linear9": 0.3260269656649997,
|
| 174 |
+
"eval_mcc_normal": 0.32393715908077586,
|
| 175 |
+
"eval_mcc_quad15": 0.3263857337114928,
|
| 176 |
+
"eval_mcc_quad5": 0.32636888989630636,
|
| 177 |
+
"eval_mcc_quad9": 0.32668627904470604,
|
| 178 |
+
"eval_mcc_wa15": 0.3226863764219731,
|
| 179 |
+
"eval_mcc_wa5": 0.32472352218263323,
|
| 180 |
+
"eval_mcc_wa9": 0.32522102251148893,
|
| 181 |
+
"eval_precision_linear15": 0.5993342210386152,
|
| 182 |
+
"eval_precision_linear5": 0.5936739659367397,
|
| 183 |
+
"eval_precision_linear9": 0.59665282823041,
|
| 184 |
+
"eval_precision_normal": 0.5877679697351829,
|
| 185 |
+
"eval_precision_quad15": 0.5937380191693291,
|
| 186 |
+
"eval_precision_quad5": 0.5930929017458901,
|
| 187 |
+
"eval_precision_quad9": 0.5937978560490046,
|
| 188 |
+
"eval_precision_wa15": 0.6023867643070246,
|
| 189 |
+
"eval_precision_wa5": 0.5933556528457379,
|
| 190 |
+
"eval_precision_wa9": 0.5958192677226695,
|
| 191 |
+
"eval_recall_linear15": 0.2759656652360515,
|
| 192 |
+
"eval_recall_linear5": 0.28424279583077866,
|
| 193 |
+
"eval_recall_linear9": 0.28197424892703865,
|
| 194 |
+
"eval_recall_normal": 0.2857755977927652,
|
| 195 |
+
"eval_recall_quad15": 0.28485591661557325,
|
| 196 |
+
"eval_recall_quad5": 0.2853464132434089,
|
| 197 |
+
"eval_recall_quad9": 0.2852851011649295,
|
| 198 |
+
"eval_recall_wa15": 0.27234825260576334,
|
| 199 |
+
"eval_recall_wa5": 0.28252605763335376,
|
| 200 |
+
"eval_recall_wa9": 0.281361128142244,
|
| 201 |
+
"eval_roc_auc_linear15": 0.80760860991749,
|
| 202 |
+
"eval_roc_auc_linear5": 0.8066333683955279,
|
| 203 |
+
"eval_roc_auc_linear9": 0.8070591391681773,
|
| 204 |
+
"eval_roc_auc_normal": 0.8044993476166182,
|
| 205 |
+
"eval_roc_auc_quad15": 0.8065383376549664,
|
| 206 |
+
"eval_roc_auc_quad5": 0.8063609260424545,
|
| 207 |
+
"eval_roc_auc_quad9": 0.8065057079644187,
|
| 208 |
+
"eval_roc_auc_wa15": 0.8078116759282439,
|
| 209 |
+
"eval_roc_auc_wa5": 0.8066756892313025,
|
| 210 |
+
"eval_roc_auc_wa9": 0.8069572826277791,
|
| 211 |
+
"eval_runtime": 4.5294,
|
| 212 |
+
"eval_samples_per_second": 38.858,
|
| 213 |
+
"eval_steps_per_second": 2.429,
|
| 214 |
+
"step": 3138
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.04,
|
| 218 |
+
"learning_rate": 1.8915399031270588e-06,
|
| 219 |
+
"loss": 0.4368,
|
| 220 |
+
"step": 3200
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.17,
|
| 224 |
+
"learning_rate": 1.8714621624046863e-06,
|
| 225 |
+
"loss": 0.4307,
|
| 226 |
+
"step": 3400
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.29,
|
| 230 |
+
"learning_rate": 1.8496935389256953e-06,
|
| 231 |
+
"loss": 0.4567,
|
| 232 |
+
"step": 3600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.42,
|
| 236 |
+
"learning_rate": 1.8263706963147695e-06,
|
| 237 |
+
"loss": 0.5066,
|
| 238 |
+
"step": 3800
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 2.55,
|
| 242 |
+
"learning_rate": 1.8015362956097257e-06,
|
| 243 |
+
"loss": 0.4802,
|
| 244 |
+
"step": 4000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.68,
|
| 248 |
+
"learning_rate": 1.7752357627187745e-06,
|
| 249 |
+
"loss": 0.42,
|
| 250 |
+
"step": 4200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.8,
|
| 254 |
+
"learning_rate": 1.7475172053296007e-06,
|
| 255 |
+
"loss": 0.4512,
|
| 256 |
+
"step": 4400
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.93,
|
| 260 |
+
"learning_rate": 1.7184313249130651e-06,
|
| 261 |
+
"loss": 0.4531,
|
| 262 |
+
"step": 4600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.0,
|
| 266 |
+
"eval_f1_linear15": 0.34841370836807234,
|
| 267 |
+
"eval_f1_linear5": 0.3547517607164595,
|
| 268 |
+
"eval_f1_linear9": 0.3510824022346369,
|
| 269 |
+
"eval_f1_normal": 0.3587308439456076,
|
| 270 |
+
"eval_f1_quad15": 0.35594323655773985,
|
| 271 |
+
"eval_f1_quad5": 0.35640903376826044,
|
| 272 |
+
"eval_f1_quad9": 0.35596823881633183,
|
| 273 |
+
"eval_f1_wa15": 0.3455930934237766,
|
| 274 |
+
"eval_f1_wa5": 0.3533507397737163,
|
| 275 |
+
"eval_f1_wa9": 0.35104107555982367,
|
| 276 |
+
"eval_loss": 0.4291151762008667,
|
| 277 |
+
"eval_mcc_linear15": 0.30831019365277706,
|
| 278 |
+
"eval_mcc_linear5": 0.31148575582692534,
|
| 279 |
+
"eval_mcc_linear9": 0.3088608120801079,
|
| 280 |
+
"eval_mcc_normal": 0.31291133063580245,
|
| 281 |
+
"eval_mcc_quad15": 0.3120778983731185,
|
| 282 |
+
"eval_mcc_quad5": 0.31208800255038166,
|
| 283 |
+
"eval_mcc_quad9": 0.3120199533246282,
|
| 284 |
+
"eval_mcc_wa15": 0.3067360087708763,
|
| 285 |
+
"eval_mcc_wa5": 0.31020020539805726,
|
| 286 |
+
"eval_mcc_wa9": 0.30887700266015655,
|
| 287 |
+
