End of training
Browse files- README.md +80 -0
- all_results.json +7 -0
- config.json +52 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- train_results.json +7 -0
- trainer_state.json +343 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: vit-eGTZANplus
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# vit-eGTZANplus
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.0164
|
| 21 |
+
- Accuracy: 0.7460
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 2
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 0.2938 | 0.09 | 10 | 1.1730 | 0.6720 |
|
| 53 |
+
| 0.2996 | 0.19 | 20 | 1.0932 | 0.6984 |
|
| 54 |
+
| 0.3255 | 0.28 | 30 | 1.2589 | 0.6878 |
|
| 55 |
+
| 0.3455 | 0.37 | 40 | 1.4433 | 0.6243 |
|
| 56 |
+
| 0.168 | 0.47 | 50 | 1.0876 | 0.7249 |
|
| 57 |
+
| 0.1967 | 0.56 | 60 | 1.3118 | 0.6772 |
|
| 58 |
+
| 0.3586 | 0.65 | 70 | 1.2526 | 0.6667 |
|
| 59 |
+
| 0.2221 | 0.75 | 80 | 1.0784 | 0.6825 |
|
| 60 |
+
| 0.2013 | 0.84 | 90 | 1.2741 | 0.6772 |
|
| 61 |
+
| 0.0979 | 0.93 | 100 | 1.1675 | 0.7196 |
|
| 62 |
+
| 0.1476 | 1.03 | 110 | 1.0856 | 0.7249 |
|
| 63 |
+
| 0.113 | 1.12 | 120 | 1.1297 | 0.7090 |
|
| 64 |
+
| 0.071 | 1.21 | 130 | 0.9953 | 0.7302 |
|
| 65 |
+
| 0.1015 | 1.31 | 140 | 1.0731 | 0.7407 |
|
| 66 |
+
| 0.0249 | 1.4 | 150 | 1.0643 | 0.7354 |
|
| 67 |
+
| 0.0555 | 1.5 | 160 | 1.0036 | 0.7460 |
|
| 68 |
+
| 0.0419 | 1.59 | 170 | 1.0492 | 0.7407 |
|
| 69 |
+
| 0.0491 | 1.68 | 180 | 0.9937 | 0.7354 |
|
| 70 |
+
| 0.0889 | 1.78 | 190 | 1.0370 | 0.7460 |
|
| 71 |
+
| 0.0676 | 1.87 | 200 | 1.0595 | 0.7302 |
|
| 72 |
+
| 0.0938 | 1.96 | 210 | 1.0164 | 0.7460 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.33.3
|
| 78 |
+
- Pytorch 2.1.0+cu121
|
| 79 |
+
- Datasets 2.14.5
|
| 80 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.15774932977195097,
|
| 4 |
+
"train_runtime": 171.8363,
|
| 5 |
+
"train_samples_per_second": 19.751,
|
| 6 |
+
"train_steps_per_second": 1.245
|
| 7 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "afro",
|
| 13 |
+
"1": "classical",
|
| 14 |
+
"10": "reggae",
|
| 15 |
+
"11": "rock",
|
| 16 |
+
"2": "country",
|
| 17 |
+
"3": "disco",
|
| 18 |
+
"4": "electro",
|
| 19 |
+
"5": "jazz",
|
| 20 |
+
"6": "latin",
|
| 21 |
+
"7": "metal",
|
| 22 |
+
"8": "pop",
|
| 23 |
+
"9": "rap"
|
| 24 |
+
},
|
| 25 |
+
"image_size": 224,
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"afro": "0",
|
| 30 |
+
"classical": "1",
|
| 31 |
+
"country": "2",
|
| 32 |
+
"disco": "3",
|
| 33 |
+
"electro": "4",
|
| 34 |
+
"jazz": "5",
|
| 35 |
+
"latin": "6",
|
| 36 |
+
"metal": "7",
|
| 37 |
+
"pop": "8",
|
| 38 |
+
"rap": "9",
|
| 39 |
+
"reggae": "10",
|
| 40 |
+
"rock": "11"
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-12,
|
| 43 |
+
"model_type": "vit",
|
| 44 |
+
"num_attention_heads": 12,
|
| 45 |
+
"num_channels": 3,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"patch_size": 16,
|
| 48 |
+
"problem_type": "single_label_classification",
|
| 49 |
+
"qkv_bias": true,
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.33.3"
|
| 52 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef48d88824b5f30df659ddd55b960db875ce54b94142d1b62d9832f35b2d397d
|
| 3 |
+
size 343299882
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.15774932977195097,
|
| 4 |
+
"train_runtime": 171.8363,
|
| 5 |
