Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-240/config.json +37 -0
- checkpoint-240/model.safetensors +3 -0
- checkpoint-240/optimizer.pt +3 -0
- checkpoint-240/rng_state.pth +3 -0
- checkpoint-240/scheduler.pt +3 -0
- checkpoint-240/trainer_state.json +348 -0
- checkpoint-240/training_args.bin +3 -0
- config.json +37 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Sep05_14-00-02_r-jjonas313-autotrain-ecb-uncertainy-y2dhdxmg-d5642-fgbr6/events.out.tfevents.1725544804.r-jjonas313-autotrain-ecb-uncertainy-y2dhdxmg-d5642-fgbr6.167.0 +2 -2
- runs/Sep05_14-00-02_r-jjonas313-autotrain-ecb-uncertainy-y2dhdxmg-d5642-fgbr6/events.out.tfevents.1725544831.r-jjonas313-autotrain-ecb-uncertainy-y2dhdxmg-d5642-fgbr6.167.1 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
base_model: distilbert/distilroberta-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: 0.49081695079803467
|
| 17 |
+
|
| 18 |
+
f1: 0.7385892116182573
|
| 19 |
+
|
| 20 |
+
precision: 0.7606837606837606
|
| 21 |
+
|
| 22 |
+
recall: 0.717741935483871
|
| 23 |
+
|
| 24 |
+
auc: 0.8412985703812317
|
| 25 |
+
|
| 26 |
+
accuracy: 0.79
|
checkpoint-240/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilroberta-base",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "certain",
|
| 16 |
+
"1": "uncertain"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"certain": 0,
|
| 22 |
+
"uncertain": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-05,
|
| 25 |
+
"max_position_embeddings": 514,
|
| 26 |
+
"model_type": "roberta",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 6,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.44.2",
|
| 34 |
+
"type_vocab_size": 1,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 50265
|
| 37 |
+
}
|
checkpoint-240/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08b471e0f87333298c15367b9f42f927cc0c61ee594799adf930155b0672a495
|
| 3 |
+
size 328492280
|
checkpoint-240/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1f7fa166e826f6ca1b80bc57084bf548e286ded54389f056f81738ca4541978
|
| 3 |
+
size 657047610
|
checkpoint-240/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d119126267194af793d63127d10340d3f3bb4ac76d871af58281d54f59c44a0e
|
| 3 |
+
size 14244
|
checkpoint-240/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32da19c9c94abacc6115819ea6b07a0a2eb5be46428ca4b721b6b0e0a645c0ec
|
| 3 |
+
size 1064
|
checkpoint-240/trainer_state.json
ADDED
|
@@ -0,0 +1,348 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.49081695079803467,
|
| 3 |
+
"best_model_checkpoint": "autotrain-wwugg-4tqdk/checkpoint-240",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 240,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 2.7021491527557373,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 15 |
+
"loss": 0.695,
|
| 16 |
+
"step": 6
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 2.2563631534576416,
|
| 21 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 22 |
+
"loss": 0.6993,
|
| 23 |
+
"step": 12
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 4.331786155700684,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6841,
|
| 30 |
+
"step": 18
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 3.505587577819824,
|
| 35 |
+
"learning_rate": 6.666666666666667e-06,
|
| 36 |
+
"loss": 0.6817,
|
| 37 |
+
"step": 24
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 2.196746587753296,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 0.6936,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 2.7702722549438477,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 0.6938,
|
| 51 |
+
"step": 36