"eval_precision_linear15": 0.6127488810001543,
|
| 288 |
+
"eval_precision_linear5": 0.6096832038254633,
|
| 289 |
+
"eval_precision_linear9": 0.6092093305059073,
|
| 290 |
+
"eval_precision_normal": 0.6061269146608315,
|
| 291 |
+
"eval_precision_quad15": 0.6090895588890539,
|
| 292 |
+
"eval_precision_quad5": 0.6082260689451102,
|
| 293 |
+
"eval_precision_quad9": 0.6088763544604423,
|
| 294 |
+
"eval_precision_wa15": 0.6136399186610355,
|
| 295 |
+
"eval_precision_wa5": 0.6086956521739131,
|
| 296 |
+
"eval_precision_wa9": 0.6093347476890438,
|
| 297 |
+
"eval_recall_linear15": 0.24340895156345801,
|
| 298 |
+
"eval_recall_linear5": 0.25015328019619865,
|
| 299 |
+
"eval_recall_linear9": 0.24659717964438996,
|
| 300 |
+
"eval_recall_normal": 0.2547516860821582,
|
| 301 |
+
"eval_recall_quad15": 0.2514408338442673,
|
| 302 |
+
"eval_recall_quad5": 0.25205395462906194,
|
| 303 |
+
"eval_recall_quad9": 0.2515021459227468,
|
| 304 |
+
"eval_recall_wa15": 0.24052728387492336,
|
| 305 |
+
"eval_recall_wa5": 0.24892703862660945,
|
| 306 |
+
"eval_recall_wa9": 0.24653586756591048,
|
| 307 |
+
"eval_roc_auc_linear15": 0.8057246641741552,
|
| 308 |
+
"eval_roc_auc_linear5": 0.804972653925688,
|
| 309 |
+
"eval_roc_auc_linear9": 0.8053168697613192,
|
| 310 |
+
"eval_roc_auc_normal": 0.8032137877859972,
|
| 311 |
+
"eval_roc_auc_quad15": 0.8048948972372107,
|
| 312 |
+
"eval_roc_auc_quad5": 0.8047431290630825,
|
| 313 |
+
"eval_roc_auc_quad9": 0.8048645033577849,
|
| 314 |
+
"eval_roc_auc_wa15": 0.8057682830955635,
|
| 315 |
+
"eval_roc_auc_wa5": 0.80499531365221,
|
| 316 |
+
"eval_roc_auc_wa9": 0.8052219718542419,
|
| 317 |
+
"eval_runtime": 4.5299,
|
| 318 |
+
"eval_samples_per_second": 38.853,
|
| 319 |
+
"eval_steps_per_second": 2.428,
|
| 320 |
+
"step": 4707
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.06,
|
| 324 |
+
"learning_rate": 1.688031323982476e-06,
|
| 325 |
+
"loss": 0.4438,
|
| 326 |
+
"step": 4800
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.19,
|
| 330 |
+
"learning_rate": 1.6563728087780745e-06,
|
| 331 |
+
"loss": 0.4308,
|
| 332 |
+
"step": 5000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.31,
|
| 336 |
+
"learning_rate": 1.6235136875547371e-06,
|
| 337 |
+
"loss": 0.4464,
|
| 338 |
+
"step": 5200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.44,
|
| 342 |
+
"learning_rate": 1.589514064658943e-06,
|
| 343 |
+
"loss": 0.3878,
|
| 344 |
+
"step": 5400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.57,
|
| 348 |
+
"learning_rate": 1.5544361305887502e-06,
|
| 349 |
+
"loss": 0.4441,
|
| 350 |
+
"step": 5600
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.7,
|
| 354 |
+
"learning_rate": 1.518344048237889e-06,
|
| 355 |
+
"loss": 0.4944,
|
| 356 |
+
"step": 5800
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.82,
|
| 360 |
+
"learning_rate": 1.4813038355320353e-06,
|
| 361 |
+
"loss": 0.4436,
|
| 362 |
+
"step": 6000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.95,
|
| 366 |
+
"learning_rate": 1.4435749234661885e-06,
|
| 367 |
+
"loss": 0.4204,
|
| 368 |
+
"step": 6200
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.0,
|
| 372 |
+
"eval_f1_linear15": 0.3765419279810608,
|
| 373 |
+
"eval_f1_linear5": 0.3818316709257275,
|
| 374 |
+
"eval_f1_linear9": 0.3801967104719398,
|
| 375 |
+
"eval_f1_normal": 0.3839088001312228,
|
| 376 |
+
"eval_f1_quad15": 0.3820224719101124,
|
| 377 |
+
"eval_f1_quad5": 0.3825500596192591,
|
| 378 |
+
"eval_f1_quad9": 0.38237109583967743,
|
| 379 |
+
"eval_f1_wa15": 0.37365389431505136,
|
| 380 |
+
"eval_f1_wa5": 0.38045720888008583,
|
| 381 |
+
"eval_f1_wa9": 0.3804487047060282,
|
| 382 |
+
"eval_loss": 0.4163249731063843,
|
| 383 |
+
"eval_mcc_linear15": 0.3169275459294067,
|
| 384 |
+
"eval_mcc_linear5": 0.3201403593601739,
|
| 385 |
+
"eval_mcc_linear9": 0.31926152703169053,
|
| 386 |
+
"eval_mcc_normal": 0.320521627049545,
|
| 387 |
+
"eval_mcc_quad15": 0.3197527279872267,
|
| 388 |
+
"eval_mcc_quad5": 0.3199814229619526,
|
| 389 |
+
"eval_mcc_quad9": 0.3201142065250296,
|
| 390 |
+
"eval_mcc_wa15": 0.315548999257092,
|
| 391 |
+
"eval_mcc_wa5": 0.31893581979756935,
|
| 392 |
+
"eval_mcc_wa9": 0.31948421963517976,
|
| 393 |
+
"eval_precision_linear15": 0.5836230204712244,
|
| 394 |
+
"eval_precision_linear5": 0.5824949698189135,
|
| 395 |
+
"eval_precision_linear9": 0.5831643002028397,
|
| 396 |
+
"eval_precision_normal": 0.5796186230807331,
|
| 397 |
+
"eval_precision_quad15": 0.5810692375109553,
|
| 398 |
+
"eval_precision_quad5": 0.5807015353888404,
|
| 399 |
+
"eval_precision_quad9": 0.5814040795895382,
|
| 400 |
+
"eval_precision_wa15": 0.5852510460251046,
