Commit
·
06f4a4a
1
Parent(s):
6564815
Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-8000/config.json +43 -0
- checkpoint-8000/model.safetensors +3 -0
- checkpoint-8000/optimizer.pt +3 -0
- checkpoint-8000/rng_state.pth +3 -0
- checkpoint-8000/scheduler.pt +3 -0
- checkpoint-8000/trainer_state.json +551 -0
- checkpoint-8000/training_args.bin +3 -0
- config.json +43 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +1 -0
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
widget:
|
| 7 |
+
- text: "I love AutoTrain"
|
| 8 |
+
datasets:
|
| 9 |
+
- MatteoWood/autotrain-data-albert-sexism-classifier
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.40832215547561646
|
| 18 |
+
|
| 19 |
+
f1: 0.6293779404077365
|
| 20 |
+
|
| 21 |
+
precision: 0.6522210184182016
|
| 22 |
+
|
| 23 |
+
recall: 0.6080808080808081
|
| 24 |
+
|
| 25 |
+
auc: 0.8514470284237725
|
| 26 |
+
|
| 27 |
+
accuracy: 0.82275
|
checkpoint-8000/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "albert-base-v2",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"AlbertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"classifier_dropout_prob": 0.1,
|
| 10 |
+
"down_scale_factor": 1,
|
| 11 |
+
"embedding_size": 128,
|
| 12 |
+
"eos_token_id": 3,
|
| 13 |
+
"gap_size": 0,
|
| 14 |
+
"hidden_act": "gelu_new",
|
| 15 |
+
"hidden_dropout_prob": 0,
|
| 16 |
+
"hidden_size": 768,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "not sexist",
|
| 19 |
+
"1": "sexist"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"inner_group_num": 1,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"not sexist": 0,
|
| 26 |
+
"sexist": 1
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"max_position_embeddings": 512,
|
| 30 |
+
"model_type": "albert",
|
| 31 |
+
"net_structure_type": 0,
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_groups": 1,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
+
"num_memory_blocks": 0,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.35.1",
|
| 41 |
+
"type_vocab_size": 2,
|
| 42 |
+
"vocab_size": 30000
|
| 43 |
+
}
|
checkpoint-8000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ef98c6ba2ed59e63787e0fd975ce8dabc4c44d40e9e1486a4882907d5777aad
|
| 3 |
+
size 46743912
|
checkpoint-8000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c60f6c447a23dd400283d18299436ab63833a110c4d47a325140c2141108702
|
| 3 |
+
size 93503245
|
checkpoint-8000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c85861af070ab4f9a2f383148a760ec3ae2933b738ff31e06ae1f187cbb6276
|
| 3 |
+
size 13990
|
checkpoint-8000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5e65f0a50b8a4b30324b008b8f16f579abbf3e3aa3a1c8a0e7a945a49f2698f
|
| 3 |
+
size 1064
|
checkpoint-8000/trainer_state.json
ADDED
|
@@ -0,0 +1,551 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.40832215547561646,
|
| 3 |
+
"best_model_checkpoint": "/tmp/model/checkpoint-8000",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8000,
|
| 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 |
+
"learning_rate": 5e-06,
|
| 14 |
+
"loss": 0.6721,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 1e-05,
|
| 20 |
+
"loss": 0.5211,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 1.5e-05,
|
| 26 |
+
"loss": 0.5088,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.2,
|
| 31 |
+
"learning_rate": 2e-05,
|
| 32 |
+
"loss": 0.4878,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.25,
|
| 37 |
+
"learning_rate": 2.5e-05,
|
| 38 |
+
"loss": 0.4926,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.3,
|
| 43 |
+
"learning_rate": 3e-05,
|
| 44 |
+
"loss": 0.5278,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.35,
|
| 49 |
+
"learning_rate": 3.5e-05,
|
| 50 |
+
"loss": 0.4698,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"learning_rate": 4e-05,
|
| 56 |
+
"loss": 0.5079,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.45,
|
| 61 |
+
"learning_rate": 4.5e-05,
|
| 62 |
+
"loss": 0.5097,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.5,
|
| 67 |
+
"learning_rate": 5e-05,
|
| 68 |
+
