Text Classification
Transformers
TensorBoard
Safetensors
bert
Trained with AutoTrain
text-embeddings-inference
Instructions to use mserloth/autotrain-df80 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mserloth/autotrain-df80 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mserloth/autotrain-df80")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mserloth/autotrain-df80") model = AutoModelForSequenceClassification.from_pretrained("mserloth/autotrain-df80", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Markus Serloth-Schwarzer commited on
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-35/config.json +38 -0
- checkpoint-35/model.safetensors +3 -0
- checkpoint-35/optimizer.pt +3 -0
- checkpoint-35/rng_state.pth +3 -0
- checkpoint-35/scheduler.pt +3 -0
- checkpoint-35/trainer_state.json +356 -0
- checkpoint-35/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/May09_16-03-27_r-zerithas-myownmodels-v1-z4ak8yoe-7b9ea-ju3lf/events.out.tfevents.1715270607.r-zerithas-myownmodels-v1-z4ak8yoe-7b9ea-ju3lf.58.0 +2 -2
- runs/May09_16-03-27_r-zerithas-myownmodels-v1-z4ak8yoe-7b9ea-ju3lf/events.out.tfevents.1715270628.r-zerithas-myownmodels-v1-z4ak8yoe-7b9ea-ju3lf.58.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +28 -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-df80/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.8816452026367188
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.5019607843137255
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.75
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.7313725490196079
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.5
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.75
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.71875
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.5079365079365079
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.75
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.75
|
| 36 |
+
|
| 37 |
+
accuracy: 0.75
|
checkpoint-35/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "oliverguhr/german-sentiment-bert",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"finetuning_task": "germansentiment",
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "negative",
|
| 15 |
+
"1": "neutral",
|
| 16 |
+
"2": "positive"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"negative": 0,
|
| 22 |
+
"neutral": 1,
|
| 23 |
+
"positive": 2
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "bert",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.40.1",
|
| 35 |
+
"type_vocab_size": 2,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 30000
|
| 38 |
+
}
|
checkpoint-35/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6235abf9f0939563c4e43a19a7bd2ecc1a5ecb10da8e75e16cecaa714cbe0bd
|
| 3 |
+
size 436358132
|
checkpoint-35/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b42969f39cea6f410944436e0b956c2a94ba59ffed5e110682241f307ff6b357
|
| 3 |
+
size 872837370
|
checkpoint-35/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7b386122074dc5ba5b10148263b9021eb8ecff5b9b1cb2ea79dc6eb58551e06
|
| 3 |
+
size 14244
|
checkpoint-35/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7263b7693ed82eab8ee04050258cb1098b31a69121a40c5d791001adffa85c79
|
| 3 |
+
size 1064
|
checkpoint-35/trainer_state.json
ADDED
|
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8816452026367188,
|
| 3 |
+
"best_model_checkpoint": "autotrain-df80/checkpoint-35",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 35,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14285714285714285,
|
| 13 |
+
"grad_norm": Infinity,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"loss": 3.1053,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2857142857142857,
|
| 20 |
+
"grad_norm": Infinity,
|
| 21 |
+
"learning_rate": 0.0,
|
| 22 |
+
"loss": 2.972,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.42857142857142855,
|
| 27 |
+
"grad_norm": Infinity,
|
| 28 |
+
"learning_rate": 0.0,
|
| 29 |
+
"loss": 3.6741,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5714285714285714,
|
| 34 |
+
"grad_norm": 70.11737060546875,
|
| 35 |
+
"learning_rate": 1.25e-05,
|
| 36 |
+
"loss": 2.1635,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7142857142857143,
|
| 41 |
+
"grad_norm": 67.73457336425781,
|
| 42 |
+
"learning_rate": 2.5e-05,
|
| 43 |
+