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 1.7466232776641846,
|
| 56 |
+
"learning_rate": 9.814814814814815e-06,
|
| 57 |
+
"loss": 0.6808,
|
| 58 |
+
"step": 42
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 2.1176140308380127,
|
| 63 |
+
"learning_rate": 9.62962962962963e-06,
|
| 64 |
+
"loss": 0.6854,
|
| 65 |
+
"step": 48
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 1.5516561269760132,
|
| 70 |
+
"learning_rate": 9.444444444444445e-06,
|
| 71 |
+
"loss": 0.6709,
|
| 72 |
+
"step": 54
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 5.013464450836182,
|
| 77 |
+
"learning_rate": 9.25925925925926e-06,
|
| 78 |
+
"loss": 0.6335,
|
| 79 |
+
"step": 60
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 2.582207679748535,
|
| 84 |
+
"learning_rate": 9.074074074074075e-06,
|
| 85 |
+
"loss": 0.6167,
|
| 86 |
+
"step": 66
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 4.556536674499512,
|
| 91 |
+
"learning_rate": 8.888888888888888e-06,
|
| 92 |
+
"loss": 0.748,
|
| 93 |
+
"step": 72
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 2.4331746101379395,
|
| 98 |
+
"learning_rate": 8.703703703703705e-06,
|
| 99 |
+
"loss": 0.6886,
|
| 100 |
+
"step": 78
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 2.409191846847534,
|
| 105 |
+
"learning_rate": 8.518518518518519e-06,
|
| 106 |
+
"loss": 0.7092,
|
| 107 |
+
"step": 84
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 2.624281167984009,
|
| 112 |
+
"learning_rate": 8.333333333333334e-06,
|
| 113 |
+
"loss": 0.6405,
|
| 114 |
+
"step": 90
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 4.394416809082031,
|
| 119 |
+
"learning_rate": 8.148148148148148e-06,
|
| 120 |
+
"loss": 0.6945,
|
| 121 |
+
"step": 96
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 2.1573126316070557,
|
| 126 |
+
"learning_rate": 7.962962962962963e-06,
|
| 127 |
+
"loss": 0.6419,
|
| 128 |
+
"step": 102
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 3.674128532409668,
|
| 133 |
+
"learning_rate": 7.77777777777778e-06,
|
| 134 |
+
"loss": 0.5952,
|
| 135 |
+
"step": 108
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.95,
|
| 139 |
+
"grad_norm": 8.696966171264648,
|
| 140 |
+
"learning_rate": 7.623456790123458e-06,
|
| 141 |
+
"loss": 0.5781,
|
| 142 |
+
"step": 114
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"grad_norm": 4.158613204956055,
|
| 147 |
+
"learning_rate": 7.438271604938272e-06,
|
| 148 |
+
"loss": 0.552,
|
| 149 |
+
"step": 120
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.7366666666666667,
|
| 154 |
+
"eval_auc": 0.8059017595307918,
|
| 155 |
+
"eval_f1": 0.639269406392694,
|
| 156 |
+
"eval_loss": 0.5482643842697144,
|
| 157 |
+
"eval_precision": 0.7368421052631579,
|
| 158 |
+
"eval_recall": 0.5645161290322581,
|
| 159 |
+
"eval_runtime": 0.4345,
|
| 160 |
+
"eval_samples_per_second": 690.4,
|
| 161 |
+
"eval_steps_per_second": 34.52,
|
| 162 |
+
"step": 120
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.05,
|
| 166 |
+
"grad_norm": 18.078632354736328,
|
| 167 |
+
"learning_rate": 7.253086419753087e-06,
|
| 168 |
+
"loss": 0.5021,
|
| 169 |
+
"step": 126
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.1,
|
| 173 |
+
"grad_norm": 5.621760845184326,
|
| 174 |
+
"learning_rate": 7.067901234567902e-06,
|
| 175 |
+
"loss": 0.5289,
|
| 176 |
+
"step": 132
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.15,
|
| 180 |
+
"grad_norm": 12.653544425964355,
|
| 181 |
+
"learning_rate": 6.913580246913581e-06,
|
| 182 |
+
"loss": 0.5398,
|
| 183 |
+
"step": 138
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.2,
|
| 187 |
+
"grad_norm": 9.49728775024414,
|
| 188 |
+
