Commit
•
cb6a2ed
1
Parent(s):
c0042c5
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-69/config.json +40 -0
- checkpoint-69/model.safetensors +3 -0
- checkpoint-69/optimizer.pt +3 -0
- checkpoint-69/rng_state.pth +3 -0
- checkpoint-69/scheduler.pt +3 -0
- checkpoint-69/trainer_state.json +489 -0
- checkpoint-69/training_args.bin +3 -0
- config.json +40 -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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
widget:
|
| 7 |
+
- text: "I love AutoTrain"
|
| 8 |
+
datasets:
|
| 9 |
+
- autotrain-cgknk-ucsd7/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.45186951756477356
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.5878571428571429
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.8695652173913043
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.8316149068322981
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.6898148148148148
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.8695652173913043
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.8216586151368759
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.572463768115942
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.8695652173913043
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.8695652173913043
|
| 36 |
+
|
| 37 |
+
accuracy: 0.8695652173913043
|
checkpoint-69/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 4,
|
| 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": "Inquiry",
|
| 15 |
+
"1": "New_Claim",
|
| 16 |
+
"2": "Others",
|
| 17 |
+
"3": "Status_FollowUP"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Inquiry": 0,
|
| 23 |
+
"New_Claim": 1,
|
| 24 |
+
"Others": 2,
|
| 25 |
+
"Status_FollowUP": 3
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-12,
|
| 28 |
+
"max_position_embeddings": 512,
|
| 29 |
+
"model_type": "bert",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"pad_token_id": 0,
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.37.0",
|
| 37 |
+
"type_vocab_size": 2,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 30522
|
| 40 |
+
}
|
checkpoint-69/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0b3579cfb969748e6dd0830f6f24eb7101f1b916c7697f5f19d1d13dc4cf31
|
| 3 |
+
size 437964800
|
checkpoint-69/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d4d4eb847b20b3a8d609d21ffd2c40461b32865ae0f0cf73f9a74a69fbf250d
|
| 3 |
+
size 876045050
|
checkpoint-69/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18f5eab34762f1b8722a679a1169dde0d3eddd3f77c37cc89392b3ec3f781a60
|
| 3 |
+
size 13990
|
checkpoint-69/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a5d539909ad039fbc5e19dc8b0411110547692ea4d43691d07028c720c0cb56
|
| 3 |
+
size 1064
|
checkpoint-69/trainer_state.json
ADDED
|
@@ -0,0 +1,489 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.45186951756477356,
|
| 3 |
+
"best_model_checkpoint": "autotrain-cgknk-ucsd7/checkpoint-69",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 69,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 7.142857142857143e-06,
|
| 14 |
+
"loss": 1.3729,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 20 |
+
"loss": 1.3925,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.13,
|
| 25 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 26 |
+
"loss": 1.3467,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.17,
|
| 31 |
+
"learning_rate": 2.857142857142857e-05,
|
| 32 |
+
"loss": 1.3622,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.22,
|
| 37 |
+
"learning_rate": 3.571428571428572e-05,
|
| 38 |
+
"loss": 1.3501,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.26,
|
| 43 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 44 |
+
"loss": 1.4273,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3,
|
| 49 |
+
"learning_rate": 5e-05,
|
| 50 |
+
"loss": 1.1846,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"learning_rate": 4.9193548387096775e-05,
|
| 56 |
+
"loss": 1.0239,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.39,
|
| 61 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 62 |
+
"loss": 1.1007,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.43,
|
| 67 |
+
"learning_rate": 4.7580645161290326e-05,
|
| 68 |
+
"loss": 0.8872,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.48,
|
| 73 |
+
"learning_rate": 4.67741935483871e-05,
|
| 74 |
+
"loss": 0.6495,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.52,
|