"loss": 2.6355,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8571428571428571,
|
| 48 |
+
"grad_norm": 71.76345825195312,
|
| 49 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 50 |
+
"loss": 3.7052,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"grad_norm": 21.13036346435547,
|
| 56 |
+
"learning_rate": 5e-05,
|
| 57 |
+
"loss": 1.9736,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"eval_accuracy": 0.5416666666666666,
|
| 63 |
+
"eval_f1_macro": 0.23423423423423426,
|
| 64 |
+
"eval_f1_micro": 0.5416666666666666,
|
| 65 |
+
"eval_f1_weighted": 0.40990990990990994,
|
| 66 |
+
"eval_loss": 2.0108728408813477,
|
| 67 |
+
"eval_precision_macro": 0.18840579710144925,
|
| 68 |
+
"eval_precision_micro": 0.5416666666666666,
|
| 69 |
+
"eval_precision_weighted": 0.3297101449275362,
|
| 70 |
+
"eval_recall_macro": 0.30952380952380953,
|
| 71 |
+
"eval_recall_micro": 0.5416666666666666,
|
| 72 |
+
"eval_recall_weighted": 0.5416666666666666,
|
| 73 |
+
"eval_runtime": 0.0836,
|
| 74 |
+
"eval_samples_per_second": 287.125,
|
| 75 |
+
"eval_steps_per_second": 23.927,
|
| 76 |
+
"step": 7
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.1428571428571428,
|
| 80 |
+
"grad_norm": 37.35652542114258,
|
| 81 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 82 |
+
"loss": 1.4028,
|
| 83 |
+
"step": 8
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.2857142857142856,
|
| 87 |
+
"grad_norm": 72.43930053710938,
|
| 88 |
+
"learning_rate": 4.67741935483871e-05,
|
| 89 |
+
"loss": 0.5302,
|
| 90 |
+
"step": 9
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.4285714285714286,
|
| 94 |
+
"grad_norm": 10.876357078552246,
|
| 95 |
+
"learning_rate": 4.516129032258064e-05,
|
| 96 |
+
"loss": 0.8016,
|
| 97 |
+
"step": 10
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.5714285714285714,
|
| 101 |
+
"grad_norm": 26.06935691833496,
|
| 102 |
+
"learning_rate": 4.3548387096774194e-05,
|
| 103 |
+
"loss": 2.2303,
|
| 104 |
+
"step": 11
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.7142857142857144,
|
| 108 |
+
"grad_norm": Infinity,
|
| 109 |
+
"learning_rate": 4.3548387096774194e-05,
|
| 110 |
+
"loss": 1.7161,
|
| 111 |
+
"step": 12
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.8571428571428572,
|
| 115 |
+
"grad_norm": 21.18684959411621,
|
| 116 |
+
"learning_rate": 4.1935483870967746e-05,
|
| 117 |
+
"loss": 1.4677,
|
| 118 |
+
"step": 13
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.0,
|
| 122 |
+
"grad_norm": 13.552129745483398,
|
| 123 |
+
"learning_rate": 4.032258064516129e-05,
|
| 124 |
+
"loss": 0.6474,
|
| 125 |
+
"step": 14
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.0,
|
| 129 |
+
"eval_accuracy": 0.5416666666666666,
|
| 130 |
+
"eval_f1_macro": 0.3638583638583639,
|
| 131 |
+
"eval_f1_micro": 0.5416666666666666,
|
| 132 |
+
"eval_f1_weighted": 0.5375457875457875,
|
| 133 |
+
"eval_loss": 1.3520864248275757,
|
| 134 |
+
"eval_precision_macro": 0.3611111111111111,
|
| 135 |
+
"eval_precision_micro": 0.5416666666666666,
|
| 136 |
+
"eval_precision_weighted": 0.5451388888888888,
|
| 137 |
+
"eval_recall_macro": 0.37566137566137564,
|
| 138 |
+
"eval_recall_micro": 0.5416666666666666,
|
| 139 |
+
"eval_recall_weighted": 0.5416666666666666,
|
| 140 |
+
"eval_runtime": 0.0825,
|
| 141 |
+
"eval_samples_per_second": 291.009,
|
| 142 |
+
"eval_steps_per_second": 24.251,
|
| 143 |
+
"step": 14
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.142857142857143,
|
| 147 |
+
"grad_norm": 11.4788236618042,
|
| 148 |
+
"learning_rate": 3.870967741935484e-05,
|
| 149 |
+
"loss": 0.5563,
|
| 150 |
+
"step": 15
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.2857142857142856,
|
| 154 |
+
"grad_norm": 36.51395034790039,
|
| 155 |
+
"learning_rate": 3.7096774193548386e-05,
|
| 156 |
+
"loss": 0.4919,
|
| 157 |
+
"step": 16
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.4285714285714284,
|
| 161 |
+
"grad_norm": 64.92756652832031,
|
| 162 |
+
"learning_rate": 3.548387096774194e-05,
|
| 163 |
+
"loss": 1.3394,
|
| 164 |
+
"step": 17
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.571428571428571,
|
| 168 |
+
"grad_norm": 58.25400924682617,
|
| 169 |
+
"learning_rate": 3.387096774193548e-05,
|
| 170 |
+
"loss": 1.069,
|
| 171 |
+
"step": 18
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.7142857142857144,
|
| 175 |
+
"grad_norm": 33.65617370605469,