"learning_rate": 6.728395061728395e-06,
|
| 189 |
+
"loss": 0.461,
|
| 190 |
+
"step": 144
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.25,
|
| 194 |
+
"grad_norm": 14.803725242614746,
|
| 195 |
+
"learning_rate": 6.543209876543211e-06,
|
| 196 |
+
"loss": 0.507,
|
| 197 |
+
"step": 150
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.3,
|
| 201 |
+
"grad_norm": 8.009759902954102,
|
| 202 |
+
"learning_rate": 6.358024691358025e-06,
|
| 203 |
+
"loss": 0.4539,
|
| 204 |
+
"step": 156
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.35,
|
| 208 |
+
"grad_norm": 23.24822998046875,
|
| 209 |
+
"learning_rate": 6.17283950617284e-06,
|
| 210 |
+
"loss": 0.6103,
|
| 211 |
+
"step": 162
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.4,
|
| 215 |
+
"grad_norm": 7.31872034072876,
|
| 216 |
+
"learning_rate": 5.9876543209876546e-06,
|
| 217 |
+
"loss": 0.4221,
|
| 218 |
+
"step": 168
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.45,
|
| 222 |
+
"grad_norm": 15.505521774291992,
|
| 223 |
+
"learning_rate": 5.80246913580247e-06,
|
| 224 |
+
"loss": 0.6041,
|
| 225 |
+
"step": 174
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.5,
|
| 229 |
+
"grad_norm": 8.58930778503418,
|
| 230 |
+
"learning_rate": 5.617283950617285e-06,
|
| 231 |
+
"loss": 0.4632,
|
| 232 |
+
"step": 180
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.55,
|
| 236 |
+
"grad_norm": 10.237075805664062,
|
| 237 |
+
"learning_rate": 5.432098765432099e-06,
|
| 238 |
+
"loss": 0.3598,
|
| 239 |
+
"step": 186
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.6,
|
| 243 |
+
"grad_norm": 6.4447174072265625,
|
| 244 |
+
"learning_rate": 5.2777777777777785e-06,
|
| 245 |
+
"loss": 0.5065,
|
| 246 |
+
"step": 192
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.65,
|
| 250 |
+
"grad_norm": 13.765176773071289,
|
| 251 |
+
"learning_rate": 5.092592592592593e-06,
|
| 252 |
+
"loss": 0.4728,
|
| 253 |
+
"step": 198
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.7,
|
| 257 |
+
"grad_norm": 13.332409858703613,
|
| 258 |
+
"learning_rate": 4.907407407407408e-06,
|
| 259 |
+
"loss": 0.5397,
|
| 260 |
+
"step": 204
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.75,
|
| 264 |
+
"grad_norm": 7.632176399230957,
|
| 265 |
+
"learning_rate": 4.722222222222222e-06,
|
| 266 |
+
"loss": 0.4811,
|
| 267 |
+
"step": 210
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.8,
|
| 271 |
+
"grad_norm": 10.296161651611328,
|
| 272 |
+
"learning_rate": 4.537037037037038e-06,
|
| 273 |
+
"loss": 0.4853,
|
| 274 |
+
"step": 216
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.85,
|
| 278 |
+
"grad_norm": 8.207991600036621,
|
| 279 |
+
"learning_rate": 4.351851851851852e-06,
|
| 280 |
+
"loss": 0.404,
|
| 281 |
+
"step": 222
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.9,
|
| 285 |
+
"grad_norm": 12.581914901733398,
|
| 286 |
+
"learning_rate": 4.166666666666667e-06,
|
| 287 |
+
"loss": 0.5348,
|
| 288 |
+
"step": 228
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.95,
|
| 292 |
+
"grad_norm": 13.914998054504395,
|
| 293 |
+
"learning_rate": 3.9814814814814814e-06,
|
| 294 |
+
"loss": 0.4228,
|
| 295 |
+
"step": 234
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.0,
|
| 299 |
+
"grad_norm": 13.199369430541992,
|
| 300 |
+
"learning_rate": 3.796296296296297e-06,
|
| 301 |
+
"loss": 0.4319,
|
| 302 |
+
"step": 240
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"eval_accuracy": 0.79,
|
| 307 |
+
"eval_auc": 0.8412985703812317,
|
| 308 |
+
"eval_f1": 0.7385892116182573,
|
| 309 |
+
"eval_loss": 0.49081695079803467,
|
| 310 |
+
"eval_precision": 0.7606837606837606,