| 79 |
+
"learning_rate": 4.596774193548387e-05,
|
| 80 |
+
"loss": 0.8359,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.57,
|
| 85 |
+
"learning_rate": 4.516129032258064e-05,
|
| 86 |
+
"loss": 0.9285,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.61,
|
| 91 |
+
"learning_rate": 4.435483870967742e-05,
|
| 92 |
+
"loss": 0.8296,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"learning_rate": 4.3548387096774194e-05,
|
| 98 |
+
"loss": 0.4654,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.7,
|
| 103 |
+
"learning_rate": 4.2741935483870973e-05,
|
| 104 |
+
"loss": 0.743,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.74,
|
| 109 |
+
"learning_rate": 4.1935483870967746e-05,
|
| 110 |
+
"loss": 0.9514,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.78,
|
| 115 |
+
"learning_rate": 4.112903225806452e-05,
|
| 116 |
+
"loss": 1.0205,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.83,
|
| 121 |
+
"learning_rate": 4.032258064516129e-05,
|
| 122 |
+
"loss": 0.7075,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.87,
|
| 127 |
+
"learning_rate": 3.951612903225806e-05,
|
| 128 |
+
"loss": 0.9395,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.91,
|
| 133 |
+
"learning_rate": 3.870967741935484e-05,
|
| 134 |
+
"loss": 0.6195,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.96,
|
| 139 |
+
"learning_rate": 3.7903225806451614e-05,
|
| 140 |
+
"loss": 0.2973,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.0,
|
| 145 |
+
"learning_rate": 3.7096774193548386e-05,
|
| 146 |
+
"loss": 0.9383,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.0,
|
| 151 |
+
"eval_accuracy": 0.8260869565217391,
|
| 152 |
+
"eval_f1_macro": 0.44425770308123247,
|
| 153 |
+
"eval_f1_micro": 0.8260869565217391,
|
| 154 |
+
"eval_f1_weighted": 0.7692607477773717,
|
| 155 |
+
"eval_loss": 0.6277322173118591,
|
| 156 |
+
"eval_precision_macro": 0.4186507936507936,
|
| 157 |
+
"eval_precision_micro": 0.8260869565217391,
|
| 158 |
+
"eval_precision_weighted": 0.7213595583160801,
|
| 159 |
+
"eval_recall_macro": 0.4744245524296675,
|
| 160 |
+
"eval_recall_micro": 0.8260869565217391,
|
| 161 |
+
"eval_recall_weighted": 0.8260869565217391,
|
| 162 |
+
"eval_runtime": 0.6688,
|
| 163 |
+
"eval_samples_per_second": 68.776,
|
| 164 |
+
"eval_steps_per_second": 4.485,
|
| 165 |
+
"step": 23
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.04,
|
| 169 |
+
"learning_rate": 3.6290322580645165e-05,
|
| 170 |
+
"loss": 0.7685,
|
| 171 |
+
"step": 24
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.09,
|
| 175 |
+
"learning_rate": 3.548387096774194e-05,
|
| 176 |
+
"loss": 0.3426,
|
| 177 |
+
"step": 25
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.13,
|
| 181 |
+
"learning_rate": 3.467741935483872e-05,
|
| 182 |
+
"loss": 0.8852,
|
| 183 |
+
"step": 26
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.17,
|
| 187 |
+
"learning_rate": 3.387096774193548e-05,
|
| 188 |
+
"loss": 0.2917,
|
| 189 |
+
"step": 27
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.22,
|
| 193 |
+
"learning_rate": 3.306451612903226e-05,
|
| 194 |
+
"loss": 0.2149,
|
| 195 |
+
"step": 28
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.26,
|
| 199 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 200 |
+
"loss": 0.5661,
|
| 201 |
+
"step": 29
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.3,
|
| 205 |
+
"learning_rate": 3.1451612903225806e-05,
|
| 206 |
+
"loss": 0.8716,
|
| 207 |
+
"step": 30
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.35,
|
| 211 |
+
"learning_rate": 3.0645161290322585e-05,
|
| 212 |
+
"loss": 0.5167,
|
| 213 |
+
"step": 31
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.39,
|
| 217 |
+
"learning_rate": 2.9838709677419357e-05,
|
| 218 |
+
"loss": 0.4871,
|
| 219 |
+
"step": 32
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.43,
|
| 223 |
+
"learning_rate": 2.9032258064516133e-05,
|
| 224 |
+
"loss": 0.5126,
|
| 225 |
+
"step": 33
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.48,
|
| 229 |
+
"learning_rate": 2.822580645161291e-05,
|
| 230 |
+
"loss": 0.1555,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.52,
|
| 235 |
+
"learning_rate": 2.7419354838709678e-05,
|
| 236 |
+
"loss": 1.0101,
|
| 237 |
+
"step": 35
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.57,
|
| 241 |
+
"learning_rate": 2.661290322580645e-05,
|
| 242 |
+
"loss": 0.1561,