"loss": 0.5008,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.55,
|
| 73 |
+
"learning_rate": 4.9444444444444446e-05,
|
| 74 |
+
"loss": 0.583,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.6,
|
| 79 |
+
"learning_rate": 4.888888888888889e-05,
|
| 80 |
+
"loss": 0.5405,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.65,
|
| 85 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 86 |
+
"loss": 0.5719,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7,
|
| 91 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 92 |
+
"loss": 0.5587,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.75,
|
| 97 |
+
"learning_rate": 4.722222222222222e-05,
|
| 98 |
+
"loss": 0.5935,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.8,
|
| 103 |
+
"learning_rate": 4.666666666666667e-05,
|
| 104 |
+
"loss": 0.6098,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.85,
|
| 109 |
+
"learning_rate": 4.6111111111111115e-05,
|
| 110 |
+
"loss": 0.5785,
|
| 111 |
+
"step": 1700
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.9,
|
| 115 |
+
"learning_rate": 4.555555555555556e-05,
|
| 116 |
+
"loss": 0.5504,
|
| 117 |
+
"step": 1800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.95,
|
| 121 |
+
"learning_rate": 4.5e-05,
|
| 122 |
+
"loss": 0.528,
|
| 123 |
+
"step": 1900
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0,
|
| 127 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 128 |
+
"loss": 0.5097,
|
| 129 |
+
"step": 2000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.0,
|
| 133 |
+
"eval_accuracy": 0.82325,
|
| 134 |
+
"eval_auc": 0.7562535655558911,
|
| 135 |
+
"eval_f1": 0.4812912692589876,
|
| 136 |
+
"eval_loss": 0.46430468559265137,
|
| 137 |
+
"eval_precision": 0.8793565683646113,
|
| 138 |
+
"eval_recall": 0.33131313131313134,
|
| 139 |
+
"eval_runtime": 732.6664,
|
| 140 |
+
"eval_samples_per_second": 5.46,
|
| 141 |
+
"eval_steps_per_second": 0.341,
|
| 142 |
+
"step": 2000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.05,
|
| 146 |
+
"learning_rate": 4.388888888888889e-05,
|
| 147 |
+
"loss": 0.4879,
|
| 148 |
+
"step": 2100
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.1,
|
| 152 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 153 |
+
"loss": 0.4754,
|
| 154 |
+
"step": 2200
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.15,
|
| 158 |
+
"learning_rate": 4.277777777777778e-05,
|
| 159 |
+
"loss": 0.4998,
|
| 160 |
+
"step": 2300
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.2,
|
| 164 |
+
"learning_rate": 4.222222222222222e-05,
|
| 165 |
+
"loss": 0.491,
|
| 166 |
+
"step": 2400
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.25,
|
| 170 |
+
"learning_rate": 4.166666666666667e-05,
|
| 171 |
+
"loss": 0.4905,
|
| 172 |
+
"step": 2500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.3,
|
| 176 |
+
"learning_rate": 4.111111111111111e-05,
|
| 177 |
+
"loss": 0.4822,
|
| 178 |
+
"step": 2600
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.35,
|
| 182 |
+
"learning_rate": 4.055555555555556e-05,
|
| 183 |
+
"loss": 0.4856,
|
| 184 |
+
"step": 2700
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.4,
|
| 188 |
+
"learning_rate": 4e-05,
|
| 189 |
+
"loss": 0.4613,
|
| 190 |
+
"step": 2800
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.45,
|
| 194 |
+
"learning_rate": 3.944444444444445e-05,
|
| 195 |
+
"loss": 0.4575,
|
| 196 |
+
"step": 2900
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.5,
|
| 200 |
+
"learning_rate": 3.888888888888889e-05,
|
| 201 |
+
"loss": 0.4852,
|
| 202 |
+
"step": 3000
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.55,
|
| 206 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 207 |
+
"loss": 0.4677,
|
| 208 |
+
"step": 3100
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.6,
|
| 212 |
+
"learning_rate": 3.777777777777778e-05,
|
| 213 |
+
"loss": 0.471,
|
| 214 |
+
"step": 3200
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.65,
|
| 218 |
+
"learning_rate": 3.722222222222222e-05,
|
| 219 |
+
"loss": 0.5252,
|
| 220 |
+
"step": 3300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.7,
