Upload folder using huggingface_hub
Browse files- README.md +26 -0
- added_tokens.json +3 -0
- checkpoint-1800/config.json +44 -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 +559 -0
- checkpoint-1800/training_args.bin +3 -0
- config.json +44 -0
- model.safetensors +3 -0
- runs/Jun06_00-39-21_r-nansk13-bert-auto-sent-multi-6iitkada-8a0be-1lk3n/events.out.tfevents.1717634367.r-nansk13-bert-auto-sent-multi-6iitkada-8a0be-1lk3n.107.0 +2 -2
- runs/Jun06_00-39-21_r-nansk13-bert-auto-sent-multi-6iitkada-8a0be-1lk3n/events.out.tfevents.1717681878.r-nansk13-bert-auto-sent-multi-6iitkada-8a0be-1lk3n.107.1 +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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
base_model: microsoft/deberta-v3-base
|
| 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: 0.35031697154045105
|
| 17 |
+
|
| 18 |
+
f1: 0.869073275862069
|
| 19 |
+
|
| 20 |
+
precision: 0.8529878371232152
|
| 21 |
+
|
| 22 |
+
recall: 0.885777045579352
|
| 23 |
+
|
| 24 |
+
auc: 0.9395007159925164
|
| 25 |
+
|
| 26 |
+
accuracy: 0.865
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-1800/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 3 |
+
"_num_labels": 2,
|
| 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": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "n\u00e9gatif",
|
| 13 |
+
"1": "positif"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"n\u00e9gatif": 0,
|
| 19 |
+
"positif": 1
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-07,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"max_relative_positions": -1,
|
| 24 |
+
"model_type": "deberta-v2",
|
| 25 |
+
"norm_rel_ebd": "layer_norm",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_dropout": 0,
|
| 30 |
+
"pooler_hidden_act": "gelu",
|
| 31 |
+
"pooler_hidden_size": 768,
|
| 32 |
+
"pos_att_type": [
|
| 33 |
+
"p2c",
|
| 34 |
+
"c2p"
|
| 35 |
+
],
|
| 36 |
+
"position_biased_input": false,
|
| 37 |
+
"position_buckets": 256,
|
| 38 |
+
"relative_attention": true,
|
| 39 |
+
"share_att_key": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.41.0",
|
| 42 |
+
"type_vocab_size": 0,
|
| 43 |
+
"vocab_size": 128100
|
| 44 |
+
}
|
checkpoint-1800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d2695e10fae203b54db36a56aca65a5113be059968b5bbde76d3b070dda2cce
|
| 3 |
+
size 737719272
|
checkpoint-1800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30f1095ce1734865157d75b0b7095249b1e96516dec5d7f1d1c370eb07e90cc0
|
| 3 |
+
size 1475552762
|
checkpoint-1800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebeeea6845b87db0ada509bc64c353931778b0d558a35372b7ab10f4f5f503a1
|
| 3 |
+
size 13990
|
checkpoint-1800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfec6396f28f0c50374fd7dd7f123a511264023e43c1fa1b2e3f1d3240c5c2f7
|
| 3 |
+
size 1064
|
checkpoint-1800/trainer_state.json
ADDED
|
@@ -0,0 +1,559 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.35031697154045105,
|
| 3 |
+
"best_model_checkpoint": "deberta-sent-multi/checkpoint-1800",
|
| 4 |
+
"epoch": 1.0,
|
| 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": 0.013888888888888888,
|
| 13 |
+
"grad_norm": 1.9551440477371216,
|
| 14 |
+
"learning_rate": 2.3148148148148148e-06,
|
| 15 |
+
"loss": 0.6935,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.027777777777777776,
|
| 20 |
+
"grad_norm": 1.187191128730774,
|
| 21 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 22 |
+
"loss": 0.6957,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.041666666666666664,
|
| 27 |
+
"grad_norm": 0.9179525375366211,
|
| 28 |
+
"learning_rate": 6.944444444444445e-06,
|