|
| 243 |
+
"step": 36
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.61,
|
| 247 |
+
"learning_rate": 2.5806451612903226e-05,
|
| 248 |
+
"loss": 0.7768,
|
| 249 |
+
"step": 37
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.65,
|
| 253 |
+
"learning_rate": 2.5e-05,
|
| 254 |
+
"loss": 0.7654,
|
| 255 |
+
"step": 38
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.7,
|
| 259 |
+
"learning_rate": 2.4193548387096777e-05,
|
| 260 |
+
"loss": 0.4026,
|
| 261 |
+
"step": 39
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.74,
|
| 265 |
+
"learning_rate": 2.338709677419355e-05,
|
| 266 |
+
"loss": 0.6544,
|
| 267 |
+
"step": 40
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.78,
|
| 271 |
+
"learning_rate": 2.258064516129032e-05,
|
| 272 |
+
"loss": 0.1682,
|
| 273 |
+
"step": 41
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.83,
|
| 277 |
+
"learning_rate": 2.1774193548387097e-05,
|
| 278 |
+
"loss": 0.6621,
|
| 279 |
+
"step": 42
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.87,
|
| 283 |
+
"learning_rate": 2.0967741935483873e-05,
|
| 284 |
+
"loss": 0.5287,
|
| 285 |
+
"step": 43
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.91,
|
| 289 |
+
"learning_rate": 2.0161290322580645e-05,
|
| 290 |
+
"loss": 0.5501,
|
| 291 |
+
"step": 44
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.96,
|
| 295 |
+
"learning_rate": 1.935483870967742e-05,
|
| 296 |
+
"loss": 0.4162,
|
| 297 |
+
"step": 45
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.0,
|
| 301 |
+
"learning_rate": 1.8548387096774193e-05,
|
| 302 |
+
"loss": 0.5118,
|
| 303 |
+
"step": 46
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.0,
|
| 307 |
+
"eval_accuracy": 0.8478260869565217,
|
| 308 |
+
"eval_f1_macro": 0.45611111111111113,
|
| 309 |
+
"eval_f1_micro": 0.8478260869565218,
|
| 310 |
+
"eval_f1_weighted": 0.7890338164251207,
|
| 311 |
+
"eval_loss": 0.4621887505054474,
|
| 312 |
+
"eval_precision_macro": 0.4273879142300195,
|
| 313 |
+
"eval_precision_micro": 0.8478260869565217,
|
| 314 |
+
"eval_precision_weighted": 0.7380710229680482,
|
| 315 |
+
"eval_recall_macro": 0.4891304347826087,
|
| 316 |
+
"eval_recall_micro": 0.8478260869565217,
|
| 317 |
+
"eval_recall_weighted": 0.8478260869565217,
|
| 318 |
+
"eval_runtime": 0.6179,
|
| 319 |
+
"eval_samples_per_second": 74.442,
|
| 320 |
+
"eval_steps_per_second": 4.855,
|
| 321 |
+
"step": 46
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.04,
|
| 325 |
+
"learning_rate": 1.774193548387097e-05,
|
| 326 |
+
"loss": 0.3888,
|
| 327 |
+
"step": 47
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.09,
|
| 331 |
+
"learning_rate": 1.693548387096774e-05,
|
| 332 |
+
"loss": 0.3377,
|
| 333 |
+
"step": 48
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.13,
|
| 337 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 338 |
+
"loss": 0.593,
|
| 339 |
+
"step": 49
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.17,
|
| 343 |
+
"learning_rate": 1.5322580645161292e-05,
|
| 344 |
+
"loss": 0.6547,
|
| 345 |
+
"step": 50
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.22,
|
| 349 |
+
"learning_rate": 1.4516129032258066e-05,
|
| 350 |
+
"loss": 0.2477,
|
| 351 |
+
"step": 51
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.26,
|
| 355 |
+
"learning_rate": 1.3709677419354839e-05,
|
| 356 |
+
"loss": 0.1499,
|
| 357 |
+
"step": 52
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.3,
|
| 361 |
+
"learning_rate": 1.2903225806451613e-05,
|
| 362 |
+
"loss": 0.1146,
|
| 363 |
+
"step": 53
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.35,
|
| 367 |
+
"learning_rate": 1.2096774193548388e-05,
|
| 368 |
+
"loss": 0.0913,
|
| 369 |
+
"step": 54
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.39,
|
| 373 |
+
"learning_rate": 1.129032258064516e-05,
|
| 374 |
+
"loss": 0.1403,
|
| 375 |
+
"step": 55
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.43,
|
| 379 |
+
"learning_rate": 1.0483870967741936e-05,
|
| 380 |
+
"loss": 0.3745,
|
| 381 |
+
"step": 56
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.48,
|
| 385 |
+
"learning_rate": 9.67741935483871e-06,
|
| 386 |
+
"loss": 0.9547,
|
| 387 |
+
"step": 57
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.52,
|
| 391 |
+
"learning_rate": 8.870967741935484e-06,
|
| 392 |
+
"loss": 0.0937,
|
| 393 |
+
"step": 58
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.57,
