Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-87/config.json +36 -0
- checkpoint-87/model.safetensors +3 -0
- checkpoint-87/optimizer.pt +3 -0
- checkpoint-87/rng_state.pth +3 -0
- checkpoint-87/scheduler.pt +3 -0
- checkpoint-87/trainer_state.json +669 -0
- checkpoint-87/training_args.bin +3 -0
- config.json +36 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -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 |
+
- autotrain-dqbuy-csoh4/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.001261080033145845
|
| 18 |
+
|
| 19 |
+
f1: 1.0
|
| 20 |
+
|
| 21 |
+
precision: 1.0
|
| 22 |
+
|
| 23 |
+
recall: 1.0
|
| 24 |
+
|
| 25 |
+
auc: 1.0
|
| 26 |
+
|
| 27 |
+
accuracy: 1.0
|
checkpoint-87/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 0,
|
| 15 |
+
"1": 1
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"0": 0,
|
| 21 |
+
"1": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.39.0",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
checkpoint-87/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56885b528b3e7ffa356e4fd5236be511d1302e589866ad4e49fa7eaa80cde10d
|
| 3 |
+
size 437958648
|
checkpoint-87/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e35432f974f2b9145ae4ad81810ac49b9974d085ccfa5b40c03654669ff0dcab
|
| 3 |
+
size 876032762
|
checkpoint-87/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f59653fa629d1bac9f942af8734e27353c82eee90693f576f8197c43d758dfa5
|
| 3 |
+
size 13990
|
checkpoint-87/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:721216a32fabcd50e0932d4e8fba1d367f6616dd55a64b4ce0cb538742bf3307
|
| 3 |
+
size 1064
|
checkpoint-87/trainer_state.json
ADDED
|
@@ -0,0 +1,669 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.001261080033145845,
|
| 3 |
+
"best_model_checkpoint": "autotrain-dqbuy-csoh4/checkpoint-87",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 87,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 2.824599027633667,
|
| 14 |
+
"learning_rate": 5.555555555555556e-06,
|
| 15 |
+
"loss": 0.7058,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07,
|
| 20 |
+
"grad_norm": 6.748022556304932,
|
| 21 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 22 |
+
"loss": 0.7086,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1,
|
| 27 |
+
"grad_norm": 4.103569507598877,
|
| 28 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 29 |
+
"loss": 0.6357,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.14,
|
| 34 |
+
"grad_norm": 4.464776515960693,
|
| 35 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 36 |
+
"loss": 0.7411,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.17,
|
| 41 |
+
"grad_norm": 4.445616245269775,
|
| 42 |
+
"learning_rate": 2.777777777777778e-05,
|
| 43 |
+
"loss": 0.7055,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"grad_norm": 4.427251815795898,
|
| 49 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 50 |
+
"loss": 0.658,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.24,
|
| 55 |
+
"grad_norm": 6.564526557922363,
|
| 56 |
+
"learning_rate": 3.888888888888889e-05,
|
| 57 |
+
"loss": 0.5802,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.28,
|
| 62 |
+
"grad_norm": 9.006092071533203,
|
| 63 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 64 |
+
"loss": 0.5654,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.31,
|
| 69 |
+
"grad_norm": 7.685911178588867,
|
| 70 |
+
"learning_rate": 5e-05,
|
| 71 |
+
"loss": 0.4856,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.34,
|
| 76 |
+
"grad_norm": 7.40333890914917,
|
| 77 |
+
"learning_rate": 4.935897435897436e-05,
|
| 78 |
+
"loss": 0.4301,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.38,