|
| 176 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 177 |
+
"loss": 0.474,
|
| 178 |
+
"step": 19
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.857142857142857,
|
| 182 |
+
"grad_norm": 24.85539436340332,
|
| 183 |
+
"learning_rate": 3.0645161290322585e-05,
|
| 184 |
+
"loss": 0.8503,
|
| 185 |
+
"step": 20
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.0,
|
| 189 |
+
"grad_norm": 9.094024658203125,
|
| 190 |
+
"learning_rate": 2.9032258064516133e-05,
|
| 191 |
+
"loss": 0.8696,
|
| 192 |
+
"step": 21
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 3.0,
|
| 196 |
+
"eval_accuracy": 0.5833333333333334,
|
| 197 |
+
"eval_f1_macro": 0.3013468013468013,
|
| 198 |
+
"eval_f1_micro": 0.5833333333333334,
|
| 199 |
+
"eval_f1_weighted": 0.48947811447811446,
|
| 200 |
+
"eval_loss": 0.96966552734375,
|
| 201 |
+
"eval_precision_macro": 0.3636363636363636,
|
| 202 |
+
"eval_precision_micro": 0.5833333333333334,
|
| 203 |
+
"eval_precision_weighted": 0.5321969696969697,
|
| 204 |
+
"eval_recall_macro": 0.34656084656084657,
|
| 205 |
+
"eval_recall_micro": 0.5833333333333334,
|
| 206 |
+
"eval_recall_weighted": 0.5833333333333334,
|
| 207 |
+
"eval_runtime": 0.0817,
|
| 208 |
+
"eval_samples_per_second": 293.685,
|
| 209 |
+
"eval_steps_per_second": 24.474,
|
| 210 |
+
"step": 21
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.142857142857143,
|
| 214 |
+
"grad_norm": 9.66805362701416,
|
| 215 |
+
"learning_rate": 2.7419354838709678e-05,
|
| 216 |
+
"loss": 0.52,
|
| 217 |
+
"step": 22
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 3.2857142857142856,
|
| 221 |
+
"grad_norm": 9.8311767578125,
|
| 222 |
+
"learning_rate": 2.5806451612903226e-05,
|
| 223 |
+
"loss": 0.51,
|
| 224 |
+
"step": 23
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.4285714285714284,
|
| 228 |
+
"grad_norm": 11.982104301452637,
|
| 229 |
+
"learning_rate": 2.4193548387096777e-05,
|
| 230 |
+
"loss": 0.4699,
|
| 231 |
+
"step": 24
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 3.571428571428571,
|
| 235 |
+
"grad_norm": 14.817587852478027,
|
| 236 |
+
"learning_rate": 2.258064516129032e-05,
|
| 237 |
+
"loss": 1.1386,
|
| 238 |
+
"step": 25
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.7142857142857144,
|
| 242 |
+
"grad_norm": 3.237607955932617,
|
| 243 |
+
"learning_rate": 2.0967741935483873e-05,
|
| 244 |
+
"loss": 0.3454,
|
| 245 |
+
"step": 26
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.857142857142857,
|
| 249 |
+
"grad_norm": 26.063825607299805,
|
| 250 |
+
"learning_rate": 1.935483870967742e-05,
|
| 251 |
+
"loss": 0.918,
|
| 252 |
+
"step": 27
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 4.0,
|
| 256 |
+
"grad_norm": 22.578527450561523,
|
| 257 |
+
"learning_rate": 1.774193548387097e-05,
|
| 258 |
+
"loss": 0.5343,
|
| 259 |
+
"step": 28
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 4.0,
|
| 263 |
+
"eval_accuracy": 0.5833333333333334,
|
| 264 |
+
"eval_f1_macro": 0.3013468013468013,
|
| 265 |
+
"eval_f1_micro": 0.5833333333333334,
|
| 266 |
+
"eval_f1_weighted": 0.48947811447811446,
|
| 267 |
+
"eval_loss": 0.9342803955078125,
|
| 268 |
+
"eval_precision_macro": 0.3636363636363636,
|
| 269 |
+
"eval_precision_micro": 0.5833333333333334,
|
| 270 |
+
"eval_precision_weighted": 0.5321969696969697,
|
| 271 |
+
"eval_recall_macro": 0.34656084656084657,
|
| 272 |
+
"eval_recall_micro": 0.5833333333333334,
|
| 273 |
+
"eval_recall_weighted": 0.5833333333333334,
|
| 274 |
+
"eval_runtime": 0.08,
|
| 275 |
+
"eval_samples_per_second": 300.024,
|
| 276 |
+
"eval_steps_per_second": 25.002,
|
| 277 |
+
"step": 28
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 4.142857142857143,
|
| 281 |
+
"grad_norm": 7.312303066253662,
|
| 282 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 283 |
+
"loss": 0.5345,
|
| 284 |
+
"step": 29
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.285714285714286,
|
| 288 |
+
"grad_norm": 5.162611484527588,
|
| 289 |
+
"learning_rate": 1.4516129032258066e-05,
|
| 290 |
+
"loss": 0.3541,
|
| 291 |
+
"step": 30
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 4.428571428571429,
|
| 295 |
+
"grad_norm": 6.131501197814941,
|
| 296 |
+
"learning_rate": 1.2903225806451613e-05,
|
| 297 |
+
"loss": 0.4523,
|
| 298 |
+
"step": 31
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.571428571428571,
