Text Classification
Transformers
TensorBoard
Safetensors
bert
Trained with AutoTrain
text-embeddings-inference
Instructions to use mserloth/V13 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mserloth/V13 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mserloth/V13")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mserloth/V13") model = AutoModelForSequenceClassification.from_pretrained("mserloth/V13", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Markus Serloth-Schwarzer commited on
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-312/config.json +38 -0
- checkpoint-312/model.safetensors +3 -0
- checkpoint-312/optimizer.pt +3 -0
- checkpoint-312/rng_state.pth +3 -0
- checkpoint-312/scheduler.pt +3 -0
- checkpoint-312/trainer_state.json +365 -0
- checkpoint-312/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/May02_11-23-07_r-zerithas-myownmodels-v1-b1g0511n-fc7a5-8npzw/events.out.tfevents.1714648988.r-zerithas-myownmodels-v1-b1g0511n-fc7a5-8npzw.62.0 +2 -2
- runs/May02_11-23-07_r-zerithas-myownmodels-v1-b1g0511n-fc7a5-8npzw/events.out.tfevents.1714649081.r-zerithas-myownmodels-v1-b1g0511n-fc7a5-8npzw.62.1 +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 |
+
- V13/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.587009608745575
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.7086614173228346
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.7435897435897436
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.7361195235210982
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.7210665002427016
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.7435897435897436
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.7538358857008742
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.7157125819916518
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.7435897435897436
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.7435897435897436
|
| 36 |
+
|
| 37 |
+
accuracy: 0.7435897435897436
|
checkpoint-312/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-312/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9202fa9a07074efaaa2e1919694d34065825e4ac99f0f45a51c58fbaf2b18f3a
|
| 3 |
+
size 436358132
|
checkpoint-312/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0b9c71222f4295d677565f953824075aeaec9558dafba117415adeed3a6cd33
|
| 3 |
+
size 872837370
|
checkpoint-312/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d4b1efcc78ff6da9d0c781f6c23ed3165cb1043d09b2876292decec1e8a4919
|
| 3 |
+
size 14244
|
checkpoint-312/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30b7649033f15856c6fe4f4b844477fc5d0fdf5208dd476580522775bee50a0a
|
| 3 |
+
size 1064
|
checkpoint-312/trainer_state.json
ADDED
|
@@ -0,0 +1,365 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.587009608745575,
|
| 3 |
+
"best_model_checkpoint": "V13/checkpoint-312",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 312,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04487179487179487,
|
| 13 |
+
"grad_norm": 63.9647331237793,
|
| 14 |
+
"learning_rate": 6.41025641025641e-07,
|
| 15 |
+
"loss": 3.0773,
|
| 16 |
+
"step": 7
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08974358974358974,
|
| 20 |
+
"grad_norm": 58.97015380859375,
|
| 21 |
+
"learning_rate": 2.136752136752137e-06,
|
| 22 |
+
"loss": 2.7492,
|
| 23 |
+
"step": 14
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1346153846153846,
|
| 27 |
+
"grad_norm": 64.63655090332031,
|
| 28 |
+
"learning_rate": 3.632478632478633e-06,
|
| 29 |
+
"loss": 2.1906,
|
| 30 |
+
"step": 21
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1794871794871795,
|
| 34 |
+
"grad_norm": 29.906232833862305,
|
| 35 |
+
"learning_rate": 5.128205128205128e-06,
|
| 36 |
+
"loss": 2.3421,
|
| 37 |
+
"step": 28
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.22435897435897437,
|
| 41 |
+
"grad_norm": 22.833885192871094,
|
| 42 |
+
"learning_rate": 6.623931623931625e-06,
|