|
| 83 |
+
"grad_norm": 6.077232360839844,
|
| 84 |
+
"learning_rate": 4.871794871794872e-05,
|
| 85 |
+
"loss": 0.4697,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.41,
|
| 90 |
+
"grad_norm": 5.466095924377441,
|
| 91 |
+
"learning_rate": 4.8076923076923084e-05,
|
| 92 |
+
"loss": 0.3609,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.45,
|
| 97 |
+
"grad_norm": 5.6128926277160645,
|
| 98 |
+
"learning_rate": 4.7435897435897435e-05,
|
| 99 |
+
"loss": 0.3193,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.48,
|
| 104 |
+
"grad_norm": 8.095768928527832,
|
| 105 |
+
"learning_rate": 4.67948717948718e-05,
|
| 106 |
+
"loss": 0.3874,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.52,
|
| 111 |
+
"grad_norm": 9.85012435913086,
|
| 112 |
+
"learning_rate": 4.615384615384616e-05,
|
| 113 |
+
"loss": 0.4325,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.55,
|
| 118 |
+
"grad_norm": 6.090405464172363,
|
| 119 |
+
"learning_rate": 4.5512820512820516e-05,
|
| 120 |
+
"loss": 0.2458,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.59,
|
| 125 |
+
"grad_norm": 6.12266206741333,
|
| 126 |
+
"learning_rate": 4.4871794871794874e-05,
|
| 127 |
+
"loss": 0.212,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.62,
|
| 132 |
+
"grad_norm": 7.611598491668701,
|
| 133 |
+
"learning_rate": 4.423076923076923e-05,
|
| 134 |
+
"loss": 0.3424,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.66,
|
| 139 |
+
"grad_norm": 4.582031726837158,
|
| 140 |
+
"learning_rate": 4.358974358974359e-05,
|
| 141 |
+
"loss": 0.1958,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.69,
|
| 146 |
+
"grad_norm": 3.4648311138153076,
|
| 147 |
+
"learning_rate": 4.294871794871795e-05,
|
| 148 |
+
"loss": 0.1415,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.72,
|
| 153 |
+
"grad_norm": 3.185857057571411,
|
| 154 |
+
"learning_rate": 4.230769230769231e-05,
|
| 155 |
+
"loss": 0.1007,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.76,
|
| 160 |
+
"grad_norm": 3.845075845718384,
|
| 161 |
+
"learning_rate": 4.166666666666667e-05,
|
| 162 |
+
"loss": 0.1594,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.79,
|
| 167 |
+
"grad_norm": 3.450348377227783,
|
| 168 |
+
"learning_rate": 4.1025641025641023e-05,
|
| 169 |
+
"loss": 0.1306,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.83,
|
| 174 |
+
"grad_norm": 2.483905553817749,
|
| 175 |
+
"learning_rate": 4.038461538461539e-05,
|
| 176 |
+
"loss": 0.094,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.86,
|
| 181 |
+
"grad_norm": 1.797173261642456,
|
| 182 |
+
"learning_rate": 3.974358974358974e-05,
|
| 183 |
+
"loss": 0.0627,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9,
|
| 188 |
+
"grad_norm": 2.8019638061523438,
|
| 189 |
+
"learning_rate": 3.9102564102564105e-05,
|
| 190 |
+
"loss": 0.101,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.93,
|
| 195 |
+
"grad_norm": 1.3755440711975098,
|
| 196 |
+
"learning_rate": 3.846153846153846e-05,
|
| 197 |
+
"loss": 0.0512,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.97,
|
| 202 |
+
"grad_norm": 3.547283887863159,
|
| 203 |
+
"learning_rate": 3.782051282051282e-05,
|
| 204 |
+
"loss": 0.0754,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.0,
|
| 209 |
+
"grad_norm": 1.6434054374694824,
|
| 210 |
+
"learning_rate": 3.717948717948718e-05,
|
| 211 |
+
"loss": 0.0561,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0,
|
| 216 |
+
"eval_accuracy": 1.0,
|
| 217 |
+
"eval_auc": 1.0,
|
| 218 |
+
"eval_f1": 1.0,
|
| 219 |
+
"eval_loss": 0.03799514099955559,
|
| 220 |
+
"eval_precision": 1.0,
|
