daccuong2002
commited on
Commit
•
1e49d2a
1
Parent(s):
4aff16e
Upload folder using huggingface_hub
Browse files- README.md +36 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- checkpoint-3318/config.json +46 -0
- checkpoint-3318/model.safetensors +3 -0
- checkpoint-3318/optimizer.pt +3 -0
- checkpoint-3318/rng_state.pth +3 -0
- checkpoint-3318/scheduler.pt +3 -0
- checkpoint-3318/trainer_state.json +1020 -0
- checkpoint-3318/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- runs/Jul19_08-08-26_r-daccuong2002-runmay3-jzutjz7y-f713d-ewa9l/events.out.tfevents.1721376507.r-daccuong2002-runmay3-jzutjz7y-f713d-ewa9l.98.0 +2 -2
- runs/Jul19_08-08-26_r-daccuong2002-runmay3-jzutjz7y-f713d-ewa9l/events.out.tfevents.1721396576.r-daccuong2002-runmay3-jzutjz7y-f713d-ewa9l.98.1 +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: vinai/phobert-base-v2
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.3279833495616913
|
17 |
+
|
18 |
+
f1_macro: 0.876649943334319
|
19 |
+
|
20 |
+
f1_micro: 0.9077217308152044
|
21 |
+
|
22 |
+
f1_weighted: 0.9087694078887676
|
23 |
+
|
24 |
+
precision_macro: 0.8488349060784007
|
25 |
+
|
26 |
+
precision_micro: 0.9077217308152044
|
27 |
+
|
28 |
+
precision_weighted: 0.9121960695781595
|
29 |
+
|
30 |
+
recall_macro: 0.9108354827796887
|
31 |
+
|
32 |
+
recall_micro: 0.9077217308152044
|
33 |
+
|
34 |
+
recall_weighted: 0.9077217308152044
|
35 |
+
|
36 |
+
accuracy: 0.9077217308152044
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask>": 64000
|
3 |
+
}
|
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3318/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/phobert-base-v2",
|
3 |
+
"_num_labels": 6,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "2733522",
|
16 |
+
"1": "2733534",
|
17 |
+
"2": "2733540",
|
18 |
+
"3": "2733546",
|
19 |
+
"4": "2733552",
|
20 |
+
"5": "2733570"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"2733522": 0,
|
26 |
+
"2733534": 1,
|
27 |
+
"2733540": 2,
|
28 |
+
"2733546": 3,
|
29 |
+
"2733552": 4,
|
30 |
+
"2733570": 5
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"max_position_embeddings": 258,
|
34 |
+
"model_type": "roberta",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"pad_token_id": 1,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"problem_type": "single_label_classification",
|
40 |
+
"tokenizer_class": "PhobertTokenizer",
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.42.2",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 64001
|
46 |
+
}
|
checkpoint-3318/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a7f3216c6c1b6968f4f4281cf1783c8a31a1b4bfab39a5c662e9187b46dd9a4
|
3 |
+
size 540035688
|
checkpoint-3318/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c19526db84c55352b658c866c30e730017626871256e7e12c7b10b866f0a5f54
|
3 |
+
size 1080185594
|
checkpoint-3318/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee3e85b34fcc1f3e72b38b7a9e71564fc210aedb1f14a96c4fe8318c124f297d
|
3 |
+
size 13990
|
checkpoint-3318/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c1e7c83cf538fc428c3e82626883d7aafd057626237481ba3d141d2e7e4f6e7
|
3 |
+
size 1064
|
checkpoint-3318/trainer_state.json
ADDED
@@ -0,0 +1,1020 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3279833495616913,
|
3 |
+
"best_model_checkpoint": "PhoBert-MultiLabel-KMeans/checkpoint-3318",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3318,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.022603978300180832,
|
13 |
+
"grad_norm": 3.841909170150757,
|
14 |
+
"learning_rate": 3.765060240963856e-06,
|
15 |
+
"loss": 1.7878,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.045207956600361664,
|
20 |
+
"grad_norm": 2.6476118564605713,
|
21 |
+
"learning_rate": 7.530120481927712e-06,
|
22 |
+
"loss": 1.7541,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06781193490054249,
|
27 |
+
"grad_norm": 3.1488897800445557,
|
28 |
+
"learning_rate": 1.1295180722891567e-05,
|
29 |
+
"loss": 1.7143,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09041591320072333,
|
34 |
+
"grad_norm": 3.9978089332580566,
|
35 |
+
"learning_rate": 1.5060240963855424e-05,
|
36 |
+
"loss": 1.6553,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.11301989150090416,
|
41 |
+
"grad_norm": 4.824118614196777,
|
42 |
+
"learning_rate": 1.882530120481928e-05,
|
43 |
+
"loss": 1.5607,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.13562386980108498,
|
48 |
+
"grad_norm": 4.588301658630371,
|
49 |
+
"learning_rate": 2.2590361445783133e-05,
|
50 |
+