| 43 |
+
"loss": 1.7169,
|
| 44 |
+
"step": 35
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2692307692307692,
|
| 48 |
+
"grad_norm": 30.393211364746094,
|
| 49 |
+
"learning_rate": 8.11965811965812e-06,
|
| 50 |
+
"loss": 1.6294,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3141025641025641,
|
| 55 |
+
"grad_norm": 38.7406005859375,
|
| 56 |
+
"learning_rate": 9.615384615384616e-06,
|
| 57 |
+
"loss": 1.6305,
|
| 58 |
+
"step": 49
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.358974358974359,
|
| 62 |
+
"grad_norm": 13.8955659866333,
|
| 63 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 64 |
+
"loss": 1.3634,
|
| 65 |
+
"step": 56
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.40384615384615385,
|
| 69 |
+
"grad_norm": 19.50594711303711,
|
| 70 |
+
"learning_rate": 1.2606837606837608e-05,
|
| 71 |
+
"loss": 1.0247,
|
| 72 |
+
"step": 63
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.44871794871794873,
|
| 76 |
+
"grad_norm": 9.244388580322266,
|
| 77 |
+
"learning_rate": 1.4102564102564104e-05,
|
| 78 |
+
"loss": 0.752,
|
| 79 |
+
"step": 70
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4935897435897436,
|
| 83 |
+
"grad_norm": 9.010939598083496,
|
| 84 |
+
"learning_rate": 1.5598290598290598e-05,
|
| 85 |
+
"loss": 0.6144,
|
| 86 |
+
"step": 77
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5384615384615384,
|
| 90 |
+
"grad_norm": 16.850486755371094,
|
| 91 |
+
"learning_rate": 1.7094017094017095e-05,
|
| 92 |
+
"loss": 0.8148,
|
| 93 |
+
"step": 84
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5833333333333334,
|
| 97 |
+
"grad_norm": 14.541914939880371,
|
| 98 |
+
"learning_rate": 1.858974358974359e-05,
|
| 99 |
+
"loss": 0.7843,
|
| 100 |
+
"step": 91
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6282051282051282,
|
| 104 |
+
"grad_norm": 15.613171577453613,
|
| 105 |
+
"learning_rate": 2.0085470085470087e-05,
|
| 106 |
+
"loss": 0.7653,
|
| 107 |
+
"step": 98
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6730769230769231,
|
| 111 |
+
"grad_norm": 17.819730758666992,
|
| 112 |
+
"learning_rate": 2.1581196581196585e-05,
|
| 113 |
+
"loss": 0.8886,
|
| 114 |
+
"step": 105
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.717948717948718,
|
| 118 |
+
"grad_norm": 25.498430252075195,
|
| 119 |
+
"learning_rate": 2.307692307692308e-05,
|
| 120 |
+
"loss": 0.8585,
|
| 121 |
+
"step": 112
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7628205128205128,
|
| 125 |
+
"grad_norm": 6.939703464508057,
|
| 126 |
+
"learning_rate": 2.4572649572649573e-05,
|
| 127 |
+
"loss": 0.7819,
|
| 128 |
+
"step": 119
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8076923076923077,
|
| 132 |
+
"grad_norm": 5.337686061859131,
|
| 133 |
+
"learning_rate": 2.606837606837607e-05,
|
| 134 |
+
"loss": 0.7656,
|
| 135 |
+
"step": 126
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8525641025641025,
|
| 139 |
+
"grad_norm": 5.561918258666992,
|
| 140 |
+
"learning_rate": 2.756410256410257e-05,
|
| 141 |
+
"loss": 0.6922,
|
| 142 |
+
"step": 133
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8974358974358975,
|
| 146 |
+
"grad_norm": 4.981381416320801,
|
| 147 |
+
"learning_rate": 2.9059829059829063e-05,
|
| 148 |
+
"loss": 0.6088,
|
| 149 |
+
"step": 140
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9423076923076923,
|
| 153 |
+
"grad_norm": 10.54244613647461,
|
| 154 |
+
"learning_rate": 3.055555555555556e-05,
|
| 155 |
+
"loss": 0.6644,
|
| 156 |
+
"step": 147
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.9871794871794872,
|
| 160 |
+
"grad_norm": 18.519126892089844,
|
| 161 |
+
"learning_rate": 3.205128205128206e-05,
|
| 162 |
+
"loss": 0.6198,
|
| 163 |
+
"step": 154
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.0,
|
| 167 |
+
"eval_accuracy": 0.6955128205128205,
|
| 168 |
+
"eval_f1_macro": 0.6747979178342244,
|
| 169 |
+
"eval_f1_micro": 0.6955128205128205,
|
