daccuong2002
commited on
Commit
•
9d65309
1
Parent(s):
7c28d83
Upload folder using huggingface_hub
Browse files- README.md +36 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- checkpoint-2862/config.json +46 -0
- checkpoint-2862/model.safetensors +3 -0
- checkpoint-2862/optimizer.pt +3 -0
- checkpoint-2862/rng_state.pth +3 -0
- checkpoint-2862/scheduler.pt +3 -0
- checkpoint-2862/trainer_state.json +894 -0
- checkpoint-2862/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- runs/Jul19_08-09-13_r-daccuong2002-runmay4-ndr9vdx7-9196b-ai5k0/events.out.tfevents.1721376553.r-daccuong2002-runmay4-ndr9vdx7-9196b-ai5k0.96.0 +2 -2
- runs/Jul19_08-09-13_r-daccuong2002-runmay4-ndr9vdx7-9196b-ai5k0/events.out.tfevents.1721396911.r-daccuong2002-runmay4-ndr9vdx7-9196b-ai5k0.96.1 +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: 0.3763463497161865
|
17 |
+
|
18 |
+
f1_macro: 0.8947470035372601
|
19 |
+
|
20 |
+
f1_micro: 0.9194358116184557
|
21 |
+
|
22 |
+
f1_weighted: 0.9196235681987903
|
23 |
+
|
24 |
+
precision_macro: 0.8811990938584341
|
25 |
+
|
26 |
+
precision_micro: 0.9194358116184557
|
27 |
+
|
28 |
+
precision_weighted: 0.9204284600348198
|
29 |
+
|
30 |
+
recall_macro: 0.9094848524838759
|
31 |
+
|
32 |
+
recall_micro: 0.9194358116184557
|
33 |
+
|
34 |
+
recall_weighted: 0.9194358116184557
|
35 |
+
|
36 |
+
accuracy: 0.9194358116184557
|
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-2862/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-2862/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:690730a8b78a9ee5be3d7ebe456225c54d25dda514619217793eb22fd46fdc1e
|
3 |
+
size 540035688
|
checkpoint-2862/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:280b3d810035a4f70f5684c889f3e7d1f88692ac9a500f0876f9e61e43969521
|
3 |
+
size 1080185594
|
checkpoint-2862/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:648c11bd463f1932b5d0d5a595849cb4e21b3eef4d71cf3d9193e1dcf0fa752e
|
3 |
+
size 13990
|
checkpoint-2862/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b622fd4477b83a90eb51839651f895031ad1cfb43adca5204ed4178aa770c1f1
|
3 |
+
size 1064
|
checkpoint-2862/trainer_state.json
ADDED
@@ -0,0 +1,894 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3763463497161865,
|
3 |
+
"best_model_checkpoint": "PhoBert-SingleLabel-KMeans/checkpoint-2862",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2862,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02620545073375262,
|
13 |
+
"grad_norm": 3.5584876537323,
|
14 |
+
"learning_rate": 4.355400696864112e-06,
|
15 |
+
"loss": 1.7744,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.05241090146750524,
|
20 |
+
"grad_norm": 3.515974283218384,
|
21 |
+
"learning_rate": 8.710801393728225e-06,
|
22 |
+
"loss": 1.6878,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.07861635220125786,
|
27 |
+
"grad_norm": 3.664238691329956,
|
28 |
+
"learning_rate": 1.3066202090592336e-05,
|
29 |
+
"loss": 1.5996,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.10482180293501048,
|
34 |
+
"grad_norm": 4.6186723709106445,
|
35 |
+
"learning_rate": 1.742160278745645e-05,
|
36 |
+
"loss": 1.4775,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.1310272536687631,
|
41 |
+
"grad_norm": 5.333361625671387,
|
42 |
+
"learning_rate": 2.1777003484320557e-05,
|
43 |
+
"loss": 1.3713,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.15723270440251572,
|
48 |
+
"grad_norm": 10.412248611450195,
|
49 |
+
"learning_rate": 2.6132404181184672e-05,
|
50 |
+
"loss": 1.0538,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.18343815513626835,
|
55 |
+
"grad_norm": 3.342909812927246,
|
56 |
+
"learning_rate": 3.048780487804878e-05,
|
57 |
+
"loss": 0.9225,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.20964360587002095,
|
62 |
+
"grad_norm": 5.6379547119140625,
