Text Classification
Transformers
TensorBoard
Safetensors
bert
Trained with AutoTrain
text-embeddings-inference
Instructions to use mserloth/v19 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mserloth/v19 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mserloth/v19")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mserloth/v19") model = AutoModelForSequenceClassification.from_pretrained("mserloth/v19", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Markus Serloth-Schwarzer commited on
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-368/config.json +38 -0
- checkpoint-368/model.safetensors +3 -0
- checkpoint-368/optimizer.pt +3 -0
- checkpoint-368/rng_state.pth +3 -0
- checkpoint-368/scheduler.pt +3 -0
- checkpoint-368/trainer_state.json +421 -0
- checkpoint-368/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/May05_10-02-06_r-zerithas-myownmodels-v1-mnofk6gk-c6a2e-l4mk2/events.out.tfevents.1714903326.r-zerithas-myownmodels-v1-mnofk6gk-c6a2e-l4mk2.61.0 +2 -2
- runs/May05_10-02-06_r-zerithas-myownmodels-v1-mnofk6gk-c6a2e-l4mk2/events.out.tfevents.1714903434.r-zerithas-myownmodels-v1-mnofk6gk-c6a2e-l4mk2.61.1 +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 |
+
- v19/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.5771334767341614
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.713149936591552
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.7587301587301587
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.7515986825907809
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.7044296788482836
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.7587301587301587
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.7628139007541002
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.7482673192543582
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.7587301587301587
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.7587301587301587
|
| 36 |
+
|
| 37 |
+
accuracy: 0.7587301587301587
|
checkpoint-368/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-368/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38b3c110754ad3c8e2a43c1637135bfe058885ccc4441cd9a180f4c1c35498b3
|
| 3 |
+
size 436358132
|
checkpoint-368/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7980332de89674575897cfd18c93a288ae18135c48d4468cb39182f8f6c8036
|
| 3 |
+
size 872837370
|
checkpoint-368/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81a015d4b82aa3f4f8f7751d19ab5eef07ecd5ae6dfac663659a976b02d88991
|
| 3 |
+
size 14244
|
checkpoint-368/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aea5a160e4be2583e335c7160be6317155a2e6a68e817ec264da1339fb24450a
|
| 3 |
+
size 1064
|
checkpoint-368/trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5771334767341614,
|
| 3 |
+
"best_model_checkpoint": "v19/checkpoint-368",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 368,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03804347826086957,
|
| 13 |
+
"grad_norm": 63.9192008972168,
|
| 14 |
+
"learning_rate": 8.152173913043479e-07,
|
| 15 |
+
"loss": 2.8905,
|
| 16 |
+
"step": 7
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07608695652173914,
|
| 20 |
+
"grad_norm": 46.61458206176758,
|
| 21 |
+
"learning_rate": 2.7173913043478263e-06,
|
| 22 |
+
"loss": 2.4535,
|
| 23 |
+
"step": 14
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11413043478260869,
|
| 27 |
+
"grad_norm": 38.13865280151367,
|
| 28 |
+
"learning_rate": 4.619565217391304e-06,