|
| 224 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 225 |
+
"loss": 0.4541,
|
| 226 |
+
"step": 3400
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.75,
|
| 230 |
+
"learning_rate": 3.611111111111111e-05,
|
| 231 |
+
"loss": 0.4445,
|
| 232 |
+
"step": 3500
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.8,
|
| 236 |
+
"learning_rate": 3.555555555555556e-05,
|
| 237 |
+
"loss": 0.4596,
|
| 238 |
+
"step": 3600
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.85,
|
| 242 |
+
"learning_rate": 3.5e-05,
|
| 243 |
+
"loss": 0.4849,
|
| 244 |
+
"step": 3700
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.9,
|
| 248 |
+
"learning_rate": 3.444444444444445e-05,
|
| 249 |
+
"loss": 0.4627,
|
| 250 |
+
"step": 3800
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.95,
|
| 254 |
+
"learning_rate": 3.388888888888889e-05,
|
| 255 |
+
"loss": 0.4527,
|
| 256 |
+
"step": 3900
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.0,
|
| 260 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 261 |
+
"loss": 0.5032,
|
| 262 |
+
"step": 4000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.0,
|
| 266 |
+
"eval_accuracy": 0.81575,
|
| 267 |
+
"eval_auc": 0.6002357461659787,
|
| 268 |
+
"eval_f1": 0.43088803088803085,
|
| 269 |
+
"eval_loss": 0.4803480803966522,
|
| 270 |
+
"eval_precision": 0.9147540983606557,
|
| 271 |
+
"eval_recall": 0.2818181818181818,
|
| 272 |
+
"eval_runtime": 839.8305,
|
| 273 |
+
"eval_samples_per_second": 4.763,
|
| 274 |
+
"eval_steps_per_second": 0.298,
|
| 275 |
+
"step": 4000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.05,
|
| 279 |
+
"learning_rate": 3.277777777777778e-05,
|
| 280 |
+
"loss": 0.4538,
|
| 281 |
+
"step": 4100
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.1,
|
| 285 |
+
"learning_rate": 3.222222222222223e-05,
|
| 286 |
+
"loss": 0.5285,
|
| 287 |
+
"step": 4200
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.15,
|
| 291 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 292 |
+
"loss": 0.521,
|
| 293 |
+
"step": 4300
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.2,
|
| 297 |
+
"learning_rate": 3.111111111111111e-05,
|
| 298 |
+
"loss": 0.4688,
|
| 299 |
+
"step": 4400
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.25,
|
| 303 |
+
"learning_rate": 3.055555555555556e-05,
|
| 304 |
+
"loss": 0.475,
|
| 305 |
+
"step": 4500
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.3,
|
| 309 |
+
"learning_rate": 3e-05,
|
| 310 |
+
"loss": 0.4601,
|
| 311 |
+
"step": 4600
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.35,
|
| 315 |
+
"learning_rate": 2.9444444444444448e-05,
|
| 316 |
+
"loss": 0.4704,
|
| 317 |
+
"step": 4700
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.4,
|
| 321 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 322 |
+
"loss": 0.4612,
|
| 323 |
+
"step": 4800
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.45,
|
| 327 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 328 |
+
"loss": 0.5431,
|
| 329 |
+
"step": 4900
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.5,
|
| 333 |
+
"learning_rate": 2.777777777777778e-05,
|
| 334 |
+
"loss": 0.4435,
|
| 335 |
+
"step": 5000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.55,
|
| 339 |
+
"learning_rate": 2.7222222222222223e-05,
|
| 340 |
+
"loss": 0.5247,
|
| 341 |
+
"step": 5100
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.6,
|
| 345 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 346 |
+
"loss": 0.4707,
|
| 347 |
+
"step": 5200
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.65,
|
| 351 |
+
"learning_rate": 2.6111111111111114e-05,
|
| 352 |
+
"loss": 0.4859,
|
| 353 |
+
"step": 5300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.7,
|
| 357 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 358 |
+
"loss": 0.4493,
|
| 359 |
+
"step": 5400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.75,
|
| 363 |
+
"learning_rate": 2.5e-05,
|
| 364 |
+
"loss": 0.4551,
|
| 365 |
+
"step": 5500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.8,
|