|
63 |
+
"learning_rate": 3.48432055749129e-05,
|
64 |
+
"loss": 0.8722,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2358490566037736,
|
69 |
+
"grad_norm": 14.341384887695312,
|
70 |
+
"learning_rate": 3.9198606271777003e-05,
|
71 |
+
"loss": 0.8813,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.2620545073375262,
|
76 |
+
"grad_norm": 8.06952953338623,
|
77 |
+
"learning_rate": 4.3554006968641115e-05,
|
78 |
+
"loss": 0.8815,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2882599580712788,
|
83 |
+
"grad_norm": 16.64231300354004,
|
84 |
+
"learning_rate": 4.7909407665505226e-05,
|
85 |
+
"loss": 0.6877,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.31446540880503143,
|
90 |
+
"grad_norm": 10.036324501037598,
|
91 |
+
"learning_rate": 4.974757281553398e-05,
|
92 |
+
"loss": 0.612,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.34067085953878407,
|
97 |
+
"grad_norm": 28.696367263793945,
|
98 |
+
"learning_rate": 4.9262135922330097e-05,
|
99 |
+
"loss": 0.5523,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3668763102725367,
|
104 |
+
"grad_norm": 2.96999192237854,
|
105 |
+
"learning_rate": 4.877669902912622e-05,
|
106 |
+
"loss": 0.5393,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.39308176100628933,
|
111 |
+
"grad_norm": 0.7660526037216187,
|
112 |
+
"learning_rate": 4.829126213592233e-05,
|
113 |
+
"loss": 0.6644,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.4192872117400419,
|
118 |
+
"grad_norm": 23.782712936401367,
|
119 |
+
"learning_rate": 4.780582524271845e-05,
|
120 |
+
"loss": 0.5915,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.44549266247379454,
|
125 |
+
"grad_norm": 14.538418769836426,
|
126 |
+
"learning_rate": 4.732038834951457e-05,
|
127 |
+
"loss": 0.4766,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.4716981132075472,
|
132 |
+
"grad_norm": 1.3607491254806519,
|
133 |
+
"learning_rate": 4.683495145631068e-05,
|
134 |
+
"loss": 0.592,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4979035639412998,
|
139 |
+
"grad_norm": 2.8048417568206787,
|
140 |
+
"learning_rate": 4.63495145631068e-05,
|
141 |
+
"loss": 0.6274,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.5241090146750524,
|
146 |
+
"grad_norm": 294.476806640625,
|
147 |
+
"learning_rate": 4.586407766990292e-05,
|
148 |
+
"loss": 0.4636,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.550314465408805,
|
153 |
+
"grad_norm": 3.9831271171569824,
|
154 |
+
"learning_rate": 4.5378640776699033e-05,
|
155 |
+
"loss": 0.6935,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5765199161425576,
|
160 |
+
"grad_norm": 8.449265480041504,
|
161 |
+
"learning_rate": 4.489320388349515e-05,
|
162 |
+
"loss": 0.5617,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.6027253668763103,
|
167 |
+
"grad_norm": 0.5198196172714233,
|
168 |
+
"learning_rate": 4.440776699029127e-05,
|
169 |
+
"loss": 0.6695,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.6289308176100629,
|
174 |
+
"grad_norm": 0.511917769908905,
|
175 |
+
"learning_rate": 4.3922330097087384e-05,
|
176 |
+
"loss": 0.6177,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.6551362683438156,
|
181 |
+
"grad_norm": 0.4070751368999481,
|
182 |
+
"learning_rate": 4.34368932038835e-05,
|
183 |
+
"loss": 0.4971,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.6813417190775681,
|
188 |
+
"grad_norm": 24.54846954345703,
|
189 |
+
"learning_rate": 4.295145631067961e-05,
|
190 |
+
"loss": 0.3295,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.7075471698113207,
|
195 |
+
"grad_norm": 26.0633487701416,
|
196 |
+
"learning_rate": 4.246601941747573e-05,
|
197 |
+
"loss": 0.4744,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.7337526205450734,
|
202 |
+
"grad_norm": 4.230802059173584,
