DarkPhantom323
commited on
Commit
•
a07457e
1
Parent(s):
c5b494b
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-3246/config.json +37 -0
- checkpoint-3246/model.safetensors +3 -0
- checkpoint-3246/optimizer.pt +3 -0
- checkpoint-3246/rng_state.pth +3 -0
- checkpoint-3246/scheduler.pt +3 -0
- checkpoint-3246/trainer_state.json +978 -0
- checkpoint-3246/training_args.bin +3 -0
- config.json +37 -0
- model.safetensors +3 -0
- runs/Apr30_06-35-24_r-darkphantom323-nlp-8t0qt349-3e504-sss3p/events.out.tfevents.1714458926.r-darkphantom323-nlp-8t0qt349-3e504-sss3p.85.0 +2 -2
- runs/Apr30_06-35-24_r-darkphantom323-nlp-8t0qt349-3e504-sss3p/events.out.tfevents.1714470322.r-darkphantom323-nlp-8t0qt349-3e504-sss3p.85.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +28 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
widget:
|
7 |
+
- text: "I love AutoTrain"
|
8 |
+
datasets:
|
9 |
+
- actsa-distilbert/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 1.0657285451889038
|
18 |
+
|
19 |
+
f1_macro: 0.2095479509928179
|
20 |
+
|
21 |
+
f1_micro: 0.4584103512014787
|
22 |
+
|
23 |
+
f1_weighted: 0.2881768494245037
|
24 |
+
|
25 |
+
precision_macro: 0.1528034504004929
|
26 |
+
|
27 |
+
precision_micro: 0.4584103512014787
|
28 |
+
|
29 |
+
precision_weighted: 0.21014005008866307
|
30 |
+
|
31 |
+
recall_macro: 0.3333333333333333
|
32 |
+
|
33 |
+
recall_micro: 0.4584103512014787
|
34 |
+
|
35 |
+
recall_weighted: 0.4584103512014787
|
36 |
+
|
37 |
+
accuracy: 0.4584103512014787
|
checkpoint-3246/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-multilingual-cased",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForSequenceClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "-1",
|
14 |
+
"1": "0",
|
15 |
+
"2": "1"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"-1": 0,
|
20 |
+
"0": 1,
|
21 |
+
"1": 2
|
22 |
+
},
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "distilbert",
|
25 |
+
"n_heads": 12,
|
26 |
+
"n_layers": 6,
|
27 |
+
"output_past": true,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"qa_dropout": 0.1,
|
31 |
+
"seq_classif_dropout": 0.2,
|
32 |
+
"sinusoidal_pos_embds": false,
|
33 |
+
"tie_weights_": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.40.1",
|
36 |
+
"vocab_size": 119547
|
37 |
+
}
|
checkpoint-3246/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5005299aa0690636d670f974407b6164dda3900224afc1feaccc28066f9c637
|
3 |
+
size 541320452
|
checkpoint-3246/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:718d20a7dee401162ae0de314ecd95a332e4c5b17328560ab242ed1913cf4010
|
3 |
+
size 1082700154
|
checkpoint-3246/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5811efc33f7f2680665fe38c6d29ee1ed2135594bce17534a487ccdf35852fad
|
3 |
+
size 13990
|
checkpoint-3246/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:112b844cc222aa9232c1da2152f79efbd82e5d57d6c3afdf39275cc9404b52d7
|
3 |
+
size 1064
|
checkpoint-3246/trainer_state.json
ADDED
@@ -0,0 +1,978 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0657285451889038,
|
3 |
+
"best_model_checkpoint": "actsa-distilbert/checkpoint-3246",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3246,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02310536044362292,
|
13 |
+
"grad_norm": 2.318068265914917,
|
14 |
+
"learning_rate": 3.846153846153846e-05,
|
15 |
+
"loss": 1.0841,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04621072088724584,
|
20 |
+
"grad_norm": 3.620454788208008,
|
21 |
+
"learning_rate": 7.692307692307693e-05,
|
22 |
+
"loss": 1.0888,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06931608133086876,
|
27 |
+
"grad_norm": 2.4006574153900146,
|
28 |
+
"learning_rate": 0.0001153846153846154,
|
29 |
+
"loss": 1.0742,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09242144177449169,
|
34 |
+
"grad_norm": 4.676277160644531,
|
35 |
+
"learning_rate": 0.00015384615384615385,
|
36 |
+
"loss": 1.0871,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.11552680221811461,
|
41 |
+
"grad_norm": 6.01164436340332,
|
42 |
+
"learning_rate": 0.00019230769230769233,
|
43 |
+
"loss": 1.1146,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.13863216266173753,
|
48 |
+
"grad_norm": 2.2937514781951904,
|
49 |
+
"learning_rate": 0.0002307692307692308,
|
50 |
+
"loss": 1.0578,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.16173752310536044,