"loss": 1.4288,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.15822784810126583,
|
55 |
+
"grad_norm": 14.850578308105469,
|
56 |
+
"learning_rate": 2.635542168674699e-05,
|
57 |
+
"loss": 1.2511,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.18083182640144665,
|
62 |
+
"grad_norm": 11.93288516998291,
|
63 |
+
"learning_rate": 3.012048192771085e-05,
|
64 |
+
"loss": 1.1645,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.20343580470162748,
|
69 |
+
"grad_norm": 10.374913215637207,
|
70 |
+
"learning_rate": 3.38855421686747e-05,
|
71 |
+
"loss": 1.1245,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.22603978300180833,
|
76 |
+
"grad_norm": 5.814253330230713,
|
77 |
+
"learning_rate": 3.765060240963856e-05,
|
78 |
+
"loss": 1.1271,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.24864376130198915,
|
83 |
+
"grad_norm": 19.154064178466797,
|
84 |
+
"learning_rate": 4.141566265060241e-05,
|
85 |
+
"loss": 1.0359,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.27124773960216997,
|
90 |
+
"grad_norm": 12.057534217834473,
|
91 |
+
"learning_rate": 4.5180722891566266e-05,
|
92 |
+
"loss": 0.9842,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.2938517179023508,
|
97 |
+
"grad_norm": 5.480999946594238,
|
98 |
+
"learning_rate": 4.8945783132530124e-05,
|
99 |
+
"loss": 1.165,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.31645569620253167,
|
104 |
+
"grad_norm": 27.02998924255371,
|
105 |
+
"learning_rate": 4.969859343603483e-05,
|
106 |
+
"loss": 1.0626,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.33905967450271246,
|
111 |
+
"grad_norm": 8.911443710327148,
|
112 |
+
"learning_rate": 4.927997320830543e-05,
|
113 |
+
"loss": 0.9147,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3616636528028933,
|
118 |
+
"grad_norm": 7.904396057128906,
|
119 |
+
"learning_rate": 4.886135298057603e-05,
|
120 |
+
"loss": 0.8824,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.38426763110307416,
|
125 |
+
"grad_norm": 40.34563064575195,
|
126 |
+
"learning_rate": 4.844273275284662e-05,
|
127 |
+
"loss": 0.9151,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.40687160940325495,
|
132 |
+
"grad_norm": 11.78642749786377,
|
133 |
+
"learning_rate": 4.8024112525117214e-05,
|
134 |
+
"loss": 0.9926,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4294755877034358,
|
139 |
+
"grad_norm": 8.729843139648438,
|
140 |
+
"learning_rate": 4.760549229738781e-05,
|
141 |
+
"loss": 0.8049,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.45207956600361665,
|
146 |
+
"grad_norm": 3.0259087085723877,
|
147 |
+
"learning_rate": 4.718687206965841e-05,
|
148 |
+
"loss": 0.9043,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.47468354430379744,
|
153 |
+
"grad_norm": 3.1441285610198975,
|
154 |
+
"learning_rate": 4.676825184192901e-05,
|
155 |
+
"loss": 1.024,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.4972875226039783,
|
160 |
+
"grad_norm": 297.1407775878906,
|
161 |
+
"learning_rate": 4.63496316141996e-05,
|
162 |
+
"loss": 0.7747,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5198915009041591,
|
167 |
+
"grad_norm": 21.502670288085938,
|
168 |
+
"learning_rate": 4.5931011386470195e-05,
|
169 |
+
"loss": 1.106,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5424954792043399,
|
174 |
+
"grad_norm": 7.8344340324401855,
|
175 |
+
"learning_rate": 4.551239115874079e-05,
|
176 |
+
"loss": 0.9031,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.5650994575045208,
|
181 |
+
"grad_norm": 9.26258373260498,
|
182 |
+
"learning_rate": 4.509377093101139e-05,
|
183 |
+
"loss": 0.9796,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.5877034358047016,
|
188 |
+
"grad_norm": 21.926687240600586,
|
189 |
+
"learning_rate": 4.467515070328199e-05,
|
190 |
+
"loss": 0.8663,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6103074141048824,
|
195 |
+
"grad_norm": 17.36395263671875,
|
196 |
+
"learning_rate": 4.425653047555258e-05,
|
197 |
+
"loss": 0.866,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.6329113924050633,
|
202 |
+
"grad_norm": 9.919265747070312,
|
203 |
+
"learning_rate": 4.3837910247823175e-05,
|
204 |
+
"loss": 0.8074,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.6555153707052441,
|
209 |
+
"grad_norm": 15.072575569152832,
|
210 |
+
"learning_rate": 4.3419290020093775e-05,
|
211 |
+
"loss": 0.9021,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.6781193490054249,
|
216 |
+
"grad_norm": 2.6935675144195557,
|
217 |
+
"learning_rate": 4.300066979236437e-05,
|
218 |
+
