Edelweisse/Sentiment-Bpjs
Browse files- README.md +67 -0
- config.json +37 -0
- model.safetensors +3 -0
- trainer_state.json +433 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: results
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# results
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa](https://huggingface.co/ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4952
|
| 22 |
+
- Accuracy: 0.8351
|
| 23 |
+
- F1: 0.8359
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 3e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 64
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 200
|
| 49 |
+
- num_epochs: 5
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 55 |
+
| 0.6964 | 1.0 | 73 | 0.5906 | 0.8110 | 0.8152 |
|
| 56 |
+
| 0.6407 | 2.0 | 146 | 0.4614 | 0.8007 | 0.8035 |
|
| 57 |
+
| 0.418 | 3.0 | 219 | 0.4952 | 0.8351 | 0.8359 |
|
| 58 |
+
| 0.1811 | 4.0 | 292 | 0.5943 | 0.8110 | 0.8114 |
|
| 59 |
+
| 0.1383 | 5.0 | 365 | 0.6963 | 0.8110 | 0.8121 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.41.1
|
| 65 |
+
- Pytorch 2.3.0+cu118
|
| 66 |
+
- Datasets 2.19.1
|
| 67 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.3,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.3,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Positive",
|
| 14 |
+
"1": "Neutral",
|
| 15 |
+
"2": "Negative"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Negative": 2,
|
| 21 |
+
"Neutral": 1,
|
| 22 |
+
"Positive": 0
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.41.1",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 32000
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed9497c6351d4ee6aa1bdd31c7912c8e1825912070b994c6dd0c0f2ca501c50b
|
| 3 |
+
size 442502140
|
trainer_state.json
ADDED
|
@@ -0,0 +1,433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8897849462365591,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-465",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 465,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.10752688172043011,
|
| 13 |
+
"grad_norm": 77.31194305419922,
|
| 14 |
+
"learning_rate": 1.5e-06,
|
| 15 |
+
"loss": 1.0774,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.21505376344086022,
|
| 20 |
+
"grad_norm": 21.743606567382812,
|
| 21 |
+
"learning_rate": 3e-06,
|
| 22 |
+
"loss": 1.205,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3225806451612903,
|
| 27 |
+
"grad_norm": 46.53227233886719,
|
| 28 |
+
"learning_rate": 4.5e-06,
|
| 29 |
+
"loss": 0.9877,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.43010752688172044,
|
| 34 |
+
"grad_norm": 60.25495147705078,
|
| 35 |
+
"learning_rate": 6e-06,
|
| 36 |
+
"loss": 0.7626,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5376344086021505,
|
| 41 |
+
"grad_norm": 42.291969299316406,
|
| 42 |
+
"learning_rate": 7.5e-06,
|
| 43 |
+
"loss": 0.6559,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6451612903225806,
|
| 48 |
+
"grad_norm": 27.09429931640625,
|
| 49 |
+
"learning_rate": 9e-06,
|
| 50 |
+
"loss": 0.3539,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7526881720430108,
|
| 55 |
+
"grad_norm": 29.117910385131836,
|
| 56 |
+
"learning_rate": 1.05e-05,
|
| 57 |
+
"loss": 0.516,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8602150537634409,
|
| 62 |
+
"grad_norm": 35.026817321777344,
|
| 63 |
+
"learning_rate": 1.2e-05,
|
| 64 |
+
"loss": 0.5457,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.967741935483871,
|
| 69 |
+
"grad_norm": 17.851289749145508,
|
| 70 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 71 |
+
"loss": 0.5821,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"eval_accuracy": 0.8655913978494624,
|
| 77 |
+
"eval_f1": 0.8661634583786485,
|
| 78 |
+