|
55 |
+
"grad_norm": 2.6013343334198,
|
56 |
+
"learning_rate": 0.0002692307692307692,
|
57 |
+
"loss": 1.0571,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.18484288354898337,
|
62 |
+
"grad_norm": 3.571342945098877,
|
63 |
+
"learning_rate": 0.0003076923076923077,
|
64 |
+
"loss": 1.145,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.20794824399260628,
|
69 |
+
"grad_norm": 2.3125054836273193,
|
70 |
+
"learning_rate": 0.00034615384615384613,
|
71 |
+
"loss": 1.0901,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.23105360443622922,
|
76 |
+
"grad_norm": 5.343853950500488,
|
77 |
+
"learning_rate": 0.00038461538461538467,
|
78 |
+
"loss": 1.0198,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2541589648798521,
|
83 |
+
"grad_norm": 4.148077487945557,
|
84 |
+
"learning_rate": 0.0004230769230769231,
|
85 |
+
"loss": 1.0066,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.27726432532347506,
|
90 |
+
"grad_norm": 3.7557380199432373,
|
91 |
+
"learning_rate": 0.0004615384615384616,
|
92 |
+
"loss": 1.0734,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.300369685767098,
|
97 |
+
"grad_norm": 3.485323190689087,
|
98 |
+
"learning_rate": 0.0005,
|
99 |
+
"loss": 1.0569,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3234750462107209,
|
104 |
+
"grad_norm": 2.63746976852417,
|
105 |
+
"learning_rate": 0.0004957206436152003,
|
106 |
+
"loss": 1.1081,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.3465804066543438,
|
111 |
+
"grad_norm": 5.485255718231201,
|
112 |
+
"learning_rate": 0.0004914412872304005,
|
113 |
+
"loss": 1.1346,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.36968576709796674,
|
118 |
+
"grad_norm": 2.920285940170288,
|
119 |
+
"learning_rate": 0.00048716193084560086,
|
120 |
+
"loss": 1.0998,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.3927911275415896,
|
125 |
+
"grad_norm": 2.696606397628784,
|
126 |
+
"learning_rate": 0.0004828825744608011,
|
127 |
+
"loss": 1.1216,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.41589648798521256,
|
132 |
+
"grad_norm": 2.0741255283355713,
|
133 |
+
"learning_rate": 0.0004786032180760014,
|
134 |
+
"loss": 1.1092,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4390018484288355,
|
139 |
+
"grad_norm": 2.102992534637451,
|
140 |
+
"learning_rate": 0.0004743238616912017,
|
141 |
+
"loss": 1.1172,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.46210720887245843,
|
146 |
+
"grad_norm": 1.4443374872207642,
|
147 |
+
"learning_rate": 0.0004700445053064019,
|
148 |
+
"loss": 1.0929,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.4852125693160813,
|
153 |
+
"grad_norm": 2.7878777980804443,
|
154 |
+
"learning_rate": 0.0004657651489216022,
|
155 |
+
"loss": 1.125,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5083179297597042,
|
160 |
+
"grad_norm": 2.387270212173462,
|
161 |
+
"learning_rate": 0.00046148579253680244,
|
162 |
+
"loss": 1.1069,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5314232902033271,
|
167 |
+
"grad_norm": 2.1369564533233643,
|
168 |
+
"learning_rate": 0.00045720643615200274,
|
169 |
+
"loss": 1.085,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5545286506469501,
|
174 |
+
"grad_norm": 2.407505989074707,
|
175 |
+
"learning_rate": 0.00045292707976720304,
|
176 |
+
"loss": 1.095,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.577634011090573,
|
181 |
+
"grad_norm": 1.3333139419555664,
|
182 |
+
"learning_rate": 0.0004486477233824033,
|
183 |
+
"loss": 1.1035,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.600739371534196,
|
188 |
+
"grad_norm": 1.891635537147522,
|
189 |
+
"learning_rate": 0.0004443683669976036,
|
190 |
+
"loss": 0.9419,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6238447319778189,
|
195 |
+
"grad_norm": 2.536003589630127,
|
196 |
+
"learning_rate": 0.00044008901061280383,
|
197 |
+
"loss": 1.1685,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.6469500924214417,
|
202 |
+
"grad_norm": 2.3016841411590576,
|
203 |
+
"learning_rate": 0.00043580965422800413,
|
204 |
+
"loss": 1.0619,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.6700554528650647,
|
209 |
+
"grad_norm": 1.4672470092773438,
|
210 |
+
"learning_rate": 0.00043153029784320443,
|
211 |
+
"loss": 1.1276,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.6931608133086876,
|
216 |
+