"loss": 0.8359,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7007233273056058,
|
223 |
+
"grad_norm": 2.398829698562622,
|
224 |
+
"learning_rate": 4.258204956463496e-05,
|
225 |
+
"loss": 0.8454,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.7233273056057866,
|
230 |
+
"grad_norm": 1.5908894538879395,
|
231 |
+
"learning_rate": 4.216342933690556e-05,
|
232 |
+
"loss": 0.7676,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.7459312839059674,
|
237 |
+
"grad_norm": 12.428017616271973,
|
238 |
+
"learning_rate": 4.1744809109176155e-05,
|
239 |
+
"loss": 0.8397,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.7685352622061483,
|
244 |
+
"grad_norm": 8.742015838623047,
|
245 |
+
"learning_rate": 4.1326188881446755e-05,
|
246 |
+
"loss": 0.8207,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.7911392405063291,
|
251 |
+
"grad_norm": 16.055889129638672,
|
252 |
+
"learning_rate": 4.090756865371735e-05,
|
253 |
+
"loss": 0.7526,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.8137432188065099,
|
258 |
+
"grad_norm": 2.839799642562866,
|
259 |
+
"learning_rate": 4.048894842598794e-05,
|
260 |
+
"loss": 0.6883,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.8363471971066908,
|
265 |
+
"grad_norm": 30.43299102783203,
|
266 |
+
"learning_rate": 4.007032819825854e-05,
|
267 |
+
"loss": 0.9797,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.8589511754068716,
|
272 |
+
"grad_norm": 3.6067237854003906,
|
273 |
+
"learning_rate": 3.965170797052914e-05,
|
274 |
+
"loss": 0.7248,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.8815551537070524,
|
279 |
+
"grad_norm": 1.6388925313949585,
|
280 |
+
"learning_rate": 3.9233087742799736e-05,
|
281 |
+
"loss": 0.9144,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.9041591320072333,
|
286 |
+
"grad_norm": 1.7512284517288208,
|
287 |
+
"learning_rate": 3.881446751507033e-05,
|
288 |
+
"loss": 0.8286,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.9267631103074141,
|
293 |
+
"grad_norm": 1.7240828275680542,
|
294 |
+
"learning_rate": 3.839584728734092e-05,
|
295 |
+
"loss": 0.8361,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.9493670886075949,
|
300 |
+
"grad_norm": 12.430205345153809,
|
301 |
+
"learning_rate": 3.797722705961152e-05,
|
302 |
+
"loss": 0.8154,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.9719710669077758,
|
307 |
+
"grad_norm": 2.2587053775787354,
|
308 |
+
"learning_rate": 3.755860683188212e-05,
|
309 |
+
"loss": 0.7517,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.9945750452079566,
|
314 |
+
"grad_norm": 4.7276105880737305,
|
315 |
+
"learning_rate": 3.7139986604152716e-05,
|
316 |
+
"loss": 0.7314,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.0,
|
321 |
+
"eval_accuracy": 0.8646904135787712,
|
322 |
+
"eval_f1_macro": 0.7969114035222423,
|
323 |
+
"eval_f1_micro": 0.8646904135787712,
|
324 |
+
"eval_f1_weighted": 0.8686677177148115,
|
325 |
+
"eval_loss": 0.474561870098114,
|
326 |
+
"eval_precision_macro": 0.7463296033587281,
|
327 |
+
"eval_precision_micro": 0.8646904135787712,
|
328 |
+
"eval_precision_weighted": 0.8811279472143232,
|
329 |
+
"eval_recall_macro": 0.8754275642409685,
|
330 |
+
"eval_recall_micro": 0.8646904135787712,
|
331 |
+
"eval_recall_weighted": 0.8646904135787712,
|
332 |
+
"eval_runtime": 684.5188,
|
333 |
+
"eval_samples_per_second": 6.111,
|
334 |
+
"eval_steps_per_second": 0.383,
|
335 |
+
"step": 1106
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.0171790235081375,
|
339 |
+
"grad_norm": 4.729485988616943,
|
340 |
+
"learning_rate": 3.672136637642331e-05,
|
341 |
+
"loss": 0.7628,
|
342 |
+
"step": 1125
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.0397830018083183,
|
346 |
+
"grad_norm": 13.282486915588379,
|
347 |
+
"learning_rate": 3.63027461486939e-05,
|
348 |
+
"loss": 0.7394,
|
349 |
+
"step": 1150
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.062386980108499,
|
353 |
+
"grad_norm": 9.316232681274414,
|
354 |
+
"learning_rate": 3.58841259209645e-05,
|
355 |
+
"loss": 0.677,
|
356 |
+
"step": 1175
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.0849909584086799,
|
360 |
+
"grad_norm": 4.590908050537109,
|
361 |
+
"learning_rate": 3.54655056932351e-05,
|
362 |
+
"loss": 0.9049,
|
363 |
+
"step": 1200
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.1075949367088607,
|
367 |
+
"grad_norm": 7.4369988441467285,
|
368 |
+
"learning_rate": 3.5046885465505696e-05,
|
369 |
+
"loss": 0.8201,
|
370 |
+
"step": 1225
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.1301989150090417,
