Commit
•
ac64dc7
1
Parent(s):
282620f
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- added_tokens.json +3 -0
- checkpoint-1800/config.json +70 -0
- checkpoint-1800/model.safetensors +3 -0
- checkpoint-1800/optimizer.pt +3 -0
- checkpoint-1800/rng_state.pth +3 -0
- checkpoint-1800/scheduler.pt +3 -0
- checkpoint-1800/trainer_state.json +495 -0
- checkpoint-1800/training_args.bin +3 -0
- config.json +70 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- training_params.json +30 -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 |
+
- website-classifier/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.45181071758270264
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.9103583954158208
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.9108333333333334
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.9103583954158205
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.9123282026272069
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.9108333333333334
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.9123282026272069
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.9108333333333334
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.9108333333333334
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.9108333333333334
|
| 36 |
+
|
| 37 |
+
accuracy: 0.9108333333333334
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-1800/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-large",
|
| 3 |
+
"_num_labels": 15,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DebertaV2ForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Arts",
|
| 13 |
+
"1": "Business",
|
| 14 |
+
"2": "Computers",
|
| 15 |
+
"3": "Games",
|
| 16 |
+
"4": "Health",
|
| 17 |
+
"5": "Home",
|
| 18 |
+
"6": "Kids",
|
| 19 |
+
"7": "News",
|
| 20 |
+
"8": "Porn",
|
| 21 |
+
"9": "Recreation",
|
| 22 |
+
"10": "Reference",
|
| 23 |
+
"11": "Science",
|
| 24 |
+
"12": "Shopping",
|
| 25 |
+
"13": "Society",
|
| 26 |
+
"14": "Sports"
|
| 27 |
+
},
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 4096,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"Arts": 0,
|
| 32 |
+
"Business": 1,
|
| 33 |
+
"Computers": 2,
|
| 34 |
+
"Games": 3,
|
| 35 |
+
"Health": 4,
|
| 36 |
+
"Home": 5,
|
| 37 |
+
"Kids": 6,
|
| 38 |
+
"News": 7,
|
| 39 |
+
"Porn": 8,
|
| 40 |
+
"Recreation": 9,
|
| 41 |
+
"Reference": 10,
|
| 42 |
+
"Science": 11,
|
| 43 |
+
"Shopping": 12,
|
| 44 |
+
"Society": 13,
|
| 45 |
+
"Sports": 14
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-07,
|
| 48 |
+
"max_position_embeddings": 512,
|
| 49 |
+
"max_relative_positions": -1,
|
| 50 |
+
"model_type": "deberta-v2",
|
| 51 |
+
"norm_rel_ebd": "layer_norm",
|
| 52 |
+
"num_attention_heads": 16,
|
| 53 |
+
"num_hidden_layers": 24,
|
| 54 |
+
"pad_token_id": 0,
|
| 55 |
+
"pooler_dropout": 0,
|
| 56 |
+
"pooler_hidden_act": "gelu",
|
| 57 |
+
"pooler_hidden_size": 1024,
|
| 58 |
+
"pos_att_type": [
|
| 59 |
+
"p2c",
|
| 60 |
+
"c2p"
|
| 61 |
+
],
|
| 62 |
+
"position_biased_input": false,
|
| 63 |
+
"position_buckets": 256,
|
| 64 |
+
"relative_attention": true,
|
| 65 |
+
"share_att_key": true,
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.38.2",
|
| 68 |
+
"type_vocab_size": 0,
|
| 69 |
+
"vocab_size": 128100
|
| 70 |
+
}
|
checkpoint-1800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dd69e23f064fe1e3004384753dec1ff2b66445790bee058eb0d8670e9f3145d
|
| 3 |
+
size 1740357748
|
checkpoint-1800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e3d80404db4317e0bfbcd3e15d5cfc0bfcd2afa9b15114315e6f2ed99f1b1a6
|
| 3 |
+
size 3480946800
|