|
203 |
+
"learning_rate": 4.198058252427184e-05,
|
204 |
+
"loss": 0.4744,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.759958071278826,
|
209 |
+
"grad_norm": 3.7451541423797607,
|
210 |
+
"learning_rate": 4.1495145631067964e-05,
|
211 |
+
"loss": 0.5867,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.7861635220125787,
|
216 |
+
"grad_norm": 8.754020690917969,
|
217 |
+
"learning_rate": 4.100970873786408e-05,
|
218 |
+
"loss": 0.4409,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.8123689727463312,
|
223 |
+
"grad_norm": 0.14476385712623596,
|
224 |
+
"learning_rate": 4.052427184466019e-05,
|
225 |
+
"loss": 0.5824,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.8385744234800838,
|
230 |
+
"grad_norm": 0.38359129428863525,
|
231 |
+
"learning_rate": 4.0038834951456314e-05,
|
232 |
+
"loss": 0.4913,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.8647798742138365,
|
237 |
+
"grad_norm": 34.098060607910156,
|
238 |
+
"learning_rate": 3.955339805825243e-05,
|
239 |
+
"loss": 0.3129,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.8909853249475891,
|
244 |
+
"grad_norm": 3.0660719871520996,
|
245 |
+
"learning_rate": 3.906796116504854e-05,
|
246 |
+
"loss": 0.6103,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.9171907756813418,
|
251 |
+
"grad_norm": 7.5438385009765625,
|
252 |
+
"learning_rate": 3.858252427184466e-05,
|
253 |
+
"loss": 0.495,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.9433962264150944,
|
258 |
+
"grad_norm": 67.45906829833984,
|
259 |
+
"learning_rate": 3.809708737864078e-05,
|
260 |
+
"loss": 0.5724,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.9696016771488469,
|
265 |
+
"grad_norm": 3.6292409896850586,
|
266 |
+
"learning_rate": 3.7611650485436894e-05,
|
267 |
+
"loss": 0.3536,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.9958071278825996,
|
272 |
+
"grad_norm": 29.442237854003906,
|
273 |
+
"learning_rate": 3.712621359223301e-05,
|
274 |
+
"loss": 0.4138,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.0,
|
279 |
+
"eval_accuracy": 0.9000717188620607,
|
280 |
+
"eval_f1_macro": 0.8889047304060399,
|
281 |
+
"eval_f1_micro": 0.9000717188620607,
|
282 |
+
"eval_f1_weighted": 0.9004594891408181,
|
283 |
+
"eval_loss": 0.446470707654953,
|
284 |
+
"eval_precision_macro": 0.8923438114196293,
|
285 |
+
"eval_precision_micro": 0.9000717188620607,
|
286 |
+
"eval_precision_weighted": 0.9041587013504236,
|
287 |
+
"eval_recall_macro": 0.8879970575079902,
|
288 |
+
"eval_recall_micro": 0.9000717188620607,
|
289 |
+
"eval_recall_weighted": 0.9000717188620607,
|
290 |
+
"eval_runtime": 755.376,
|
291 |
+
"eval_samples_per_second": 5.538,
|
292 |
+
"eval_steps_per_second": 0.347,
|
293 |
+
"step": 954
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.0220125786163523,
|
297 |
+
"grad_norm": 15.653645515441895,
|
298 |
+
"learning_rate": 3.664077669902913e-05,
|
299 |
+
"loss": 0.3952,
|
300 |
+
"step": 975
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.0482180293501049,
|
304 |
+
"grad_norm": 0.11768877506256104,
|
305 |
+
"learning_rate": 3.6155339805825244e-05,
|
306 |
+
"loss": 0.3761,
|
307 |
+
"step": 1000
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.0744234800838575,
|
311 |
+
"grad_norm": 2.6586456298828125,
|
312 |
+
"learning_rate": 3.566990291262136e-05,
|
313 |
+
"loss": 0.3241,
|
314 |
+
"step": 1025
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.10062893081761,
|
318 |
+
"grad_norm": 4.2325119972229,
|
319 |
+
"learning_rate": 3.518446601941748e-05,
|
320 |
+
"loss": 0.5266,
|
321 |
+
"step": 1050
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.1268343815513626,
|
325 |
+
"grad_norm": 0.2591557502746582,
|
326 |
+
"learning_rate": 3.4699029126213595e-05,
|
327 |
+
"loss": 0.3688,
|
328 |
