Text Classification
Transformers
TensorBoard
Safetensors
bert
Trained with AutoTrain
text-embeddings-inference
Instructions to use mserloth/v14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mserloth/v14 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mserloth/v14")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mserloth/v14") model = AutoModelForSequenceClassification.from_pretrained("mserloth/v14", 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/May02_12-39-46_r-zerithas-myownmodels-v1-yosrlj49-ad972-n0zxv/events.out.tfevents.1714653587.r-zerithas-myownmodels-v1-yosrlj49-ad972-n0zxv.61.0 +2 -2
- runs/May02_12-39-46_r-zerithas-myownmodels-v1-yosrlj49-ad972-n0zxv/events.out.tfevents.1714653692.r-zerithas-myownmodels-v1-yosrlj49-ad972-n0zxv.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 |
+
- v14/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.5613215565681458
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.7270965370193369
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.7587301587301587
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.7500760798400677
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.7107159142726859
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.7587301587301587
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.7611013397607105
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.777733466267863
|
| 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 sha256:6d254c82a56d339d3670d6962aa69167f9dc58e90a856032d0e74f93ae98151f
|
| 3 |
+
size 436358132
|
checkpoint-368/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97d8cb50dd4730a08b159309cd93d39598f4ac0af4cab4afe90e1ca91f2b85df
|
| 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 sha256:2451c6dce9a69191cc857a1c42a145f84089b324eee2bacd6dd521722a01fbca
|
| 3 |
+
size 1064
|
checkpoint-368/trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5613215565681458,
|
| 3 |
+
"best_model_checkpoint": "v14/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": 64.65226745605469,
|
| 14 |
+
"learning_rate": 1.6304347826086957e-06,
|
| 15 |
+
"loss": 2.888,
|
| 16 |
+
"step": 7
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07608695652173914,
|
| 20 |
+
"grad_norm": 34.6030387878418,
|
| 21 |
+
"learning_rate": 5.4347826086956525e-06,
|
| 22 |
+
"loss": 2.3409,
|
| 23 |
+
"step": 14
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11413043478260869,
|
| 27 |
+
"grad_norm": 183.6501922607422,
|
| 28 |
+
"learning_rate": 9.239130434782608e-06,
|
| 29 |
+
"loss": 2.1865,
|
| 30 |
+
"step": 21
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15217391304347827,
|
| 34 |
+
"grad_norm": 69.03346252441406,
|
| 35 |
+
"learning_rate": 1.3043478260869566e-05,
|
| 36 |
+
"loss": 1.4345,
|
| 37 |
+
"step": 28
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19021739130434784,
|
| 41 |
+
"grad_norm": 21.692445755004883,
|
| 42 |
+
"learning_rate": 1.6847826086956524e-05,
|
| 43 |
+
"loss": 1.242,
|
| 44 |
+
"step": 35
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22826086956521738,
|
| 48 |
+
"grad_norm": 10.194106101989746,
|
| 49 |
+
"learning_rate": 2.065217391304348e-05,
|
| 50 |
+
"loss": 1.0663,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.266304347826087,
|
| 55 |
+
"grad_norm": 5.273725509643555,
|
| 56 |
+
"learning_rate": 2.4456521739130436e-05,
|
| 57 |
+
"loss": 0.7684,
|
| 58 |
+
"step": 49
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.30434782608695654,
|
| 62 |
+
"grad_norm": 14.056107521057129,
|
| 63 |
+
"learning_rate": 2.826086956521739e-05,
|
| 64 |
+
"loss": 0.8307,
|
| 65 |
+
"step": 56
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3423913043478261,
|
| 69 |
+
"grad_norm": 10.979012489318848,
|
| 70 |
+
"learning_rate": 3.2065217391304345e-05,
|
| 71 |
+
"loss": 0.9566,
|
| 72 |
+
"step": 63
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3804347826086957,
|
| 76 |
+
"grad_norm": 14.053420066833496,
|
| 77 |
+
"learning_rate": 3.58695652173913e-05,
|
| 78 |
+
"loss": 0.7582,
|