"grad_norm": 2.2047739028930664,
|
217 |
+
"learning_rate": 0.0004272509414584047,
|
218 |
+
"loss": 1.0428,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7162661737523105,
|
223 |
+
"grad_norm": 4.394761562347412,
|
224 |
+
"learning_rate": 0.000422971585073605,
|
225 |
+
"loss": 1.082,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.7393715341959335,
|
230 |
+
"grad_norm": 1.6812162399291992,
|
231 |
+
"learning_rate": 0.00041869222868880517,
|
232 |
+
"loss": 1.1325,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.7624768946395564,
|
237 |
+
"grad_norm": 2.4136714935302734,
|
238 |
+
"learning_rate": 0.00041441287230400547,
|
239 |
+
"loss": 1.0486,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.7855822550831792,
|
244 |
+
"grad_norm": 1.2103418111801147,
|
245 |
+
"learning_rate": 0.00041013351591920577,
|
246 |
+
"loss": 1.093,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.8086876155268022,
|
251 |
+
"grad_norm": 2.494950771331787,
|
252 |
+
"learning_rate": 0.000405854159534406,
|
253 |
+
"loss": 1.0638,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.8317929759704251,
|
258 |
+
"grad_norm": 1.8322207927703857,
|
259 |
+
"learning_rate": 0.0004015748031496063,
|
260 |
+
"loss": 0.9711,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.8548983364140481,
|
265 |
+
"grad_norm": 2.9408106803894043,
|
266 |
+
"learning_rate": 0.00039729544676480656,
|
267 |
+
"loss": 1.1413,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.878003696857671,
|
272 |
+
"grad_norm": 1.0680229663848877,
|
273 |
+
"learning_rate": 0.00039301609038000686,
|
274 |
+
"loss": 1.0609,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.9011090573012939,
|
279 |
+
"grad_norm": 1.952222466468811,
|
280 |
+
"learning_rate": 0.00038873673399520716,
|
281 |
+
"loss": 1.0954,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.9242144177449169,
|
286 |
+
"grad_norm": 3.1969923973083496,
|
287 |
+
"learning_rate": 0.0003844573776104074,
|
288 |
+
"loss": 1.0895,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.9473197781885397,
|
293 |
+
"grad_norm": 2.0018506050109863,
|
294 |
+
"learning_rate": 0.0003801780212256077,
|
295 |
+
"loss": 1.0697,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.9704251386321626,
|
300 |
+
"grad_norm": 2.0683329105377197,
|
301 |
+
"learning_rate": 0.00037589866484080795,
|
302 |
+
"loss": 1.0999,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.9935304990757856,
|
307 |
+
"grad_norm": 2.1113333702087402,
|
308 |
+
"learning_rate": 0.00037161930845600825,
|
309 |
+
"loss": 1.1089,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.0,
|
314 |
+
"eval_accuracy": 0.4584103512014787,
|
315 |
+
"eval_f1_macro": 0.2095479509928179,
|
316 |
+
"eval_f1_micro": 0.4584103512014787,
|
317 |
+
"eval_f1_weighted": 0.2881768494245037,
|
318 |
+
"eval_loss": 1.0685529708862305,
|
319 |
+
"eval_precision_macro": 0.1528034504004929,
|
320 |
+
"eval_precision_micro": 0.4584103512014787,
|
321 |
+
"eval_precision_weighted": 0.21014005008866307,
|
322 |
+
"eval_recall_macro": 0.3333333333333333,
|
323 |
+
"eval_recall_micro": 0.4584103512014787,
|
324 |
+
"eval_recall_weighted": 0.4584103512014787,
|
325 |
+
"eval_runtime": 103.9446,
|
326 |
+
"eval_samples_per_second": 10.409,
|
327 |
+
"eval_steps_per_second": 1.308,
|
328 |
+
"step": 1082
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.0166358595194085,
|
332 |
+
"grad_norm": 2.078071117401123,
|
333 |
+
"learning_rate": 0.0003673399520712085,
|
334 |
+
"loss": 1.0538,
|
335 |
+
"step": 1100
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.0397412199630314,
|
339 |
+
"grad_norm": 1.2932239770889282,
|
340 |
+
"learning_rate": 0.00036306059568640874,
|
341 |
+
"loss": 1.1108,
|
342 |
+
"step": 1125
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.0628465804066543,
|
346 |
+
"grad_norm": 1.8026275634765625,
|
347 |
+
"learning_rate": 0.00035878123930160904,
|
348 |
+
"loss": 1.0782,
|
349 |
+
"step": 1150
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.0859519408502774,
|
353 |
+
"grad_norm": 2.0047168731689453,
|
354 |
+
"learning_rate": 0.0003545018829168093,
|
355 |
+
"loss": 1.0754,
|
356 |
+
"step": 1175
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.1090573012939002,
|
360 |
+
"grad_norm": 2.5215866565704346,
|
361 |
+
"learning_rate": 0.0003502225265320096,
