Text Classification
Transformers
TensorBoard
Safetensors
bert
Trained with AutoTrain
text-embeddings-inference
Instructions to use mserloth/v20 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mserloth/v20 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mserloth/v20")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mserloth/v20") model = AutoModelForSequenceClassification.from_pretrained("mserloth/v20", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Markus Serloth-Schwarzer commited on
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-316/config.json +38 -0
- checkpoint-316/model.safetensors +3 -0
- checkpoint-316/optimizer.pt +3 -0
- checkpoint-316/rng_state.pth +3 -0
- checkpoint-316/scheduler.pt +3 -0
- checkpoint-316/trainer_state.json +421 -0
- checkpoint-316/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/May05_10-37-35_r-zerithas-myownmodels-v1-1qgyqe4s-88912-ms88x/events.out.tfevents.1714905455.r-zerithas-myownmodels-v1-1qgyqe4s-88912-ms88x.59.0 +2 -2
- runs/May05_10-37-35_r-zerithas-myownmodels-v1-1qgyqe4s-88912-ms88x/events.out.tfevents.1714905549.r-zerithas-myownmodels-v1-1qgyqe4s-88912-ms88x.59.1 +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 |
+
- v20/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.6413357257843018
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.7163881004940608
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.725925925925926
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.7259726456194447
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.6712302319912927
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.725925925925926
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.7310670226564031
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.8041251807057194
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.725925925925926
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.725925925925926
|
| 36 |
+
|
| 37 |
+
accuracy: 0.725925925925926
|
checkpoint-316/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-316/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3e00e4dcfcec97be98271f56649edf83f795204f15ca20934b9c83a85e8f52d
|
| 3 |
+
size 436358132
|
checkpoint-316/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e798d40009f3de2d1fef324f6f38d94a6c4cefd502c68e86f4a40f308924bf8
|
| 3 |
+
size 872837370
|
checkpoint-316/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d37d0c2378085fc9d053ff7674206eb408803bd39f209de1ece74b9951e6224f
|
| 3 |
+
size 14244
|
checkpoint-316/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:934b0d1ad3455b623c2fa235fcbe3d83a32b6e43271681ea08f6ceb6d338fbb4
|
| 3 |
+
size 1064
|
checkpoint-316/trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6413357257843018,
|
| 3 |
+
"best_model_checkpoint": "v20/checkpoint-316",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 316,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0379746835443038,
|
| 13 |
+
"grad_norm": 65.4650650024414,
|
| 14 |
+
"learning_rate": 9.493670886075951e-07,
|
| 15 |
+
"loss": 3.0463,
|
| 16 |
+
"step": 6
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0759493670886076,
|
| 20 |
+
"grad_norm": 40.186553955078125,
|
| 21 |
+
"learning_rate": 2.531645569620253e-06,
|
| 22 |
+
"loss": 2.849,
|
| 23 |
+
"step": 12
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11392405063291139,
|
| 27 |
+
"grad_norm": 74.00092315673828,
|
| 28 |
+
"learning_rate": 4.430379746835443e-06,
|
| 29 |
+
"loss": 2.5506,
|
| 30 |