|
| 401 |
+
"eval_precision_wa5": 0.5817768803634528,
|
| 402 |
+
"eval_precision_wa9": 0.583301659698467,
|
| 403 |
+
"eval_recall_linear15": 0.27792765174739426,
|
| 404 |
+
"eval_recall_linear5": 0.28399754751686085,
|
| 405 |
+
"eval_recall_linear9": 0.2820355610055181,
|
| 406 |
+
"eval_recall_normal": 0.2870018393623544,
|
| 407 |
+
"eval_recall_quad15": 0.28454935622317595,
|
| 408 |
+
"eval_recall_quad5": 0.28522378908645,
|
| 409 |
+
"eval_recall_quad9": 0.28485591661557325,
|
| 410 |
+
"eval_recall_wa15": 0.27443286327406496,
|
| 411 |
+
"eval_recall_wa5": 0.2826486817903127,
|
| 412 |
+
"eval_recall_wa9": 0.28228080931943594,
|
| 413 |
+
"eval_roc_auc_linear15": 0.8063752996776014,
|
| 414 |
+
"eval_roc_auc_linear5": 0.8056729910719764,
|
| 415 |
+
"eval_roc_auc_linear9": 0.8059640862273263,
|
| 416 |
+
"eval_roc_auc_normal": 0.8042229154366783,
|
| 417 |
+
"eval_roc_auc_quad15": 0.8056316233054919,
|
| 418 |
+
"eval_roc_auc_quad5": 0.8055016275477461,
|
| 419 |
+
"eval_roc_auc_quad9": 0.80560361604484,
|
| 420 |
+
"eval_roc_auc_wa15": 0.8064620395044502,
|
| 421 |
+
"eval_roc_auc_wa5": 0.8056776498886022,
|
| 422 |
+
"eval_roc_auc_wa9": 0.8058749878389411,
|
| 423 |
+
"eval_runtime": 4.5449,
|
| 424 |
+
"eval_samples_per_second": 38.725,
|
| 425 |
+
"eval_steps_per_second": 2.42,
|
| 426 |
+
"step": 6276
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 4.08,
|
| 430 |
+
"learning_rate": 1.4048471970299596e-06,
|
| 431 |
+
"loss": 0.4483,
|
| 432 |
+
"step": 6400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 4.21,
|
| 436 |
+
"learning_rate": 1.3653789432973484e-06,
|
| 437 |
+
"loss": 0.4249,
|
| 438 |
+
"step": 6600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 4.33,
|
| 442 |
+
"learning_rate": 1.3252423557266372e-06,
|
| 443 |
+
"loss": 0.498,
|
| 444 |
+
"step": 6800
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 4.46,
|
| 448 |
+
"learning_rate": 1.2845108502606751e-06,
|
| 449 |
+
"loss": 0.4261,
|
| 450 |
+
"step": 7000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 4.59,
|
| 454 |
+
"learning_rate": 1.2432589310379164e-06,
|
| 455 |
+
"loss": 0.4872,
|
| 456 |
+
"step": 7200
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 4.72,
|
| 460 |
+
"learning_rate": 1.201562054112983e-06,
|
| 461 |
+
"loss": 0.4162,
|
| 462 |
+
"step": 7400
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.84,
|
| 466 |
+
"learning_rate": 1.1594964894360269e-06,
|
| 467 |
+
"loss": 0.3986,
|
| 468 |
+
"step": 7600
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 4.97,
|
| 472 |
+
"learning_rate": 1.117139181343355e-06,
|
| 473 |
+
"loss": 0.4683,
|
| 474 |
+
"step": 7800
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.0,
|
| 478 |
+
"eval_f1_linear15": 0.40388198757763977,
|
| 479 |
+
"eval_f1_linear5": 0.4084696823869105,
|
| 480 |
+
"eval_f1_linear9": 0.40613648659092666,
|
| 481 |
+
"eval_f1_normal": 0.41057518897970147,
|
| 482 |
+
"eval_f1_quad15": 0.40876024787344595,
|
| 483 |
+
"eval_f1_quad5": 0.4094439744674306,
|
| 484 |
+
"eval_f1_quad9": 0.409034939202709,
|
| 485 |
+
"eval_f1_wa15": 0.39979717606677584,
|
| 486 |
+
"eval_f1_wa5": 0.407537281800316,
|
| 487 |
+
"eval_f1_wa9": 0.4062149731380204,
|
| 488 |
+
"eval_loss": 0.4134209454059601,
|
| 489 |
+
"eval_mcc_linear15": 0.3236991339184922,
|
| 490 |
+
"eval_mcc_linear5": 0.3263789088111363,
|
| 491 |
+
"eval_mcc_linear9": 0.32483715554559417,
|
| 492 |
+
"eval_mcc_normal": 0.3278059014869018,
|
| 493 |
+
"eval_mcc_quad15": 0.3266531471076965,
|
| 494 |
+
"eval_mcc_quad5": 0.3271541181453389,
|
| 495 |
+
"eval_mcc_quad9": 0.3268947787727873,
|
| 496 |
+
"eval_mcc_wa15": 0.3204093885663472,
|
| 497 |
+
"eval_mcc_wa5": 0.32556276853276983,
|
| 498 |
+
"eval_mcc_wa9": 0.32500064634052006,
|
| 499 |
+
"eval_precision_linear15": 0.5504761904761905,
|
| 500 |
+
"eval_precision_linear5": 0.5488877392653906,
|
| 501 |
+
"eval_precision_linear9": 0.5492265886287625,
|
| 502 |
+
"eval_precision_normal": 0.5486616757255666,
|
| 503 |
+
"eval_precision_quad15": 0.5490642125943542,
|
| 504 |
+
"eval_precision_quad5": 0.5490924092409241,
|
| 505 |
+
"eval_precision_quad9": 0.549183715643728,
|
| 506 |
+
"eval_precision_wa15": 0.5494210977701544,
|
| 507 |
+
"eval_precision_wa5": 0.5484908204543097,
|
| 508 |
+
"eval_precision_wa9": 0.5495137509149849,
|
| 509 |
+
"eval_recall_linear15": 0.31894543225015326,
|
| 510 |
+
"eval_recall_linear5": 0.3252605763335377,
|
| 511 |
+
"eval_recall_linear9": 0.3221949724095647,
|
| 512 |
+
"eval_recall_normal": 0.3280196198651134,
|
| 513 |
+
"eval_recall_quad15": 0.325567136725935,
|
| 514 |
+