| 221 |
+
"eval_recall": 1.0,
|
| 222 |
+
"eval_runtime": 12.4273,
|
| 223 |
+
"eval_samples_per_second": 4.667,
|
| 224 |
+
"eval_steps_per_second": 0.322,
|
| 225 |
+
"step": 29
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.03,
|
| 229 |
+
"grad_norm": 1.0573060512542725,
|
| 230 |
+
"learning_rate": 3.653846153846154e-05,
|
| 231 |
+
"loss": 0.0401,
|
| 232 |
+
"step": 30
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.07,
|
| 236 |
+
"grad_norm": 1.024086833000183,
|
| 237 |
+
"learning_rate": 3.58974358974359e-05,
|
| 238 |
+
"loss": 0.0351,
|
| 239 |
+
"step": 31
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.1,
|
| 243 |
+
"grad_norm": 1.4142544269561768,
|
| 244 |
+
"learning_rate": 3.525641025641026e-05,
|
| 245 |
+
"loss": 0.0479,
|
| 246 |
+
"step": 32
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.14,
|
| 250 |
+
"grad_norm": 0.5282940864562988,
|
| 251 |
+
"learning_rate": 3.461538461538462e-05,
|
| 252 |
+
"loss": 0.0184,
|
| 253 |
+
"step": 33
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.17,
|
| 257 |
+
"grad_norm": 0.584181547164917,
|
| 258 |
+
"learning_rate": 3.397435897435898e-05,
|
| 259 |
+
"loss": 0.0205,
|
| 260 |
+
"step": 34
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.21,
|
| 264 |
+
"grad_norm": 0.4381491541862488,
|
| 265 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 266 |
+
"loss": 0.0151,
|
| 267 |
+
"step": 35
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.24,
|
| 271 |
+
"grad_norm": 0.584669291973114,
|
| 272 |
+
"learning_rate": 3.269230769230769e-05,
|
| 273 |
+
"loss": 0.0178,
|
| 274 |
+
"step": 36
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.28,
|
| 278 |
+
"grad_norm": 0.42940378189086914,
|
| 279 |
+
"learning_rate": 3.205128205128206e-05,
|
| 280 |
+
"loss": 0.0148,
|
| 281 |
+
"step": 37
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.31,
|
| 285 |
+
"grad_norm": 0.4280998706817627,
|
| 286 |
+
"learning_rate": 3.141025641025641e-05,
|
| 287 |
+
"loss": 0.0141,
|
| 288 |
+
"step": 38
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.34,
|
| 292 |
+
"grad_norm": 0.25962451100349426,
|
| 293 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 294 |
+
"loss": 0.0089,
|
| 295 |
+
"step": 39
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.38,
|
| 299 |
+
"grad_norm": 0.28061753511428833,
|
| 300 |
+
"learning_rate": 3.012820512820513e-05,
|
| 301 |
+
"loss": 0.0094,
|
| 302 |
+
"step": 40
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.41,
|
| 306 |
+
"grad_norm": 0.18858705461025238,
|
| 307 |
+
"learning_rate": 2.948717948717949e-05,
|
| 308 |
+
"loss": 0.0066,
|
| 309 |
+
"step": 41
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.45,
|
| 313 |
+
"grad_norm": 0.20241191983222961,
|
| 314 |
+
"learning_rate": 2.8846153846153845e-05,
|
| 315 |
+
"loss": 0.007,
|
| 316 |
+
"step": 42
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.48,
|
| 320 |
+
"grad_norm": 0.31241366267204285,
|
| 321 |
+
"learning_rate": 2.8205128205128207e-05,
|
| 322 |
+
"loss": 0.0071,
|
| 323 |
+
"step": 43
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.52,
|
| 327 |
+
"grad_norm": 0.1785881519317627,
|
| 328 |
+
"learning_rate": 2.756410256410257e-05,
|
| 329 |
+
"loss": 0.0064,
|
| 330 |
+
"step": 44
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.55,
|
| 334 |
+
"grad_norm": 0.12396790832281113,
|
| 335 |
+
"learning_rate": 2.6923076923076923e-05,
|
| 336 |
+
"loss": 0.0045,
|
| 337 |
+
"step": 45
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.59,
|
| 341 |
+
"grad_norm": 0.13662201166152954,
|
| 342 |
+
"learning_rate": 2.6282051282051285e-05,