checkpoint-1800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99d925c357da513500b99a8f0353e021fd75413db8f83570744eda68f91174ca
|
| 3 |
+
size 14244
|
checkpoint-1800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9434fb9607a68ee8daf0b5c0c46a29d3f5316a2d8b7bc4d1c4b3d831088e8e4c
|
| 3 |
+
size 1064
|
checkpoint-1800/trainer_state.json
ADDED
|
@@ -0,0 +1,495 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.45181071758270264,
|
| 3 |
+
"best_model_checkpoint": "website-classifier/checkpoint-1800",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 4.491672039031982,
|
| 14 |
+
"learning_rate": 8.333333333333334e-06,
|
| 15 |
+
"loss": 2.7552,
|
| 16 |
+
"step": 30
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 6.483436107635498,
|
| 21 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 22 |
+
"loss": 2.7259,
|
| 23 |
+
"step": 60
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 8.029026985168457,
|
| 28 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 29 |
+
"loss": 2.6183,
|
| 30 |
+
"step": 90
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 10.646072387695312,
|
| 35 |
+
"learning_rate": 3.277777777777778e-05,
|
| 36 |
+
"loss": 2.598,
|
| 37 |
+
"step": 120
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 10.159834861755371,
|
| 42 |
+
"learning_rate": 4.111111111111111e-05,
|
| 43 |
+
"loss": 2.1777,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 14.836869239807129,
|
| 49 |
+
"learning_rate": 4.9166666666666665e-05,
|
| 50 |
+
"loss": 1.7938,
|
| 51 |
+
"step": 180
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 10.7587890625,
|
| 56 |
+
"learning_rate": 4.9166666666666665e-05,
|
| 57 |
+
"loss": 1.95,
|
| 58 |
+
"step": 210
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 31.001468658447266,
|
| 63 |
+
"learning_rate": 4.8240740740740744e-05,
|
| 64 |
+
"loss": 1.7602,
|
| 65 |
+
"step": 240
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 9.250581741333008,
|
| 70 |
+
"learning_rate": 4.731481481481482e-05,
|
| 71 |
+
"loss": 1.6735,
|
| 72 |
+
"step": 270
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 14.803194046020508,
|
| 77 |
+
"learning_rate": 4.638888888888889e-05,
|
| 78 |
+
"loss": 1.2047,
|
| 79 |
+
"step": 300
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 41.04203796386719,
|
| 84 |
+
"learning_rate": 4.546296296296296e-05,
|
| 85 |
+
"loss": 1.4807,
|
| 86 |
+
"step": 330
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 15.050979614257812,
|
| 91 |
+
"learning_rate": 4.4537037037037036e-05,
|
| 92 |
+
"loss": 1.3084,
|
| 93 |
+
"step": 360
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 13.59727668762207,
|
| 98 |
+
"learning_rate": 4.3611111111111116e-05,
|
| 99 |
+
"loss": 1.3297,
|
| 100 |
+
"step": 390
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 6.688912391662598,
|
| 105 |
+
"learning_rate": 4.268518518518519e-05,
|
| 106 |
+
"loss": 1.3379,
|
| 107 |
+
"step": 420
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 7.42189359664917,
|
| 112 |
+
"learning_rate": 4.1820987654320994e-05,
|
| 113 |
+
"loss": 1.4812,
|
| 114 |
+
"step": 450
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 6.354011058807373,
|
| 119 |
+
"learning_rate": 4.089506172839506e-05,
|
| 120 |
+
"loss": 1.5017,
|
| 121 |
+
"step": 480
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 25.94729995727539,
|
| 126 |
+
"learning_rate": 3.996913580246914e-05,
|
| 127 |
+
"loss": 1.1041,
|
| 128 |
+
"step": 510
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 24.99347686767578,
|
| 133 |
+
"learning_rate": 3.904320987654321e-05,
|
| 134 |
+