+
"step": 1075
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.1530398322851152,
|
332 |
+
"grad_norm": 7.8002777099609375,
|
333 |
+
"learning_rate": 3.421359223300971e-05,
|
334 |
+
"loss": 0.3996,
|
335 |
+
"step": 1100
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.179245283018868,
|
339 |
+
"grad_norm": 7.753486633300781,
|
340 |
+
"learning_rate": 3.372815533980583e-05,
|
341 |
+
"loss": 0.5435,
|
342 |
+
"step": 1125
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.2054507337526206,
|
346 |
+
"grad_norm": 4.600539684295654,
|
347 |
+
"learning_rate": 3.3242718446601945e-05,
|
348 |
+
"loss": 0.4125,
|
349 |
+
"step": 1150
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.2316561844863732,
|
353 |
+
"grad_norm": 0.507254421710968,
|
354 |
+
"learning_rate": 3.275728155339806e-05,
|
355 |
+
"loss": 0.3485,
|
356 |
+
"step": 1175
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.2578616352201257,
|
360 |
+
"grad_norm": 2.2480947971343994,
|
361 |
+
"learning_rate": 3.227184466019418e-05,
|
362 |
+
"loss": 0.3006,
|
363 |
+
"step": 1200
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.2840670859538785,
|
367 |
+
"grad_norm": 0.17361511290073395,
|
368 |
+
"learning_rate": 3.1786407766990296e-05,
|
369 |
+
"loss": 0.372,
|
370 |
+
"step": 1225
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.310272536687631,
|
374 |
+
"grad_norm": 2.2198197841644287,
|
375 |
+
"learning_rate": 3.130097087378641e-05,
|
376 |
+
"loss": 0.4539,
|
377 |
+
"step": 1250
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.3364779874213837,
|
381 |
+
"grad_norm": 2.0315468311309814,
|
382 |
+
"learning_rate": 3.0815533980582525e-05,
|
383 |
+
"loss": 0.482,
|
384 |
+
"step": 1275
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.3626834381551363,
|
388 |
+
"grad_norm": 8.348484992980957,
|
389 |
+
"learning_rate": 3.0330097087378646e-05,
|
390 |
+
"loss": 0.3263,
|
391 |
+
"step": 1300
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 1.3888888888888888,
|
395 |
+
"grad_norm": 7.209967136383057,
|
396 |
+
"learning_rate": 2.9844660194174757e-05,
|
397 |
+
"loss": 0.332,
|
398 |
+
"step": 1325
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.4150943396226414,
|
402 |
+
"grad_norm": 56.43852615356445,
|
403 |
+
"learning_rate": 2.9359223300970872e-05,
|
404 |
+
"loss": 0.5554,
|
405 |
+
"step": 1350
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.441299790356394,
|
409 |
+
"grad_norm": 1.4395267963409424,
|
410 |
+
"learning_rate": 2.887378640776699e-05,
|
411 |
+
"loss": 0.4749,
|
412 |
+
"step": 1375
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.4675052410901468,
|
416 |
+
"grad_norm": 70.63890838623047,
|
417 |
+
"learning_rate": 2.8388349514563105e-05,
|
418 |
+
"loss": 0.4356,
|
419 |
+
"step": 1400
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.4937106918238994,
|
423 |
+
"grad_norm": 52.49846649169922,
|
424 |
+
"learning_rate": 2.7902912621359222e-05,
|
425 |
+
"loss": 0.3524,
|
426 |
+
"step": 1425
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 1.519916142557652,
|
430 |
+
"grad_norm": 39.48180389404297,
|
431 |
+
"learning_rate": 2.741747572815534e-05,
|
432 |
+
"loss": 0.4155,
|
433 |
+
"step": 1450
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 1.5461215932914047,
|
437 |
+
"grad_norm": 4.6654510498046875,
|
438 |
+
"learning_rate": 2.6932038834951455e-05,
|
439 |
+
"loss": 0.3802,
|
440 |
+
"step": 1475
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.5723270440251573,
|
444 |
+
"grad_norm": 2.445298433303833,
|
445 |
+
"learning_rate": 2.6446601941747573e-05,
|
446 |
+
"loss": 0.2013,
|
447 |
+
"step": 1500
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.59853249475891,
|
451 |
+
"grad_norm": 0.5410274267196655,
|
452 |
+