|
| 343 |
+
"loss": 0.005,
|
| 344 |
+
"step": 46
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.62,
|
| 348 |
+
"grad_norm": 0.12291555851697922,
|
| 349 |
+
"learning_rate": 2.564102564102564e-05,
|
| 350 |
+
"loss": 0.0045,
|
| 351 |
+
"step": 47
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.66,
|
| 355 |
+
"grad_norm": 0.14628447592258453,
|
| 356 |
+
"learning_rate": 2.5e-05,
|
| 357 |
+
"loss": 0.0053,
|
| 358 |
+
"step": 48
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.69,
|
| 362 |
+
"grad_norm": 0.0980817899107933,
|
| 363 |
+
"learning_rate": 2.435897435897436e-05,
|
| 364 |
+
"loss": 0.0036,
|
| 365 |
+
"step": 49
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.72,
|
| 369 |
+
"grad_norm": 0.08451791852712631,
|
| 370 |
+
"learning_rate": 2.3717948717948718e-05,
|
| 371 |
+
"loss": 0.0031,
|
| 372 |
+
"step": 50
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.76,
|
| 376 |
+
"grad_norm": 0.09122524410486221,
|
| 377 |
+
"learning_rate": 2.307692307692308e-05,
|
| 378 |
+
"loss": 0.0034,
|
| 379 |
+
"step": 51
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.79,
|
| 383 |
+
"grad_norm": 0.10025107860565186,
|
| 384 |
+
"learning_rate": 2.2435897435897437e-05,
|
| 385 |
+
"loss": 0.0036,
|
| 386 |
+
"step": 52
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.83,
|
| 390 |
+
"grad_norm": 0.0931243970990181,
|
| 391 |
+
"learning_rate": 2.1794871794871795e-05,
|
| 392 |
+
"loss": 0.0034,
|
| 393 |
+
"step": 53
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.86,
|
| 397 |
+
"grad_norm": 0.08457471430301666,
|
| 398 |
+
"learning_rate": 2.1153846153846154e-05,
|
| 399 |
+
"loss": 0.0032,
|
| 400 |
+
"step": 54
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.9,
|
| 404 |
+
"grad_norm": 0.06439072638750076,
|
| 405 |
+
"learning_rate": 2.0512820512820512e-05,
|
| 406 |
+
"loss": 0.0024,
|
| 407 |
+
"step": 55
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.93,
|
| 411 |
+
"grad_norm": 0.06784728914499283,
|
| 412 |
+
"learning_rate": 1.987179487179487e-05,
|
| 413 |
+
"loss": 0.0026,
|
| 414 |
+
"step": 56
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.97,
|
| 418 |
+
"grad_norm": 0.06939765810966492,
|
| 419 |
+
"learning_rate": 1.923076923076923e-05,
|
| 420 |
+
"loss": 0.0025,
|
| 421 |
+
"step": 57
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.0,
|
| 425 |
+
"grad_norm": 0.06746659427881241,
|
| 426 |
+
"learning_rate": 1.858974358974359e-05,
|
| 427 |
+
"loss": 0.0023,
|
| 428 |
+
"step": 58
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.0,
|
| 432 |
+
"eval_accuracy": 1.0,
|
| 433 |
+
"eval_auc": 1.0,
|
| 434 |
+
"eval_f1": 1.0,
|
| 435 |
+
"eval_loss": 0.0019378147553652525,
|
| 436 |
+
"eval_precision": 1.0,
|
| 437 |
+
"eval_recall": 1.0,
|
| 438 |
+
"eval_runtime": 11.2694,
|
| 439 |
+
"eval_samples_per_second": 5.147,
|
| 440 |
+
"eval_steps_per_second": 0.355,
|
| 441 |
+
"step": 58
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.03,
|
| 445 |
+
"grad_norm": 0.06836142390966415,
|
| 446 |
+
"learning_rate": 1.794871794871795e-05,
|
| 447 |
+
"loss": 0.0025,
|
| 448 |
+
"step": 59
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.07,
|
| 452 |
+
"grad_norm": 0.06278906017541885,
|
| 453 |
+
"learning_rate": 1.730769230769231e-05,
|
| 454 |
+
"loss": 0.0023,
|
| 455 |
+
"step": 60
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.1,
|
| 459 |
+
"grad_norm": 0.06410923600196838,
|
| 460 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 461 |
+
"loss": 0.0023,
|
| 462 |
+
"step": 61
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.14,
|
| 466 |
+