|
| 29 |
+
"loss": 2.3807,
|
| 30 |
+
"step": 21
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15217391304347827,
|
| 34 |
+
"grad_norm": 85.5317153930664,
|
| 35 |
+
"learning_rate": 6.521739130434783e-06,
|
| 36 |
+
"loss": 1.6676,
|
| 37 |
+
"step": 28
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19021739130434784,
|
| 41 |
+
"grad_norm": 23.912166595458984,
|
| 42 |
+
"learning_rate": 8.423913043478262e-06,
|
| 43 |
+
"loss": 1.4964,
|
| 44 |
+
"step": 35
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22826086956521738,
|
| 48 |
+
"grad_norm": 32.738983154296875,
|
| 49 |
+
"learning_rate": 1.032608695652174e-05,
|
| 50 |
+
"loss": 1.4033,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.266304347826087,
|
| 55 |
+
"grad_norm": 19.695199966430664,
|
| 56 |
+
"learning_rate": 1.2228260869565218e-05,
|
| 57 |
+
"loss": 1.0368,
|
| 58 |
+
"step": 49
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.30434782608695654,
|
| 62 |
+
"grad_norm": 18.504451751708984,
|
| 63 |
+
"learning_rate": 1.4130434782608694e-05,
|
| 64 |
+
"loss": 1.1664,
|
| 65 |
+
"step": 56
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3423913043478261,
|
| 69 |
+
"grad_norm": 24.36909294128418,
|
| 70 |
+
"learning_rate": 1.6032608695652173e-05,
|
| 71 |
+
"loss": 1.1207,
|
| 72 |
+
"step": 63
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3804347826086957,
|
| 76 |
+
"grad_norm": 9.182580947875977,
|
| 77 |
+
"learning_rate": 1.793478260869565e-05,
|
| 78 |
+
"loss": 0.8311,
|
| 79 |
+
"step": 70
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.41847826086956524,
|
| 83 |
+
"grad_norm": 27.781766891479492,
|
| 84 |
+
"learning_rate": 1.9836956521739132e-05,
|
| 85 |
+
"loss": 0.8243,
|
| 86 |
+
"step": 77
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.45652173913043476,
|
| 90 |
+
"grad_norm": 11.38399887084961,
|
| 91 |
+
"learning_rate": 2.173913043478261e-05,
|
| 92 |
+
"loss": 0.6721,
|
| 93 |
+
"step": 84
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4945652173913043,
|
| 97 |
+
"grad_norm": 8.822359085083008,
|
| 98 |
+
"learning_rate": 2.3641304347826088e-05,
|
| 99 |
+
"loss": 0.6353,
|
| 100 |
+
"step": 91
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.532608695652174,
|
| 104 |
+
"grad_norm": 12.496397018432617,
|
| 105 |
+
"learning_rate": 2.554347826086957e-05,
|
| 106 |
+
"loss": 0.6571,
|
| 107 |
+
"step": 98
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5706521739130435,
|
| 111 |
+
"grad_norm": 15.013715744018555,
|
| 112 |
+
"learning_rate": 2.7445652173913044e-05,
|
| 113 |
+
"loss": 0.6634,
|
| 114 |
+
"step": 105
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6086956521739131,
|
| 118 |
+
"grad_norm": 19.115114212036133,
|
| 119 |
+
"learning_rate": 2.9347826086956526e-05,
|
| 120 |
+
"loss": 0.654,
|
| 121 |
+
"step": 112
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6467391304347826,
|
| 125 |
+
"grad_norm": 8.66184139251709,
|
| 126 |
+
"learning_rate": 3.125e-05,
|
| 127 |
+
"loss": 0.6429,
|
| 128 |
+
"step": 119
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6847826086956522,
|
| 132 |
+
"grad_norm": 6.31260347366333,
|
| 133 |
+
"learning_rate": 3.3152173913043475e-05,
|
| 134 |
+
"loss": 0.673,
|
| 135 |
+
"step": 126
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7228260869565217,
|
| 139 |
+
"grad_norm": 9.37307071685791,
|
| 140 |
+
"learning_rate": 3.505434782608696e-05,
|
| 141 |
+