"eval_recall_quad5": 0.32642550582464747,
|
| 515 |
+
"eval_recall_quad9": 0.3258736971183323,
|
| 516 |
+
"eval_recall_wa15": 0.3142244022072348,
|
| 517 |
+
"eval_recall_wa5": 0.3242182709993869,
|
| 518 |
+
"eval_recall_wa9": 0.3221949724095647,
|
| 519 |
+
"eval_roc_auc_linear15": 0.8068749907498796,
|
| 520 |
+
"eval_roc_auc_linear5": 0.8061695862034426,
|
| 521 |
+
"eval_roc_auc_linear9": 0.8064517223321093,
|
| 522 |
+
"eval_roc_auc_normal": 0.8048219216773794,
|
| 523 |
+
"eval_roc_auc_quad15": 0.8061379920003204,
|
| 524 |
+
"eval_roc_auc_quad5": 0.806012611658161,
|
| 525 |
+
"eval_roc_auc_quad9": 0.8061105090592962,
|
| 526 |
+
"eval_roc_auc_wa15": 0.8069751029192083,
|
| 527 |
+
"eval_roc_auc_wa5": 0.8061660720344324,
|
| 528 |
+
"eval_roc_auc_wa9": 0.8063637348349755,
|
| 529 |
+
"eval_runtime": 4.5198,
|
| 530 |
+
"eval_samples_per_second": 38.94,
|
| 531 |
+
"eval_steps_per_second": 2.434,
|
| 532 |
+
"step": 7845
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 5.1,
|
| 536 |
+
"learning_rate": 1.0745676078144965e-06,
|
| 537 |
+
"loss": 0.4378,
|
| 538 |
+
"step": 8000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 5.23,
|
| 542 |
+
"learning_rate": 1.0320733887263715e-06,
|
| 543 |
+
"loss": 0.4127,
|
| 544 |
+
"step": 8200
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 5.35,
|
| 548 |
+
"learning_rate": 9.893072403474226e-07,
|
| 549 |
+
"loss": 0.4306,
|
| 550 |
+
"step": 8400
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 5.48,
|
| 554 |
+
"learning_rate": 9.465606506574173e-07,
|
| 555 |
+
"loss": 0.394,
|
| 556 |
+
"step": 8600
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 5.61,
|
| 560 |
+
"learning_rate": 9.039118096913243e-07,
|
| 561 |
+
"loss": 0.4483,
|
| 562 |
+
"step": 8800
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 5.74,
|
| 566 |
+
"learning_rate": 8.614387286867812e-07,
|
| 567 |
+
"loss": 0.4357,
|
| 568 |
+
"step": 9000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 5.86,
|
| 572 |
+
"learning_rate": 8.192190973896378e-07,
|
| 573 |
+
"loss": 0.4501,
|
| 574 |
+
"step": 9200
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 5.99,
|
| 578 |
+
"learning_rate": 7.773301419475566e-07,
|
| 579 |
+
"loss": 0.4657,
|
| 580 |
+
"step": 9400
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 6.0,
|
| 584 |
+
"eval_f1_linear15": 0.3973536013862088,
|
| 585 |
+
"eval_f1_linear5": 0.40126666406036204,
|
| 586 |
+
"eval_f1_linear9": 0.3992471473944242,
|
| 587 |
+
"eval_f1_normal": 0.402918682690807,
|
| 588 |
+
"eval_f1_quad15": 0.4013610763454318,
|
| 589 |
+
"eval_f1_quad5": 0.4018286250146524,
|
| 590 |
+
"eval_f1_quad9": 0.4014544317159949,
|
| 591 |
+
"eval_f1_wa15": 0.39333623521032013,
|
| 592 |
+
"eval_f1_wa5": 0.3997494224971614,
|
| 593 |
+
"eval_f1_wa9": 0.39879201474683296,
|
| 594 |
+
"eval_loss": 0.42429545521736145,
|
| 595 |
+
"eval_mcc_linear15": 0.32093875107555864,
|
| 596 |
+
"eval_mcc_linear5": 0.3230403167015584,
|
| 597 |
+
"eval_mcc_linear9": 0.32165806078964254,
|
| 598 |
+
"eval_mcc_normal": 0.3243653321968564,
|
| 599 |
+
"eval_mcc_quad15": 0.32331242096001933,
|
| 600 |
+
"eval_mcc_quad5": 0.32352841939102917,
|
| 601 |
+
"eval_mcc_quad9": 0.3232983667210768,
|
| 602 |
+
"eval_mcc_wa15": 0.3178220794858389,
|
| 603 |
+
"eval_mcc_wa5": 0.3217270404691512,
|
| 604 |
+
"eval_mcc_wa9": 0.3211876210332284,
|
| 605 |
+
"eval_precision_linear15": 0.5554332269074095,
|
| 606 |
+
"eval_precision_linear5": 0.5536735354407164,
|
| 607 |
+
"eval_precision_linear9": 0.5537909278799086,
|
| 608 |
+
"eval_precision_normal": 0.5540888602704443,
|
| 609 |
+
"eval_precision_quad15": 0.5542233743789156,
|
| 610 |
+
"eval_precision_quad5": 0.5539157599913821,
|
| 611 |
+
"eval_precision_quad9": 0.5540088486025683,
|
| 612 |
+
"eval_precision_wa15": 0.5546255998214485,
|
| 613 |
+
"eval_precision_wa5": 0.5530278409706424,
|
| 614 |
+
"eval_precision_wa9": 0.5533906607162294,
|
| 615 |
+
"eval_recall_linear15": 0.309319435928878,
|
| 616 |
+
"eval_recall_linear5": 0.31465358675659105,
|
| 617 |
+
"eval_recall_linear9": 0.3121397915389332,
|
| 618 |
+
"eval_recall_normal": 0.31655426118945434,
|
| 619 |
+
"eval_recall_quad15": 0.31459227467811157,
|
| 620 |
+
"eval_recall_quad5": 0.31526670754138564,
|
| 621 |
+
"eval_recall_quad9": 0.31477621091354996,
|
| 622 |
+
"eval_recall_wa15": 0.30472103004291845,
|
| 623 |
+
"eval_recall_wa5": 0.31299816063764563,
|
| 624 |
+
"eval_recall_wa9": 0.3117106069895769,
|
| 625 |
+
"eval_roc_auc_linear15": 0.8059102996260461,
|
| 626 |
+
"eval_roc_auc_linear5": 0.8053483898757984,
|
| 627 |
+
"eval_roc_auc_linear9": 0.8055808883671958,