+
"step": 18
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1518987341772152,
|
| 34 |
+
"grad_norm": 46.56471252441406,
|
| 35 |
+
"learning_rate": 6.329113924050633e-06,
|
| 36 |
+
"loss": 1.7567,
|
| 37 |
+
"step": 24
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.189873417721519,
|
| 41 |
+
"grad_norm": 22.335067749023438,
|
| 42 |
+
"learning_rate": 8.227848101265822e-06,
|
| 43 |
+
"loss": 1.9796,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22784810126582278,
|
| 48 |
+
"grad_norm": 29.599504470825195,
|
| 49 |
+
"learning_rate": 1.0126582278481012e-05,
|
| 50 |
+
"loss": 1.7674,
|
| 51 |
+
"step": 36
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26582278481012656,
|
| 55 |
+
"grad_norm": 41.137115478515625,
|
| 56 |
+
"learning_rate": 1.2025316455696203e-05,
|
| 57 |
+
"loss": 1.6933,
|
| 58 |
+
"step": 42
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3037974683544304,
|
| 62 |
+
"grad_norm": 23.3687801361084,
|
| 63 |
+
"learning_rate": 1.3924050632911393e-05,
|
| 64 |
+
"loss": 1.0355,
|
| 65 |
+
"step": 48
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.34177215189873417,
|
| 69 |
+
"grad_norm": 21.55877685546875,
|
| 70 |
+
"learning_rate": 1.5822784810126583e-05,
|
| 71 |
+
"loss": 1.0989,
|
| 72 |
+
"step": 54
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.379746835443038,
|
| 76 |
+
"grad_norm": 8.896882057189941,
|
| 77 |
+
"learning_rate": 1.7721518987341772e-05,
|
| 78 |
+
"loss": 0.7754,
|
| 79 |
+
"step": 60
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4177215189873418,
|
| 83 |
+
"grad_norm": 7.6988325119018555,
|
| 84 |
+
"learning_rate": 1.962025316455696e-05,
|
| 85 |
+
"loss": 0.7127,
|
| 86 |
+
"step": 66
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.45569620253164556,
|
| 90 |
+
"grad_norm": 14.948259353637695,
|
| 91 |
+
"learning_rate": 2.1518987341772153e-05,
|
| 92 |
+
"loss": 0.8826,
|
| 93 |
+
"step": 72
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4936708860759494,
|
| 97 |
+
"grad_norm": 7.500838279724121,
|
| 98 |
+
"learning_rate": 2.341772151898734e-05,
|
| 99 |
+
"loss": 0.7229,
|
| 100 |
+
"step": 78
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5316455696202531,
|
| 104 |
+
"grad_norm": 17.73823356628418,
|
| 105 |
+
"learning_rate": 2.5316455696202533e-05,
|
| 106 |
+
"loss": 0.6217,
|
| 107 |
+
"step": 84
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.569620253164557,
|
| 111 |
+
"grad_norm": 3.832500696182251,
|
| 112 |
+
"learning_rate": 2.7215189873417722e-05,
|
| 113 |
+
"loss": 0.6923,
|
| 114 |
+
"step": 90
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6075949367088608,
|
| 118 |
+
"grad_norm": 16.606800079345703,
|
| 119 |
+
"learning_rate": 2.9113924050632914e-05,
|
| 120 |
+
"loss": 0.6619,
|
| 121 |
+
"step": 96
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6455696202531646,
|
| 125 |
+
"grad_norm": 26.466333389282227,
|
| 126 |
+
"learning_rate": 3.10126582278481e-05,
|
| 127 |
+
"loss": 0.7988,
|
| 128 |
+
"step": 102
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6835443037974683,
|
| 132 |
+
"grad_norm": 3.720935821533203,
|
| 133 |
+
"learning_rate": 3.291139240506329e-05,
|
| 134 |
+
"loss": 0.7249,
|
| 135 |
+
"step": 108
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7215189873417721,
|
| 139 |
+
"grad_norm": 36.33977127075195,
|
| 140 |
+
"learning_rate": 3.4810126582278487e-05,
|
| 141 |
+
"loss": 0.7391,
|
| 142 |
+
"step": 114