| 29 |
+
"loss": 0.6948,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05555555555555555,
|
| 34 |
+
"grad_norm": 1.4890326261520386,
|
| 35 |
+
"learning_rate": 9.259259259259259e-06,
|
| 36 |
+
"loss": 0.6827,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06944444444444445,
|
| 41 |
+
"grad_norm": 7.563885688781738,
|
| 42 |
+
"learning_rate": 1.1574074074074075e-05,
|
| 43 |
+
"loss": 0.5348,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08333333333333333,
|
| 48 |
+
"grad_norm": 5.335231781005859,
|
| 49 |
+
"learning_rate": 1.388888888888889e-05,
|
| 50 |
+
"loss": 0.5517,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09722222222222222,
|
| 55 |
+
"grad_norm": 31.28253746032715,
|
| 56 |
+
"learning_rate": 1.6203703703703704e-05,
|
| 57 |
+
"loss": 0.4477,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1111111111111111,
|
| 62 |
+
"grad_norm": 3.2105932235717773,
|
| 63 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 64 |
+
"loss": 0.5092,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.125,
|
| 69 |
+
"grad_norm": 4.380924701690674,
|
| 70 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 71 |
+
"loss": 0.3824,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1388888888888889,
|
| 76 |
+
"grad_norm": 2.6306023597717285,
|
| 77 |
+
"learning_rate": 2.314814814814815e-05,
|
| 78 |
+
"loss": 0.3407,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1527777777777778,
|
| 83 |
+
"grad_norm": 54.588436126708984,
|
| 84 |
+
"learning_rate": 2.5462962962962965e-05,
|
| 85 |
+
"loss": 0.6848,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.16666666666666666,
|
| 90 |
+
"grad_norm": 9.066441535949707,
|
| 91 |
+
"learning_rate": 2.777777777777778e-05,
|
| 92 |
+
"loss": 0.5151,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18055555555555555,
|
| 97 |
+
"grad_norm": 2.912062168121338,
|
| 98 |
+
"learning_rate": 3.0092592592592593e-05,
|
| 99 |
+
"loss": 0.3909,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.19444444444444445,
|
| 104 |
+
"grad_norm": 14.664259910583496,
|
| 105 |
+
"learning_rate": 3.240740740740741e-05,
|
| 106 |
+
"loss": 0.4754,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.20833333333333334,
|
| 111 |
+
"grad_norm": 17.37154769897461,
|
| 112 |
+
"learning_rate": 3.472222222222222e-05,
|
| 113 |
+
"loss": 0.4067,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2222222222222222,
|
| 118 |
+
"grad_norm": 7.159306049346924,
|
| 119 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 120 |
+
"loss": 0.5269,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2361111111111111,
|
| 125 |
+
"grad_norm": 24.980106353759766,
|
| 126 |
+
"learning_rate": 3.935185185185186e-05,
|
| 127 |
+
"loss": 0.3985,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.25,
|
| 132 |
+
"grad_norm": 10.40503215789795,
|
| 133 |
+
"learning_rate": 4.166666666666667e-05,
|
| 134 |
+
"loss": 0.5491,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2638888888888889,
|
| 139 |
+
"grad_norm": 2.9398627281188965,
|
| 140 |
+
"learning_rate": 4.3981481481481486e-05,
|
| 141 |
+
"loss": 0.3183,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2777777777777778,
|
| 146 |
+
"grad_norm": 20.303274154663086,
|
| 147 |
+
"learning_rate": 4.62962962962963e-05,
|
| 148 |
+
"loss": 0.4905,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2916666666666667,
|
| 153 |
+
"grad_norm": 5.474150657653809,
|
| 154 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 155 |
+
"loss": 0.4931,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3055555555555556,
|
| 160 |
+
"grad_norm": 18.128984451293945,