|
| 628 |
+
"eval_roc_auc_normal": 0.8040759603939825,
|
| 629 |
+
"eval_roc_auc_quad15": 0.805317539627867,
|
| 630 |
+
"eval_roc_auc_quad5": 0.8052055044477385,
|
| 631 |
+
"eval_roc_auc_quad9": 0.8052911294377869,
|
| 632 |
+
"eval_roc_auc_wa15": 0.8059048122441224,
|
| 633 |
+
"eval_roc_auc_wa5": 0.8053332810533473,
|
| 634 |
+
"eval_roc_auc_wa9": 0.8054955571013535,
|
| 635 |
+
"eval_runtime": 4.5046,
|
| 636 |
+
"eval_samples_per_second": 39.071,
|
| 637 |
+
"eval_steps_per_second": 2.442,
|
| 638 |
+
"step": 9414
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 6.12,
|
| 642 |
+
"learning_rate": 7.358484836516071e-07,
|
| 643 |
+
"loss": 0.3882,
|
| 644 |
+
"step": 9600
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 6.25,
|
| 648 |
+
"learning_rate": 6.948499987842294e-07,
|
| 649 |
+
"loss": 0.4381,
|
| 650 |
+
"step": 9800
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 6.37,
|
| 654 |
+
"learning_rate": 6.544096798299399e-07,
|
| 655 |
+
"loss": 0.4504,
|
| 656 |
+
"step": 10000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 6.5,
|
| 660 |
+
"learning_rate": 6.147988458044519e-07,
|
| 661 |
+
"loss": 0.3965,
|
| 662 |
+
"step": 10200
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.63,
|
| 666 |
+
"learning_rate": 5.756919131292126e-07,
|
| 667 |
+
"loss": 0.4618,
|
| 668 |
+
"step": 10400
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 6.76,
|
| 672 |
+
"learning_rate": 5.37361104687286e-07,
|
| 673 |
+
"loss": 0.4533,
|
| 674 |
+
"step": 10600
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.88,
|
| 678 |
+
"learning_rate": 4.998765333759618e-07,
|
| 679 |
+
"loss": 0.4408,
|
| 680 |
+
"step": 10800
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 7.0,
|
| 684 |
+
"eval_f1_linear15": 0.4065172800804985,
|
| 685 |
+
"eval_f1_linear5": 0.41061484696032874,
|
| 686 |
+
"eval_f1_linear9": 0.40916618524937415,
|
| 687 |
+
"eval_f1_normal": 0.4113464332135484,
|
| 688 |
+
"eval_f1_quad15": 0.41099988493844203,
|
| 689 |
+
"eval_f1_quad5": 0.4116632821180888,
|
| 690 |
+
"eval_f1_quad9": 0.4110608268773491,
|
| 691 |
+
"eval_f1_wa15": 0.40360696517412936,
|
| 692 |
+
"eval_f1_wa5": 0.41027020794096164,
|
| 693 |
+
"eval_f1_wa9": 0.4088546679499519,
|
| 694 |
+
"eval_loss": 0.42155590653419495,
|
| 695 |
+
"eval_mcc_linear15": 0.325831772262827,
|
| 696 |
+
"eval_mcc_linear5": 0.32814418737854223,
|
| 697 |
+
"eval_mcc_linear9": 0.3273615296249899,
|
| 698 |
+
"eval_mcc_normal": 0.32747959405776367,
|
| 699 |
+
"eval_mcc_quad15": 0.3281656144755262,
|
| 700 |
+
"eval_mcc_quad5": 0.3286330614304788,
|
| 701 |
+
"eval_mcc_quad9": 0.3282267299759905,
|
| 702 |
+
"eval_mcc_wa15": 0.3238062527211354,
|
| 703 |
+
"eval_mcc_wa5": 0.3280152340529937,
|
| 704 |
+
"eval_mcc_wa9": 0.32684823780633904,
|
| 705 |
+
"eval_precision_linear15": 0.5511596180081856,
|
| 706 |
+
"eval_precision_linear5": 0.5494912118408881,
|
| 707 |
+
"eval_precision_linear9": 0.5501812532366649,
|
| 708 |
+
"eval_precision_normal": 0.5463038180341186,
|
| 709 |
+
"eval_precision_quad15": 0.5488067192461333,
|
| 710 |
+
"eval_precision_quad5": 0.5487792420063337,
|
| 711 |
+
"eval_precision_quad9": 0.5488529291274068,
|
| 712 |
+
"eval_precision_wa15": 0.5512847738373328,
|
| 713 |
+
"eval_precision_wa5": 0.5498094158854435,
|
| 714 |
+
"eval_precision_wa9": 0.5494050698396276,
|
| 715 |
+
"eval_recall_linear15": 0.3220110361741263,
|
| 716 |
+
"eval_recall_linear5": 0.3277743715511956,
|
| 717 |
+
"eval_recall_linear9": 0.3256897608828939,
|
| 718 |
+
"eval_recall_normal": 0.3298589822194972,
|
| 719 |
+
"eval_recall_quad15": 0.3285101164929491,
|
| 720 |
+
"eval_recall_quad5": 0.32936848559166154,
|
| 721 |
+
"eval_recall_quad9": 0.32857142857142857,
|
| 722 |
+
"eval_recall_wa15": 0.3183323114653587,
|
| 723 |
+
"eval_recall_wa5": 0.32722256284488044,
|
| 724 |
+
"eval_recall_wa9": 0.325567136725935,
|
| 725 |
+
"eval_roc_auc_linear15": 0.8053933726419908,
|
| 726 |
+
"eval_roc_auc_linear5": 0.8048350296680737,
|
| 727 |
+
"eval_roc_auc_linear9": 0.8050637395556057,
|
| 728 |
+
"eval_roc_auc_normal": 0.8035813884523846,
|
| 729 |
+
"eval_roc_auc_quad15": 0.8048078422048333,
|
| 730 |
+
"eval_roc_auc_quad5": 0.8046954755985853,
|
| 731 |
+
"eval_roc_auc_quad9": 0.8047812167631334,
|
| 732 |
+
"eval_roc_auc_wa15": 0.8053874907051632,
|
| 733 |
+
"eval_roc_auc_wa5": 0.8048173663218174,
|
| 734 |
+
"eval_roc_auc_wa9": 0.8049744403826138,
|
| 735 |
+
"eval_runtime": 4.5698,
|
| 736 |
+
"eval_samples_per_second": 38.514,
|
| 737 |
+
"eval_steps_per_second": 2.407,
|
| 738 |
+
"step": 10983
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 7.01,