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.759493670886076,
|
| 146 |
+
"grad_norm": 3.5479769706726074,
|
| 147 |
+
"learning_rate": 3.670886075949367e-05,
|
| 148 |
+
"loss": 0.785,
|
| 149 |
+
"step": 120
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7974683544303798,
|
| 153 |
+
"grad_norm": 10.044807434082031,
|
| 154 |
+
"learning_rate": 3.8607594936708864e-05,
|
| 155 |
+
"loss": 0.6791,
|
| 156 |
+
"step": 126
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8354430379746836,
|
| 160 |
+
"grad_norm": 5.0542826652526855,
|
| 161 |
+
"learning_rate": 4.050632911392405e-05,
|
| 162 |
+
"loss": 0.8218,
|
| 163 |
+
"step": 132
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8734177215189873,
|
| 167 |
+
"grad_norm": 6.254321098327637,
|
| 168 |
+
"learning_rate": 4.240506329113924e-05,
|
| 169 |
+
"loss": 0.642,
|
| 170 |
+
"step": 138
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9113924050632911,
|
| 174 |
+
"grad_norm": 13.176085472106934,
|
| 175 |
+
"learning_rate": 4.430379746835443e-05,
|
| 176 |
+
"loss": 0.7776,
|
| 177 |
+
"step": 144
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9493670886075949,
|
| 181 |
+
"grad_norm": 11.755087852478027,
|
| 182 |
+
"learning_rate": 4.6202531645569625e-05,
|
| 183 |
+
"loss": 0.692,
|
| 184 |
+
"step": 150
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9873417721518988,
|
| 188 |
+
"grad_norm": 17.802106857299805,
|
| 189 |
+
"learning_rate": 4.810126582278481e-05,
|
| 190 |
+
"loss": 0.8154,
|
| 191 |
+
"step": 156
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0,
|
| 195 |
+
"eval_accuracy": 0.6777777777777778,
|
| 196 |
+
"eval_f1_macro": 0.6322818503775589,
|
| 197 |
+
"eval_f1_micro": 0.6777777777777778,
|
| 198 |
+
"eval_f1_weighted": 0.6770410976200751,
|
| 199 |
+
"eval_loss": 0.6622010469436646,
|
| 200 |
+
"eval_precision_macro": 0.7243898689419271,
|
| 201 |
+
"eval_precision_micro": 0.6777777777777778,
|
| 202 |
+
"eval_precision_weighted": 0.7080866119203488,
|
| 203 |
+
"eval_recall_macro": 0.6038604850039704,
|
| 204 |
+
"eval_recall_micro": 0.6777777777777778,
|
| 205 |
+
"eval_recall_weighted": 0.6777777777777778,
|
| 206 |
+
"eval_runtime": 0.7136,
|
| 207 |
+
"eval_samples_per_second": 378.368,
|
| 208 |
+
"eval_steps_per_second": 23.823,
|
| 209 |
+
"step": 158
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.0253164556962024,
|
| 213 |
+
"grad_norm": 19.294593811035156,
|
| 214 |
+
"learning_rate": 5e-05,
|
| 215 |
+
"loss": 0.6055,
|
| 216 |
+
"step": 162
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.0632911392405062,
|
| 220 |
+
"grad_norm": 19.850807189941406,
|
| 221 |
+
"learning_rate": 4.9789029535864986e-05,
|
| 222 |
+
"loss": 0.5312,
|
| 223 |
+
"step": 168
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.1012658227848102,
|
| 227 |
+
"grad_norm": 7.075973987579346,
|
| 228 |
+
"learning_rate": 4.957805907172996e-05,
|
| 229 |
+
"loss": 0.7629,
|
| 230 |
+
"step": 174
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.139240506329114,
|
| 234 |
+
"grad_norm": 26.967010498046875,
|
| 235 |
+
"learning_rate": 4.936708860759494e-05,
|
| 236 |
+
"loss": 0.4555,
|
| 237 |
+
"step": 180
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.1772151898734178,
|
| 241 |
+
"grad_norm": 6.135197639465332,
|
| 242 |
+
"learning_rate": 4.9156118143459915e-05,
|
| 243 |
+
"loss": 0.6125,
|
| 244 |
+
"step": 186
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.2151898734177216,
|
| 248 |
+
"grad_norm": 7.731626033782959,
|