| 79 |
+
"step": 70
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.41847826086956524,
|
| 83 |
+
"grad_norm": 16.430551528930664,
|
| 84 |
+
"learning_rate": 3.9673913043478264e-05,
|
| 85 |
+
"loss": 0.7526,
|
| 86 |
+
"step": 77
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.45652173913043476,
|
| 90 |
+
"grad_norm": 5.450341701507568,
|
| 91 |
+
"learning_rate": 4.347826086956522e-05,
|
| 92 |
+
"loss": 0.6625,
|
| 93 |
+
"step": 84
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4945652173913043,
|
| 97 |
+
"grad_norm": 4.27205228805542,
|
| 98 |
+
"learning_rate": 4.7282608695652177e-05,
|
| 99 |
+
"loss": 0.6021,
|
| 100 |
+
"step": 91
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.532608695652174,
|
| 104 |
+
"grad_norm": 4.392812252044678,
|
| 105 |
+
"learning_rate": 4.98792270531401e-05,
|
| 106 |
+
"loss": 0.6189,
|
| 107 |
+
"step": 98
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5706521739130435,
|
| 111 |
+
"grad_norm": 15.128705024719238,
|
| 112 |
+
"learning_rate": 4.945652173913044e-05,
|
| 113 |
+
"loss": 0.5954,
|
| 114 |
+
"step": 105
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6086956521739131,
|
| 118 |
+
"grad_norm": 17.607074737548828,
|
| 119 |
+
"learning_rate": 4.9033816425120776e-05,
|
| 120 |
+
"loss": 0.7061,
|
| 121 |
+
"step": 112
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6467391304347826,
|
| 125 |
+
"grad_norm": 17.542278289794922,
|
| 126 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 127 |
+
"loss": 0.7778,
|
| 128 |
+
"step": 119
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6847826086956522,
|
| 132 |
+
"grad_norm": 5.61037540435791,
|
| 133 |
+
"learning_rate": 4.818840579710145e-05,
|
| 134 |
+
"loss": 0.5989,
|
| 135 |
+
"step": 126
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7228260869565217,
|
| 139 |
+
"grad_norm": 4.548270225524902,
|
| 140 |
+
"learning_rate": 4.776570048309179e-05,
|
| 141 |
+
"loss": 0.6089,
|
| 142 |
+
"step": 133
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7608695652173914,
|
| 146 |
+
"grad_norm": 16.008230209350586,
|
| 147 |
+
"learning_rate": 4.7342995169082125e-05,
|
| 148 |
+
"loss": 0.5782,
|
| 149 |
+
"step": 140
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7989130434782609,
|
| 153 |
+
"grad_norm": 18.840465545654297,
|
| 154 |
+
"learning_rate": 4.6920289855072464e-05,
|
| 155 |
+
"loss": 0.5273,
|
| 156 |
+
"step": 147
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8369565217391305,
|
| 160 |
+
"grad_norm": 16.69438362121582,
|
| 161 |
+
"learning_rate": 4.64975845410628e-05,
|
| 162 |
+
"loss": 0.6971,
|
| 163 |
+
"step": 154
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.875,
|
| 167 |
+
"grad_norm": 12.149147033691406,
|
| 168 |
+
"learning_rate": 4.607487922705314e-05,
|
| 169 |
+
"loss": 0.6922,
|
| 170 |
+
"step": 161
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9130434782608695,
|
| 174 |
+
"grad_norm": 13.31081771850586,
|
| 175 |
+
"learning_rate": 4.565217391304348e-05,
|
| 176 |
+
"loss": 0.6343,
|
| 177 |
+
"step": 168
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9510869565217391,
|
| 181 |
+
"grad_norm": 10.712788581848145,
|
| 182 |
+
"learning_rate": 4.522946859903382e-05,
|
| 183 |
+
"loss": 0.6026,
|
| 184 |
+
"step": 175
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9891304347826086,
|
| 188 |
+
"grad_norm": 12.103906631469727,
|
| 189 |
+
"learning_rate": 4.480676328502416e-05,
|
| 190 |
+
"loss": 0.7,
|
| 191 |
+
"step": 182
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0,
|
| 195 |
+
"eval_accuracy": 0.7174603174603175,
|
| 196 |
+
"eval_f1_macro": 0.6656844689993862,
|
| 197 |
+
"eval_f1_micro": 0.7174603174603175,
|
| 198 |
+
"eval_f1_weighted": 0.6947692127802625,
|
| 199 |
+
"eval_loss": 0.6087798476219177,
|
| 200 |
+
"eval_precision_macro": 0.6825396825396824,
|
| 201 |
+
"eval_precision_micro": 0.7174603174603175,
|
| 202 |
+
"eval_precision_weighted": 0.7275888133030991,
|
| 203 |
+
"eval_recall_macro": 0.7052901900359526,
|
| 204 |
+