|
362 |
+
"loss": 1.0822,
|
363 |
+
"step": 1200
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.1321626617375231,
|
367 |
+
"grad_norm": 1.7528326511383057,
|
368 |
+
"learning_rate": 0.0003459431701472099,
|
369 |
+
"loss": 1.0956,
|
370 |
+
"step": 1225
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.155268022181146,
|
374 |
+
"grad_norm": 2.345102548599243,
|
375 |
+
"learning_rate": 0.00034166381376241013,
|
376 |
+
"loss": 1.0284,
|
377 |
+
"step": 1250
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.1783733826247689,
|
381 |
+
"grad_norm": 2.051119327545166,
|
382 |
+
"learning_rate": 0.00033738445737761043,
|
383 |
+
"loss": 1.0811,
|
384 |
+
"step": 1275
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.201478743068392,
|
388 |
+
"grad_norm": 2.405728340148926,
|
389 |
+
"learning_rate": 0.0003331051009928107,
|
390 |
+
"loss": 1.0661,
|
391 |
+
"step": 1300
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 1.2245841035120149,
|
395 |
+
"grad_norm": 2.118389368057251,
|
396 |
+
"learning_rate": 0.000328825744608011,
|
397 |
+
"loss": 1.0821,
|
398 |
+
"step": 1325
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.2476894639556377,
|
402 |
+
"grad_norm": 1.383575677871704,
|
403 |
+
"learning_rate": 0.0003245463882232113,
|
404 |
+
"loss": 1.0988,
|
405 |
+
"step": 1350
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.2707948243992606,
|
409 |
+
"grad_norm": 0.9262095093727112,
|
410 |
+
"learning_rate": 0.00032026703183841147,
|
411 |
+
"loss": 1.0855,
|
412 |
+
"step": 1375
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.2939001848428835,
|
416 |
+
"grad_norm": 0.8497403860092163,
|
417 |
+
"learning_rate": 0.00031598767545361177,
|
418 |
+
"loss": 1.0734,
|
419 |
+
"step": 1400
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.3170055452865066,
|
423 |
+
"grad_norm": 2.554072856903076,
|
424 |
+
"learning_rate": 0.000311708319068812,
|
425 |
+
"loss": 1.0495,
|
426 |
+
"step": 1425
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 1.3401109057301293,
|
430 |
+
"grad_norm": 2.196169853210449,
|
431 |
+
"learning_rate": 0.0003074289626840123,
|
432 |
+
"loss": 1.0611,
|
433 |
+
"step": 1450
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 1.3632162661737524,
|
437 |
+
"grad_norm": 1.9735369682312012,
|
438 |
+
"learning_rate": 0.0003031496062992126,
|
439 |
+
"loss": 1.0689,
|
440 |
+
"step": 1475
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.3863216266173752,
|
444 |
+
"grad_norm": 1.28324556350708,
|
445 |
+
"learning_rate": 0.00029887024991441286,
|
446 |
+
"loss": 1.1195,
|
447 |
+
"step": 1500
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.4094269870609981,
|
451 |
+
"grad_norm": 2.870333671569824,
|
452 |
+
"learning_rate": 0.00029459089352961316,
|
453 |
+
"loss": 1.0909,
|
454 |
+
"step": 1525
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 1.432532347504621,
|
458 |
+
"grad_norm": 2.790924549102783,
|
459 |
+
"learning_rate": 0.00029031153714481346,
|
460 |
+
"loss": 1.1001,
|
461 |
+
"step": 1550
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 1.4556377079482439,
|
465 |
+
"grad_norm": 1.2432293891906738,
|
466 |
+
"learning_rate": 0.0002860321807600137,
|
467 |
+
"loss": 1.124,
|
468 |
+
"step": 1575
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 1.478743068391867,
|
472 |
+
"grad_norm": 0.8692905306816101,
|
473 |
+
"learning_rate": 0.000281752824375214,
|
474 |
+
"loss": 1.0717,
|
475 |
+
"step": 1600
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 1.5018484288354899,
|
479 |
+
"grad_norm": 1.2673799991607666,
|
480 |
+
"learning_rate": 0.00027747346799041425,
|
481 |
+
"loss": 1.086,
|
482 |
+
"step": 1625
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.5249537892791127,
|
486 |
+
"grad_norm": 1.9591180086135864,
|
487 |
+
"learning_rate": 0.00027319411160561455,
|
488 |
+
"loss": 1.0408,
|
489 |
+
"step": 1650
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.5480591497227358,
|
493 |
+
"grad_norm": 1.8689022064208984,
|
494 |
+
"learning_rate": 0.00026891475522081485,
|
495 |
+
"loss": 1.0499,
|
496 |
+
"step": 1675
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 1.5711645101663585,
|
500 |
+
"grad_norm": 2.0180625915527344,
|
501 |
+
"learning_rate": 0.00026463539883601504,
|
502 |
+
"loss": 1.0936,
|
503 |
+
"step": 1700