|
| 161 |
+
"learning_rate": 4.9897119341563785e-05,
|
| 162 |
+
"loss": 0.636,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3194444444444444,
|
| 167 |
+
"grad_norm": 41.586219787597656,
|
| 168 |
+
"learning_rate": 4.963991769547325e-05,
|
| 169 |
+
"loss": 0.3997,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3333333333333333,
|
| 174 |
+
"grad_norm": 11.251654624938965,
|
| 175 |
+
"learning_rate": 4.938271604938271e-05,
|
| 176 |
+
"loss": 0.6164,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3472222222222222,
|
| 181 |
+
"grad_norm": 3.6719627380371094,
|
| 182 |
+
"learning_rate": 4.912551440329218e-05,
|
| 183 |
+
"loss": 0.4721,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3611111111111111,
|
| 188 |
+
"grad_norm": 6.4116435050964355,
|
| 189 |
+
"learning_rate": 4.886831275720165e-05,
|
| 190 |
+
"loss": 0.5444,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.375,
|
| 195 |
+
"grad_norm": 8.13191032409668,
|
| 196 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 197 |
+
"loss": 0.4481,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3888888888888889,
|
| 202 |
+
"grad_norm": 2.3826730251312256,
|
| 203 |
+
"learning_rate": 4.835390946502058e-05,
|
| 204 |
+
"loss": 0.4876,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4027777777777778,
|
| 209 |
+
"grad_norm": 9.0649995803833,
|
| 210 |
+
"learning_rate": 4.809670781893004e-05,
|
| 211 |
+
"loss": 0.5457,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4166666666666667,
|
| 216 |
+
"grad_norm": 3.2031192779541016,
|
| 217 |
+
"learning_rate": 4.783950617283951e-05,
|
| 218 |
+
"loss": 0.4291,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4305555555555556,
|
| 223 |
+
"grad_norm": 3.011695384979248,
|
| 224 |
+
"learning_rate": 4.758230452674897e-05,
|
| 225 |
+
"loss": 0.5681,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4444444444444444,
|
| 230 |
+
"grad_norm": 17.774301528930664,
|
| 231 |
+
"learning_rate": 4.732510288065844e-05,
|
| 232 |
+
"loss": 0.5143,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4583333333333333,
|
| 237 |
+
"grad_norm": 3.0613749027252197,
|
| 238 |
+
"learning_rate": 4.70679012345679e-05,
|
| 239 |
+
"loss": 0.603,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4722222222222222,
|
| 244 |
+
"grad_norm": 7.315563201904297,
|
| 245 |
+
"learning_rate": 4.6810699588477366e-05,
|
| 246 |
+
"loss": 0.5161,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4861111111111111,
|
| 251 |
+
"grad_norm": 10.456121444702148,
|
| 252 |
+
"learning_rate": 4.6553497942386833e-05,
|
| 253 |
+
"loss": 0.39,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5,
|
| 258 |
+
"grad_norm": 9.36212158203125,
|
| 259 |
+
"learning_rate": 4.62962962962963e-05,
|
| 260 |
+
"loss": 0.4058,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5138888888888888,
|
| 265 |
+
"grad_norm": 2.4673802852630615,
|
| 266 |
+
"learning_rate": 4.603909465020577e-05,
|
| 267 |
+
"loss": 0.3361,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5277777777777778,
|
| 272 |
+
"grad_norm": 7.2702202796936035,
|
| 273 |
+
"learning_rate": 4.578189300411523e-05,
|
| 274 |
+
"loss": 0.3313,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5416666666666666,
|
| 279 |
+
"grad_norm": 15.533823013305664,
|
| 280 |
+
"learning_rate": 4.5524691358024696e-05,
|
| 281 |
+
"loss": 0.4702,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5555555555555556,
|
| 286 |
+
"grad_norm": 12.91049861907959,
|
| 287 |
+
"learning_rate": 4.5267489711934157e-05,
|
| 288 |
+
"loss": 0.4219,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5694444444444444,