"eval_recall_micro": 0.7174603174603175,
|
| 205 |
+
"eval_recall_weighted": 0.7174603174603175,
|
| 206 |
+
"eval_runtime": 0.818,
|
| 207 |
+
"eval_samples_per_second": 385.094,
|
| 208 |
+
"eval_steps_per_second": 24.45,
|
| 209 |
+
"step": 184
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.0271739130434783,
|
| 213 |
+
"grad_norm": 7.486086845397949,
|
| 214 |
+
"learning_rate": 4.438405797101449e-05,
|
| 215 |
+
"loss": 0.5548,
|
| 216 |
+
"step": 189
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.065217391304348,
|
| 220 |
+
"grad_norm": 9.37061595916748,
|
| 221 |
+
"learning_rate": 4.396135265700484e-05,
|
| 222 |
+
"loss": 0.4451,
|
| 223 |
+
"step": 196
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.1032608695652173,
|
| 227 |
+
"grad_norm": 15.137778282165527,
|
| 228 |
+
"learning_rate": 4.353864734299517e-05,
|
| 229 |
+
"loss": 0.6486,
|
| 230 |
+
"step": 203
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.141304347826087,
|
| 234 |
+
"grad_norm": 24.97420883178711,
|
| 235 |
+
"learning_rate": 4.3115942028985515e-05,
|
| 236 |
+
"loss": 0.532,
|
| 237 |
+
"step": 210
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.1793478260869565,
|
| 241 |
+
"grad_norm": 38.207862854003906,
|
| 242 |
+
"learning_rate": 4.269323671497585e-05,
|
| 243 |
+
"loss": 0.6486,
|
| 244 |
+
"step": 217
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.2173913043478262,
|
| 248 |
+
"grad_norm": 13.841968536376953,
|
| 249 |
+
"learning_rate": 4.2270531400966186e-05,
|
| 250 |
+
"loss": 0.4632,
|
| 251 |
+
"step": 224
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.2554347826086958,
|
| 255 |
+
"grad_norm": 8.249053001403809,
|
| 256 |
+
"learning_rate": 4.1847826086956525e-05,
|
| 257 |
+
"loss": 0.6479,
|
| 258 |
+
"step": 231
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.2934782608695652,
|
| 262 |
+
"grad_norm": 21.454967498779297,
|
| 263 |
+
"learning_rate": 4.1425120772946864e-05,
|
| 264 |
+
"loss": 0.4801,
|
| 265 |
+
"step": 238
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.3315217391304348,
|
| 269 |
+
"grad_norm": 28.133909225463867,
|
| 270 |
+
"learning_rate": 4.1002415458937196e-05,
|
| 271 |
+
"loss": 0.7423,
|
| 272 |
+
"step": 245
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.3695652173913042,
|
| 276 |
+
"grad_norm": 37.68894958496094,
|
| 277 |
+
"learning_rate": 4.057971014492754e-05,
|
| 278 |
+
"loss": 0.435,
|
| 279 |
+
"step": 252
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.4076086956521738,
|
| 283 |
+
"grad_norm": 4.886007308959961,
|
| 284 |
+
"learning_rate": 4.0157004830917874e-05,
|
| 285 |
+
"loss": 0.5117,
|
| 286 |
+
"step": 259
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.4456521739130435,
|
| 290 |
+
"grad_norm": 7.007717132568359,
|
| 291 |
+
"learning_rate": 3.973429951690821e-05,
|
| 292 |
+
"loss": 0.5957,
|
| 293 |
+
"step": 266
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.483695652173913,
|
| 297 |
+
"grad_norm": 9.524471282958984,
|
| 298 |
+
"learning_rate": 3.931159420289855e-05,
|
| 299 |
+
"loss": 0.383,
|
| 300 |
+
"step": 273
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.5217391304347827,
|
| 304 |
+
"grad_norm": 9.553020477294922,
|
| 305 |
+
"learning_rate": 3.888888888888889e-05,
|
| 306 |
+
"loss": 0.5468,
|
| 307 |
+
"step": 280
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.5597826086956523,
|
| 311 |
+
"grad_norm": 7.057467937469482,
|
| 312 |
+
"learning_rate": 3.846618357487923e-05,
|
| 313 |
+
"loss": 0.332,
|
| 314 |
+
"step": 287
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.5978260869565217,
|
| 318 |
+
"grad_norm": 18.69020652770996,
|
| 319 |
+
"learning_rate": 3.804347826086957e-05,
|
| 320 |
+
"loss": 0.4083,
|
| 321 |
+
"step": 294
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.6358695652173914,
|
| 325 |
+
"grad_norm": 11.055662155151367,
|
| 326 |
+
"learning_rate": 3.762077294685991e-05,
|
| 327 |
+
"loss": 0.5954,
|
| 328 |
+
"step": 301
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.6739130434782608,