"eval_loss": 0.3687117397785187,
|
| 79 |
+
"eval_runtime": 1.6159,
|
| 80 |
+
"eval_samples_per_second": 230.212,
|
| 81 |
+
"eval_steps_per_second": 3.713,
|
| 82 |
+
"step": 93
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.075268817204301,
|
| 86 |
+
"grad_norm": 13.748136520385742,
|
| 87 |
+
"learning_rate": 1.5e-05,
|
| 88 |
+
"loss": 0.307,
|
| 89 |
+
"step": 100
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.1827956989247312,
|
| 93 |
+
"grad_norm": 3.2135958671569824,
|
| 94 |
+
"learning_rate": 1.65e-05,
|
| 95 |
+
"loss": 0.4692,
|
| 96 |
+
"step": 110
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.2903225806451613,
|
| 100 |
+
"grad_norm": 11.485154151916504,
|
| 101 |
+
"learning_rate": 1.8e-05,
|
| 102 |
+
"loss": 0.3206,
|
| 103 |
+
"step": 120
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.3978494623655915,
|
| 107 |
+
"grad_norm": 7.797122478485107,
|
| 108 |
+
"learning_rate": 1.95e-05,
|
| 109 |
+
"loss": 0.3138,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.5053763440860215,
|
| 114 |
+
"grad_norm": 6.313217639923096,
|
| 115 |
+
"learning_rate": 2.1e-05,
|
| 116 |
+
"loss": 0.3135,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.6129032258064515,
|
| 121 |
+
"grad_norm": 18.319936752319336,
|
| 122 |
+
"learning_rate": 2.25e-05,
|
| 123 |
+
"loss": 0.2156,
|
| 124 |
+
"step": 150
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.7204301075268817,
|
| 128 |
+
"grad_norm": 21.939163208007812,
|
| 129 |
+
"learning_rate": 2.4e-05,
|
| 130 |
+
"loss": 0.2749,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.827956989247312,
|
| 135 |
+
"grad_norm": 20.2148380279541,
|
| 136 |
+
"learning_rate": 2.55e-05,
|
| 137 |
+
"loss": 0.4502,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.935483870967742,
|
| 142 |
+
"grad_norm": 22.044946670532227,
|
| 143 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 144 |
+
"loss": 0.364,
|
| 145 |
+
"step": 180
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.0,
|
| 149 |
+
"eval_accuracy": 0.8763440860215054,
|
| 150 |
+
"eval_f1": 0.8742605847498066,
|
| 151 |
+
"eval_loss": 0.34187108278274536,
|
| 152 |
+
"eval_runtime": 1.6404,
|
| 153 |
+
"eval_samples_per_second": 226.774,
|
| 154 |
+
"eval_steps_per_second": 3.658,
|
| 155 |
+
"step": 186
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.043010752688172,
|
| 159 |
+
"grad_norm": 1.5786309242248535,
|
| 160 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 161 |
+
"loss": 0.251,
|
| 162 |
+
"step": 190
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.150537634408602,
|
| 166 |
+
"grad_norm": 0.3100162446498871,
|
| 167 |
+
"learning_rate": 3e-05,
|
| 168 |
+
"loss": 0.0491,
|
| 169 |
+
"step": 200
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.258064516129032,
|
| 173 |
+
"grad_norm": 10.301804542541504,
|
| 174 |
+
"learning_rate": 2.8867924528301887e-05,
|
| 175 |
+
"loss": 0.0978,
|
| 176 |
+
"step": 210
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.3655913978494625,
|
| 180 |
+
"grad_norm": 0.5391497015953064,
|
| 181 |
+
"learning_rate": 2.7735849056603773e-05,
|
| 182 |
+
"loss": 0.2325,
|
| 183 |
+
"step": 220
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.4731182795698925,
|
| 187 |
+
"grad_norm": 33.04327392578125,
|
| 188 |
+
"learning_rate": 2.6603773584905663e-05,
|
| 189 |
+
"loss": 0.3053,
|
| 190 |
+
"step": 230
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.5806451612903225,
|
| 194 |
+
"grad_norm": 1.8449115753173828,
|
| 195 |
+
"learning_rate": 2.547169811320755e-05,
|
| 196 |
+
"loss": 0.1469,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.688172043010753,
|
| 201 |
+
"grad_norm": 41.86624526977539,
|
| 202 |
+
"learning_rate": 2.4339622641509435e-05,