|
374 |
+
"grad_norm": 46.419105529785156,
|
375 |
+
"learning_rate": 3.462826523777629e-05,
|
376 |
+
"loss": 0.7825,
|
377 |
+
"step": 1250
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.1528028933092225,
|
381 |
+
"grad_norm": 11.992456436157227,
|
382 |
+
"learning_rate": 3.420964501004689e-05,
|
383 |
+
"loss": 0.6292,
|
384 |
+
"step": 1275
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.1754068716094033,
|
388 |
+
"grad_norm": 5.902411460876465,
|
389 |
+
"learning_rate": 3.379102478231748e-05,
|
390 |
+
"loss": 0.7238,
|
391 |
+
"step": 1300
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 1.198010849909584,
|
395 |
+
"grad_norm": 0.5739479660987854,
|
396 |
+
"learning_rate": 3.3372404554588077e-05,
|
397 |
+
"loss": 0.6716,
|
398 |
+
"step": 1325
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.2206148282097649,
|
402 |
+
"grad_norm": 39.53816604614258,
|
403 |
+
"learning_rate": 3.295378432685868e-05,
|
404 |
+
"loss": 0.9233,
|
405 |
+
"step": 1350
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.2432188065099457,
|
409 |
+
"grad_norm": 6.763810157775879,
|
410 |
+
"learning_rate": 3.253516409912927e-05,
|
411 |
+
"loss": 0.7302,
|
412 |
+
"step": 1375
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.2658227848101267,
|
416 |
+
"grad_norm": 13.701122283935547,
|
417 |
+
"learning_rate": 3.211654387139987e-05,
|
418 |
+
"loss": 0.7074,
|
419 |
+
"step": 1400
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.2884267631103075,
|
423 |
+
"grad_norm": 3.521284580230713,
|
424 |
+
"learning_rate": 3.1697923643670464e-05,
|
425 |
+
"loss": 0.7279,
|
426 |
+
"step": 1425
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 1.3110307414104883,
|
430 |
+
"grad_norm": 1.2048885822296143,
|
431 |
+
"learning_rate": 3.127930341594106e-05,
|
432 |
+
"loss": 0.6119,
|
433 |
+
"step": 1450
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 1.333634719710669,
|
437 |
+
"grad_norm": 1.5905373096466064,
|
438 |
+
"learning_rate": 3.086068318821165e-05,
|
439 |
+
"loss": 0.639,
|
440 |
+
"step": 1475
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.3562386980108498,
|
444 |
+
"grad_norm": 3.3090178966522217,
|
445 |
+
"learning_rate": 3.0442062960482254e-05,
|
446 |
+
"loss": 0.7074,
|
447 |
+
"step": 1500
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.3788426763110309,
|
451 |
+
"grad_norm": 1.7795202732086182,
|
452 |
+
"learning_rate": 3.002344273275285e-05,
|
453 |
+
"loss": 0.6383,
|
454 |
+
"step": 1525
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 1.4014466546112117,
|
458 |
+
"grad_norm": 10.706816673278809,
|
459 |
+
"learning_rate": 2.9604822505023444e-05,
|
460 |
+
"loss": 0.7385,
|
461 |
+
"step": 1550
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 1.4240506329113924,
|
465 |
+
"grad_norm": 11.373717308044434,
|
466 |
+
"learning_rate": 2.918620227729404e-05,
|
467 |
+
"loss": 0.7328,
|
468 |
+
"step": 1575
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 1.4466546112115732,
|
472 |
+
"grad_norm": 1.1606653928756714,
|
473 |
+
"learning_rate": 2.8767582049564634e-05,
|
474 |
+
"loss": 0.7943,
|
475 |
+
"step": 1600
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 1.469258589511754,
|
479 |
+
"grad_norm": 4.997502326965332,
|
480 |
+
"learning_rate": 2.8348961821835234e-05,
|
481 |
+
"loss": 0.7762,
|
482 |
+
"step": 1625
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.4918625678119348,
|
486 |
+
"grad_norm": 10.411747932434082,
|
487 |
+
"learning_rate": 2.793034159410583e-05,
|
488 |
+
"loss": 0.6818,
|
489 |
+
"step": 1650
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.5144665461121156,
|
493 |
+
"grad_norm": 1.0002527236938477,
|
494 |
+
"learning_rate": 2.7511721366376424e-05,
|
495 |
+
"loss": 0.4924,
|
496 |
+
"step": 1675
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 1.5370705244122966,
|
500 |
+
"grad_norm": 1.6328582763671875,
|
501 |
+
"learning_rate": 2.709310113864702e-05,
|
502 |
+
"loss": 0.7116,
|
503 |
+
"step": 1700
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 1.5596745027124774,
|
507 |
+
"grad_norm": 3.9850947856903076,
|
508 |
+
"learning_rate": 2.6674480910917614e-05,
|
509 |
+
"loss": 0.7846,
|
510 |
+
"step": 1725
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 1.5822784810126582,
|
514 |
+
"grad_norm": 12.702369689941406,
|
515 |
+
"learning_rate": 2.625586068318821e-05,
|
516 |
+
"loss": 0.6727,
|
517 |
+
"step": 1750
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 1.604882459312839,