+
"train_samples_per_second": 19.751,
|
| 6 |
+
"train_steps_per_second": 1.245
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,343 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9937486052513123,
|
| 3 |
+
"best_model_checkpoint": "./vit-eGTZANplus\\checkpoint-180",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 214,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"learning_rate": 0.00019065420560747664,
|
| 14 |
+
"loss": 0.2938,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"eval_accuracy": 0.671957671957672,
|
| 20 |
+
"eval_loss": 1.1729912757873535,
|
| 21 |
+
"eval_runtime": 3.4907,
|
| 22 |
+
"eval_samples_per_second": 54.143,
|
| 23 |
+
"eval_steps_per_second": 6.875,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.19,
|
| 28 |
+
"learning_rate": 0.0001813084112149533,
|
| 29 |
+
"loss": 0.2996,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.19,
|
| 34 |
+
"eval_accuracy": 0.6984126984126984,
|
| 35 |
+
"eval_loss": 1.093176007270813,
|
| 36 |
+
"eval_runtime": 3.2942,
|
| 37 |
+
"eval_samples_per_second": 57.373,
|
| 38 |
+
"eval_steps_per_second": 7.286,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.28,
|
| 43 |
+
"learning_rate": 0.00017196261682242992,
|
| 44 |
+
"loss": 0.3255,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.28,
|
| 49 |
+
"eval_accuracy": 0.6878306878306878,
|
| 50 |
+
"eval_loss": 1.2588934898376465,
|
| 51 |
+
"eval_runtime": 3.3856,
|
| 52 |
+
"eval_samples_per_second": 55.825,
|
| 53 |
+
"eval_steps_per_second": 7.089,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.37,
|
| 58 |
+
"learning_rate": 0.00016261682242990654,
|
| 59 |
+
"loss": 0.3455,
|
| 60 |
+
"step": 40
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.37,
|
| 64 |
+
"eval_accuracy": 0.6243386243386243,
|
| 65 |
+
"eval_loss": 1.4432997703552246,
|
| 66 |
+
"eval_runtime": 3.3445,
|
| 67 |
+
"eval_samples_per_second": 56.51,
|
| 68 |
+
"eval_steps_per_second": 7.176,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.47,
|
| 73 |
+
"learning_rate": 0.00015327102803738317,
|
| 74 |
+
"loss": 0.168,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.47,
|
| 79 |
+
"eval_accuracy": 0.7248677248677249,
|
| 80 |
+
"eval_loss": 1.0876396894454956,
|
| 81 |
+
"eval_runtime": 3.1209,
|
| 82 |
+
"eval_samples_per_second": 60.56,
|
| 83 |
+
"eval_steps_per_second": 7.69,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.56,
|
| 88 |
+
"learning_rate": 0.00014392523364485982,
|
| 89 |
+
"loss": 0.1967,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.56,
|
| 94 |
+
"eval_accuracy": 0.6772486772486772,
|
| 95 |
+
"eval_loss": 1.3117926120758057,
|
| 96 |
+
"eval_runtime": 3.1799,
|
| 97 |
+
"eval_samples_per_second": 59.436,
|
| 98 |
+
"eval_steps_per_second": 7.547,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.65,
|
| 103 |
+
"learning_rate": 0.00013457943925233645,
|
| 104 |
+
"loss": 0.3586,
|
| 105 |
+
"step": 70
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.65,
|
| 109 |
+
"eval_accuracy": 0.6666666666666666,
|
| 110 |
+
"eval_loss": 1.252642273902893,
|
| 111 |
+
"eval_runtime": 3.2198,
|
| 112 |
+
"eval_samples_per_second": 58.699,
|
| 113 |
+
"eval_steps_per_second": 7.454,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.75,
|
| 118 |
+
"learning_rate": 0.00012523364485981308,