"grad_norm": 0.06301634013652802,
|
| 467 |
+
"learning_rate": 1.602564102564103e-05,
|
| 468 |
+
"loss": 0.0023,
|
| 469 |
+
"step": 62
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.17,
|
| 473 |
+
"grad_norm": 0.05662798881530762,
|
| 474 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 475 |
+
"loss": 0.0021,
|
| 476 |
+
"step": 63
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.21,
|
| 480 |
+
"grad_norm": 0.05281390994787216,
|
| 481 |
+
"learning_rate": 1.4743589743589745e-05,
|
| 482 |
+
"loss": 0.002,
|
| 483 |
+
"step": 64
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.24,
|
| 487 |
+
"grad_norm": 0.05998377129435539,
|
| 488 |
+
"learning_rate": 1.4102564102564104e-05,
|
| 489 |
+
"loss": 0.0022,
|
| 490 |
+
"step": 65
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.28,
|
| 494 |
+
"grad_norm": 0.057209353893995285,
|
| 495 |
+
"learning_rate": 1.3461538461538462e-05,
|
| 496 |
+
"loss": 0.0022,
|
| 497 |
+
"step": 66
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.31,
|
| 501 |
+
"grad_norm": 0.053095847368240356,
|
| 502 |
+
"learning_rate": 1.282051282051282e-05,
|
| 503 |
+
"loss": 0.002,
|
| 504 |
+
"step": 67
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.34,
|
| 508 |
+
"grad_norm": 0.05224345251917839,
|
| 509 |
+
"learning_rate": 1.217948717948718e-05,
|
| 510 |
+
"loss": 0.0019,
|
| 511 |
+
"step": 68
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.38,
|
| 515 |
+
"grad_norm": 0.05752864480018616,
|
| 516 |
+
"learning_rate": 1.153846153846154e-05,
|
| 517 |
+
"loss": 0.0021,
|
| 518 |
+
"step": 69
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.41,
|
| 522 |
+
"grad_norm": 0.0516027957201004,
|
| 523 |
+
"learning_rate": 1.0897435897435898e-05,
|
| 524 |
+
"loss": 0.0019,
|
| 525 |
+
"step": 70
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.45,
|
| 529 |
+
"grad_norm": 0.04573483765125275,
|
| 530 |
+
"learning_rate": 1.0256410256410256e-05,
|
| 531 |
+
"loss": 0.0017,
|
| 532 |
+
"step": 71
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.48,
|
| 536 |
+
"grad_norm": 0.04595545306801796,
|
| 537 |
+
"learning_rate": 9.615384615384616e-06,
|
| 538 |
+
"loss": 0.0017,
|
| 539 |
+
"step": 72
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.52,
|
| 543 |
+
"grad_norm": 0.05478372424840927,
|
| 544 |
+
"learning_rate": 8.974358974358976e-06,
|
| 545 |
+
"loss": 0.002,
|
| 546 |
+
"step": 73
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.55,
|
| 550 |
+
"grad_norm": 0.05210402235388756,
|
| 551 |
+
"learning_rate": 8.333333333333334e-06,
|
| 552 |
+
"loss": 0.0019,
|
| 553 |
+
"step": 74
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.59,
|
| 557 |
+
"grad_norm": 0.035762719810009,
|
| 558 |
+
"learning_rate": 7.692307692307694e-06,
|
| 559 |
+
"loss": 0.0014,
|
| 560 |
+
"step": 75
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.62,
|
| 564 |
+
"grad_norm": 0.04364189878106117,
|
| 565 |
+
"learning_rate": 7.051282051282052e-06,
|
| 566 |
+
"loss": 0.0016,
|
| 567 |
+
"step": 76
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.66,
|
| 571 |
+
"grad_norm": 0.04866515472531319,
|
| 572 |
+
"learning_rate": 6.41025641025641e-06,
|
| 573 |
+
"loss": 0.0018,
|
| 574 |
+
"step": 77
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.69,
|
| 578 |
+
"grad_norm": 0.04439650475978851,
|
| 579 |
+
"learning_rate": 5.76923076923077e-06,
|
| 580 |
+
"loss": 0.0017,
|
| 581 |
+
"step": 78
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.72,
|
| 585 |
+
"grad_norm": 0.04400671273469925,
|
| 586 |
+
"learning_rate": 5.128205128205128e-06,
|
| 587 |
+
"loss": 0.0017,
|