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 1.5942698706099816,
|
507 |
+
"grad_norm": 0.9715362191200256,
|
508 |
+
"learning_rate": 0.00026035604245121534,
|
509 |
+
"loss": 1.0886,
|
510 |
+
"step": 1725
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 1.6173752310536045,
|
514 |
+
"grad_norm": 1.5542079210281372,
|
515 |
+
"learning_rate": 0.0002560766860664156,
|
516 |
+
"loss": 1.0825,
|
517 |
+
"step": 1750
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 1.6404805914972274,
|
521 |
+
"grad_norm": 2.8334264755249023,
|
522 |
+
"learning_rate": 0.0002517973296816159,
|
523 |
+
"loss": 1.0932,
|
524 |
+
"step": 1775
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 1.6635859519408502,
|
528 |
+
"grad_norm": 0.5704463720321655,
|
529 |
+
"learning_rate": 0.0002475179732968162,
|
530 |
+
"loss": 1.1057,
|
531 |
+
"step": 1800
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 1.6866913123844731,
|
535 |
+
"grad_norm": 2.452209949493408,
|
536 |
+
"learning_rate": 0.00024323861691201643,
|
537 |
+
"loss": 1.0569,
|
538 |
+
"step": 1825
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.7097966728280962,
|
542 |
+
"grad_norm": 1.304701805114746,
|
543 |
+
"learning_rate": 0.0002389592605272167,
|
544 |
+
"loss": 1.0859,
|
545 |
+
"step": 1850
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 1.7329020332717189,
|
549 |
+
"grad_norm": 1.5926436185836792,
|
550 |
+
"learning_rate": 0.000234679904142417,
|
551 |
+
"loss": 1.0832,
|
552 |
+
"step": 1875
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 1.756007393715342,
|
556 |
+
"grad_norm": 2.683790445327759,
|
557 |
+
"learning_rate": 0.00023040054775761728,
|
558 |
+
"loss": 1.0539,
|
559 |
+
"step": 1900
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 1.7791127541589649,
|
563 |
+
"grad_norm": 1.4463739395141602,
|
564 |
+
"learning_rate": 0.00022612119137281752,
|
565 |
+
"loss": 1.0358,
|
566 |
+
"step": 1925
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 1.8022181146025877,
|
570 |
+
"grad_norm": 3.22567081451416,
|
571 |
+
"learning_rate": 0.0002218418349880178,
|
572 |
+
"loss": 0.9887,
|
573 |
+
"step": 1950
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 1.8253234750462108,
|
577 |
+
"grad_norm": 0.9853553771972656,
|
578 |
+
"learning_rate": 0.00021756247860321807,
|
579 |
+
"loss": 1.0566,
|
580 |
+
"step": 1975
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 1.8484288354898335,
|
584 |
+
"grad_norm": 1.0822279453277588,
|
585 |
+
"learning_rate": 0.00021328312221841837,
|
586 |
+
"loss": 1.0437,
|
587 |
+
"step": 2000
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 1.8715341959334566,
|
591 |
+
"grad_norm": 1.9909262657165527,
|
592 |
+
"learning_rate": 0.00020900376583361864,
|
593 |
+
"loss": 1.0059,
|
594 |
+
"step": 2025
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 1.8946395563770795,
|
598 |
+
"grad_norm": 1.8531982898712158,
|
599 |
+
"learning_rate": 0.0002047244094488189,
|
600 |
+
"loss": 1.0671,
|
601 |
+
"step": 2050
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 1.9177449168207024,
|
605 |
+
"grad_norm": 1.0466595888137817,
|
606 |
+
"learning_rate": 0.00020044505306401916,
|
607 |
+
"loss": 1.0766,
|
608 |
+
"step": 2075
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 1.9408502772643255,
|
612 |
+
"grad_norm": 0.8994802236557007,
|
613 |
+
"learning_rate": 0.00019616569667921946,
|
614 |
+
"loss": 0.9991,
|
615 |
+
"step": 2100
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 1.9639556377079481,
|
619 |
+
"grad_norm": 1.929488182067871,
|
620 |
+
"learning_rate": 0.00019188634029441973,
|
621 |
+
"loss": 1.0905,
|
622 |
+
"step": 2125
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.9870609981515712,
|
626 |
+
"grad_norm": 1.9165269136428833,
|
627 |
+
"learning_rate": 0.00018760698390962,
|
628 |
+
"loss": 1.039,
|
629 |
+
"step": 2150
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 2.0,
|
633 |
+
"eval_accuracy": 0.4584103512014787,
|
634 |
+
"eval_f1_macro": 0.2095479509928179,
|
635 |
+
"eval_f1_micro": 0.4584103512014787,
|
636 |
+
"eval_f1_weighted": 0.2881768494245037,
|
637 |
+
"eval_loss": 1.0747383832931519,
|
638 |
+
"eval_precision_macro": 0.1528034504004929,
|
639 |
+
"eval_precision_micro": 0.4584103512014787,
|
640 |
+
"eval_precision_weighted": 0.21014005008866307,
|
641 |
+