|
521 |
+
"grad_norm": 22.720844268798828,
|
522 |
+
"learning_rate": 2.583724045545881e-05,
|
523 |
+
"loss": 0.6354,
|
524 |
+
"step": 1775
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 1.6274864376130198,
|
528 |
+
"grad_norm": 7.914674282073975,
|
529 |
+
"learning_rate": 2.5418620227729404e-05,
|
530 |
+
"loss": 0.8122,
|
531 |
+
"step": 1800
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 1.6500904159132008,
|
535 |
+
"grad_norm": 10.155131340026855,
|
536 |
+
"learning_rate": 2.5e-05,
|
537 |
+
"loss": 0.5847,
|
538 |
+
"step": 1825
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.6726943942133814,
|
542 |
+
"grad_norm": 4.096177577972412,
|
543 |
+
"learning_rate": 2.4581379772270598e-05,
|
544 |
+
"loss": 0.6681,
|
545 |
+
"step": 1850
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 1.6952983725135624,
|
549 |
+
"grad_norm": 1.1155363321304321,
|
550 |
+
"learning_rate": 2.4162759544541195e-05,
|
551 |
+
"loss": 0.5517,
|
552 |
+
"step": 1875
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 1.7179023508137432,
|
556 |
+
"grad_norm": 0.886872410774231,
|
557 |
+
"learning_rate": 2.3744139316811788e-05,
|
558 |
+
"loss": 0.6529,
|
559 |
+
"step": 1900
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 1.740506329113924,
|
563 |
+
"grad_norm": 45.21336364746094,
|
564 |
+
"learning_rate": 2.3325519089082385e-05,
|
565 |
+
"loss": 0.7317,
|
566 |
+
"step": 1925
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 1.763110307414105,
|
570 |
+
"grad_norm": 2.183527946472168,
|
571 |
+
"learning_rate": 2.290689886135298e-05,
|
572 |
+
"loss": 0.5836,
|
573 |
+
"step": 1950
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 1.7857142857142856,
|
577 |
+
"grad_norm": 9.820974349975586,
|
578 |
+
"learning_rate": 2.2488278633623578e-05,
|
579 |
+
"loss": 0.717,
|
580 |
+
"step": 1975
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 1.8083182640144666,
|
584 |
+
"grad_norm": 2.521716594696045,
|
585 |
+
"learning_rate": 2.2069658405894175e-05,
|
586 |
+
"loss": 0.665,
|
587 |
+
"step": 2000
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 1.8309222423146474,
|
591 |
+
"grad_norm": 43.333824157714844,
|
592 |
+
"learning_rate": 2.1651038178164772e-05,
|
593 |
+
"loss": 0.4805,
|
594 |
+
"step": 2025
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 1.8535262206148282,
|
598 |
+
"grad_norm": 1.851754069328308,
|
599 |
+
"learning_rate": 2.1232417950435365e-05,
|
600 |
+
"loss": 0.6131,
|
601 |
+
"step": 2050
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 1.8761301989150092,
|
605 |
+
"grad_norm": 1.0132567882537842,
|
606 |
+
"learning_rate": 2.0813797722705962e-05,
|
607 |
+
"loss": 0.6625,
|
608 |
+
"step": 2075
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 1.8987341772151898,
|
612 |
+
"grad_norm": 18.15288543701172,
|
613 |
+
"learning_rate": 2.039517749497656e-05,
|
614 |
+
"loss": 0.692,
|
615 |
+
"step": 2100
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 1.9213381555153708,
|
619 |
+
"grad_norm": 2.7393548488616943,
|
620 |
+
"learning_rate": 1.9976557267247152e-05,
|
621 |
+
"loss": 0.8157,
|
622 |
+
"step": 2125
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.9439421338155516,
|
626 |
+
"grad_norm": 2.785061836242676,
|
627 |
+
"learning_rate": 1.9557937039517752e-05,
|
628 |
+
"loss": 0.6455,
|
629 |
+
"step": 2150
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 1.9665461121157324,
|
633 |
+
"grad_norm": 7.032905578613281,
|
634 |
+
"learning_rate": 1.9139316811788345e-05,
|
635 |
+
"loss": 0.673,
|
636 |
+
"step": 2175
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 1.9891500904159132,
|
640 |
+
"grad_norm": 6.695957660675049,
|
641 |
+
"learning_rate": 1.8720696584058942e-05,
|
642 |
+
"loss": 0.6465,
|
643 |
+
"step": 2200
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 2.0,
|
647 |
+
"eval_accuracy": 0.8864451350705236,
|
648 |
+
"eval_f1_macro": 0.8559865482684758,
|
649 |
+
"eval_f1_micro": 0.8864451350705236,
|
650 |
+
"eval_f1_weighted": 0.8885254655749029,
|
651 |
+
"eval_loss": 0.3843747675418854,
|
652 |
+
"eval_precision_macro": 0.8270066883752536,
|
653 |
+
"eval_precision_micro": 0.8864451350705236,
|
654 |
+
"eval_precision_weighted": 0.8971130501570121,
|
655 |
+
"eval_recall_macro": 0.8950094171847649,
|
656 |
+
"eval_recall_micro": 0.8864451350705236,
|
657 |
+
"eval_recall_weighted": 0.8864451350705236,
|
658 |
+
"eval_runtime": 708.9221,
|
659 |
+
"eval_samples_per_second": 5.901,
|
660 |
+