|
| 293 |
+
"grad_norm": 8.368412017822266,
|
| 294 |
+
"learning_rate": 4.5010288065843624e-05,
|
| 295 |
+
"loss": 0.3685,
|
| 296 |
+
"step": 1025
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5833333333333334,
|
| 300 |
+
"grad_norm": 38.96614074707031,
|
| 301 |
+
"learning_rate": 4.4753086419753084e-05,
|
| 302 |
+
"loss": 0.4168,
|
| 303 |
+
"step": 1050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5972222222222222,
|
| 307 |
+
"grad_norm": 5.273324489593506,
|
| 308 |
+
"learning_rate": 4.449588477366255e-05,
|
| 309 |
+
"loss": 0.5382,
|
| 310 |
+
"step": 1075
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6111111111111112,
|
| 314 |
+
"grad_norm": 9.082724571228027,
|
| 315 |
+
"learning_rate": 4.423868312757202e-05,
|
| 316 |
+
"loss": 0.525,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.625,
|
| 321 |
+
"grad_norm": 12.262503623962402,
|
| 322 |
+
"learning_rate": 4.3981481481481486e-05,
|
| 323 |
+
"loss": 0.3931,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6388888888888888,
|
| 328 |
+
"grad_norm": 31.51844596862793,
|
| 329 |
+
"learning_rate": 4.372427983539095e-05,
|
| 330 |
+
"loss": 0.3836,
|
| 331 |
+
"step": 1150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6527777777777778,
|
| 335 |
+
"grad_norm": 4.899830341339111,
|
| 336 |
+
"learning_rate": 4.3467078189300414e-05,
|
| 337 |
+
"loss": 0.4635,
|
| 338 |
+
"step": 1175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6666666666666666,
|
| 342 |
+
"grad_norm": 8.966187477111816,
|
| 343 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 344 |
+
"loss": 0.3706,
|
| 345 |
+
"step": 1200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6805555555555556,
|
| 349 |
+
"grad_norm": 12.4137544631958,
|
| 350 |
+
"learning_rate": 4.295267489711934e-05,
|
| 351 |
+
"loss": 0.6281,
|
| 352 |
+
"step": 1225
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6944444444444444,
|
| 356 |
+
"grad_norm": 4.339605808258057,
|
| 357 |
+
"learning_rate": 4.269547325102881e-05,
|
| 358 |
+
"loss": 0.4616,
|
| 359 |
+
"step": 1250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7083333333333334,
|
| 363 |
+
"grad_norm": 27.38968276977539,
|
| 364 |
+
"learning_rate": 4.243827160493827e-05,
|
| 365 |
+
"loss": 0.4681,
|
| 366 |
+
"step": 1275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7222222222222222,
|
| 370 |
+
"grad_norm": 4.831294059753418,
|
| 371 |
+
"learning_rate": 4.2181069958847744e-05,
|
| 372 |
+
"loss": 0.4135,
|
| 373 |
+
"step": 1300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7361111111111112,
|
| 377 |
+
"grad_norm": 9.18549633026123,
|
| 378 |
+
"learning_rate": 4.1923868312757205e-05,
|
| 379 |
+
"loss": 0.444,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.75,
|
| 384 |
+
"grad_norm": 3.1465399265289307,
|
| 385 |
+
"learning_rate": 4.166666666666667e-05,
|
| 386 |
+
"loss": 0.3754,
|
| 387 |
+
"step": 1350
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7638888888888888,
|
| 391 |
+
"grad_norm": 16.972923278808594,
|
| 392 |
+
"learning_rate": 4.140946502057613e-05,
|
| 393 |
+
"loss": 0.466,
|
| 394 |
+
"step": 1375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7777777777777778,
|
| 398 |
+
"grad_norm": 1.612660527229309,
|
| 399 |
+
"learning_rate": 4.11522633744856e-05,
|
| 400 |
+
"loss": 0.3867,
|
| 401 |
+
"step": 1400
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7916666666666666,
|
| 405 |
+
"grad_norm": 7.258045673370361,
|
| 406 |
+
"learning_rate": 4.089506172839506e-05,
|
| 407 |
+
"loss": 0.5741,
|
| 408 |
+
"step": 1425