|
| 119 |
+
"loss": 0.2221,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.75,
|
| 124 |
+
"eval_accuracy": 0.6825396825396826,
|
| 125 |
+
"eval_loss": 1.0784260034561157,
|
| 126 |
+
"eval_runtime": 3.045,
|
| 127 |
+
"eval_samples_per_second": 62.069,
|
| 128 |
+
"eval_steps_per_second": 7.882,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.84,
|
| 133 |
+
"learning_rate": 0.00011588785046728972,
|
| 134 |
+
"loss": 0.2013,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.84,
|
| 139 |
+
"eval_accuracy": 0.6772486772486772,
|
| 140 |
+
"eval_loss": 1.274102807044983,
|
| 141 |
+
"eval_runtime": 3.14,
|
| 142 |
+
"eval_samples_per_second": 60.19,
|
| 143 |
+
"eval_steps_per_second": 7.643,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.93,
|
| 148 |
+
"learning_rate": 0.00010654205607476636,
|
| 149 |
+
"loss": 0.0979,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.93,
|
| 154 |
+
"eval_accuracy": 0.7195767195767195,
|
| 155 |
+
"eval_loss": 1.1675456762313843,
|
| 156 |
+
"eval_runtime": 3.0991,
|
| 157 |
+
"eval_samples_per_second": 60.986,
|
| 158 |
+
"eval_steps_per_second": 7.744,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.03,
|
| 163 |
+
"learning_rate": 9.813084112149533e-05,
|
| 164 |
+
"loss": 0.1476,
|
| 165 |
+
"step": 110
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.03,
|
| 169 |
+
"eval_accuracy": 0.7248677248677249,
|
| 170 |
+
"eval_loss": 1.0856043100357056,
|
| 171 |
+
"eval_runtime": 3.1542,
|
| 172 |
+
"eval_samples_per_second": 59.919,
|
| 173 |
+
"eval_steps_per_second": 7.609,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.12,
|
| 178 |
+
"learning_rate": 8.878504672897197e-05,
|
| 179 |
+
"loss": 0.113,
|
| 180 |
+
"step": 120
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.12,
|
| 184 |
+
"eval_accuracy": 0.708994708994709,
|
| 185 |
+
"eval_loss": 1.1296759843826294,
|
| 186 |
+
"eval_runtime": 3.093,
|
| 187 |
+
"eval_samples_per_second": 61.105,
|
| 188 |
+
"eval_steps_per_second": 7.759,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.21,
|
| 193 |
+
"learning_rate": 7.94392523364486e-05,
|
| 194 |
+
"loss": 0.071,
|
| 195 |
+
"step": 130
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.21,
|
| 199 |
+
"eval_accuracy": 0.7301587301587301,
|
| 200 |
+
"eval_loss": 0.9953044652938843,
|
| 201 |
+
"eval_runtime": 3.1568,
|
| 202 |
+
"eval_samples_per_second": 59.871,
|
| 203 |
+
"eval_steps_per_second": 7.603,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.31,
|
| 208 |
+
"learning_rate": 7.009345794392523e-05,
|
| 209 |
+
"loss": 0.1015,
|
| 210 |
+
"step": 140
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.31,
|
| 214 |
+
"eval_accuracy": 0.7407407407407407,
|
| 215 |
+
"eval_loss": 1.0731220245361328,
|
| 216 |
+
"eval_runtime": 3.2435,
|
| 217 |
+
"eval_samples_per_second": 58.27,
|
| 218 |
+
"eval_steps_per_second": 7.399,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.4,
|
| 223 |
+
"learning_rate": 6.074766355140187e-05,
|
| 224 |
+
"loss": 0.0249,
|
| 225 |
+
"step": 150
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.4,
|
| 229 |
+
"eval_accuracy": 0.7354497354497355,
|
| 230 |
+
"eval_loss": 1.0643069744110107,
|
| 231 |
+
"eval_runtime": 3.1959,
|
| 232 |
+
"eval_samples_per_second": 59.139,
|
| 233 |
+