| 249 |
+
"learning_rate": 4.89451476793249e-05,
|
| 250 |
+
"loss": 0.6275,
|
| 251 |
+
"step": 192
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.2531645569620253,
|
| 255 |
+
"grad_norm": 5.7555413246154785,
|
| 256 |
+
"learning_rate": 4.8734177215189874e-05,
|
| 257 |
+
"loss": 0.5737,
|
| 258 |
+
"step": 198
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.2911392405063291,
|
| 262 |
+
"grad_norm": 13.562360763549805,
|
| 263 |
+
"learning_rate": 4.852320675105486e-05,
|
| 264 |
+
"loss": 0.6323,
|
| 265 |
+
"step": 204
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.3291139240506329,
|
| 269 |
+
"grad_norm": 7.536093235015869,
|
| 270 |
+
"learning_rate": 4.8312236286919834e-05,
|
| 271 |
+
"loss": 0.8549,
|
| 272 |
+
"step": 210
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.3670886075949367,
|
| 276 |
+
"grad_norm": 29.301607131958008,
|
| 277 |
+
"learning_rate": 4.810126582278481e-05,
|
| 278 |
+
"loss": 0.6907,
|
| 279 |
+
"step": 216
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.4050632911392404,
|
| 283 |
+
"grad_norm": 29.65777587890625,
|
| 284 |
+
"learning_rate": 4.789029535864979e-05,
|
| 285 |
+
"loss": 0.5163,
|
| 286 |
+
"step": 222
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.4430379746835442,
|
| 290 |
+
"grad_norm": 7.790624618530273,
|
| 291 |
+
"learning_rate": 4.771448663853728e-05,
|
| 292 |
+
"loss": 0.6114,
|
| 293 |
+
"step": 228
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.481012658227848,
|
| 297 |
+
"grad_norm": 6.330058574676514,
|
| 298 |
+
"learning_rate": 4.7503516174402255e-05,
|
| 299 |
+
"loss": 0.504,
|
| 300 |
+
"step": 234
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.518987341772152,
|
| 304 |
+
"grad_norm": 9.592399597167969,
|
| 305 |
+
"learning_rate": 4.729254571026723e-05,
|
| 306 |
+
"loss": 0.6023,
|
| 307 |
+
"step": 240
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.5569620253164556,
|
| 311 |
+
"grad_norm": 16.343538284301758,
|
| 312 |
+
"learning_rate": 4.708157524613221e-05,
|
| 313 |
+
"loss": 0.5629,
|
| 314 |
+
"step": 246
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.5949367088607596,
|
| 318 |
+
"grad_norm": 10.249645233154297,
|
| 319 |
+
"learning_rate": 4.690576652601969e-05,
|
| 320 |
+
"loss": 0.4879,
|
| 321 |
+
"step": 252
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.6329113924050633,
|
| 325 |
+
"grad_norm": 16.510406494140625,
|
| 326 |
+
"learning_rate": 4.669479606188467e-05,
|
| 327 |
+
"loss": 0.5899,
|
| 328 |
+
"step": 258
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.6708860759493671,
|
| 332 |
+
"grad_norm": 26.869653701782227,
|
| 333 |
+
"learning_rate": 4.648382559774965e-05,
|
| 334 |
+
"loss": 0.6104,
|
| 335 |
+
"step": 264
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.7088607594936709,
|
| 339 |
+
"grad_norm": 31.33711051940918,
|
| 340 |
+
"learning_rate": 4.627285513361463e-05,
|
| 341 |
+
"loss": 0.6123,
|
| 342 |
+
"step": 270
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.7468354430379747,
|
| 346 |
+
"grad_norm": 19.872238159179688,
|
| 347 |
+
"learning_rate": 4.606188466947961e-05,
|
| 348 |
+
"loss": 0.5996,
|
| 349 |
+
"step": 276
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.7848101265822784,
|
| 353 |
+
"grad_norm": 226.0241241455078,
|
| 354 |
+
"learning_rate": 4.585091420534459e-05,
|
| 355 |
+
"loss": 0.6073,
|
| 356 |
+
"step": 282
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.8227848101265822,
|
| 360 |
+