|
| 742 |
+
"learning_rate": 4.6330676419569717e-07,
|
| 743 |
+
"loss": 0.4273,
|
| 744 |
+
"step": 11000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 7.14,
|
| 748 |
+
"learning_rate": 4.2771868883426745e-07,
|
| 749 |
+
"loss": 0.444,
|
| 750 |
+
"step": 11200
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 7.27,
|
| 754 |
+
"learning_rate": 3.9317740331166237e-07,
|
| 755 |
+
"loss": 0.4245,
|
| 756 |
+
"step": 11400
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 7.39,
|
| 760 |
+
"learning_rate": 3.5974608890953463e-07,
|
| 761 |
+
"loss": 0.387,
|
| 762 |
+
"step": 11600
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 7.52,
|
| 766 |
+
"learning_rate": 3.274858966029933e-07,
|
| 767 |
+
"loss": 0.443,
|
| 768 |
+
"step": 11800
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 7.65,
|
| 772 |
+
"learning_rate": 2.964558352061408e-07,
|
| 773 |
+
"loss": 0.4681,
|
| 774 |
+
"step": 12000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 7.78,
|
| 778 |
+
"learning_rate": 2.66712663435949e-07,
|
| 779 |
+
"loss": 0.3884,
|
| 780 |
+
"step": 12200
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 7.9,
|
| 784 |
+
"learning_rate": 2.3831078609190304e-07,
|
| 785 |
+
"loss": 0.4251,
|
| 786 |
+
"step": 12400
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 8.0,
|
| 790 |
+
"eval_f1_linear15": 0.393263794888128,
|
| 791 |
+
"eval_f1_linear5": 0.39768859336657963,
|
| 792 |
+
"eval_f1_linear9": 0.3957944852211862,
|
| 793 |
+
"eval_f1_normal": 0.3991789041528502,
|
| 794 |
+
"eval_f1_quad15": 0.398401329587274,
|
| 795 |
+
"eval_f1_quad5": 0.3980071962358151,
|
| 796 |
+
"eval_f1_quad9": 0.3983540397246182,
|
| 797 |
+
"eval_f1_wa15": 0.3908229745393501,
|
| 798 |
+
"eval_f1_wa5": 0.396655571405928,
|
| 799 |
+
"eval_f1_wa9": 0.3957159857199525,
|
| 800 |
+
"eval_loss": 0.42632922530174255,
|
| 801 |
+
"eval_mcc_linear15": 0.320051928307795,
|
| 802 |
+
"eval_mcc_linear5": 0.3232336424996233,
|
| 803 |
+
"eval_mcc_linear9": 0.32183051483152925,
|
| 804 |
+
"eval_mcc_normal": 0.3240750595719067,
|
| 805 |
+
"eval_mcc_quad15": 0.32403252491820744,
|
| 806 |
+
"eval_mcc_quad5": 0.3232497851575241,
|
| 807 |
+
"eval_mcc_quad9": 0.32392953718336454,
|
| 808 |
+
"eval_mcc_wa15": 0.3185867330709127,
|
| 809 |
+
"eval_mcc_wa5": 0.3224181640331171,
|
| 810 |
+
"eval_mcc_wa9": 0.32165845987632,
|
| 811 |
+
"eval_precision_linear15": 0.5607402361489555,
|
| 812 |
+
"eval_precision_linear5": 0.5609647163912461,
|
| 813 |
+
"eval_precision_linear9": 0.5607644744238336,
|
| 814 |
+
"eval_precision_normal": 0.5604078918199956,
|
| 815 |
+
"eval_precision_quad15": 0.5617676598593907,
|
| 816 |
+
"eval_precision_quad5": 0.5604053000779423,
|
| 817 |
+
"eval_precision_quad9": 0.5615796519410977,
|
| 818 |
+
"eval_precision_wa15": 0.561373291996785,
|
| 819 |
+
"eval_precision_wa5": 0.5607214877884831,
|
| 820 |
+
"eval_precision_wa9": 0.5604494382022472,
|
| 821 |
+
"eval_recall_linear15": 0.30282035561005516,
|
| 822 |
+
"eval_recall_linear5": 0.3080318822808093,
|
| 823 |
+
"eval_recall_linear9": 0.30582464745554877,
|
| 824 |
+
"eval_recall_normal": 0.30999386879215207,
|
| 825 |
+
"eval_recall_quad15": 0.30864500306560394,
|
| 826 |
+
"eval_recall_quad5": 0.30858369098712446,
|
| 827 |
+
"eval_recall_quad9": 0.30864500306560394,
|
| 828 |
+
"eval_recall_wa15": 0.2997547516860822,
|
| 829 |
+
"eval_recall_wa5": 0.30686695278969955,
|
| 830 |
+
"eval_recall_wa9": 0.30582464745554877,
|
| 831 |
+
"eval_roc_auc_linear15": 0.804613145141984,
|
| 832 |
+
"eval_roc_auc_linear5": 0.8041217401610808,
|
| 833 |
+
"eval_roc_auc_linear9": 0.804330923964816,
|
| 834 |
+
"eval_roc_auc_normal": 0.802881359058921,
|
| 835 |
+
"eval_roc_auc_quad15": 0.8040911446202597,
|
| 836 |
+
"eval_roc_auc_quad5": 0.8039859624204166,
|
| 837 |
+
"eval_roc_auc_quad9": 0.8040656050813342,
|
| 838 |
+
"eval_roc_auc_wa15": 0.804563721879546,
|
| 839 |
+
"eval_roc_auc_wa5": 0.8041048347986343,
|
| 840 |
+
"eval_roc_auc_wa9": 0.8042458197872405,
|
| 841 |
+
"eval_runtime": 4.4893,
|
| 842 |
+
"eval_samples_per_second": 39.205,
|
| 843 |
+
"eval_steps_per_second": 2.45,
|
| 844 |
+
"step": 12552
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 8.03,
|
| 848 |
+
"learning_rate": 2.1143364919642338e-07,
|
| 849 |
+
"loss": 0.4778,
|
| 850 |
+
"step": 12600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 8.16,
|
| 854 |
+
"learning_rate": 1.8586033454298977e-07,
|
| 855 |
+
"loss": 0.4648,
|
| 856 |
+
"step": 12800
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 8.29,
|
| 860 |
+
"learning_rate": 1.61776205561981e-07,
|