|
| 203 |
+
"loss": 0.0985,
|
| 204 |
+
"step": 250
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.795698924731183,
|
| 208 |
+
"grad_norm": 12.837655067443848,
|
| 209 |
+
"learning_rate": 2.320754716981132e-05,
|
| 210 |
+
"loss": 0.1707,
|
| 211 |
+
"step": 260
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.903225806451613,
|
| 215 |
+
"grad_norm": 7.691096305847168,
|
| 216 |
+
"learning_rate": 2.2075471698113208e-05,
|
| 217 |
+
"loss": 0.1889,
|
| 218 |
+
"step": 270
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.0,
|
| 222 |
+
"eval_accuracy": 0.8548387096774194,
|
| 223 |
+
"eval_f1": 0.8514191596326964,
|
| 224 |
+
"eval_loss": 0.5420617461204529,
|
| 225 |
+
"eval_runtime": 1.6403,
|
| 226 |
+
"eval_samples_per_second": 226.793,
|
| 227 |
+
"eval_steps_per_second": 3.658,
|
| 228 |
+
"step": 279
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.010752688172043,
|
| 232 |
+
"grad_norm": 24.820016860961914,
|
| 233 |
+
"learning_rate": 2.0943396226415094e-05,
|
| 234 |
+
"loss": 0.2798,
|
| 235 |
+
"step": 280
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 3.118279569892473,
|
| 239 |
+
"grad_norm": 0.1231377124786377,
|
| 240 |
+
"learning_rate": 1.981132075471698e-05,
|
| 241 |
+
"loss": 0.1421,
|
| 242 |
+
"step": 290
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.225806451612903,
|
| 246 |
+
"grad_norm": 22.27264404296875,
|
| 247 |
+
"learning_rate": 1.8679245283018867e-05,
|
| 248 |
+
"loss": 0.1455,
|
| 249 |
+
"step": 300
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.3333333333333335,
|
| 253 |
+
"grad_norm": 43.31319046020508,
|
| 254 |
+
"learning_rate": 1.7547169811320753e-05,
|
| 255 |
+
"loss": 0.1223,
|
| 256 |
+
"step": 310
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 3.4408602150537635,
|
| 260 |
+
"grad_norm": 0.16742512583732605,
|
| 261 |
+
"learning_rate": 1.6415094339622643e-05,
|
| 262 |
+
"loss": 0.0214,
|
| 263 |
+
"step": 320
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.5483870967741935,
|
| 267 |
+
"grad_norm": 44.84831619262695,
|
| 268 |
+
"learning_rate": 1.528301886792453e-05,
|
| 269 |
+
"loss": 0.0278,
|
| 270 |
+
"step": 330
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.6559139784946235,
|
| 274 |
+
"grad_norm": 16.63416862487793,
|
| 275 |
+
"learning_rate": 1.4150943396226415e-05,
|
| 276 |
+
"loss": 0.0238,
|
| 277 |
+
"step": 340
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 3.763440860215054,
|
| 281 |
+
"grad_norm": 0.019003387540578842,
|
| 282 |
+
"learning_rate": 1.3018867924528303e-05,
|
| 283 |
+
"loss": 0.0788,
|
| 284 |
+
"step": 350
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.870967741935484,
|
| 288 |
+
"grad_norm": 0.062045346945524216,
|
| 289 |
+
"learning_rate": 1.188679245283019e-05,
|
| 290 |
+
"loss": 0.0247,
|
| 291 |
+
"step": 360
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.978494623655914,
|
| 295 |
+
"grad_norm": 36.90345001220703,
|
| 296 |
+
"learning_rate": 1.0754716981132076e-05,
|
| 297 |
+
"loss": 0.1049,
|
| 298 |
+
"step": 370
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.0,
|
| 302 |
+
"eval_accuracy": 0.8844086021505376,
|
| 303 |
+
"eval_f1": 0.8851071788381587,
|
| 304 |
+
"eval_loss": 0.5284830927848816,
|
| 305 |
+
"eval_runtime": 1.6712,
|
| 306 |
+
"eval_samples_per_second": 222.589,
|
| 307 |
+
"eval_steps_per_second": 3.59,
|
| 308 |
+
"step": 372
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.086021505376344,
|
| 312 |
+
"grad_norm": 0.04606785252690315,
|
| 313 |
+
"learning_rate": 9.622641509433962e-06,
|
| 314 |
+
"loss": 0.0563,
|
| 315 |
+
"step": 380
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.193548387096774,
|
| 319 |
+
"grad_norm": 0.11379247903823853,