"learning_rate": 2.596116504854369e-05,
|
453 |
+
"loss": 0.3016,
|
454 |
+
"step": 1525
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 1.6247379454926625,
|
458 |
+
"grad_norm": 6.175892353057861,
|
459 |
+
"learning_rate": 2.5475728155339806e-05,
|
460 |
+
"loss": 0.4059,
|
461 |
+
"step": 1550
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 1.650943396226415,
|
465 |
+
"grad_norm": 19.350805282592773,
|
466 |
+
"learning_rate": 2.4990291262135923e-05,
|
467 |
+
"loss": 0.2649,
|
468 |
+
"step": 1575
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 1.6771488469601676,
|
472 |
+
"grad_norm": 0.5931205749511719,
|
473 |
+
"learning_rate": 2.450485436893204e-05,
|
474 |
+
"loss": 0.2931,
|
475 |
+
"step": 1600
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 1.7033542976939202,
|
479 |
+
"grad_norm": 20.36564826965332,
|
480 |
+
"learning_rate": 2.4019417475728156e-05,
|
481 |
+
"loss": 0.2659,
|
482 |
+
"step": 1625
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.7295597484276728,
|
486 |
+
"grad_norm": 0.1273786723613739,
|
487 |
+
"learning_rate": 2.3533980582524274e-05,
|
488 |
+
"loss": 0.2192,
|
489 |
+
"step": 1650
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.7557651991614256,
|
493 |
+
"grad_norm": 39.38661193847656,
|
494 |
+
"learning_rate": 2.304854368932039e-05,
|
495 |
+
"loss": 0.4232,
|
496 |
+
"step": 1675
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 1.7819706498951782,
|
500 |
+
"grad_norm": 35.051902770996094,
|
501 |
+
"learning_rate": 2.2563106796116507e-05,
|
502 |
+
"loss": 0.4047,
|
503 |
+
"step": 1700
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 1.808176100628931,
|
507 |
+
"grad_norm": 10.8402738571167,
|
508 |
+
"learning_rate": 2.2077669902912624e-05,
|
509 |
+
"loss": 0.257,
|
510 |
+
"step": 1725
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 1.8343815513626835,
|
514 |
+
"grad_norm": 18.704975128173828,
|
515 |
+
"learning_rate": 2.159223300970874e-05,
|
516 |
+
"loss": 0.3526,
|
517 |
+
"step": 1750
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 1.8605870020964361,
|
521 |
+
"grad_norm": 0.09916484355926514,
|
522 |
+
"learning_rate": 2.1106796116504857e-05,
|
523 |
+
"loss": 0.3903,
|
524 |
+
"step": 1775
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 1.8867924528301887,
|
528 |
+
"grad_norm": 4.514852046966553,
|
529 |
+
"learning_rate": 2.062135922330097e-05,
|
530 |
+
"loss": 0.3345,
|
531 |
+
"step": 1800
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 1.9129979035639413,
|
535 |
+
"grad_norm": 31.562023162841797,
|
536 |
+
"learning_rate": 2.0135922330097086e-05,
|
537 |
+
"loss": 0.5511,
|
538 |
+
"step": 1825
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.9392033542976939,
|
542 |
+
"grad_norm": 13.065159797668457,
|
543 |
+
"learning_rate": 1.9650485436893204e-05,
|
544 |
+
"loss": 0.2387,
|
545 |
+
"step": 1850
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 1.9654088050314464,
|
549 |
+
"grad_norm": 41.689964294433594,
|
550 |
+
"learning_rate": 1.9165048543689322e-05,
|
551 |
+
"loss": 0.3024,
|
552 |
+
"step": 1875
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 1.991614255765199,
|
556 |
+
"grad_norm": 10.776809692382812,
|
557 |
+
"learning_rate": 1.8679611650485437e-05,
|
558 |
+
"loss": 0.3133,
|
559 |
+
"step": 1900
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 2.0,
|
563 |
+
"eval_accuracy": 0.9022232847238824,
|
564 |
+
"eval_f1_macro": 0.8791017264419937,
|
565 |
+
"eval_f1_micro": 0.9022232847238824,
|
566 |
+
"eval_f1_weighted": 0.9030036030460146,
|
567 |
+
"eval_loss": 0.4108516573905945,
|
568 |
+
"eval_precision_macro": 0.8552051719676482,
|
569 |
+
"eval_precision_micro": 0.9022232847238824,
|
570 |
+
"eval_precision_weighted": 0.906337005319111,
|
571 |