| 861 |
+
"loss": 0.3812,
|
| 862 |
+
"step": 13000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 8.41,
|
| 866 |
+
"learning_rate": 1.392253158001454e-07,
|
| 867 |
+
"loss": 0.4801,
|
| 868 |
+
"step": 13200
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 8.54,
|
| 872 |
+
"learning_rate": 1.1824891427575135e-07,
|
| 873 |
+
"loss": 0.4257,
|
| 874 |
+
"step": 13400
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 8.67,
|
| 878 |
+
"learning_rate": 9.888537002784026e-08,
|
| 879 |
+
"loss": 0.4362,
|
| 880 |
+
"step": 13600
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 8.8,
|
| 884 |
+
"learning_rate": 8.117010193339979e-08,
|
| 885 |
+
"loss": 0.3878,
|
| 886 |
+
"step": 13800
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 8.92,
|
| 890 |
+
"learning_rate": 6.51355139208325e-08,
|
| 891 |
+
"loss": 0.4417,
|
| 892 |
+
"step": 14000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 9.0,
|
| 896 |
+
"eval_f1_linear15": 0.3922634271099744,
|
| 897 |
+
"eval_f1_linear5": 0.3967453859892836,
|
| 898 |
+
"eval_f1_linear9": 0.3946834334832266,
|
| 899 |
+
"eval_f1_normal": 0.39824130555335496,
|
| 900 |
+
"eval_f1_quad15": 0.3978102189781022,
|
| 901 |
+
"eval_f1_quad5": 0.39790575916230364,
|
| 902 |
+
"eval_f1_quad9": 0.39769886927196985,
|
| 903 |
+
"eval_f1_wa15": 0.3903201250050082,
|
| 904 |
+
"eval_f1_wa5": 0.395756347598045,
|
| 905 |
+
"eval_f1_wa9": 0.39423842113639984,
|
| 906 |
+
"eval_loss": 0.4259018898010254,
|
| 907 |
+
"eval_mcc_linear15": 0.32027937656257643,
|
| 908 |
+
"eval_mcc_linear5": 0.32314902118858246,
|
| 909 |
+
"eval_mcc_linear9": 0.3216262073262593,
|
| 910 |
+
"eval_mcc_normal": 0.3242122776475081,
|
| 911 |
+
"eval_mcc_quad15": 0.32425814576982825,
|
| 912 |
+
"eval_mcc_quad5": 0.32431468962314003,
|
| 913 |
+
"eval_mcc_quad9": 0.32416705849149374,
|
| 914 |
+
"eval_mcc_wa15": 0.31891049484782574,
|
| 915 |
+
"eval_mcc_wa5": 0.3223616499276571,
|
| 916 |
+
"eval_mcc_wa9": 0.3210337480602992,
|
| 917 |
+
"eval_precision_linear15": 0.5632315813633234,
|
| 918 |
+
"eval_precision_linear5": 0.5625211029825549,
|
| 919 |
+
"eval_precision_linear9": 0.5623086517745776,
|
| 920 |
+
"eval_precision_normal": 0.5625559534467324,
|
| 921 |
+
"eval_precision_quad15": 0.5634974151494718,
|
| 922 |
+
"eval_precision_quad5": 0.5634688833969894,
|
| 923 |
+
"eval_precision_quad9": 0.5634626194491287,
|
| 924 |
+
"eval_precision_wa15": 0.5631864955486183,
|
| 925 |
+
"eval_precision_wa5": 0.5622671333408603,
|
| 926 |
+
"eval_precision_wa9": 0.561550668782589,
|
| 927 |
+
"eval_recall_linear15": 0.3009196811771919,
|
| 928 |
+
"eval_recall_linear5": 0.30643776824034336,
|
| 929 |
+
"eval_recall_linear9": 0.3040465971796444,
|
| 930 |
+
"eval_recall_normal": 0.3082158185162477,
|
| 931 |
+
"eval_recall_quad15": 0.3074187614960147,
|
| 932 |
+
"eval_recall_quad5": 0.3075413856529736,
|
| 933 |
+
"eval_recall_quad9": 0.3072961373390558,
|
| 934 |
+
"eval_recall_wa15": 0.29865113427345186,
|
| 935 |
+
"eval_recall_wa5": 0.30533415082771304,
|
| 936 |
+
"eval_recall_wa9": 0.3037400367872471,
|
| 937 |
+
"eval_roc_auc_linear15": 0.8043950128330297,
|
| 938 |
+
"eval_roc_auc_linear5": 0.8039100991570833,
|
| 939 |
+
"eval_roc_auc_linear9": 0.8041163733376,
|
| 940 |
+
"eval_roc_auc_normal": 0.8026596235869059,
|
| 941 |
+
"eval_roc_auc_quad15": 0.8038778736661152,
|
| 942 |
+
"eval_roc_auc_quad5": 0.803772609924925,
|
| 943 |
+
"eval_roc_auc_quad9": 0.8038528032091307,
|
| 944 |
+
"eval_roc_auc_wa15": 0.8043429232562305,
|
| 945 |
+
"eval_roc_auc_wa5": 0.8038900443697155,
|
| 946 |
+
"eval_roc_auc_wa9": 0.8040313366727525,
|
| 947 |
+
"eval_runtime": 4.5498,
|
| 948 |
+
"eval_samples_per_second": 38.683,
|
| 949 |
+
"eval_steps_per_second": 2.418,
|
| 950 |
+
"step": 14121
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 9.05,
|
| 954 |
+
"learning_rate": 5.0810935698227695e-08,
|
| 955 |
+
"loss": 0.4295,
|
| 956 |
+
"step": 14200
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 9.18,
|
| 960 |
+
"learning_rate": 3.822256910484922e-08,
|
| 961 |
+
"loss": 0.4416,
|
| 962 |
+
"step": 14400
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 9.31,
|
| 966 |
+
"learning_rate": 2.7393440183973826e-08,
|
| 967 |
+
"loss": 0.4132,
|
| 968 |
+
"step": 14600
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 9.43,
|
| 972 |
+
"learning_rate": 1.8343357064744104e-08,
|
| 973 |
+
"loss": 0.4015,
|
| 974 |
+
"step": 14800
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 9.56,
|
| 978 |
+
"learning_rate": 1.1088873730079274e-08,
|
| 979 |
+
"loss": 0.3694,
|
| 980 |
+