"loss": 0.5492,
|
| 142 |
+
"step": 133
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7608695652173914,
|
| 146 |
+
"grad_norm": 19.3261661529541,
|
| 147 |
+
"learning_rate": 3.695652173913043e-05,
|
| 148 |
+
"loss": 0.6397,
|
| 149 |
+
"step": 140
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7989130434782609,
|
| 153 |
+
"grad_norm": 15.380707740783691,
|
| 154 |
+
"learning_rate": 3.885869565217391e-05,
|
| 155 |
+
"loss": 0.6132,
|
| 156 |
+
"step": 147
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8369565217391305,
|
| 160 |
+
"grad_norm": 10.869492530822754,
|
| 161 |
+
"learning_rate": 4.076086956521739e-05,
|
| 162 |
+
"loss": 0.7432,
|
| 163 |
+
"step": 154
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.875,
|
| 167 |
+
"grad_norm": 29.385499954223633,
|
| 168 |
+
"learning_rate": 4.266304347826087e-05,
|
| 169 |
+
"loss": 0.67,
|
| 170 |
+
"step": 161
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9130434782608695,
|
| 174 |
+
"grad_norm": 10.063030242919922,
|
| 175 |
+
"learning_rate": 4.456521739130435e-05,
|
| 176 |
+
"loss": 0.6507,
|
| 177 |
+
"step": 168
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9510869565217391,
|
| 181 |
+
"grad_norm": 16.420034408569336,
|
| 182 |
+
"learning_rate": 4.646739130434783e-05,
|
| 183 |
+
"loss": 0.629,
|
| 184 |
+
"step": 175
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9891304347826086,
|
| 188 |
+
"grad_norm": 20.766639709472656,
|
| 189 |
+
"learning_rate": 4.836956521739131e-05,
|
| 190 |
+
"loss": 0.7708,
|
| 191 |
+
"step": 182
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0,
|
| 195 |
+
"eval_accuracy": 0.5968253968253968,
|
| 196 |
+
"eval_f1_macro": 0.454484367602753,
|
| 197 |
+
"eval_f1_micro": 0.5968253968253968,
|
| 198 |
+
"eval_f1_weighted": 0.465185203450384,
|
| 199 |
+
"eval_loss": 0.716547429561615,
|
| 200 |
+
"eval_precision_macro": 0.6810100104586883,
|
| 201 |
+
"eval_precision_micro": 0.5968253968253968,
|
| 202 |
+
"eval_precision_weighted": 0.7494923623117259,
|
| 203 |
+
"eval_recall_macro": 0.6516662134807698,
|
| 204 |
+
"eval_recall_micro": 0.5968253968253968,
|
| 205 |
+
"eval_recall_weighted": 0.5968253968253968,
|
| 206 |
+
"eval_runtime": 0.8391,
|
| 207 |
+
"eval_samples_per_second": 375.394,
|
| 208 |
+
"eval_steps_per_second": 23.835,
|
| 209 |
+
"step": 184
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.0271739130434783,
|
| 213 |
+
"grad_norm": 5.850246906280518,
|
| 214 |
+
"learning_rate": 4.9969806763285025e-05,
|
| 215 |
+
"loss": 0.6568,
|
| 216 |
+
"step": 189
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.065217391304348,
|
| 220 |
+
"grad_norm": 13.868361473083496,
|
| 221 |
+
"learning_rate": 4.9758454106280194e-05,
|
| 222 |
+
"loss": 0.5564,
|
| 223 |
+
"step": 196
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.1032608695652173,
|
| 227 |
+
"grad_norm": 21.7174072265625,
|
| 228 |
+
"learning_rate": 4.9547101449275364e-05,
|
| 229 |
+
"loss": 0.6629,
|
| 230 |
+
"step": 203
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.141304347826087,
|
| 234 |
+
"grad_norm": 24.38075065612793,
|
| 235 |
+
"learning_rate": 4.933574879227053e-05,
|
| 236 |
+
"loss": 0.5487,
|
| 237 |
+
"step": 210
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.1793478260869565,
|
| 241 |
+
"grad_norm": 19.306556701660156,
|
| 242 |
+
"learning_rate": 4.91243961352657e-05,
|
| 243 |
+
"loss": 0.6809,
|
| 244 |
+
"step": 217