"eval_recall_macro": 0.3333333333333333,
|
642 |
+
"eval_recall_micro": 0.4584103512014787,
|
643 |
+
"eval_recall_weighted": 0.4584103512014787,
|
644 |
+
"eval_runtime": 105.3751,
|
645 |
+
"eval_samples_per_second": 10.268,
|
646 |
+
"eval_steps_per_second": 1.291,
|
647 |
+
"step": 2164
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 2.010166358595194,
|
651 |
+
"grad_norm": 4.0738606452941895,
|
652 |
+
"learning_rate": 0.00018332762752482028,
|
653 |
+
"loss": 1.0268,
|
654 |
+
"step": 2175
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 2.033271719038817,
|
658 |
+
"grad_norm": 2.0423989295959473,
|
659 |
+
"learning_rate": 0.00017904827114002055,
|
660 |
+
"loss": 1.0547,
|
661 |
+
"step": 2200
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 2.05637707948244,
|
665 |
+
"grad_norm": 2.3596909046173096,
|
666 |
+
"learning_rate": 0.00017476891475522082,
|
667 |
+
"loss": 1.0647,
|
668 |
+
"step": 2225
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 2.0794824399260627,
|
672 |
+
"grad_norm": 1.9593594074249268,
|
673 |
+
"learning_rate": 0.0001704895583704211,
|
674 |
+
"loss": 1.1023,
|
675 |
+
"step": 2250
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 2.102587800369686,
|
679 |
+
"grad_norm": 1.8953109979629517,
|
680 |
+
"learning_rate": 0.00016621020198562137,
|
681 |
+
"loss": 1.093,
|
682 |
+
"step": 2275
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 2.1256931608133085,
|
686 |
+
"grad_norm": 1.6998157501220703,
|
687 |
+
"learning_rate": 0.00016193084560082164,
|
688 |
+
"loss": 1.0777,
|
689 |
+
"step": 2300
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 2.1487985212569316,
|
693 |
+
"grad_norm": 1.0082741975784302,
|
694 |
+
"learning_rate": 0.0001576514892160219,
|
695 |
+
"loss": 1.0999,
|
696 |
+
"step": 2325
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 2.1719038817005547,
|
700 |
+
"grad_norm": 1.887078046798706,
|
701 |
+
"learning_rate": 0.0001533721328312222,
|
702 |
+
"loss": 1.1067,
|
703 |
+
"step": 2350
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 2.1950092421441774,
|
707 |
+
"grad_norm": 1.8659969568252563,
|
708 |
+
"learning_rate": 0.00014909277644642246,
|
709 |
+
"loss": 1.0769,
|
710 |
+
"step": 2375
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 2.2181146025878005,
|
714 |
+
"grad_norm": 0.916480302810669,
|
715 |
+
"learning_rate": 0.00014481342006162273,
|
716 |
+
"loss": 1.048,
|
717 |
+
"step": 2400
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 2.241219963031423,
|
721 |
+
"grad_norm": 1.9037351608276367,
|
722 |
+
"learning_rate": 0.000140534063676823,
|
723 |
+
"loss": 1.0509,
|
724 |
+
"step": 2425
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 2.2643253234750462,
|
728 |
+
"grad_norm": 1.9867937564849854,
|
729 |
+
"learning_rate": 0.00013625470729202328,
|
730 |
+
"loss": 1.0609,
|
731 |
+
"step": 2450
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 2.287430683918669,
|
735 |
+
"grad_norm": 2.044760227203369,
|
736 |
+
"learning_rate": 0.00013197535090722358,
|
737 |
+
"loss": 1.0351,
|
738 |
+
"step": 2475
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 2.310536044362292,
|
742 |
+
"grad_norm": 2.0097403526306152,
|
743 |
+
"learning_rate": 0.00012769599452242385,
|
744 |
+
"loss": 1.0433,
|
745 |
+
"step": 2500
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 2.333641404805915,
|
749 |
+
"grad_norm": 1.9191139936447144,
|
750 |
+
"learning_rate": 0.0001234166381376241,
|
751 |
+
"loss": 1.0219,
|
752 |
+
"step": 2525
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 2.3567467652495377,
|
756 |
+
"grad_norm": 1.9857523441314697,
|
757 |
+
"learning_rate": 0.00011913728175282437,
|
758 |
+
"loss": 1.0892,
|
759 |
+
"step": 2550
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 2.379852125693161,
|
763 |
+
"grad_norm": 2.7910494804382324,
|
764 |
+
"learning_rate": 0.00011485792536802465,
|
765 |
+
"loss": 1.1069,
|
766 |
+
"step": 2575
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 2.402957486136784,
|
770 |
+
"grad_norm": 1.5788651704788208,
|
771 |
+
"learning_rate": 0.00011057856898322493,
|
772 |
+
"loss": 1.0685,
|
773 |
+
"step": 2600
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 2.4260628465804066,
|
777 |
+
"grad_norm": 2.1729698181152344,
|
778 |
+
"learning_rate": 0.0001062992125984252,
|
779 |
+