| 369 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 370 |
+
"loss": 0.4418,
|
| 371 |
+
"step": 5600
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.85,
|
| 375 |
+
"learning_rate": 2.3888888888888892e-05,
|
| 376 |
+
"loss": 0.4,
|
| 377 |
+
"step": 5700
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.9,
|
| 381 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 382 |
+
"loss": 0.4447,
|
| 383 |
+
"step": 5800
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.95,
|
| 387 |
+
"learning_rate": 2.277777777777778e-05,
|
| 388 |
+
"loss": 0.4662,
|
| 389 |
+
"step": 5900
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.0,
|
| 393 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 394 |
+
"loss": 0.4614,
|
| 395 |
+
"step": 6000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.0,
|
| 399 |
+
"eval_accuracy": 0.8225,
|
| 400 |
+
"eval_auc": 0.8300171146682774,
|
| 401 |
+
"eval_f1": 0.4637462235649546,
|
| 402 |
+
"eval_loss": 0.4134385883808136,
|
| 403 |
+
"eval_precision": 0.9191616766467066,
|
| 404 |
+
"eval_recall": 0.3101010101010101,
|
| 405 |
+
"eval_runtime": 1074.678,
|
| 406 |
+
"eval_samples_per_second": 3.722,
|
| 407 |
+
"eval_steps_per_second": 0.233,
|
| 408 |
+
"step": 6000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.05,
|
| 412 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 413 |
+
"loss": 0.3887,
|
| 414 |
+
"step": 6100
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.1,
|
| 418 |
+
"learning_rate": 2.111111111111111e-05,
|
| 419 |
+
"loss": 0.4219,
|
| 420 |
+
"step": 6200
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 3.15,
|
| 424 |
+
"learning_rate": 2.0555555555555555e-05,
|
| 425 |
+
"loss": 0.4113,
|
| 426 |
+
"step": 6300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 3.2,
|
| 430 |
+
"learning_rate": 2e-05,
|
| 431 |
+
"loss": 0.4091,
|
| 432 |
+
"step": 6400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.25,
|
| 436 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 437 |
+
"loss": 0.4306,
|
| 438 |
+
"step": 6500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 3.3,
|
| 442 |
+
"learning_rate": 1.888888888888889e-05,
|
| 443 |
+
"loss": 0.3961,
|
| 444 |
+
"step": 6600
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.35,
|
| 448 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 449 |
+
"loss": 0.4306,
|
| 450 |
+
"step": 6700
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.4,
|
| 454 |
+
"learning_rate": 1.777777777777778e-05,
|
| 455 |
+
"loss": 0.3746,
|
| 456 |
+
"step": 6800
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.45,
|
| 460 |
+
"learning_rate": 1.7222222222222224e-05,
|
| 461 |
+
"loss": 0.3861,
|
| 462 |
+
"step": 6900
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 3.5,
|
| 466 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 467 |
+
"loss": 0.4354,
|
| 468 |
+
"step": 7000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.55,
|
| 472 |
+
"learning_rate": 1.6111111111111115e-05,
|
| 473 |
+
"loss": 0.426,
|
| 474 |
+
"step": 7100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.6,
|
| 478 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 479 |
+
"loss": 0.3891,
|
| 480 |
+
"step": 7200
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 3.65,
|
| 484 |
+
"learning_rate": 1.5e-05,
|
| 485 |
+
"loss": 0.4191,
|
| 486 |
+
"step": 7300
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 3.7,
|
| 490 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 491 |
+
"loss": 0.3823,
|
| 492 |
+
"step": 7400
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 3.75,
|
| 496 |
+
"learning_rate": 1.388888888888889e-05,
|
| 497 |
+
"loss": 0.4206,
|
| 498 |
+
"step": 7500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.8,
|
| 502 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 503 |
+
"loss": 0.374,
|
| 504 |
+
"step": 7600
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.85,
|
| 508 |
+
"learning_rate": 1.2777777777777777e-05,
|
| 509 |
+
"loss": 0.3572,
|
| 510 |
+
"step": 7700
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.9,