+
"eval_recall_macro": 0.9078028911862802,
|
572 |
+
"eval_recall_micro": 0.9022232847238824,
|
573 |
+
"eval_recall_weighted": 0.9022232847238824,
|
574 |
+
"eval_runtime": 882.9584,
|
575 |
+
"eval_samples_per_second": 4.737,
|
576 |
+
"eval_steps_per_second": 0.297,
|
577 |
+
"step": 1908
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 2.0178197064989516,
|
581 |
+
"grad_norm": 7.140912055969238,
|
582 |
+
"learning_rate": 1.8194174757281555e-05,
|
583 |
+
"loss": 0.2435,
|
584 |
+
"step": 1925
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 2.0440251572327046,
|
588 |
+
"grad_norm": 13.220586776733398,
|
589 |
+
"learning_rate": 1.770873786407767e-05,
|
590 |
+
"loss": 0.2558,
|
591 |
+
"step": 1950
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 2.070230607966457,
|
595 |
+
"grad_norm": 4.269901275634766,
|
596 |
+
"learning_rate": 1.7223300970873787e-05,
|
597 |
+
"loss": 0.2658,
|
598 |
+
"step": 1975
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 2.0964360587002098,
|
602 |
+
"grad_norm": 0.11073017865419388,
|
603 |
+
"learning_rate": 1.6737864077669905e-05,
|
604 |
+
"loss": 0.1196,
|
605 |
+
"step": 2000
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 2.1226415094339623,
|
609 |
+
"grad_norm": 0.16363948583602905,
|
610 |
+
"learning_rate": 1.625242718446602e-05,
|
611 |
+
"loss": 0.3133,
|
612 |
+
"step": 2025
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 2.148846960167715,
|
616 |
+
"grad_norm": 0.40826770663261414,
|
617 |
+
"learning_rate": 1.5766990291262138e-05,
|
618 |
+
"loss": 0.2075,
|
619 |
+
"step": 2050
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 2.1750524109014675,
|
623 |
+
"grad_norm": 0.336016982793808,
|
624 |
+
"learning_rate": 1.5281553398058256e-05,
|
625 |
+
"loss": 0.2866,
|
626 |
+
"step": 2075
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 2.20125786163522,
|
630 |
+
"grad_norm": 0.0927320122718811,
|
631 |
+
"learning_rate": 1.479611650485437e-05,
|
632 |
+
"loss": 0.2213,
|
633 |
+
"step": 2100
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 2.2274633123689727,
|
637 |
+
"grad_norm": 0.058554600924253464,
|
638 |
+
"learning_rate": 1.4310679611650485e-05,
|
639 |
+
"loss": 0.1864,
|
640 |
+
"step": 2125
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 2.2536687631027252,
|
644 |
+
"grad_norm": 0.06633560359477997,
|
645 |
+
"learning_rate": 1.3825242718446601e-05,
|
646 |
+
"loss": 0.2221,
|
647 |
+
"step": 2150
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 2.279874213836478,
|
651 |
+
"grad_norm": 24.724422454833984,
|
652 |
+
"learning_rate": 1.3339805825242719e-05,
|
653 |
+
"loss": 0.2335,
|
654 |
+
"step": 2175
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 2.3060796645702304,
|
658 |
+
"grad_norm": 0.0917593464255333,
|
659 |
+
"learning_rate": 1.2854368932038835e-05,
|
660 |
+
"loss": 0.2385,
|
661 |
+
"step": 2200
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 2.3322851153039834,
|
665 |
+
"grad_norm": 0.06267809122800827,
|
666 |
+
"learning_rate": 1.2368932038834952e-05,
|
667 |
+
"loss": 0.2185,
|
668 |
+
"step": 2225
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 2.358490566037736,
|
672 |
+
"grad_norm": 0.05579007416963577,
|
673 |
+
"learning_rate": 1.1883495145631068e-05,
|
674 |
+
"loss": 0.2324,
|
675 |
+
"step": 2250
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 2.3846960167714886,
|
679 |
+
"grad_norm": 3.492902994155884,
|
680 |
+
"learning_rate": 1.1398058252427186e-05,
|
681 |
+
"loss": 0.4154,
|
682 |
+
"step": 2275
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 2.410901467505241,
|
686 |
+
"grad_norm": 0.16507238149642944,
|
687 |
+
"learning_rate": 1.0912621359223302e-05,
|
688 |
+
"loss": 0.2711,
|
689 |
+
"step": 2300