|
| 320 |
+
"learning_rate": 8.49056603773585e-06,
|
| 321 |
+
"loss": 0.0007,
|
| 322 |
+
"step": 390
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.301075268817204,
|
| 326 |
+
"grad_norm": 0.057167768478393555,
|
| 327 |
+
"learning_rate": 7.358490566037736e-06,
|
| 328 |
+
"loss": 0.0008,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 4.408602150537634,
|
| 333 |
+
"grad_norm": 1.8930367231369019,
|
| 334 |
+
"learning_rate": 6.226415094339623e-06,
|
| 335 |
+
"loss": 0.0016,
|
| 336 |
+
"step": 410
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.516129032258064,
|
| 340 |
+
"grad_norm": 0.10506568104028702,
|
| 341 |
+
"learning_rate": 5.094339622641509e-06,
|
| 342 |
+
"loss": 0.0183,
|
| 343 |
+
"step": 420
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 4.623655913978495,
|
| 347 |
+
"grad_norm": 0.29419633746147156,
|
| 348 |
+
"learning_rate": 3.962264150943396e-06,
|
| 349 |
+
"loss": 0.0379,
|
| 350 |
+
"step": 430
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.731182795698925,
|
| 354 |
+
"grad_norm": 1.4433554410934448,
|
| 355 |
+
"learning_rate": 2.830188679245283e-06,
|
| 356 |
+
"loss": 0.0011,
|
| 357 |
+
"step": 440
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.838709677419355,
|
| 361 |
+
"grad_norm": 0.05199088156223297,
|
| 362 |
+
"learning_rate": 1.69811320754717e-06,
|
| 363 |
+
"loss": 0.0276,
|
| 364 |
+
"step": 450
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.946236559139785,
|
| 368 |
+
"grad_norm": 0.017505839467048645,
|
| 369 |
+
"learning_rate": 5.660377358490566e-07,
|
| 370 |
+
"loss": 0.0009,
|
| 371 |
+
"step": 460
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 5.0,
|
| 375 |
+
"eval_accuracy": 0.8897849462365591,
|
| 376 |
+
"eval_f1": 0.8902518525126154,
|
| 377 |
+
"eval_loss": 0.518719494342804,
|
| 378 |
+
"eval_runtime": 1.6655,
|
| 379 |
+
"eval_samples_per_second": 223.351,
|
| 380 |
+
"eval_steps_per_second": 3.602,
|
| 381 |
+
"step": 465
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 5.0,
|
| 385 |
+
"step": 465,
|
| 386 |
+
"total_flos": 312883992936900.0,
|
| 387 |
+
"train_loss": 0.26607618075144546,
|
| 388 |
+
"train_runtime": 161.9779,
|
| 389 |
+
"train_samples_per_second": 45.84,
|
| 390 |
+
"train_steps_per_second": 2.871
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.0,
|
| 394 |
+
"eval_accuracy": 0.8897849462365591,
|
| 395 |
+
"eval_f1": 0.8902518525126154,
|
| 396 |
+
"eval_loss": 0.518719494342804,
|
| 397 |
+
"eval_runtime": 1.6415,
|
| 398 |
+
"eval_samples_per_second": 226.619,
|
| 399 |
+
"eval_steps_per_second": 3.655,
|
| 400 |
+
"step": 465
|
| 401 |
+
}
|
| 402 |
+
],
|
| 403 |
+
"logging_steps": 10,
|
| 404 |
+
"max_steps": 465,
|
| 405 |
+
"num_input_tokens_seen": 0,
|
| 406 |
+
"num_train_epochs": 5,
|
| 407 |
+
"save_steps": 500,
|
| 408 |
+
"stateful_callbacks": {
|
| 409 |
+
"EarlyStoppingCallback": {
|
| 410 |
+
"args": {
|
| 411 |
+
"early_stopping_patience": 3,
|
| 412 |
+
"early_stopping_threshold": 0.0
|
| 413 |
+
},
|
| 414 |
+
"attributes": {
|
| 415 |
+
"early_stopping_patience_counter": 0
|
| 416 |
+
}
|
| 417 |
+
},
|
| 418 |
+
"TrainerControl": {
|
| 419 |
+
"args": {
|
| 420 |
+
"should_epoch_stop": false,
|
| 421 |
+
"should_evaluate": false,
|
| 422 |
+
"should_log": false,
|
| 423 |
+
"should_save": true,
|
| 424 |
+
"should_training_stop": true
|
| 425 |
+
},
|
| 426 |
+
"attributes": {}
|
| 427 |
+
}
|
| 428 |
+
},
|
| 429 |
+
"total_flos": 312883992936900.0,
|
| 430 |
+
"train_batch_size": 16,
|
| 431 |
+
"trial_name": null,
|
| 432 |
+
"trial_params": null
|
| 433 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28d00dd1bd5aac8d5a91f4faf8efeec9a6ea4285ea80b5b6b5863e5b6cd5ae5d
|
| 3 |
+
size 5048
|