"eval_steps_per_second": 7.51,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.5,
|
| 238 |
+
"learning_rate": 5.14018691588785e-05,
|
| 239 |
+
"loss": 0.0555,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.5,
|
| 244 |
+
"eval_accuracy": 0.746031746031746,
|
| 245 |
+
"eval_loss": 1.0035866498947144,
|
| 246 |
+
"eval_runtime": 3.1827,
|
| 247 |
+
"eval_samples_per_second": 59.384,
|
| 248 |
+
"eval_steps_per_second": 7.541,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.59,
|
| 253 |
+
"learning_rate": 4.205607476635514e-05,
|
| 254 |
+
"loss": 0.0419,
|
| 255 |
+
"step": 170
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.59,
|
| 259 |
+
"eval_accuracy": 0.7407407407407407,
|
| 260 |
+
"eval_loss": 1.0491830110549927,
|
| 261 |
+
"eval_runtime": 3.1052,
|
| 262 |
+
"eval_samples_per_second": 60.865,
|
| 263 |
+
"eval_steps_per_second": 7.729,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.68,
|
| 268 |
+
"learning_rate": 3.2710280373831774e-05,
|
| 269 |
+
"loss": 0.0491,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.68,
|
| 274 |
+
"eval_accuracy": 0.7354497354497355,
|
| 275 |
+
"eval_loss": 0.9937486052513123,
|
| 276 |
+
"eval_runtime": 3.1957,
|
| 277 |
+
"eval_samples_per_second": 59.141,
|
| 278 |
+
"eval_steps_per_second": 7.51,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.78,
|
| 283 |
+
"learning_rate": 2.3364485981308414e-05,
|
| 284 |
+
"loss": 0.0889,
|
| 285 |
+
"step": 190
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.78,
|
| 289 |
+
"eval_accuracy": 0.746031746031746,
|
| 290 |
+
"eval_loss": 1.0369799137115479,
|
| 291 |
+
"eval_runtime": 3.1029,
|
| 292 |
+
"eval_samples_per_second": 60.911,
|
| 293 |
+
"eval_steps_per_second": 7.735,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.87,
|
| 298 |
+
"learning_rate": 1.4018691588785047e-05,
|
| 299 |
+
"loss": 0.0676,
|
| 300 |
+
"step": 200
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.87,
|
| 304 |
+
"eval_accuracy": 0.7301587301587301,
|
| 305 |
+
"eval_loss": 1.0594910383224487,
|
| 306 |
+
"eval_runtime": 3.1165,
|
| 307 |
+
"eval_samples_per_second": 60.644,
|
| 308 |
+
"eval_steps_per_second": 7.701,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.96,
|
| 313 |
+
"learning_rate": 4.6728971962616825e-06,
|
| 314 |
+
"loss": 0.0938,
|
| 315 |
+
"step": 210
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.96,
|
| 319 |
+
"eval_accuracy": 0.746031746031746,
|
| 320 |
+
"eval_loss": 1.0163832902908325,
|
| 321 |
+
"eval_runtime": 3.1414,
|
| 322 |
+
"eval_samples_per_second": 60.164,
|
| 323 |
+
"eval_steps_per_second": 7.64,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.0,
|
| 328 |
+
"step": 214,
|
| 329 |
+
"total_flos": 2.6303138531028173e+17,
|
| 330 |
+
"train_loss": 0.15774932977195097,
|
| 331 |
+
"train_runtime": 171.8363,
|
| 332 |
+
"train_samples_per_second": 19.751,
|
| 333 |
+
"train_steps_per_second": 1.245
|
| 334 |
+
}
|
| 335 |
+
],
|
| 336 |
+
"logging_steps": 10,
|
| 337 |
+
"max_steps": 214,
|
| 338 |
+
"num_train_epochs": 2,
|
| 339 |
+
"save_steps": 10,
|
| 340 |
+
"total_flos": 2.6303138531028173e+17,
|
| 341 |
+
"trial_name": null,
|
| 342 |
+
"trial_params": null
|
| 343 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d93d4580814b34788969c13590bb700db5d1bd27277cf34b8c1aa31afd7950a
|
| 3 |
+
size 4472
|