"eval_steps_per_second": 0.37,
|
661 |
+
"step": 2212
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 2.011754068716094,
|
665 |
+
"grad_norm": 0.2900655269622803,
|
666 |
+
"learning_rate": 1.830207635632954e-05,
|
667 |
+
"loss": 0.4926,
|
668 |
+
"step": 2225
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 2.034358047016275,
|
672 |
+
"grad_norm": 0.25579121708869934,
|
673 |
+
"learning_rate": 1.7883456128600136e-05,
|
674 |
+
"loss": 0.5601,
|
675 |
+
"step": 2250
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 2.0569620253164556,
|
679 |
+
"grad_norm": 10.494261741638184,
|
680 |
+
"learning_rate": 1.746483590087073e-05,
|
681 |
+
"loss": 0.4779,
|
682 |
+
"step": 2275
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 2.0795660036166366,
|
686 |
+
"grad_norm": 2.495044231414795,
|
687 |
+
"learning_rate": 1.704621567314133e-05,
|
688 |
+
"loss": 0.6575,
|
689 |
+
"step": 2300
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 2.102169981916817,
|
693 |
+
"grad_norm": 19.166954040527344,
|
694 |
+
"learning_rate": 1.6627595445411922e-05,
|
695 |
+
"loss": 0.5641,
|
696 |
+
"step": 2325
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 2.124773960216998,
|
700 |
+
"grad_norm": 6.6829915046691895,
|
701 |
+
"learning_rate": 1.620897521768252e-05,
|
702 |
+
"loss": 0.6266,
|
703 |
+
"step": 2350
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 2.147377938517179,
|
707 |
+
"grad_norm": 18.80038070678711,
|
708 |
+
"learning_rate": 1.5790354989953116e-05,
|
709 |
+
"loss": 0.6087,
|
710 |
+
"step": 2375
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 2.1699819168173597,
|
714 |
+
"grad_norm": 32.67726135253906,
|
715 |
+
"learning_rate": 1.537173476222371e-05,
|
716 |
+
"loss": 0.8013,
|
717 |
+
"step": 2400
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 2.1925858951175408,
|
721 |
+
"grad_norm": 4.437242031097412,
|
722 |
+
"learning_rate": 1.4953114534494308e-05,
|
723 |
+
"loss": 0.6542,
|
724 |
+
"step": 2425
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 2.2151898734177213,
|
728 |
+
"grad_norm": 7.463759899139404,
|
729 |
+
"learning_rate": 1.4534494306764904e-05,
|
730 |
+
"loss": 0.5717,
|
731 |
+
"step": 2450
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 2.2377938517179023,
|
735 |
+
"grad_norm": 4.608203411102295,
|
736 |
+
"learning_rate": 1.41158740790355e-05,
|
737 |
+
"loss": 0.5789,
|
738 |
+
"step": 2475
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 2.2603978300180834,
|
742 |
+
"grad_norm": 1.7395381927490234,
|
743 |
+
"learning_rate": 1.3697253851306096e-05,
|
744 |
+
"loss": 0.5181,
|
745 |
+
"step": 2500
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 2.283001808318264,
|
749 |
+
"grad_norm": 21.39842414855957,
|
750 |
+
"learning_rate": 1.3278633623576691e-05,
|
751 |
+
"loss": 0.5867,
|
752 |
+
"step": 2525
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 2.305605786618445,
|
756 |
+
"grad_norm": 15.271064758300781,
|
757 |
+
"learning_rate": 1.2860013395847286e-05,
|
758 |
+
"loss": 0.62,
|
759 |
+
"step": 2550
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 2.3282097649186255,
|
763 |
+
"grad_norm": 1.706192135810852,
|
764 |
+
"learning_rate": 1.2441393168117885e-05,
|
765 |
+
"loss": 0.6125,
|
766 |
+
"step": 2575
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 2.3508137432188065,
|
770 |
+
"grad_norm": 0.2807926833629608,
|
771 |
+
"learning_rate": 1.202277294038848e-05,
|
772 |
+
"loss": 0.6651,
|
773 |
+
"step": 2600
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 2.3734177215189876,
|
777 |
+
"grad_norm": 1.556008219718933,
|
778 |
+
"learning_rate": 1.1604152712659077e-05,
|
779 |
+
"loss": 0.4651,
|
780 |
+
"step": 2625
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 2.396021699819168,
|
784 |
+
"grad_norm": 13.534441947937012,
|
785 |
+
"learning_rate": 1.1185532484929673e-05,
|
786 |
+
"loss": 0.6178,
|
787 |
+
"step": 2650
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 2.418625678119349,
|
791 |
+
"grad_norm": 29.2789249420166,
|
792 |
+
"learning_rate": 1.0766912257200268e-05,
|
793 |
+
"loss": 0.5291,
|
794 |
+
"step": 2675
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 2.4412296564195297,
|
798 |
+
"grad_norm": 37.51542663574219,
|
799 |
+
"learning_rate": 1.0348292029470865e-05,
|
800 |
+
"loss": 0.5774,
|
801 |
+
"step": 2700
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 2.4638336347197107,
|
805 |
+
"grad_norm": 0.8940380215644836,
|
806 |
+
"learning_rate": 9.92967180174146e-06,
|
807 |