|
| 311 |
+
"eval_recall": 0.717741935483871,
|
| 312 |
+
"eval_runtime": 0.4303,
|
| 313 |
+
"eval_samples_per_second": 697.176,
|
| 314 |
+
"eval_steps_per_second": 34.859,
|
| 315 |
+
"step": 240
|
| 316 |
+
}
|
| 317 |
+
],
|
| 318 |
+
"logging_steps": 6,
|
| 319 |
+
"max_steps": 360,
|
| 320 |
+
"num_input_tokens_seen": 0,
|
| 321 |
+
"num_train_epochs": 3,
|
| 322 |
+
"save_steps": 500,
|
| 323 |
+
"stateful_callbacks": {
|
| 324 |
+
"EarlyStoppingCallback": {
|
| 325 |
+
"args": {
|
| 326 |
+
"early_stopping_patience": 5,
|
| 327 |
+
"early_stopping_threshold": 0.01
|
| 328 |
+
},
|
| 329 |
+
"attributes": {
|
| 330 |
+
"early_stopping_patience_counter": 0
|
| 331 |
+
}
|
| 332 |
+
},
|
| 333 |
+
"TrainerControl": {
|
| 334 |
+
"args": {
|
| 335 |
+
"should_epoch_stop": false,
|
| 336 |
+
"should_evaluate": false,
|
| 337 |
+
"should_log": false,
|
| 338 |
+
"should_save": true,
|
| 339 |
+
"should_training_stop": false
|
| 340 |
+
},
|
| 341 |
+
"attributes": {}
|
| 342 |
+
}
|
| 343 |
+
},
|
| 344 |
+
"total_flos": 158960878387200.0,
|
| 345 |
+
"train_batch_size": 10,
|
| 346 |
+
"trial_name": null,
|
| 347 |
+
"trial_params": null
|
| 348 |
+
}
|
checkpoint-240/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2baa63b9ec6ce4e4eaecc6209dc645db458e16bd22eee90a8ec249ae21a7a4b0
|
| 3 |
+
size 5240
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilroberta-base",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "certain",
|
| 16 |
+
"1": "uncertain"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"certain": 0,
|
| 22 |
+
"uncertain": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-05,
|
| 25 |
+
"max_position_embeddings": 514,
|
| 26 |
+
"model_type": "roberta",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 6,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.44.2",
|
| 34 |
+
"type_vocab_size": 1,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 50265
|
| 37 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08b471e0f87333298c15367b9f42f927cc0c61ee594799adf930155b0672a495
|
| 3 |
+
size 328492280
|
runs/Sep05_14-00-02_r-jjonas313-autotrain-ecb-uncertainy-y2dhdxmg-d5642-fgbr6/events.out.tfevents.1725544804.r-jjonas313-autotrain-ecb-uncertainy-y2dhdxmg-d5642-fgbr6.167.0
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 sha256:2ae81250208f4418d49d3e3dfb7d2fdbe5db3e810ff88287b301b05cd5e12512
|
| 3 |
+
size 19592
|
runs/Sep05_14-00-02_r-jjonas313-autotrain-ecb-uncertainy-y2dhdxmg-d5642-fgbr6/events.out.tfevents.1725544831.r-jjonas313-autotrain-ecb-uncertainy-y2dhdxmg-d5642-fgbr6.167.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac1420c45c2c6237eed901f051b637ad118e085494c21f5688cbcb878131509
|
| 3 |
+
size 607
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 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": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
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 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2baa63b9ec6ce4e4eaecc6209dc645db458e16bd22eee90a8ec249ae21a7a4b0
|
| 3 |
+
size 5240
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-wwugg-4tqdk/autotrain-data",
|
| 3 |
+
"model": "distilbert/distilroberta-base",
|
| 4 |
+
"lr": 1e-05,
|
| 5 |
+
"epochs": 3,
|
| 6 |
+
"max_seq_length": 256,
|
| 7 |
+
"batch_size": 10,
|
| 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": 333,
|
| 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-wwugg-4tqdk",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"push_to_hub": true,
|
| 25 |
+
"eval_strategy": "epoch",
|
| 26 |
+
"username": "jjonas313",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|