"loss": 1.109,
|
| 135 |
+
"step": 540
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.95,
|
| 139 |
+
"grad_norm": 41.66750717163086,
|
| 140 |
+
"learning_rate": 3.8117283950617286e-05,
|
| 141 |
+
"loss": 1.073,
|
| 142 |
+
"step": 570
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"grad_norm": 6.238738059997559,
|
| 147 |
+
"learning_rate": 3.719135802469136e-05,
|
| 148 |
+
"loss": 1.2524,
|
| 149 |
+
"step": 600
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.775,
|
| 154 |
+
"eval_f1_macro": 0.7753958544292094,
|
| 155 |
+
"eval_f1_micro": 0.775,
|
| 156 |
+
"eval_f1_weighted": 0.7753958544292096,
|
| 157 |
+
"eval_loss": 0.9330267310142517,
|
| 158 |
+
"eval_precision_macro": 0.796061342783982,
|
| 159 |
+
"eval_precision_micro": 0.775,
|
| 160 |
+
"eval_precision_weighted": 0.7960613427839818,
|
| 161 |
+
"eval_recall_macro": 0.775,
|
| 162 |
+
"eval_recall_micro": 0.775,
|
| 163 |
+
"eval_recall_weighted": 0.775,
|
| 164 |
+
"eval_runtime": 24.168,
|
| 165 |
+
"eval_samples_per_second": 49.652,
|
| 166 |
+
"eval_steps_per_second": 3.103,
|
| 167 |
+
"step": 600
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.05,
|
| 171 |
+
"grad_norm": 8.009809494018555,
|
| 172 |
+
"learning_rate": 3.626543209876543e-05,
|
| 173 |
+
"loss": 0.9211,
|
| 174 |
+
"step": 630
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.1,
|
| 178 |
+
"grad_norm": 17.96474838256836,
|
| 179 |
+
"learning_rate": 3.533950617283951e-05,
|
| 180 |
+
"loss": 1.0106,
|
| 181 |
+
"step": 660
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.15,
|
| 185 |
+
"grad_norm": 8.952888488769531,
|
| 186 |
+
"learning_rate": 3.441358024691358e-05,
|
| 187 |
+
"loss": 0.8015,
|
| 188 |
+
"step": 690
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.2,
|
| 192 |
+
"grad_norm": 45.105072021484375,
|
| 193 |
+
"learning_rate": 3.348765432098766e-05,
|
| 194 |
+
"loss": 0.7559,
|
| 195 |
+
"step": 720
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.25,
|
| 199 |
+
"grad_norm": 7.327918529510498,
|
| 200 |
+
"learning_rate": 3.256172839506173e-05,
|
| 201 |
+
"loss": 1.0116,
|
| 202 |
+
"step": 750
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.3,
|
| 206 |
+
"grad_norm": 48.14884948730469,
|
| 207 |
+
"learning_rate": 3.16358024691358e-05,
|
| 208 |
+
"loss": 1.5269,
|
| 209 |
+
"step": 780
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.35,
|
| 213 |
+
"grad_norm": 10.317117691040039,
|
| 214 |
+
"learning_rate": 3.0709876543209876e-05,
|
| 215 |
+
"loss": 0.9947,
|
| 216 |
+
"step": 810
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.4,
|
| 220 |
+
"grad_norm": 39.09126281738281,
|
| 221 |
+
"learning_rate": 2.9783950617283952e-05,
|
| 222 |
+
"loss": 0.8826,
|
| 223 |
+
"step": 840
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.45,
|
| 227 |
+
"grad_norm": 7.045171737670898,
|
| 228 |
+
"learning_rate": 2.8858024691358025e-05,
|
| 229 |
+
"loss": 0.8446,
|
| 230 |
+
"step": 870
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.5,
|
| 234 |
+
"grad_norm": 10.068076133728027,
|
| 235 |
+
"learning_rate": 2.79320987654321e-05,
|
| 236 |
+
"loss": 0.7001,
|
| 237 |
+
"step": 900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.55,
|
| 241 |
+
"grad_norm": 15.41380500793457,
|
| 242 |
+
"learning_rate": 2.700617283950617e-05,
|
| 243 |
+
"loss": 0.8341,
|
| 244 |
+
"step": 930
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.6,
|
| 248 |
+
"grad_norm": 9.957711219787598,
|
| 249 |
+
"learning_rate": 2.6080246913580247e-05,
|
| 250 |
+
"loss": 0.6945,
|
| 251 |
+
"step": 960
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.65,