+
"loss": 0.6371,
|
808 |
+
"step": 2725
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 2.4864376130198913,
|
812 |
+
"grad_norm": 0.25459304451942444,
|
813 |
+
"learning_rate": 9.511051574012057e-06,
|
814 |
+
"loss": 0.5044,
|
815 |
+
"step": 2750
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 2.5090415913200723,
|
819 |
+
"grad_norm": 2.767826795578003,
|
820 |
+
"learning_rate": 9.092431346282652e-06,
|
821 |
+
"loss": 0.4203,
|
822 |
+
"step": 2775
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 2.5316455696202533,
|
826 |
+
"grad_norm": 1.5824614763259888,
|
827 |
+
"learning_rate": 8.673811118553249e-06,
|
828 |
+
"loss": 0.6947,
|
829 |
+
"step": 2800
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 2.554249547920434,
|
833 |
+
"grad_norm": 1.1196787357330322,
|
834 |
+
"learning_rate": 8.255190890823845e-06,
|
835 |
+
"loss": 0.6688,
|
836 |
+
"step": 2825
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 2.576853526220615,
|
840 |
+
"grad_norm": 0.9682297706604004,
|
841 |
+
"learning_rate": 7.83657066309444e-06,
|
842 |
+
"loss": 0.4147,
|
843 |
+
"step": 2850
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 2.599457504520796,
|
847 |
+
"grad_norm": 6.9166579246521,
|
848 |
+
"learning_rate": 7.417950435365037e-06,
|
849 |
+
"loss": 0.6114,
|
850 |
+
"step": 2875
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 2.6220614828209765,
|
854 |
+
"grad_norm": 2.9561591148376465,
|
855 |
+
"learning_rate": 6.999330207635633e-06,
|
856 |
+
"loss": 0.6869,
|
857 |
+
"step": 2900
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 2.644665461121157,
|
861 |
+
"grad_norm": 19.65010643005371,
|
862 |
+
"learning_rate": 6.58070997990623e-06,
|
863 |
+
"loss": 0.5901,
|
864 |
+
"step": 2925
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 2.667269439421338,
|
868 |
+
"grad_norm": 10.092483520507812,
|
869 |
+
"learning_rate": 6.162089752176826e-06,
|
870 |
+
"loss": 0.7184,
|
871 |
+
"step": 2950
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 2.689873417721519,
|
875 |
+
"grad_norm": 5.880400657653809,
|
876 |
+
"learning_rate": 5.7434695244474216e-06,
|
877 |
+
"loss": 0.4771,
|
878 |
+
"step": 2975
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 2.7124773960216997,
|
882 |
+
"grad_norm": 0.9661037921905518,
|
883 |
+
"learning_rate": 5.3248492967180175e-06,
|
884 |
+
"loss": 0.4992,
|
885 |
+
"step": 3000
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 2.7350813743218807,
|
889 |
+
"grad_norm": 20.191679000854492,
|
890 |
+
"learning_rate": 4.906229068988614e-06,
|
891 |
+
"loss": 0.6437,
|
892 |
+
"step": 3025
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 2.7576853526220617,
|
896 |
+
"grad_norm": 35.344791412353516,
|
897 |
+
"learning_rate": 4.487608841259209e-06,
|
898 |
+
"loss": 0.5925,
|
899 |
+
"step": 3050
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 2.7802893309222423,
|
903 |
+
"grad_norm": 5.644791126251221,
|
904 |
+
"learning_rate": 4.068988613529806e-06,
|
905 |
+
"loss": 0.574,
|
906 |
+
"step": 3075
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 2.8028933092224233,
|
910 |
+
"grad_norm": 8.687640190124512,
|
911 |
+
"learning_rate": 3.650368385800402e-06,
|
912 |
+
"loss": 0.5918,
|
913 |
+
"step": 3100
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 2.825497287522604,
|
917 |
+
"grad_norm": 19.680980682373047,
|
918 |
+
"learning_rate": 3.231748158070998e-06,
|
919 |
+
"loss": 0.6377,
|
920 |
+
"step": 3125
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 2.848101265822785,
|
924 |
+
"grad_norm": 0.16842712461948395,
|
925 |
+
"learning_rate": 2.813127930341594e-06,
|
926 |
+
"loss": 0.5109,
|
927 |
+
"step": 3150
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 2.8707052441229655,
|
931 |
+
"grad_norm": 1.1660349369049072,
|
932 |
+
"learning_rate": 2.3945077026121904e-06,
|
933 |
+
"loss": 0.4715,
|
934 |
+
"step": 3175
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 2.8933092224231465,
|
938 |
+
"grad_norm": 7.041762351989746,
|
939 |
+
"learning_rate": 1.9758874748827863e-06,
|
940 |
+
"loss": 0.5119,
|
941 |
+
"step": 3200
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 2.9159132007233275,
|
945 |
+
"grad_norm": 27.925931930541992,
|
946 |
+
"learning_rate": 1.5572672471533826e-06,
|
947 |
+
"loss": 0.5079,
|
948 |
+
"step": 3225
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 2.938517179023508,
|
952 |
+
"grad_norm": 1.633520483970642,
|
953 |
+
"learning_rate": 1.1386470194239785e-06,
|
954 |
+