"grad_norm": 7.545466423034668,
|
| 361 |
+
"learning_rate": 4.5639943741209564e-05,
|
| 362 |
+
"loss": 0.4792,
|
| 363 |
+
"step": 288
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.8607594936708862,
|
| 367 |
+
"grad_norm": 25.7376708984375,
|
| 368 |
+
"learning_rate": 4.542897327707454e-05,
|
| 369 |
+
"loss": 0.6874,
|
| 370 |
+
"step": 294
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.8987341772151898,
|
| 374 |
+
"grad_norm": 5.723837852478027,
|
| 375 |
+
"learning_rate": 4.5218002812939524e-05,
|
| 376 |
+
"loss": 0.6235,
|
| 377 |
+
"step": 300
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.9367088607594938,
|
| 381 |
+
"grad_norm": 14.01853084564209,
|
| 382 |
+
"learning_rate": 4.50070323488045e-05,
|
| 383 |
+
"loss": 0.5475,
|
| 384 |
+
"step": 306
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.9746835443037973,
|
| 388 |
+
"grad_norm": 5.021835803985596,
|
| 389 |
+
"learning_rate": 4.4796061884669484e-05,
|
| 390 |
+
"loss": 0.4888,
|
| 391 |
+
"step": 312
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.0,
|
| 395 |
+
"eval_accuracy": 0.725925925925926,
|
| 396 |
+
"eval_f1_macro": 0.7163881004940608,
|
| 397 |
+
"eval_f1_micro": 0.725925925925926,
|
| 398 |
+
"eval_f1_weighted": 0.7259726456194447,
|
| 399 |
+
"eval_loss": 0.6413357257843018,
|
| 400 |
+
"eval_precision_macro": 0.6712302319912927,
|
| 401 |
+
"eval_precision_micro": 0.725925925925926,
|
| 402 |
+
"eval_precision_weighted": 0.7310670226564031,
|
| 403 |
+
"eval_recall_macro": 0.8041251807057194,
|
| 404 |
+
"eval_recall_micro": 0.725925925925926,
|
| 405 |
+
"eval_recall_weighted": 0.725925925925926,
|
| 406 |
+
"eval_runtime": 0.7317,
|
| 407 |
+
"eval_samples_per_second": 369.017,
|
| 408 |
+
"eval_steps_per_second": 23.234,
|
| 409 |
+
"step": 316
|
| 410 |
+
}
|
| 411 |
+
],
|
| 412 |
+
"logging_steps": 6,
|
| 413 |
+
"max_steps": 1580,
|
| 414 |
+
"num_input_tokens_seen": 0,
|
| 415 |
+
"num_train_epochs": 10,
|
| 416 |
+
"save_steps": 500,
|
| 417 |
+
"total_flos": 165761453168640.0,
|
| 418 |
+
"train_batch_size": 8,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
checkpoint-316/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3629f8c97a9ab4390d867c941b7f323ecdf3a97a198c81da98aae3cc39a1e852
|
| 3 |
+
size 4984
|
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:a3e00e4dcfcec97be98271f56649edf83f795204f15ca20934b9c83a85e8f52d
|
| 3 |
+
size 436358132
|
runs/May05_10-37-35_r-zerithas-myownmodels-v1-1qgyqe4s-88912-ms88x/events.out.tfevents.1714905455.r-zerithas-myownmodels-v1-1qgyqe4s-88912-ms88x.59.0
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 sha256:2545adc065c4f2aee785976da2b520aa9c499eedd8dacf3f7212a1af4c99a362
|
| 3 |
+
size 36943
|
runs/May05_10-37-35_r-zerithas-myownmodels-v1-1qgyqe4s-88912-ms88x/events.out.tfevents.1714905549.r-zerithas-myownmodels-v1-1qgyqe4s-88912-ms88x.59.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5146ba82a6d6fb38f618917efa8063783a49aabc89c3ff879d8e5a7f3c163845
|
| 3 |
+
size 921
|
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 sha256:3629f8c97a9ab4390d867c941b7f323ecdf3a97a198c81da98aae3cc39a1e852
|
| 3 |
+
size 4984
|
training_params.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "v20/autotrain-data",
|
| 3 |
+
"model": "oliverguhr/german-sentiment-bert",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 10,
|
| 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": "v20",
|
| 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
|
|
|