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8055555555555556,
|
| 412 |
+
"grad_norm": 7.1187214851379395,
|
| 413 |
+
"learning_rate": 4.063786008230453e-05,
|
| 414 |
+
"loss": 0.4024,
|
| 415 |
+
"step": 1450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8194444444444444,
|
| 419 |
+
"grad_norm": 15.787425994873047,
|
| 420 |
+
"learning_rate": 4.038065843621399e-05,
|
| 421 |
+
"loss": 0.4623,
|
| 422 |
+
"step": 1475
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8333333333333334,
|
| 426 |
+
"grad_norm": 2.3647310733795166,
|
| 427 |
+
"learning_rate": 4.012345679012346e-05,
|
| 428 |
+
"loss": 0.3146,
|
| 429 |
+
"step": 1500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8472222222222222,
|
| 433 |
+
"grad_norm": 3.4890708923339844,
|
| 434 |
+
"learning_rate": 3.986625514403292e-05,
|
| 435 |
+
"loss": 0.3952,
|
| 436 |
+
"step": 1525
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8611111111111112,
|
| 440 |
+
"grad_norm": 17.58116912841797,
|
| 441 |
+
"learning_rate": 3.960905349794239e-05,
|
| 442 |
+
"loss": 0.4454,
|
| 443 |
+
"step": 1550
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.875,
|
| 447 |
+
"grad_norm": 5.0533246994018555,
|
| 448 |
+
"learning_rate": 3.935185185185186e-05,
|
| 449 |
+
"loss": 0.4524,
|
| 450 |
+
"step": 1575
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8888888888888888,
|
| 454 |
+
"grad_norm": 23.176776885986328,
|
| 455 |
+
"learning_rate": 3.909465020576132e-05,
|
| 456 |
+
"loss": 0.401,
|
| 457 |
+
"step": 1600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9027777777777778,
|
| 461 |
+
"grad_norm": 5.863523483276367,
|
| 462 |
+
"learning_rate": 3.8837448559670786e-05,
|
| 463 |
+
"loss": 0.4483,
|
| 464 |
+
"step": 1625
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9166666666666666,
|
| 468 |
+
"grad_norm": 12.402013778686523,
|
| 469 |
+
"learning_rate": 3.8580246913580246e-05,
|
| 470 |
+
"loss": 0.5053,
|
| 471 |
+
"step": 1650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9305555555555556,
|
| 475 |
+
"grad_norm": 2.132073402404785,
|
| 476 |
+
"learning_rate": 3.8323045267489713e-05,
|
| 477 |
+
"loss": 0.3247,
|
| 478 |
+
"step": 1675
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9444444444444444,
|
| 482 |
+
"grad_norm": 2.4326186180114746,
|
| 483 |
+
"learning_rate": 3.806584362139918e-05,
|
| 484 |
+
"loss": 0.4661,
|
| 485 |
+
"step": 1700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9583333333333334,
|
| 489 |
+
"grad_norm": 14.031126976013184,
|
| 490 |
+
"learning_rate": 3.780864197530865e-05,
|
| 491 |
+
"loss": 0.4249,
|
| 492 |
+
"step": 1725
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.9722222222222222,
|
| 496 |
+
"grad_norm": 24.70652198791504,
|
| 497 |
+
"learning_rate": 3.755144032921811e-05,
|
| 498 |
+
"loss": 0.3789,
|
| 499 |
+
"step": 1750
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.9861111111111112,
|
| 503 |
+
"grad_norm": 2.8892605304718018,
|
| 504 |
+
"learning_rate": 3.7294238683127576e-05,
|
| 505 |
+
"loss": 0.4248,
|
| 506 |
+
"step": 1775
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.0,
|
| 510 |
+
"grad_norm": 6.622640132904053,
|
| 511 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 512 |
+
"loss": 0.3189,
|
| 513 |
+
"step": 1800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.0,
|
| 517 |
+
"eval_accuracy": 0.865,
|
| 518 |
+
"eval_auc": 0.9395007159925164,
|
| 519 |
+
"eval_f1": 0.869073275862069,
|
| 520 |
+
"eval_loss": 0.35031697154045105,
|
| 521 |
+
"eval_precision": 0.8529878371232152,
|
| 522 |
+
"eval_recall": 0.885777045579352,
|
| 523 |
+