|
| 332 |
+
"grad_norm": 8.085113525390625,
|
| 333 |
+
"learning_rate": 3.719806763285024e-05,
|
| 334 |
+
"loss": 0.6091,
|
| 335 |
+
"step": 308
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.7119565217391304,
|
| 339 |
+
"grad_norm": 20.802650451660156,
|
| 340 |
+
"learning_rate": 3.6775362318840586e-05,
|
| 341 |
+
"loss": 0.4324,
|
| 342 |
+
"step": 315
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.75,
|
| 346 |
+
"grad_norm": 8.253288269042969,
|
| 347 |
+
"learning_rate": 3.635265700483092e-05,
|
| 348 |
+
"loss": 0.3371,
|
| 349 |
+
"step": 322
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.7880434782608696,
|
| 353 |
+
"grad_norm": 13.99079704284668,
|
| 354 |
+
"learning_rate": 3.592995169082126e-05,
|
| 355 |
+
"loss": 0.5806,
|
| 356 |
+
"step": 329
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.8260869565217392,
|
| 360 |
+
"grad_norm": 12.388429641723633,
|
| 361 |
+
"learning_rate": 3.5507246376811596e-05,
|
| 362 |
+
"loss": 0.3447,
|
| 363 |
+
"step": 336
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.8641304347826086,
|
| 367 |
+
"grad_norm": 4.741861343383789,
|
| 368 |
+
"learning_rate": 3.5084541062801935e-05,
|
| 369 |
+
"loss": 0.5249,
|
| 370 |
+
"step": 343
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.9021739130434783,
|
| 374 |
+
"grad_norm": 9.289843559265137,
|
| 375 |
+
"learning_rate": 3.4661835748792274e-05,
|
| 376 |
+
"loss": 0.6764,
|
| 377 |
+
"step": 350
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.9402173913043477,
|
| 381 |
+
"grad_norm": 10.707498550415039,
|
| 382 |
+
"learning_rate": 3.423913043478261e-05,
|
| 383 |
+
"loss": 0.5032,
|
| 384 |
+
"step": 357
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.9782608695652173,
|
| 388 |
+
"grad_norm": 12.9315185546875,
|
| 389 |
+
"learning_rate": 3.381642512077295e-05,
|
| 390 |
+
"loss": 0.4453,
|
| 391 |
+
"step": 364
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.0,
|
| 395 |
+
"eval_accuracy": 0.7587301587301587,
|
| 396 |
+
"eval_f1_macro": 0.7270965370193369,
|
| 397 |
+
"eval_f1_micro": 0.7587301587301587,
|
| 398 |
+
"eval_f1_weighted": 0.7500760798400677,
|
| 399 |
+
"eval_loss": 0.5613215565681458,
|
| 400 |
+
"eval_precision_macro": 0.7107159142726859,
|
| 401 |
+
"eval_precision_micro": 0.7587301587301587,
|
| 402 |
+
"eval_precision_weighted": 0.7611013397607105,
|
| 403 |
+
"eval_recall_macro": 0.777733466267863,
|
| 404 |
+
"eval_recall_micro": 0.7587301587301587,
|
| 405 |
+
"eval_recall_weighted": 0.7587301587301587,
|
| 406 |
+
"eval_runtime": 0.8123,
|
| 407 |
+
"eval_samples_per_second": 387.767,
|
| 408 |
+
"eval_steps_per_second": 24.62,
|
| 409 |
+
"step": 368
|
| 410 |
+
}
|
| 411 |
+
],
|
| 412 |
+
"logging_steps": 7,
|
| 413 |
+
"max_steps": 920,
|
| 414 |
+
"num_input_tokens_seen": 0,
|
| 415 |
+
"num_train_epochs": 5,
|
| 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:d7df67dc41ee371e0199076bb8d98f880f4bd55507ece97a2b2c8f93c8c8b03f
|
| 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 sha256:6d254c82a56d339d3670d6962aa69167f9dc58e90a856032d0e74f93ae98151f
|
| 3 |
+
size 436358132
|
runs/May02_12-39-46_r-zerithas-myownmodels-v1-yosrlj49-ad972-n0zxv/events.out.tfevents.1714653587.r-zerithas-myownmodels-v1-yosrlj49-ad972-n0zxv.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:b4b53f034a1ae6b71871b0db3f85c72dbd2e6b73f54a9b1aa208913a8bda520a
|
| 3 |
+
size 36954
|
runs/May02_12-39-46_r-zerithas-myownmodels-v1-yosrlj49-ad972-n0zxv/events.out.tfevents.1714653692.r-zerithas-myownmodels-v1-yosrlj49-ad972-n0zxv.61.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26ccfa5f0ae178eb759d747d122b258c761ce520f6924aa4aba31d35fa765137
|
| 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:d7df67dc41ee371e0199076bb8d98f880f4bd55507ece97a2b2c8f93c8c8b03f
|
| 3 |
+
size 4984
|
training_params.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "v14/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": "v14",
|
| 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
|
|
|