|
| 255 |
+
"grad_norm": 4.9840545654296875,
|
| 256 |
+
"learning_rate": 2.5154320987654324e-05,
|
| 257 |
+
"loss": 0.7595,
|
| 258 |
+
"step": 990
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.7,
|
| 262 |
+
"grad_norm": 14.547338485717773,
|
| 263 |
+
"learning_rate": 2.4228395061728396e-05,
|
| 264 |
+
"loss": 0.4924,
|
| 265 |
+
"step": 1020
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.75,
|
| 269 |
+
"grad_norm": 0.45237699151039124,
|
| 270 |
+
"learning_rate": 2.3302469135802473e-05,
|
| 271 |
+
"loss": 0.9098,
|
| 272 |
+
"step": 1050
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.8,
|
| 276 |
+
"grad_norm": 17.84574317932129,
|
| 277 |
+
"learning_rate": 2.2376543209876542e-05,
|
| 278 |
+
"loss": 0.758,
|
| 279 |
+
"step": 1080
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.85,
|
| 283 |
+
"grad_norm": 3.32464599609375,
|
| 284 |
+
"learning_rate": 2.145061728395062e-05,
|
| 285 |
+
"loss": 0.6431,
|
| 286 |
+
"step": 1110
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.9,
|
| 290 |
+
"grad_norm": 6.051296234130859,
|
| 291 |
+
"learning_rate": 2.052469135802469e-05,
|
| 292 |
+
"loss": 0.8403,
|
| 293 |
+
"step": 1140
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.95,
|
| 297 |
+
"grad_norm": 36.67551040649414,
|
| 298 |
+
"learning_rate": 1.9598765432098768e-05,
|
| 299 |
+
"loss": 0.8311,
|
| 300 |
+
"step": 1170
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.0,
|
| 304 |
+
"grad_norm": 14.538824081420898,
|
| 305 |
+
"learning_rate": 1.867283950617284e-05,
|
| 306 |
+
"loss": 0.6665,
|
| 307 |
+
"step": 1200
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.0,
|
| 311 |
+
"eval_accuracy": 0.855,
|
| 312 |
+
"eval_f1_macro": 0.8538278779437969,
|
| 313 |
+
"eval_f1_micro": 0.855,
|
| 314 |
+
"eval_f1_weighted": 0.853827877943797,
|
| 315 |
+
"eval_loss": 0.631514310836792,
|
| 316 |
+
"eval_precision_macro": 0.8595148734247968,
|
| 317 |
+
"eval_precision_micro": 0.855,
|
| 318 |
+
"eval_precision_weighted": 0.8595148734247969,
|
| 319 |
+
"eval_recall_macro": 0.8549999999999999,
|
| 320 |
+
"eval_recall_micro": 0.855,
|
| 321 |
+
"eval_recall_weighted": 0.855,
|
| 322 |
+
"eval_runtime": 24.1701,
|
| 323 |
+
"eval_samples_per_second": 49.648,
|
| 324 |
+
"eval_steps_per_second": 3.103,
|
| 325 |
+
"step": 1200
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.05,
|
| 329 |
+
"grad_norm": 4.500637531280518,
|
| 330 |
+
"learning_rate": 1.7746913580246917e-05,
|
| 331 |
+
"loss": 0.4377,
|
| 332 |
+
"step": 1230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.1,
|
| 336 |
+
"grad_norm": 0.43099209666252136,
|
| 337 |
+
"learning_rate": 1.682098765432099e-05,
|
| 338 |
+
"loss": 0.4461,
|
| 339 |
+
"step": 1260
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.15,
|
| 343 |
+
"grad_norm": 15.149191856384277,
|
| 344 |
+
"learning_rate": 1.5895061728395063e-05,
|
| 345 |
+
"loss": 0.5035,
|
| 346 |
+
"step": 1290
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.2,
|
| 350 |
+
"grad_norm": 20.928913116455078,
|
| 351 |
+
"learning_rate": 1.4969135802469136e-05,
|
| 352 |
+
"loss": 0.5992,
|
| 353 |
+
"step": 1320
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.25,
|
| 357 |
+
"grad_norm": 12.046993255615234,
|
| 358 |
+
"learning_rate": 1.4043209876543212e-05,
|
| 359 |
+
"loss": 0.4523,
|
| 360 |
+
"step": 1350
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.3,
|
| 364 |
+
"grad_norm": 0.5978269577026367,
|
| 365 |
+
"learning_rate": 1.3117283950617285e-05,
|
| 366 |
+
"loss": 0.483,
|
| 367 |
+
"step": 1380