|
| 302 |
+
"grad_norm": 14.81253433227539,
|
| 303 |
+
"learning_rate": 1.129032258064516e-05,
|
| 304 |
+
"loss": 0.5316,
|
| 305 |
+
"step": 32
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.714285714285714,
|
| 309 |
+
"grad_norm": 10.304619789123535,
|
| 310 |
+
"learning_rate": 9.67741935483871e-06,
|
| 311 |
+
"loss": 0.4244,
|
| 312 |
+
"step": 33
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 4.857142857142857,
|
| 316 |
+
"grad_norm": 7.296845436096191,
|
| 317 |
+
"learning_rate": 8.064516129032258e-06,
|
| 318 |
+
"loss": 0.6376,
|
| 319 |
+
"step": 34
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 5.0,
|
| 323 |
+
"grad_norm": 6.571065425872803,
|
| 324 |
+
"learning_rate": 6.451612903225806e-06,
|
| 325 |
+
"loss": 0.2192,
|
| 326 |
+
"step": 35
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 5.0,
|
| 330 |
+
"eval_accuracy": 0.75,
|
| 331 |
+
"eval_f1_macro": 0.5019607843137255,
|
| 332 |
+
"eval_f1_micro": 0.75,
|
| 333 |
+
"eval_f1_weighted": 0.7313725490196079,
|
| 334 |
+
"eval_loss": 0.8816452026367188,
|
| 335 |
+
"eval_precision_macro": 0.5,
|
| 336 |
+
"eval_precision_micro": 0.75,
|
| 337 |
+
"eval_precision_weighted": 0.71875,
|
| 338 |
+
"eval_recall_macro": 0.5079365079365079,
|
| 339 |
+
"eval_recall_micro": 0.75,
|
| 340 |
+
"eval_recall_weighted": 0.75,
|
| 341 |
+
"eval_runtime": 0.0927,
|
| 342 |
+
"eval_samples_per_second": 258.881,
|
| 343 |
+
"eval_steps_per_second": 21.573,
|
| 344 |
+
"step": 35
|
| 345 |
+
}
|
| 346 |
+
],
|
| 347 |
+
"logging_steps": 1,
|
| 348 |
+
"max_steps": 35,
|
| 349 |
+
"num_input_tokens_seen": 0,
|
| 350 |
+
"num_train_epochs": 5,
|
| 351 |
+
"save_steps": 500,
|
| 352 |
+
"total_flos": 18417939240960.0,
|
| 353 |
+
"train_batch_size": 8,
|
| 354 |
+
"trial_name": null,
|
| 355 |
+
"trial_params": null
|
| 356 |
+
}
|
checkpoint-35/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b074d9b08b9fab77846eb359c3584d45d57db10b6ceea3d40be864434a57ed0e
|
| 3 |
+
size 5048
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "oliverguhr/german-sentiment-bert",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"finetuning_task": "germansentiment",
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "negative",
|
| 15 |
+
"1": "neutral",
|
| 16 |
+
"2": "positive"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"negative": 0,
|
| 22 |
+
"neutral": 1,
|
| 23 |
+
"positive": 2
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "bert",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.40.1",
|
| 35 |
+
"type_vocab_size": 2,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 30000
|
| 38 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6235abf9f0939563c4e43a19a7bd2ecc1a5ecb10da8e75e16cecaa714cbe0bd
|
| 3 |
+
size 436358132
|
runs/May09_16-03-27_r-zerithas-myownmodels-v1-z4ak8yoe-7b9ea-ju3lf/events.out.tfevents.1715270607.r-zerithas-myownmodels-v1-z4ak8yoe-7b9ea-ju3lf.58.0
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 sha256:19808141f5e67f63669c893c6c95ce2cc80fc3f65e1fb4a9017769433124f90b
|
| 3 |
+
size 16582
|
runs/May09_16-03-27_r-zerithas-myownmodels-v1-z4ak8yoe-7b9ea-ju3lf/events.out.tfevents.1715270628.r-zerithas-myownmodels-v1-z4ak8yoe-7b9ea-ju3lf.58.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dcdf1e0f80d13a5e9d858ecc2e27523cc0c0e2fb5dcdfbcb358c26890d8315d
|
| 3 |
+
size 906
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"2": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"3": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"4": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"5": {
|
| 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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 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:b074d9b08b9fab77846eb359c3584d45d57db10b6ceea3d40be864434a57ed0e
|
| 3 |
+
size 5048
|
training_params.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-df80/autotrain-data",
|
| 3 |
+
"model": "oliverguhr/german-sentiment-bert",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 5,
|
| 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-df80",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"push_to_hub": true,
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"username": "Zerithas",
|
| 27 |
+
"log": "tensorboard"
|
| 28 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|