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.2173913043478262,
|
| 248 |
+
"grad_norm": 11.268362045288086,
|
| 249 |
+
"learning_rate": 4.891304347826087e-05,
|
| 250 |
+
"loss": 0.5441,
|
| 251 |
+
"step": 224
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.2554347826086958,
|
| 255 |
+
"grad_norm": 10.799726486206055,
|
| 256 |
+
"learning_rate": 4.870169082125604e-05,
|
| 257 |
+
"loss": 0.7062,
|
| 258 |
+
"step": 231
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.2934782608695652,
|
| 262 |
+
"grad_norm": 7.134019374847412,
|
| 263 |
+
"learning_rate": 4.849033816425121e-05,
|
| 264 |
+
"loss": 0.4888,
|
| 265 |
+
"step": 238
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.3315217391304348,
|
| 269 |
+
"grad_norm": 18.638015747070312,
|
| 270 |
+
"learning_rate": 4.8278985507246374e-05,
|
| 271 |
+
"loss": 0.5752,
|
| 272 |
+
"step": 245
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.3695652173913042,
|
| 276 |
+
"grad_norm": 22.29207992553711,
|
| 277 |
+
"learning_rate": 4.806763285024155e-05,
|
| 278 |
+
"loss": 0.4155,
|
| 279 |
+
"step": 252
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.4076086956521738,
|
| 283 |
+
"grad_norm": 15.408923149108887,
|
| 284 |
+
"learning_rate": 4.785628019323672e-05,
|
| 285 |
+
"loss": 0.5075,
|
| 286 |
+
"step": 259
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.4456521739130435,
|
| 290 |
+
"grad_norm": 11.493151664733887,
|
| 291 |
+
"learning_rate": 4.764492753623189e-05,
|
| 292 |
+
"loss": 0.4878,
|
| 293 |
+
"step": 266
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.483695652173913,
|
| 297 |
+
"grad_norm": 26.615182876586914,
|
| 298 |
+
"learning_rate": 4.743357487922706e-05,
|
| 299 |
+
"loss": 0.5762,
|
| 300 |
+
"step": 273
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.5217391304347827,
|
| 304 |
+
"grad_norm": 24.798564910888672,
|
| 305 |
+
"learning_rate": 4.722222222222222e-05,
|
| 306 |
+
"loss": 0.7204,
|
| 307 |
+
"step": 280
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.5597826086956523,
|
| 311 |
+
"grad_norm": 11.025556564331055,
|
| 312 |
+
"learning_rate": 4.701086956521739e-05,
|
| 313 |
+
"loss": 0.4635,
|
| 314 |
+
"step": 287
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.5978260869565217,
|
| 318 |
+
"grad_norm": 24.296916961669922,
|
| 319 |
+
"learning_rate": 4.679951690821257e-05,
|
| 320 |
+
"loss": 0.4529,
|
| 321 |
+
"step": 294
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.6358695652173914,
|
| 325 |
+
"grad_norm": 16.77727699279785,
|
| 326 |
+
"learning_rate": 4.6588164251207736e-05,
|
| 327 |
+
"loss": 0.5625,
|
| 328 |
+
"step": 301
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.6739130434782608,
|
| 332 |
+
"grad_norm": 19.565649032592773,
|
| 333 |
+
"learning_rate": 4.63768115942029e-05,
|
| 334 |
+
"loss": 0.6036,
|
| 335 |
+
"step": 308
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.7119565217391304,
|
| 339 |
+
"grad_norm": 15.079780578613281,
|
| 340 |
+
"learning_rate": 4.616545893719807e-05,
|
| 341 |
+
"loss": 0.3821,
|
| 342 |
+
"step": 315
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.75,
|
| 346 |
+
"grad_norm": 11.975324630737305,
|
| 347 |
+
"learning_rate": 4.595410628019324e-05,
|
| 348 |
+
"loss": 0.5276,
|
| 349 |
+
"step": 322
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.7880434782608696,
|
| 353 |
+
"grad_norm": 8.451642036437988,
|
| 354 |
+
"learning_rate": 4.574275362318841e-05,
|
| 355 |
+