| 170 |
+
"eval_f1_weighted": 0.6888607024416085,
|
| 171 |
+
"eval_loss": 0.6790350675582886,
|
| 172 |
+
"eval_precision_macro": 0.79043461935605,
|
| 173 |
+
"eval_precision_micro": 0.6955128205128205,
|
| 174 |
+
"eval_precision_weighted": 0.6978595772949476,
|
| 175 |
+
"eval_recall_macro": 0.6219737626714371,
|
| 176 |
+
"eval_recall_micro": 0.6955128205128205,
|
| 177 |
+
"eval_recall_weighted": 0.6955128205128205,
|
| 178 |
+
"eval_runtime": 0.8327,
|
| 179 |
+
"eval_samples_per_second": 374.664,
|
| 180 |
+
"eval_steps_per_second": 24.017,
|
| 181 |
+
"step": 156
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.032051282051282,
|
| 185 |
+
"grad_norm": 17.723602294921875,
|
| 186 |
+
"learning_rate": 3.354700854700855e-05,
|
| 187 |
+
"loss": 0.7364,
|
| 188 |
+
"step": 161
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.0769230769230769,
|
| 192 |
+
"grad_norm": 54.3127326965332,
|
| 193 |
+
"learning_rate": 3.504273504273504e-05,
|
| 194 |
+
"loss": 0.6054,
|
| 195 |
+
"step": 168
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.1217948717948718,
|
| 199 |
+
"grad_norm": 7.926159381866455,
|
| 200 |
+
"learning_rate": 3.653846153846154e-05,
|
| 201 |
+
"loss": 0.54,
|
| 202 |
+
"step": 175
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.1666666666666667,
|
| 206 |
+
"grad_norm": 6.779534816741943,
|
| 207 |
+
"learning_rate": 3.8034188034188035e-05,
|
| 208 |
+
"loss": 0.7181,
|
| 209 |
+
"step": 182
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.2115384615384615,
|
| 213 |
+
"grad_norm": 4.455146789550781,
|
| 214 |
+
"learning_rate": 3.952991452991453e-05,
|
| 215 |
+
"loss": 0.57,
|
| 216 |
+
"step": 189
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.2564102564102564,
|
| 220 |
+
"grad_norm": 11.916348457336426,
|
| 221 |
+
"learning_rate": 4.1025641025641023e-05,
|
| 222 |
+
"loss": 0.6322,
|
| 223 |
+
"step": 196
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.3012820512820513,
|
| 227 |
+
"grad_norm": 11.289109230041504,
|
| 228 |
+
"learning_rate": 4.252136752136752e-05,
|
| 229 |
+
"loss": 0.5207,
|
| 230 |
+
"step": 203
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3461538461538463,
|
| 234 |
+
"grad_norm": 9.974486351013184,
|
| 235 |
+
"learning_rate": 4.401709401709402e-05,
|
| 236 |
+
"loss": 0.6792,
|
| 237 |
+
"step": 210
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.391025641025641,
|
| 241 |
+
"grad_norm": 7.0826640129089355,
|
| 242 |
+
"learning_rate": 4.5512820512820516e-05,
|
| 243 |
+
"loss": 0.6701,
|
| 244 |
+
"step": 217
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.435897435897436,
|
| 248 |
+
"grad_norm": 16.46434783935547,
|
| 249 |
+
"learning_rate": 4.700854700854701e-05,
|
| 250 |
+
"loss": 0.5722,
|
| 251 |
+
"step": 224
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.4807692307692308,
|
| 255 |
+
"grad_norm": 12.298468589782715,
|
| 256 |
+
"learning_rate": 4.8504273504273505e-05,
|
| 257 |
+
"loss": 0.7939,
|
| 258 |
+
"step": 231
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.5256410256410255,
|
| 262 |
+
"grad_norm": 25.05532455444336,
|
| 263 |
+
"learning_rate": 5e-05,
|
| 264 |
+
"loss": 0.7046,
|
| 265 |
+
"step": 238
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.5705128205128205,
|
| 269 |
+
"grad_norm": 31.899816513061523,
|
| 270 |
+
"learning_rate": 4.983380816714151e-05,
|
| 271 |
+
"loss": 0.5815,
|
| 272 |
+
"step": 245
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.6153846153846154,
|
| 276 |
+
"grad_norm": 6.716318607330322,
|
| 277 |
+
"learning_rate": 4.9667616334283e-05,
|
| 278 |
+
"loss": 0.5213,
|
| 279 |
+
"step": 252
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.6602564102564101,
|
| 283 |
+
"grad_norm": 8.302348136901855,
|
| 284 |
+
"learning_rate": 4.95014245014245e-05,
|
| 285 |
+
"loss": 0.5883,
|
| 286 |
+
"step": 259
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.7051282051282053,
|
| 290 |