"loss": 1.0369,
|
780 |
+
"step": 2625
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 2.4491682070240297,
|
784 |
+
"grad_norm": 1.842307686805725,
|
785 |
+
"learning_rate": 0.00010201985621362547,
|
786 |
+
"loss": 1.0777,
|
787 |
+
"step": 2650
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 2.4722735674676524,
|
791 |
+
"grad_norm": 1.7603636980056763,
|
792 |
+
"learning_rate": 9.774049982882574e-05,
|
793 |
+
"loss": 1.0776,
|
794 |
+
"step": 2675
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 2.4953789279112755,
|
798 |
+
"grad_norm": 3.0491414070129395,
|
799 |
+
"learning_rate": 9.346114344402602e-05,
|
800 |
+
"loss": 1.04,
|
801 |
+
"step": 2700
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 2.518484288354898,
|
805 |
+
"grad_norm": 1.8501389026641846,
|
806 |
+
"learning_rate": 8.918178705922629e-05,
|
807 |
+
"loss": 1.0217,
|
808 |
+
"step": 2725
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 2.5415896487985212,
|
812 |
+
"grad_norm": 1.788746953010559,
|
813 |
+
"learning_rate": 8.490243067442658e-05,
|
814 |
+
"loss": 1.086,
|
815 |
+
"step": 2750
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 2.5646950092421443,
|
819 |
+
"grad_norm": 1.6955204010009766,
|
820 |
+
"learning_rate": 8.062307428962684e-05,
|
821 |
+
"loss": 1.0784,
|
822 |
+
"step": 2775
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 2.587800369685767,
|
826 |
+
"grad_norm": 1.7728503942489624,
|
827 |
+
"learning_rate": 7.634371790482711e-05,
|
828 |
+
"loss": 1.0826,
|
829 |
+
"step": 2800
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 2.61090573012939,
|
833 |
+
"grad_norm": 1.9343187808990479,
|
834 |
+
"learning_rate": 7.20643615200274e-05,
|
835 |
+
"loss": 1.0258,
|
836 |
+
"step": 2825
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 2.634011090573013,
|
840 |
+
"grad_norm": 1.7846380472183228,
|
841 |
+
"learning_rate": 6.778500513522765e-05,
|
842 |
+
"loss": 1.1017,
|
843 |
+
"step": 2850
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 2.657116451016636,
|
847 |
+
"grad_norm": 0.9427468180656433,
|
848 |
+
"learning_rate": 6.350564875042794e-05,
|
849 |
+
"loss": 1.0762,
|
850 |
+
"step": 2875
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 2.6802218114602585,
|
854 |
+
"grad_norm": 2.756263017654419,
|
855 |
+
"learning_rate": 5.9226292365628206e-05,
|
856 |
+
"loss": 1.0642,
|
857 |
+
"step": 2900
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 2.7033271719038816,
|
861 |
+
"grad_norm": 1.782007098197937,
|
862 |
+
"learning_rate": 5.4946935980828486e-05,
|
863 |
+
"loss": 1.0402,
|
864 |
+
"step": 2925
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 2.7264325323475047,
|
868 |
+
"grad_norm": 2.0735743045806885,
|
869 |
+
"learning_rate": 5.066757959602876e-05,
|
870 |
+
"loss": 1.0347,
|
871 |
+
"step": 2950
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 2.7495378927911274,
|
875 |
+
"grad_norm": 1.935968279838562,
|
876 |
+
"learning_rate": 4.638822321122903e-05,
|
877 |
+
"loss": 1.0703,
|
878 |
+
"step": 2975
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 2.7726432532347505,
|
882 |
+
"grad_norm": 1.8476896286010742,
|
883 |
+
"learning_rate": 4.2108866826429304e-05,
|
884 |
+
"loss": 1.0754,
|
885 |
+
"step": 3000
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 2.7957486136783736,
|
889 |
+
"grad_norm": 1.8447425365447998,
|
890 |
+
"learning_rate": 3.782951044162958e-05,
|
891 |
+
"loss": 1.0004,
|
892 |
+
"step": 3025
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 2.8188539741219962,
|
896 |
+
"grad_norm": 1.811383605003357,
|
897 |
+
"learning_rate": 3.355015405682985e-05,
|
898 |
+
"loss": 1.108,
|
899 |
+
"step": 3050
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 2.8419593345656193,
|
903 |
+
"grad_norm": 1.8410310745239258,
|
904 |
+
"learning_rate": 2.927079767203013e-05,
|
905 |
+
"loss": 1.0884,
|
906 |
+
"step": 3075
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 2.865064695009242,
|
910 |
+
"grad_norm": 1.8326698541641235,
|
911 |
+
"learning_rate": 2.49914412872304e-05,
|
912 |
+
"loss": 1.0986,
|
913 |
+
"step": 3100
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 2.888170055452865,
|
917 |
+
"grad_norm": 1.9954646825790405,
|
918 |
+
"learning_rate": 2.0712084902430675e-05,
|
919 |
+
"loss": 1.0926,
|
920 |
+
"step": 3125