"step": 15000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 9.69,
|
| 984 |
+
"learning_rate": 5.665970387078945e-09,
|
| 985 |
+
"loss": 0.4901,
|
| 986 |
+
"step": 15200
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 9.82,
|
| 990 |
+
"learning_rate": 2.0300731629632197e-09,
|
| 991 |
+
"loss": 0.4466,
|
| 992 |
+
"step": 15400
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 9.94,
|
| 996 |
+
"learning_rate": 2.1961520880697803e-10,
|
| 997 |
+
"loss": 0.4402,
|
| 998 |
+
"step": 15600
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 10.0,
|
| 1002 |
+
"eval_f1_linear15": 0.39335113803962213,
|
| 1003 |
+
"eval_f1_linear5": 0.3975440681323035,
|
| 1004 |
+
"eval_f1_linear9": 0.3956009052288879,
|
| 1005 |
+
"eval_f1_normal": 0.3988779581999921,
|
| 1006 |
+
"eval_f1_quad15": 0.39838428639315704,
|
| 1007 |
+
"eval_f1_quad5": 0.39874896076645944,
|
| 1008 |
+
"eval_f1_quad9": 0.39841615521678875,
|
| 1009 |
+
"eval_f1_wa15": 0.390850561842684,
|
| 1010 |
+
"eval_f1_wa5": 0.3966542456195988,
|
| 1011 |
+
"eval_f1_wa9": 0.3954900948826868,
|
| 1012 |
+
"eval_loss": 0.425975501537323,
|
| 1013 |
+
"eval_mcc_linear15": 0.3206369859621025,
|
| 1014 |
+
"eval_mcc_linear5": 0.3233722324850351,
|
| 1015 |
+
"eval_mcc_linear9": 0.3218662246562777,
|
| 1016 |
+
"eval_mcc_normal": 0.32401864196481456,
|
| 1017 |
+
"eval_mcc_quad15": 0.32429723530478316,
|
| 1018 |
+
"eval_mcc_quad5": 0.32463908556149096,
|
| 1019 |
+
"eval_mcc_quad9": 0.3242911548160823,
|
| 1020 |
+
"eval_mcc_wa15": 0.31880828217683166,
|
| 1021 |
+
"eval_mcc_wa5": 0.32256748695686166,
|
| 1022 |
+
"eval_mcc_wa9": 0.3216998441434868,
|
| 1023 |
+
"eval_precision_linear15": 0.5621510766776803,
|
| 1024 |
+
"eval_precision_linear5": 0.561611639619474,
|
| 1025 |
+
"eval_precision_linear9": 0.5612256392925538,
|
| 1026 |
+
"eval_precision_normal": 0.5608265748250194,
|
| 1027 |
+
"eval_precision_quad15": 0.5625139789756207,
|
| 1028 |
+
"eval_precision_quad5": 0.5627444407196335,
|
| 1029 |
+
"eval_precision_quad9": 0.562437115707099,
|
| 1030 |
+
"eval_precision_wa15": 0.5619179027250776,
|
| 1031 |
+
"eval_precision_wa5": 0.5611260655002244,
|
| 1032 |
+
"eval_precision_wa9": 0.5609865975898187,
|
| 1033 |
+
"eval_recall_linear15": 0.30251379521765787,
|
| 1034 |
+
"eval_recall_linear5": 0.3076640098099326,
|
| 1035 |
+
"eval_recall_linear9": 0.305456774984672,
|
| 1036 |
+
"eval_recall_normal": 0.3095033721643164,
|
| 1037 |
+
"eval_recall_quad15": 0.3083997547516861,
|
| 1038 |
+
"eval_recall_quad5": 0.30876762722256285,
|
| 1039 |
+
"eval_recall_quad9": 0.30846106683016555,
|
| 1040 |
+
"eval_recall_wa15": 0.2996321275291232,
|
| 1041 |
+
"eval_recall_wa5": 0.30674432863274065,
|
| 1042 |
+
"eval_recall_wa9": 0.3053954629061925,
|
| 1043 |
+
"eval_roc_auc_linear15": 0.8044600135614658,
|
| 1044 |
+
"eval_roc_auc_linear5": 0.803977486065899,
|
| 1045 |
+
"eval_roc_auc_linear9": 0.8041825042466384,
|
| 1046 |
+
"eval_roc_auc_normal": 0.802730452329666,
|
| 1047 |
+
"eval_roc_auc_quad15": 0.8039456923933532,
|
| 1048 |
+
"eval_roc_auc_quad5": 0.8038407876971257,
|
| 1049 |
+
"eval_roc_auc_quad9": 0.8039209695830786,
|
| 1050 |
+
"eval_roc_auc_wa15": 0.8044063992491602,
|
| 1051 |
+
"eval_roc_auc_wa5": 0.8039575619200438,
|
| 1052 |
+
"eval_roc_auc_wa9": 0.8040980203970507,
|
| 1053 |
+
"eval_runtime": 4.4935,
|
| 1054 |
+
"eval_samples_per_second": 39.167,
|
| 1055 |
+
"eval_steps_per_second": 2.448,
|
| 1056 |
+
"step": 15690
|
| 1057 |
+
}
|
| 1058 |
+
],
|
| 1059 |
+
"max_steps": 15690,
|
| 1060 |
+
"num_train_epochs": 10,
|
| 1061 |
+
"total_flos": 4099894279004160.0,
|
| 1062 |
+
"trial_name": null,
|
| 1063 |
+
"trial_params": null
|
| 1064 |
+
}
|
checkpoint-final/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae4f34a5e0d4b7e6d02fad944d04dd80b3b285b73ee51689b3239a9ad6d6e201
|
| 3 |
+
size 3055
|
checkpoint-final/vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"[SEP]":0,"[PAD]":1,"[MASK]":2,"[UNK]":3,"[CLS]":4, "L":5, "A":6, "G":7, "V":8, "E":9, "S":10, "I":11, "K":12, "R":13, "D":14, "T":15, "P":16, "N":17, "Q":18, "F":19, "Y":20, "M":21, "H":22, "C":23, "W":24, "X":25, "U":26, "B":27, "Z":28, "O":29}
|
checkpoint-final/vocab.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"[SEP]":0,"[PAD]":1,"[MASK]":2,"[UNK]":3,"[CLS]":4, "L":5, "A":6, "G":7, "V":8, "E":9, "S":10, "I":11, "K":12, "R":13, "D":14, "T":15, "P":16, "N":17, "Q":18, "F":19, "Y":20, "M":21, "H":22, "C":23, "W":24, "X":25, "U":26, "B":27, "Z":28, "O":29}
|
requirements.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
git+https://github.com/huggingface/transformers
|
| 2 |
+
gradio
|
| 3 |
+
torch
|