"loss": 0.4457,
|
| 356 |
+
"step": 329
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.8260869565217392,
|
| 360 |
+
"grad_norm": 10.085076332092285,
|
| 361 |
+
"learning_rate": 4.553140096618358e-05,
|
| 362 |
+
"loss": 0.3253,
|
| 363 |
+
"step": 336
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.8641304347826086,
|
| 367 |
+
"grad_norm": 4.127739429473877,
|
| 368 |
+
"learning_rate": 4.5320048309178746e-05,
|
| 369 |
+
"loss": 0.5676,
|
| 370 |
+
"step": 343
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.9021739130434783,
|
| 374 |
+
"grad_norm": 11.594162940979004,
|
| 375 |
+
"learning_rate": 4.5108695652173916e-05,
|
| 376 |
+
"loss": 0.6035,
|
| 377 |
+
"step": 350
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.9402173913043477,
|
| 381 |
+
"grad_norm": 10.497764587402344,
|
| 382 |
+
"learning_rate": 4.4897342995169085e-05,
|
| 383 |
+
"loss": 0.5138,
|
| 384 |
+
"step": 357
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.9782608695652173,
|
| 388 |
+
"grad_norm": 8.271937370300293,
|
| 389 |
+
"learning_rate": 4.4685990338164255e-05,
|
| 390 |
+
"loss": 0.4024,
|
| 391 |
+
"step": 364
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.0,
|
| 395 |
+
"eval_accuracy": 0.7587301587301587,
|
| 396 |
+
"eval_f1_macro": 0.713149936591552,
|
| 397 |
+
"eval_f1_micro": 0.7587301587301587,
|
| 398 |
+
"eval_f1_weighted": 0.7515986825907809,
|
| 399 |
+
"eval_loss": 0.5771334767341614,
|
| 400 |
+
"eval_precision_macro": 0.7044296788482836,
|
| 401 |
+
"eval_precision_micro": 0.7587301587301587,
|
| 402 |
+
"eval_precision_weighted": 0.7628139007541002,
|
| 403 |
+
"eval_recall_macro": 0.7482673192543582,
|
| 404 |
+
"eval_recall_micro": 0.7587301587301587,
|
| 405 |
+
"eval_recall_weighted": 0.7587301587301587,
|
| 406 |
+
"eval_runtime": 0.8342,
|
| 407 |
+
"eval_samples_per_second": 377.618,
|
| 408 |
+
"eval_steps_per_second": 23.976,
|
| 409 |
+
"step": 368
|
| 410 |
+
}
|
| 411 |
+
],
|
| 412 |
+
"logging_steps": 7,
|
| 413 |
+
"max_steps": 1840,
|
| 414 |
+
"num_input_tokens_seen": 0,
|
| 415 |
+
"num_train_epochs": 10,
|
| 416 |
+
"save_steps": 500,
|
| 417 |
+
"total_flos": 193388362030080.0,
|
| 418 |
+
"train_batch_size": 8,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
checkpoint-368/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f6cb388502bb091ab81145a4f1edbff95ffd66da5825f29a1ee5d4c4841c9d1
|
| 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 sha256:38b3c110754ad3c8e2a43c1637135bfe058885ccc4441cd9a180f4c1c35498b3
|
| 3 |
+
size 436358132
|
runs/May05_10-02-06_r-zerithas-myownmodels-v1-mnofk6gk-c6a2e-l4mk2/events.out.tfevents.1714903326.r-zerithas-myownmodels-v1-mnofk6gk-c6a2e-l4mk2.61.0
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:d052d465ddb80b4a8ef82b479112ff5ebaf6ff5ce0b262e1a72e216b8f2baf9b
|
| 3 |
+
size 36955
|
runs/May05_10-02-06_r-zerithas-myownmodels-v1-mnofk6gk-c6a2e-l4mk2/events.out.tfevents.1714903434.r-zerithas-myownmodels-v1-mnofk6gk-c6a2e-l4mk2.61.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85e5a564f07f8d027ea6d1decd2cebd996ef043f1cd55074c1f113c793f7ac4d
|
| 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 sha256:9f6cb388502bb091ab81145a4f1edbff95ffd66da5825f29a1ee5d4c4841c9d1
|
| 3 |
+
size 4984
|
training_params.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "v19/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": "v19",
|
| 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
|
|
|