+
"grad_norm": 40.705841064453125,
|
| 291 |
+
"learning_rate": 4.933523266856601e-05,
|
| 292 |
+
"loss": 0.5492,
|
| 293 |
+
"step": 266
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.75,
|
| 297 |
+
"grad_norm": 7.286283493041992,
|
| 298 |
+
"learning_rate": 4.9169040835707506e-05,
|
| 299 |
+
"loss": 0.6444,
|
| 300 |
+
"step": 273
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.7948717948717947,
|
| 304 |
+
"grad_norm": 9.41189956665039,
|
| 305 |
+
"learning_rate": 4.9002849002849004e-05,
|
| 306 |
+
"loss": 0.6681,
|
| 307 |
+
"step": 280
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.8397435897435899,
|
| 311 |
+
"grad_norm": 12.600714683532715,
|
| 312 |
+
"learning_rate": 4.883665716999051e-05,
|
| 313 |
+
"loss": 0.6835,
|
| 314 |
+
"step": 287
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.8846153846153846,
|
| 318 |
+
"grad_norm": 6.682600498199463,
|
| 319 |
+
"learning_rate": 4.867046533713201e-05,
|
| 320 |
+
"loss": 0.7121,
|
| 321 |
+
"step": 294
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.9294871794871795,
|
| 325 |
+
"grad_norm": 15.127613067626953,
|
| 326 |
+
"learning_rate": 4.8504273504273505e-05,
|
| 327 |
+
"loss": 0.5505,
|
| 328 |
+
"step": 301
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.9743589743589745,
|
| 332 |
+
"grad_norm": 9.874059677124023,
|
| 333 |
+
"learning_rate": 4.833808167141501e-05,
|
| 334 |
+
"loss": 0.5549,
|
| 335 |
+
"step": 308
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.0,
|
| 339 |
+
"eval_accuracy": 0.7435897435897436,
|
| 340 |
+
"eval_f1_macro": 0.7086614173228346,
|
| 341 |
+
"eval_f1_micro": 0.7435897435897436,
|
| 342 |
+
"eval_f1_weighted": 0.7361195235210982,
|
| 343 |
+
"eval_loss": 0.587009608745575,
|
| 344 |
+
"eval_precision_macro": 0.7210665002427016,
|
| 345 |
+
"eval_precision_micro": 0.7435897435897436,
|
| 346 |
+
"eval_precision_weighted": 0.7538358857008742,
|
| 347 |
+
"eval_recall_macro": 0.7157125819916518,
|
| 348 |
+
"eval_recall_micro": 0.7435897435897436,
|
| 349 |
+
"eval_recall_weighted": 0.7435897435897436,
|
| 350 |
+
"eval_runtime": 0.8226,
|
| 351 |
+
"eval_samples_per_second": 379.293,
|
| 352 |
+
"eval_steps_per_second": 24.314,
|
| 353 |
+
"step": 312
|
| 354 |
+
}
|
| 355 |
+
],
|
| 356 |
+
"logging_steps": 7,
|
| 357 |
+
"max_steps": 2340,
|
| 358 |
+
"num_input_tokens_seen": 0,
|
| 359 |
+
"num_train_epochs": 15,
|
| 360 |
+
"save_steps": 500,
|
| 361 |
+
"total_flos": 164182772662272.0,
|
| 362 |
+
"train_batch_size": 8,
|
| 363 |
+
"trial_name": null,
|
| 364 |
+
"trial_params": null
|
| 365 |
+
}
|
checkpoint-312/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24b3082fd0e35e5cf8700bf69b4d1273d0435b42e3271b95f52625a5adf2a40c
|
| 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 sha256:9202fa9a07074efaaa2e1919694d34065825e4ac99f0f45a51c58fbaf2b18f3a
|
| 3 |
+
size 436358132
|
runs/May02_11-23-07_r-zerithas-myownmodels-v1-b1g0511n-fc7a5-8npzw/events.out.tfevents.1714648988.r-zerithas-myownmodels-v1-b1g0511n-fc7a5-8npzw.62.0
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 sha256:7facfe8e979a6872c6f8bca7e4a6773ccfbfaef26fed66c4b03183975ed01567
|
| 3 |
+
size 32735
|
runs/May02_11-23-07_r-zerithas-myownmodels-v1-b1g0511n-fc7a5-8npzw/events.out.tfevents.1714649081.r-zerithas-myownmodels-v1-b1g0511n-fc7a5-8npzw.62.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b94cc00c53fcaa1b9783637a1fa45099ee04ab1c5d434f5982a4fdc90970f50b
|
| 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 sha256:24b3082fd0e35e5cf8700bf69b4d1273d0435b42e3271b95f52625a5adf2a40c
|
| 3 |
+
size 4984
|
training_params.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "V13/autotrain-data",
|
| 3 |
+
"model": "oliverguhr/german-sentiment-bert",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 15,
|
| 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": "V13",
|
| 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
|
|
|