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.35,
|
| 371 |
+
"grad_norm": 7.10316801071167,
|
| 372 |
+
"learning_rate": 1.219135802469136e-05,
|
| 373 |
+
"loss": 0.4932,
|
| 374 |
+
"step": 1410
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.4,
|
| 378 |
+
"grad_norm": 10.279694557189941,
|
| 379 |
+
"learning_rate": 1.1265432098765432e-05,
|
| 380 |
+
"loss": 0.3396,
|
| 381 |
+
"step": 1440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.45,
|
| 385 |
+
"grad_norm": 0.13266117870807648,
|
| 386 |
+
"learning_rate": 1.0339506172839507e-05,
|
| 387 |
+
"loss": 0.4377,
|
| 388 |
+
"step": 1470
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.5,
|
| 392 |
+
"grad_norm": 24.841278076171875,
|
| 393 |
+
"learning_rate": 9.413580246913581e-06,
|
| 394 |
+
"loss": 0.4452,
|
| 395 |
+
"step": 1500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.55,
|
| 399 |
+
"grad_norm": 1.116528034210205,
|
| 400 |
+
"learning_rate": 8.487654320987654e-06,
|
| 401 |
+
"loss": 0.4,
|
| 402 |
+
"step": 1530
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.6,
|
| 406 |
+
"grad_norm": 38.56851577758789,
|
| 407 |
+
"learning_rate": 7.561728395061729e-06,
|
| 408 |
+
"loss": 0.3195,
|
| 409 |
+
"step": 1560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.65,
|
| 413 |
+
"grad_norm": 12.757609367370605,
|
| 414 |
+
"learning_rate": 6.635802469135803e-06,
|
| 415 |
+
"loss": 0.4735,
|
| 416 |
+
"step": 1590
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.7,
|
| 420 |
+
"grad_norm": 0.18463416397571564,
|
| 421 |
+
"learning_rate": 5.7098765432098764e-06,
|
| 422 |
+
"loss": 0.3327,
|
| 423 |
+
"step": 1620
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.75,
|
| 427 |
+
"grad_norm": 1.0354253053665161,
|
| 428 |
+
"learning_rate": 4.78395061728395e-06,
|
| 429 |
+
"loss": 0.2695,
|
| 430 |
+
"step": 1650
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.8,
|
| 434 |
+
"grad_norm": 6.2124433517456055,
|
| 435 |
+
"learning_rate": 3.858024691358025e-06,
|
| 436 |
+
"loss": 0.4273,
|
| 437 |
+
"step": 1680
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.85,
|
| 441 |
+
"grad_norm": 51.33966827392578,
|
| 442 |
+
"learning_rate": 2.932098765432099e-06,
|
| 443 |
+
"loss": 0.3228,
|
| 444 |
+
"step": 1710
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.9,
|
| 448 |
+
"grad_norm": 0.17042000591754913,
|
| 449 |
+
"learning_rate": 2.0061728395061727e-06,
|
| 450 |
+
"loss": 0.45,
|
| 451 |
+
"step": 1740
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.95,
|
| 455 |
+
"grad_norm": 12.142667770385742,
|
| 456 |
+
"learning_rate": 1.0802469135802469e-06,
|
| 457 |
+
"loss": 0.3076,
|
| 458 |
+
"step": 1770
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.0,
|
| 462 |
+
"grad_norm": 0.21961359679698944,
|
| 463 |
+
"learning_rate": 1.54320987654321e-07,
|
| 464 |
+
"loss": 0.3804,
|
| 465 |
+
"step": 1800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.0,
|
| 469 |
+
"eval_accuracy": 0.9108333333333334,
|
| 470 |
+
"eval_f1_macro": 0.9103583954158208,
|
| 471 |
+
"eval_f1_micro": 0.9108333333333334,
|
| 472 |
+
"eval_f1_weighted": 0.9103583954158205,
|
| 473 |
+
"eval_loss": 0.45181071758270264,
|
| 474 |
+
"eval_precision_macro": 0.9123282026272069,
|
| 475 |
+
"eval_precision_micro": 0.9108333333333334,
|
| 476 |
+
"eval_precision_weighted": 0.9123282026272069,
|
| 477 |
+
"eval_recall_macro": 0.9108333333333334,
|
| 478 |
+
"eval_recall_micro": 0.9108333333333334,
|
| 479 |
+
"eval_recall_weighted": 0.9108333333333334,
|
| 480 |
+
"eval_runtime": 25.1673,
|
| 481 |
+
"eval_samples_per_second": 47.681,
|