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 2.9112754158964878,
|
924 |
+
"grad_norm": 0.8552793264389038,
|
925 |
+
"learning_rate": 1.643272851763095e-05,
|
926 |
+
"loss": 1.1081,
|
927 |
+
"step": 3150
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 2.934380776340111,
|
931 |
+
"grad_norm": 1.6706448793411255,
|
932 |
+
"learning_rate": 1.2153372132831224e-05,
|
933 |
+
"loss": 1.1125,
|
934 |
+
"step": 3175
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 2.957486136783734,
|
938 |
+
"grad_norm": 1.8879237174987793,
|
939 |
+
"learning_rate": 7.874015748031496e-06,
|
940 |
+
"loss": 1.0289,
|
941 |
+
"step": 3200
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 2.9805914972273566,
|
945 |
+
"grad_norm": 1.7822940349578857,
|
946 |
+
"learning_rate": 3.59465936323177e-06,
|
947 |
+
"loss": 1.0718,
|
948 |
+
"step": 3225
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 3.0,
|
952 |
+
"eval_accuracy": 0.4584103512014787,
|
953 |
+
"eval_f1_macro": 0.2095479509928179,
|
954 |
+
"eval_f1_micro": 0.4584103512014787,
|
955 |
+
"eval_f1_weighted": 0.2881768494245037,
|
956 |
+
"eval_loss": 1.0657285451889038,
|
957 |
+
"eval_precision_macro": 0.1528034504004929,
|
958 |
+
"eval_precision_micro": 0.4584103512014787,
|
959 |
+
"eval_precision_weighted": 0.21014005008866307,
|
960 |
+
"eval_recall_macro": 0.3333333333333333,
|
961 |
+
"eval_recall_micro": 0.4584103512014787,
|
962 |
+
"eval_recall_weighted": 0.4584103512014787,
|
963 |
+
"eval_runtime": 112.831,
|
964 |
+
"eval_samples_per_second": 9.59,
|
965 |
+
"eval_steps_per_second": 1.205,
|
966 |
+
"step": 3246
|
967 |
+
}
|
968 |
+
],
|
969 |
+
"logging_steps": 25,
|
970 |
+
"max_steps": 3246,
|
971 |
+
"num_input_tokens_seen": 0,
|
972 |
+
"num_train_epochs": 3,
|
973 |
+
"save_steps": 500,
|
974 |
+
"total_flos": 429996844283904.0,
|
975 |
+
"train_batch_size": 4,
|
976 |
+
"trial_name": null,
|
977 |
+
"trial_params": null
|
978 |
+
}
|
checkpoint-3246/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3736fcb6a461d61b48603d3aec6ba50a49f8fcbc72327f93029b520b459c467c
|
3 |
+
size 5048
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-multilingual-cased",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForSequenceClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "-1",
|
14 |
+
"1": "0",
|
15 |
+
"2": "1"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"-1": 0,
|
20 |
+
"0": 1,
|
21 |
+
"1": 2
|
22 |
+
},
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "distilbert",
|
25 |
+
"n_heads": 12,
|
26 |
+
"n_layers": 6,
|
27 |
+
"output_past": true,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"qa_dropout": 0.1,
|
31 |
+
"seq_classif_dropout": 0.2,
|
32 |
+
"sinusoidal_pos_embds": false,
|
33 |
+
"tie_weights_": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.40.1",
|
36 |
+
"vocab_size": 119547
|
37 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5005299aa0690636d670f974407b6164dda3900224afc1feaccc28066f9c637
|
3 |
+
size 541320452
|
runs/Apr30_06-35-24_r-darkphantom323-nlp-8t0qt349-3e504-sss3p/events.out.tfevents.1714458926.r-darkphantom323-nlp-8t0qt349-3e504-sss3p.85.0
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 sha256:81886543ff006ff98a20521e91969c8fb1b1d80cf57cb711bea16daf9369e2f3
|
3 |
+
size 34816
|
runs/Apr30_06-35-24_r-darkphantom323-nlp-8t0qt349-3e504-sss3p/events.out.tfevents.1714470322.r-darkphantom323-nlp-8t0qt349-3e504-sss3p.85.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:894e784379288d6c4ffcff3753ad935aaffa145f05f98f1f5a78774f1d3598a5
|
3 |
+
size 921
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 1000000000000000019884624838656,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3736fcb6a461d61b48603d3aec6ba50a49f8fcbc72327f93029b520b459c467c
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "actsa-distilbert/autotrain-data",
|
3 |
+
"model": "distilbert/distilbert-base-multilingual-cased",
|
4 |
+
"lr": 0.0005,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 4,
|
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": "actsa-distilbert",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": null,
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"evaluation_strategy": "epoch",
|
26 |
+
"username": "DarkPhantom323",
|
27 |
+
"log": "tensorboard"
|
28 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|