| 588 |
+
"step": 79
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.76,
|
| 592 |
+
"grad_norm": 0.044160932302474976,
|
| 593 |
+
"learning_rate": 4.487179487179488e-06,
|
| 594 |
+
"loss": 0.0017,
|
| 595 |
+
"step": 80
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.79,
|
| 599 |
+
"grad_norm": 0.03901780769228935,
|
| 600 |
+
"learning_rate": 3.846153846153847e-06,
|
| 601 |
+
"loss": 0.0015,
|
| 602 |
+
"step": 81
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.83,
|
| 606 |
+
"grad_norm": 0.04309386387467384,
|
| 607 |
+
"learning_rate": 3.205128205128205e-06,
|
| 608 |
+
"loss": 0.0017,
|
| 609 |
+
"step": 82
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.86,
|
| 613 |
+
"grad_norm": 0.04771938920021057,
|
| 614 |
+
"learning_rate": 2.564102564102564e-06,
|
| 615 |
+
"loss": 0.0018,
|
| 616 |
+
"step": 83
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.9,
|
| 620 |
+
"grad_norm": 0.04240768030285835,
|
| 621 |
+
"learning_rate": 1.9230769230769234e-06,
|
| 622 |
+
"loss": 0.0016,
|
| 623 |
+
"step": 84
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 2.93,
|
| 627 |
+
"grad_norm": 0.04550976678729057,
|
| 628 |
+
"learning_rate": 1.282051282051282e-06,
|
| 629 |
+
"loss": 0.0016,
|
| 630 |
+
"step": 85
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.97,
|
| 634 |
+
"grad_norm": 0.03814227506518364,
|
| 635 |
+
"learning_rate": 6.41025641025641e-07,
|
| 636 |
+
"loss": 0.0014,
|
| 637 |
+
"step": 86
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 3.0,
|
| 641 |
+
"grad_norm": 0.04036854952573776,
|
| 642 |
+
"learning_rate": 0.0,
|
| 643 |
+
"loss": 0.0015,
|
| 644 |
+
"step": 87
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.0,
|
| 648 |
+
"eval_accuracy": 1.0,
|
| 649 |
+
"eval_auc": 1.0,
|
| 650 |
+
"eval_f1": 1.0,
|
| 651 |
+
"eval_loss": 0.001261080033145845,
|
| 652 |
+
"eval_precision": 1.0,
|
| 653 |
+
"eval_recall": 1.0,
|
| 654 |
+
"eval_runtime": 12.2753,
|
| 655 |
+
"eval_samples_per_second": 4.725,
|
| 656 |
+
"eval_steps_per_second": 0.326,
|
| 657 |
+
"step": 87
|
| 658 |
+
}
|
| 659 |
+
],
|
| 660 |
+
"logging_steps": 1,
|
| 661 |
+
"max_steps": 87,
|
| 662 |
+
"num_input_tokens_seen": 0,
|
| 663 |
+
"num_train_epochs": 3,
|
| 664 |
+
"save_steps": 500,
|
| 665 |
+
"total_flos": 45386657049600.0,
|
| 666 |
+
"train_batch_size": 8,
|
| 667 |
+
"trial_name": null,
|
| 668 |
+
"trial_params": null
|
| 669 |
+
}
|
checkpoint-87/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1fab053ebc50e928e72942571f868d3e0cb7d948846aa603c1caa9d5160a66e
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 0,
|
| 15 |
+
"1": 1
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"0": 0,
|
| 21 |
+
"1": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.39.0",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56885b528b3e7ffa356e4fd5236be511d1302e589866ad4e49fa7eaa80cde10d
|
| 3 |
+
size 437958648
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1fab053ebc50e928e72942571f868d3e0cb7d948846aa603c1caa9d5160a66e
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-dqbuy-csoh4/autotrain-data",
|
| 3 |
+
"model": "google-bert/bert-base-uncased",
|
| 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": "autotrain-dqbuy-csoh4",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": null,
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"save_strategy": "epoch",
|
| 25 |
+
"push_to_hub": true,
|
| 26 |
+
"repo_id": "kurianu/autotrain-dqbuy-csoh4",
|
| 27 |
+
"evaluation_strategy": "epoch",
|
| 28 |
+
"username": "kurianu",
|
| 29 |
+
"log": "none"
|
| 30 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|