| 482 |
+
"eval_steps_per_second": 2.98,
|
| 483 |
+
"step": 1800
|
| 484 |
+
}
|
| 485 |
+
],
|
| 486 |
+
"logging_steps": 30,
|
| 487 |
+
"max_steps": 1800,
|
| 488 |
+
"num_input_tokens_seen": 0,
|
| 489 |
+
"num_train_epochs": 3,
|
| 490 |
+
"save_steps": 500,
|
| 491 |
+
"total_flos": 1.34204916842496e+16,
|
| 492 |
+
"train_batch_size": 8,
|
| 493 |
+
"trial_name": null,
|
| 494 |
+
"trial_params": null
|
| 495 |
+
}
|
checkpoint-1800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:641c918fb5891e5b10354177458ff006b197a9750ff8f3a418559a7f76138250
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-large",
|
| 3 |
+
"_num_labels": 15,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DebertaV2ForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Arts",
|
| 13 |
+
"1": "Business",
|
| 14 |
+
"2": "Computers",
|
| 15 |
+
"3": "Games",
|
| 16 |
+
"4": "Health",
|
| 17 |
+
"5": "Home",
|
| 18 |
+
"6": "Kids",
|
| 19 |
+
"7": "News",
|
| 20 |
+
"8": "Porn",
|
| 21 |
+
"9": "Recreation",
|
| 22 |
+
"10": "Reference",
|
| 23 |
+
"11": "Science",
|
| 24 |
+
"12": "Shopping",
|
| 25 |
+
"13": "Society",
|
| 26 |
+
"14": "Sports"
|
| 27 |
+
},
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 4096,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"Arts": 0,
|
| 32 |
+
"Business": 1,
|
| 33 |
+
"Computers": 2,
|
| 34 |
+
"Games": 3,
|
| 35 |
+
"Health": 4,
|
| 36 |
+
"Home": 5,
|
| 37 |
+
"Kids": 6,
|
| 38 |
+
"News": 7,
|
| 39 |
+
"Porn": 8,
|
| 40 |
+
"Recreation": 9,
|
| 41 |
+
"Reference": 10,
|
| 42 |
+
"Science": 11,
|
| 43 |
+
"Shopping": 12,
|
| 44 |
+
"Society": 13,
|
| 45 |
+
"Sports": 14
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-07,
|
| 48 |
+
"max_position_embeddings": 512,
|
| 49 |
+
"max_relative_positions": -1,
|
| 50 |
+
"model_type": "deberta-v2",
|
| 51 |
+
"norm_rel_ebd": "layer_norm",
|
| 52 |
+
"num_attention_heads": 16,
|
| 53 |
+
"num_hidden_layers": 24,
|
| 54 |
+
"pad_token_id": 0,
|
| 55 |
+
"pooler_dropout": 0,
|
| 56 |
+
"pooler_hidden_act": "gelu",
|
| 57 |
+
"pooler_hidden_size": 1024,
|
| 58 |
+
"pos_att_type": [
|
| 59 |
+
"p2c",
|
| 60 |
+
"c2p"
|
| 61 |
+
],
|
| 62 |
+
"position_biased_input": false,
|
| 63 |
+
"position_buckets": 256,
|
| 64 |
+
"relative_attention": true,
|
| 65 |
+
"share_att_key": true,
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.38.2",
|
| 68 |
+
"type_vocab_size": 0,
|
| 69 |
+
"vocab_size": 128100
|
| 70 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dd69e23f064fe1e3004384753dec1ff2b66445790bee058eb0d8670e9f3145d
|
| 3 |
+
size 1740357748
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 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": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"split_by_punct": false,
|
| 55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 56 |
+
"unk_token": "[UNK]",
|
| 57 |
+
"vocab_type": "spm"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:641c918fb5891e5b10354177458ff006b197a9750ff8f3a418559a7f76138250
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "website-classifier/autotrain-data",
|
| 3 |
+
"model": "microsoft/deberta-v3-large",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 3,
|
| 6 |
+
"max_seq_length": 512,
|
| 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": "website-classifier",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"save_strategy": "epoch",
|
| 25 |
+
"push_to_hub": true,
|
| 26 |
+
"repo_id": "KnutJaegersberg/website-classifier",
|
| 27 |
+
"evaluation_strategy": "epoch",
|
| 28 |
+
"username": "KnutJaegersberg",
|
| 29 |
+
"log": "none"
|
| 30 |
+
}
|