|
| 514 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 515 |
+
"loss": 0.395,
|
| 516 |
+
"step": 7800
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 3.95,
|
| 520 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 521 |
+
"loss": 0.3888,
|
| 522 |
+
"step": 7900
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 4.0,
|
| 526 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 527 |
+
"loss": 0.3896,
|
| 528 |
+
"step": 8000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.0,
|
| 532 |
+
"eval_accuracy": 0.82275,
|
| 533 |
+
"eval_auc": 0.8514470284237725,
|
| 534 |
+
"eval_f1": 0.6293779404077365,
|
| 535 |
+
"eval_loss": 0.40832215547561646,
|
| 536 |
+
"eval_precision": 0.6522210184182016,
|
| 537 |
+
"eval_recall": 0.6080808080808081,
|
| 538 |
+
"eval_runtime": 1078.952,
|
| 539 |
+
"eval_samples_per_second": 3.707,
|
| 540 |
+
"eval_steps_per_second": 0.232,
|
| 541 |
+
"step": 8000
|
| 542 |
+
}
|
| 543 |
+
],
|
| 544 |
+
"logging_steps": 100,
|
| 545 |
+
"max_steps": 10000,
|
| 546 |
+
"num_train_epochs": 5,
|
| 547 |
+
"save_steps": 500,
|
| 548 |
+
"total_flos": 382369628160000.0,
|
| 549 |
+
"trial_name": null,
|
| 550 |
+
"trial_params": null
|
| 551 |
+
}
|
checkpoint-8000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82f2d2bf8fedec6d9da51d644376ecec88e78dbb19d89e7700383f3b72797891
|
| 3 |
+
size 4600
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "albert-base-v2",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"AlbertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"classifier_dropout_prob": 0.1,
|
| 10 |
+
"down_scale_factor": 1,
|
| 11 |
+
"embedding_size": 128,
|
| 12 |
+
"eos_token_id": 3,
|
| 13 |
+
"gap_size": 0,
|
| 14 |
+
"hidden_act": "gelu_new",
|
| 15 |
+
"hidden_dropout_prob": 0,
|
| 16 |
+
"hidden_size": 768,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "not sexist",
|
| 19 |
+
"1": "sexist"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"inner_group_num": 1,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"not sexist": 0,
|
| 26 |
+
"sexist": 1
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"max_position_embeddings": 512,
|
| 30 |
+
"model_type": "albert",
|
| 31 |
+
"net_structure_type": 0,
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_groups": 1,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
+
"num_memory_blocks": 0,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.35.1",
|
| 41 |
+
"type_vocab_size": 2,
|
| 42 |
+
"vocab_size": 30000
|
| 43 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ef98c6ba2ed59e63787e0fd975ce8dabc4c44d40e9e1486a4882907d5777aad
|
| 3 |
+
size 46743912
|
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": {
|
| 6 |
+
"content": "[MASK]",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "[SEP]",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
| 3 |
+
size 760289
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": true,
|
| 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": true,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"keep_accents": false,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"remove_space": true,
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"tokenizer_class": "AlbertTokenizer",
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82f2d2bf8fedec6d9da51d644376ecec88e78dbb19d89e7700383f3b72797891
|
| 3 |
+
size 4600
|
training_params.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"data_path": "MatteoWood/autotrain-data-albert-sexism-classifier", "model": "albert-base-v2", "lr": 5e-05, "epochs": 5, "max_seq_length": 128, "batch_size": 8, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "train_split": "train", "valid_split": "validation", "text_column": "autotrain_text", "target_column": "autotrain_label", "logging_steps": -1, "project_name": "/tmp/model", "auto_find_batch_size": false, "fp16": false, "save_total_limit": 1, "save_strategy": "epoch", "push_to_hub": true, "repo_id": "MatteoWood/albert-sexism-classifier-0", "evaluation_strategy": "epoch", "username": "MatteoWood", "log": "none"}
|