"loss": 0.5943,
|
955 |
+
"step": 3250
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 2.961121157323689,
|
959 |
+
"grad_norm": 9.762001991271973,
|
960 |
+
"learning_rate": 7.200267916945747e-07,
|
961 |
+
"loss": 0.5058,
|
962 |
+
"step": 3275
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 2.9837251356238697,
|
966 |
+
"grad_norm": 23.335742950439453,
|
967 |
+
"learning_rate": 3.014065639651708e-07,
|
968 |
+
"loss": 0.3955,
|
969 |
+
"step": 3300
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 3.0,
|
973 |
+
"eval_accuracy": 0.9077217308152044,
|
974 |
+
"eval_f1_macro": 0.876649943334319,
|
975 |
+
"eval_f1_micro": 0.9077217308152044,
|
976 |
+
"eval_f1_weighted": 0.9087694078887676,
|
977 |
+
"eval_loss": 0.3279833495616913,
|
978 |
+
"eval_precision_macro": 0.8488349060784007,
|
979 |
+
"eval_precision_micro": 0.9077217308152044,
|
980 |
+
"eval_precision_weighted": 0.9121960695781595,
|
981 |
+
"eval_recall_macro": 0.9108354827796887,
|
982 |
+
"eval_recall_micro": 0.9077217308152044,
|
983 |
+
"eval_recall_weighted": 0.9077217308152044,
|
984 |
+
"eval_runtime": 724.2824,
|
985 |
+
"eval_samples_per_second": 5.775,
|
986 |
+
"eval_steps_per_second": 0.362,
|
987 |
+
"step": 3318
|
988 |
+
}
|
989 |
+
],
|
990 |
+
"logging_steps": 25,
|
991 |
+
"max_steps": 3318,
|
992 |
+
"num_input_tokens_seen": 0,
|
993 |
+
"num_train_epochs": 3,
|
994 |
+
"save_steps": 500,
|
995 |
+
"stateful_callbacks": {
|
996 |
+
"EarlyStoppingCallback": {
|
997 |
+
"args": {
|
998 |
+
"early_stopping_patience": 5,
|
999 |
+
"early_stopping_threshold": 0.01
|
1000 |
+
},
|
1001 |
+
"attributes": {
|
1002 |
+
"early_stopping_patience_counter": 0
|
1003 |
+
}
|
1004 |
+
},
|
1005 |
+
"TrainerControl": {
|
1006 |
+
"args": {
|
1007 |
+
"should_epoch_stop": false,
|
1008 |
+
"should_evaluate": false,
|
1009 |
+
"should_log": false,
|
1010 |
+
"should_save": true,
|
1011 |
+
"should_training_stop": true
|
1012 |
+
},
|
1013 |
+
"attributes": {}
|
1014 |
+
}
|
1015 |
+
},
|
1016 |
+
"total_flos": 1745080968172032.0,
|
1017 |
+
"train_batch_size": 8,
|
1018 |
+
"trial_name": null,
|
1019 |
+
"trial_params": null
|
1020 |
+
}
|
checkpoint-3318/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17e5f83b009843f296ef4182ec608574cca58674a944f1cb348ab1701e2ab785
|
3 |
+
size 5176
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/phobert-base-v2",
|
3 |
+
"_num_labels": 6,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "2733522",
|
16 |
+
"1": "2733534",
|
17 |
+
"2": "2733540",
|
18 |
+
"3": "2733546",
|
19 |
+
"4": "2733552",
|
20 |
+
"5": "2733570"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"2733522": 0,
|
26 |
+
"2733534": 1,
|
27 |
+
"2733540": 2,
|
28 |
+
"2733546": 3,
|
29 |
+
"2733552": 4,
|
30 |
+
"2733570": 5
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"max_position_embeddings": 258,
|
34 |
+
"model_type": "roberta",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"pad_token_id": 1,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"problem_type": "single_label_classification",
|
40 |
+
"tokenizer_class": "PhobertTokenizer",
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.42.2",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 64001
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a7f3216c6c1b6968f4f4281cf1783c8a31a1b4bfab39a5c662e9187b46dd9a4
|
3 |
+
size 540035688
|
runs/Jul19_08-08-26_r-daccuong2002-runmay3-jzutjz7y-f713d-ewa9l/events.out.tfevents.1721376507.r-daccuong2002-runmay3-jzutjz7y-f713d-ewa9l.98.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ea7075d60e5d8c86a82e10ce18fdbb1621203473819b2990d6b7b4747daa8dd
|
3 |
+
size 35938
|
runs/Jul19_08-08-26_r-daccuong2002-runmay3-jzutjz7y-f713d-ewa9l/events.out.tfevents.1721396576.r-daccuong2002-runmay3-jzutjz7y-f713d-ewa9l.98.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5043cb141674666e4c7ce9d902bc524d80589143e16617006468bee1e681bd5
|
3 |
+
size 921
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"64000": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "PhobertTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17e5f83b009843f296ef4182ec608574cca58674a944f1cb348ab1701e2ab785
|
3 |
+
size 5176
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "PhoBert-MultiLabel-KMeans/autotrain-data",
|
3 |
+
"model": "vinai/phobert-base-v2",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "PhoBert-MultiLabel-KMeans",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "daccuong2002",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|