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 2.4371069182389937,
|
693 |
+
"grad_norm": 2.3962414264678955,
|
694 |
+
"learning_rate": 1.0427184466019418e-05,
|
695 |
+
"loss": 0.2866,
|
696 |
+
"step": 2325
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 2.4633123689727463,
|
700 |
+
"grad_norm": 2.307986259460449,
|
701 |
+
"learning_rate": 9.941747572815535e-06,
|
702 |
+
"loss": 0.4232,
|
703 |
+
"step": 2350
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 2.489517819706499,
|
707 |
+
"grad_norm": 8.218997955322266,
|
708 |
+
"learning_rate": 9.45631067961165e-06,
|
709 |
+
"loss": 0.2528,
|
710 |
+
"step": 2375
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 2.5157232704402515,
|
714 |
+
"grad_norm": 0.10614609718322754,
|
715 |
+
"learning_rate": 8.970873786407767e-06,
|
716 |
+
"loss": 0.0532,
|
717 |
+
"step": 2400
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 2.541928721174004,
|
721 |
+
"grad_norm": 6.59151554107666,
|
722 |
+
"learning_rate": 8.485436893203883e-06,
|
723 |
+
"loss": 0.2535,
|
724 |
+
"step": 2425
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 2.568134171907757,
|
728 |
+
"grad_norm": 0.46849825978279114,
|
729 |
+
"learning_rate": 8.000000000000001e-06,
|
730 |
+
"loss": 0.2503,
|
731 |
+
"step": 2450
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 2.5943396226415096,
|
735 |
+
"grad_norm": 2.4090096950531006,
|
736 |
+
"learning_rate": 7.514563106796118e-06,
|
737 |
+
"loss": 0.345,
|
738 |
+
"step": 2475
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 2.620545073375262,
|
742 |
+
"grad_norm": 19.20216941833496,
|
743 |
+
"learning_rate": 7.029126213592234e-06,
|
744 |
+
"loss": 0.1694,
|
745 |
+
"step": 2500
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 2.646750524109015,
|
749 |
+
"grad_norm": 10.444535255432129,
|
750 |
+
"learning_rate": 6.543689320388349e-06,
|
751 |
+
"loss": 0.2558,
|
752 |
+
"step": 2525
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 2.6729559748427674,
|
756 |
+
"grad_norm": 0.15079370141029358,
|
757 |
+
"learning_rate": 6.058252427184466e-06,
|
758 |
+
"loss": 0.2905,
|
759 |
+
"step": 2550
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 2.69916142557652,
|
763 |
+
"grad_norm": 0.0647541806101799,
|
764 |
+
"learning_rate": 5.572815533980583e-06,
|
765 |
+
"loss": 0.1197,
|
766 |
+
"step": 2575
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 2.7253668763102725,
|
770 |
+
"grad_norm": 50.22942352294922,
|
771 |
+
"learning_rate": 5.087378640776699e-06,
|
772 |
+
"loss": 0.159,
|
773 |
+
"step": 2600
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 2.751572327044025,
|
777 |
+
"grad_norm": 0.06316754221916199,
|
778 |
+
"learning_rate": 4.601941747572816e-06,
|
779 |
+
"loss": 0.2032,
|
780 |
+
"step": 2625
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 2.7777777777777777,
|
784 |
+
"grad_norm": 0.06050650402903557,
|
785 |
+
"learning_rate": 4.116504854368932e-06,
|
786 |
+
"loss": 0.2446,
|
787 |
+
"step": 2650
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 2.8039832285115303,
|
791 |
+
"grad_norm": 7.044517993927002,
|
792 |
+
"learning_rate": 3.6310679611650486e-06,
|
793 |
+
"loss": 0.2692,
|
794 |
+
"step": 2675
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 2.830188679245283,
|
798 |
+
"grad_norm": 0.36540356278419495,
|
799 |
+
"learning_rate": 3.1456310679611653e-06,
|
800 |
+
"loss": 0.3174,
|
801 |
+
"step": 2700
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 2.8563941299790354,
|
805 |
+
"grad_norm": 1.1024131774902344,
|
806 |
+
"learning_rate": 2.660194174757282e-06,
|
807 |
+
"loss": 0.2608,
|
808 |
+
"step": 2725
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 2.882599580712788,
|
812 |
+
"grad_norm": 4.021923065185547,
|
813 |
+