"eval_runtime": 1007.1559,
|
| 524 |
+
"eval_samples_per_second": 3.574,
|
| 525 |
+
"eval_steps_per_second": 0.223,
|
| 526 |
+
"step": 1800
|
| 527 |
+
}
|
| 528 |
+
],
|
| 529 |
+
"logging_steps": 25,
|
| 530 |
+
"max_steps": 5400,
|
| 531 |
+
"num_input_tokens_seen": 0,
|
| 532 |
+
"num_train_epochs": 3,
|
| 533 |
+
"save_steps": 500,
|
| 534 |
+
"stateful_callbacks": {
|
| 535 |
+
"EarlyStoppingCallback": {
|
| 536 |
+
"args": {
|
| 537 |
+
"early_stopping_patience": 5,
|
| 538 |
+
"early_stopping_threshold": 0.01
|
| 539 |
+
},
|
| 540 |
+
"attributes": {
|
| 541 |
+
"early_stopping_patience_counter": 0
|
| 542 |
+
}
|
| 543 |
+
},
|
| 544 |
+
"TrainerControl": {
|
| 545 |
+
"args": {
|
| 546 |
+
"should_epoch_stop": false,
|
| 547 |
+
"should_evaluate": false,
|
| 548 |
+
"should_log": false,
|
| 549 |
+
"should_save": true,
|
| 550 |
+
"should_training_stop": false
|
| 551 |
+
},
|
| 552 |
+
"attributes": {}
|
| 553 |
+
}
|
| 554 |
+
},
|
| 555 |
+
"total_flos": 947216786227200.0,
|
| 556 |
+
"train_batch_size": 8,
|
| 557 |
+
"trial_name": null,
|
| 558 |
+
"trial_params": null
|
| 559 |
+
}
|
checkpoint-1800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afc3281b29435ebde1a6c9055a693bfe2cfe70cd18c3868bff897a95d6c83d86
|
| 3 |
+
size 5176
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 3 |
+
"_num_labels": 2,
|
| 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": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "n\u00e9gatif",
|
| 13 |
+
"1": "positif"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"n\u00e9gatif": 0,
|
| 19 |
+
"positif": 1
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-07,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"max_relative_positions": -1,
|
| 24 |
+
"model_type": "deberta-v2",
|
| 25 |
+
"norm_rel_ebd": "layer_norm",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_dropout": 0,
|
| 30 |
+
"pooler_hidden_act": "gelu",
|
| 31 |
+
"pooler_hidden_size": 768,
|
| 32 |
+
"pos_att_type": [
|
| 33 |
+
"p2c",
|
| 34 |
+
"c2p"
|
| 35 |
+
],
|
| 36 |
+
"position_biased_input": false,
|
| 37 |
+
"position_buckets": 256,
|
| 38 |
+
"relative_attention": true,
|
| 39 |
+
"share_att_key": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.41.0",
|
| 42 |
+
"type_vocab_size": 0,
|
| 43 |
+
"vocab_size": 128100
|
| 44 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d2695e10fae203b54db36a56aca65a5113be059968b5bbde76d3b070dda2cce
|
| 3 |
+
size 737719272
|
runs/Jun06_00-39-21_r-nansk13-bert-auto-sent-multi-6iitkada-8a0be-1lk3n/events.out.tfevents.1717634367.r-nansk13-bert-auto-sent-multi-6iitkada-8a0be-1lk3n.107.0
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:f6584281be43387212ba5649c9288043ac5a35eaf7a115937b58dea0982f2778
|
| 3 |
+
size 52605
|
runs/Jun06_00-39-21_r-nansk13-bert-auto-sent-multi-6iitkada-8a0be-1lk3n/events.out.tfevents.1717681878.r-nansk13-bert-auto-sent-multi-6iitkada-8a0be-1lk3n.107.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5293b48ae6585660edb5139b422faa2036ff68a5146eddae36df2cbf466a2332
|
| 3 |
+
size 607
|
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:afc3281b29435ebde1a6c9055a693bfe2cfe70cd18c3868bff897a95d6c83d86
|
| 3 |
+
size 5176
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "deberta-sent-multi/autotrain-data",
|
| 3 |
+
"model": "microsoft/deberta-v3-base",
|
| 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": "deberta-sent-multi",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"push_to_hub": true,
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"username": "NansK13",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|