|
| 397 |
+
"learning_rate": 8.064516129032258e-06,
|
| 398 |
+
"loss": 0.4696,
|
| 399 |
+
"step": 59
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.61,
|
| 403 |
+
"learning_rate": 7.258064516129033e-06,
|
| 404 |
+
"loss": 0.436,
|
| 405 |
+
"step": 60
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.65,
|
| 409 |
+
"learning_rate": 6.451612903225806e-06,
|
| 410 |
+
"loss": 0.7999,
|
| 411 |
+
"step": 61
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.7,
|
| 415 |
+
"learning_rate": 5.64516129032258e-06,
|
| 416 |
+
"loss": 0.261,
|
| 417 |
+
"step": 62
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.74,
|
| 421 |
+
"learning_rate": 4.838709677419355e-06,
|
| 422 |
+
"loss": 0.2922,
|
| 423 |
+
"step": 63
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.78,
|
| 427 |
+
"learning_rate": 4.032258064516129e-06,
|
| 428 |
+
"loss": 0.958,
|
| 429 |
+
"step": 64
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.83,
|
| 433 |
+
"learning_rate": 3.225806451612903e-06,
|
| 434 |
+
"loss": 0.121,
|
| 435 |
+
"step": 65
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.87,
|
| 439 |
+
"learning_rate": 2.4193548387096776e-06,
|
| 440 |
+
"loss": 0.3745,
|
| 441 |
+
"step": 66
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.91,
|
| 445 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 446 |
+
"loss": 0.0963,
|
| 447 |
+
"step": 67
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.96,
|
| 451 |
+
"learning_rate": 8.064516129032258e-07,
|
| 452 |
+
"loss": 0.4777,
|
| 453 |
+
"step": 68
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.0,
|
| 457 |
+
"learning_rate": 0.0,
|
| 458 |
+
"loss": 0.1715,
|
| 459 |
+
"step": 69
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.0,
|
| 463 |
+
"eval_accuracy": 0.8695652173913043,
|
| 464 |
+
"eval_f1_macro": 0.5878571428571429,
|
| 465 |
+
"eval_f1_micro": 0.8695652173913043,
|
| 466 |
+
"eval_f1_weighted": 0.8316149068322981,
|
| 467 |
+
"eval_loss": 0.45186951756477356,
|
| 468 |
+
"eval_precision_macro": 0.6898148148148148,
|
| 469 |
+
"eval_precision_micro": 0.8695652173913043,
|
| 470 |
+
"eval_precision_weighted": 0.8216586151368759,
|
| 471 |
+
"eval_recall_macro": 0.572463768115942,
|
| 472 |
+
"eval_recall_micro": 0.8695652173913043,
|
| 473 |
+
"eval_recall_weighted": 0.8695652173913043,
|
| 474 |
+
"eval_runtime": 0.5942,
|
| 475 |
+
"eval_samples_per_second": 77.416,
|
| 476 |
+
"eval_steps_per_second": 5.049,
|
| 477 |
+
"step": 69
|
| 478 |
+
}
|
| 479 |
+
],
|
| 480 |
+
"logging_steps": 1,
|
| 481 |
+
"max_steps": 69,
|
| 482 |
+
"num_input_tokens_seen": 0,
|
| 483 |
+
"num_train_epochs": 3,
|
| 484 |
+
"save_steps": 500,
|
| 485 |
+
"total_flos": 35717967148032.0,
|
| 486 |
+
"train_batch_size": 8,
|
| 487 |
+
"trial_name": null,
|
| 488 |
+
"trial_params": null
|
| 489 |
+
}
|
checkpoint-69/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de9f690f05c2df7ab6e5918cb3c8e8f407a1f1eabf257af90d8420030986b74c
|
| 3 |
+
size 4664
|
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 4,
|
| 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": "Inquiry",
|
| 15 |
+
"1": "New_Claim",
|
| 16 |
+
"2": "Others",
|
| 17 |
+
"3": "Status_FollowUP"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Inquiry": 0,
|
| 23 |
+
"New_Claim": 1,
|
| 24 |
+
"Others": 2,
|
| 25 |
+
"Status_FollowUP": 3
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-12,
|
| 28 |
+
"max_position_embeddings": 512,
|
| 29 |
+
"model_type": "bert",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"pad_token_id": 0,
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.37.0",
|
| 37 |
+
"type_vocab_size": 2,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 30522
|
| 40 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0b3579cfb969748e6dd0830f6f24eb7101f1b916c7697f5f19d1d13dc4cf31
|
| 3 |
+
size 437964800
|
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:de9f690f05c2df7ab6e5918cb3c8e8f407a1f1eabf257af90d8420030986b74c
|
| 3 |
+
size 4664
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-cgknk-ucsd7/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-cgknk-ucsd7",
|
| 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": "keshav-kumar/autotrain-cgknk-ucsd7",
|
| 27 |
+
"evaluation_strategy": "epoch",
|
| 28 |
+
"username": "keshav-kumar",
|
| 29 |
+
"log": "none"
|
| 30 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|