"learning_rate": 2.1747572815533982e-06,
|
814 |
+
"loss": 0.0811,
|
815 |
+
"step": 2750
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 2.908805031446541,
|
819 |
+
"grad_norm": 0.10723225027322769,
|
820 |
+
"learning_rate": 1.6893203883495145e-06,
|
821 |
+
"loss": 0.097,
|
822 |
+
"step": 2775
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 2.9350104821802936,
|
826 |
+
"grad_norm": 0.07229924201965332,
|
827 |
+
"learning_rate": 1.2038834951456312e-06,
|
828 |
+
"loss": 0.3037,
|
829 |
+
"step": 2800
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 2.961215932914046,
|
833 |
+
"grad_norm": 38.69488525390625,
|
834 |
+
"learning_rate": 7.184466019417476e-07,
|
835 |
+
"loss": 0.2884,
|
836 |
+
"step": 2825
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 2.9874213836477987,
|
840 |
+
"grad_norm": 1.4321260452270508,
|
841 |
+
"learning_rate": 2.330097087378641e-07,
|
842 |
+
"loss": 0.3024,
|
843 |
+
"step": 2850
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 3.0,
|
847 |
+
"eval_accuracy": 0.9194358116184557,
|
848 |
+
"eval_f1_macro": 0.8947470035372601,
|
849 |
+
"eval_f1_micro": 0.9194358116184557,
|
850 |
+
"eval_f1_weighted": 0.9196235681987903,
|
851 |
+
"eval_loss": 0.3763463497161865,
|
852 |
+
"eval_precision_macro": 0.8811990938584341,
|
853 |
+
"eval_precision_micro": 0.9194358116184557,
|
854 |
+
"eval_precision_weighted": 0.9204284600348198,
|
855 |
+
"eval_recall_macro": 0.9094848524838759,
|
856 |
+
"eval_recall_micro": 0.9194358116184557,
|
857 |
+
"eval_recall_weighted": 0.9194358116184557,
|
858 |
+
"eval_runtime": 833.3591,
|
859 |
+
"eval_samples_per_second": 5.019,
|
860 |
+
"eval_steps_per_second": 0.314,
|
861 |
+
"step": 2862
|
862 |
+
}
|
863 |
+
],
|
864 |
+
"logging_steps": 25,
|
865 |
+
"max_steps": 2862,
|
866 |
+
"num_input_tokens_seen": 0,
|
867 |
+
"num_train_epochs": 3,
|
868 |
+
"save_steps": 500,
|
869 |
+
"stateful_callbacks": {
|
870 |
+
"EarlyStoppingCallback": {
|
871 |
+
"args": {
|
872 |
+
"early_stopping_patience": 5,
|
873 |
+
"early_stopping_threshold": 0.01
|
874 |
+
},
|
875 |
+
"attributes": {
|
876 |
+
"early_stopping_patience_counter": 0
|
877 |
+
}
|
878 |
+
},
|
879 |
+
"TrainerControl": {
|
880 |
+
"args": {
|
881 |
+
"should_epoch_stop": false,
|
882 |
+
"should_evaluate": false,
|
883 |
+
"should_log": false,
|
884 |
+
"should_save": true,
|
885 |
+
"should_training_stop": true
|
886 |
+
},
|
887 |
+
"attributes": {}
|
888 |
+
}
|
889 |
+
},
|
890 |
+
"total_flos": 1505115067765248.0,
|
891 |
+
"train_batch_size": 8,
|
892 |
+
"trial_name": null,
|
893 |
+
"trial_params": null
|
894 |
+
}
|
checkpoint-2862/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b59ed06c5ec53c5e419a23d037aee62a6cf11f8e3f2206f5e7df1ebb9e9894f6
|
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 sha256:690730a8b78a9ee5be3d7ebe456225c54d25dda514619217793eb22fd46fdc1e
|
3 |
+
size 540035688
|
runs/Jul19_08-09-13_r-daccuong2002-runmay4-ndr9vdx7-9196b-ai5k0/events.out.tfevents.1721376553.r-daccuong2002-runmay4-ndr9vdx7-9196b-ai5k0.96.0
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 sha256:917e2c7feb5117041c54a4a92c165f8f090785582141f7e825d6cc7c94669cda
|
3 |
+
size 32143
|
runs/Jul19_08-09-13_r-daccuong2002-runmay4-ndr9vdx7-9196b-ai5k0/events.out.tfevents.1721396911.r-daccuong2002-runmay4-ndr9vdx7-9196b-ai5k0.96.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e950e3e6d50c4bd9cb2cd07dfea7e78e0285219d08b4c3659de7d5c5ef1990d
|
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:b59ed06c5ec53c5e419a23d037aee62a6cf11f8e3f2206f5e7df1ebb9e9894f6
|
3 |
+
size 5176
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "PhoBert-SingleLabel-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-SingleLabel-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
|
|