uno
Browse files- README.md +57 -0
- all_results.json +4 -0
- config.json +737 -0
- model.safetensors +3 -0
- preprocessor_config.json +32 -0
- test_results.json +4 -0
- trainer_state.json +505 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: shehan97/mobilevitv2-2.0-imagenet1k-256
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: quickdraw-MobileVITV2-1.0-Pretrained
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# quickdraw-MobileVITV2-1.0-Pretrained
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [shehan97/mobilevitv2-2.0-imagenet1k-256](https://huggingface.co/shehan97/mobilevitv2-2.0-imagenet1k-256) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- eval_loss: 0.9671
|
| 18 |
+
- eval_accuracy: 0.7622
|
| 19 |
+
- eval_runtime: 16.2585
|
| 20 |
+
- eval_samples_per_second: 15376.569
|
| 21 |
+
- eval_steps_per_second: 30.077
|
| 22 |
+
- epoch: 6.2626
|
| 23 |
+
- step: 55048
|
| 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: 0.0008
|
| 43 |
+
- train_batch_size: 512
|
| 44 |
+
- eval_batch_size: 512
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_steps: 10000
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Framework versions
|
| 53 |
+
|
| 54 |
+
- Transformers 4.40.2
|
| 55 |
+
- Pytorch 2.2.1
|
| 56 |
+
- Datasets 2.19.1
|
| 57 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.762224,
|
| 3 |
+
"eval_loss": 0.9670637845993042
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,737 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "shehan97/mobilevitv2-2.0-imagenet1k-256",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MobileViTV2ForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"aspp_dropout_prob": 0.1,
|
| 7 |
+
"aspp_out_channels": 512,
|
| 8 |
+
"atrous_rates": [
|
| 9 |
+
6,
|
| 10 |
+
12,
|
| 11 |
+
18
|
| 12 |
+
],
|
| 13 |
+
"attn_dropout": 0.0,
|
| 14 |
+
"base_attn_unit_dims": [
|
| 15 |
+
128,
|
| 16 |
+
192,
|
| 17 |
+
256
|
| 18 |
+
],
|
| 19 |
+
"classifier_dropout_prob": 0.1,
|
| 20 |
+
"conv_kernel_size": 3,
|
| 21 |
+
"expand_ratio": 2.0,
|
| 22 |
+
"ffn_dropout": 0.0,
|
| 23 |
+
"ffn_multiplier": 2,
|
| 24 |
+
"hidden_act": "swish",
|
| 25 |
+
"id2label": {
|
| 26 |
+
"0": "aircraft carrier",
|
| 27 |
+
"1": "airplane",
|
| 28 |
+
"10": "asparagus",
|
| 29 |
+
"100": "dumbbell",
|
| 30 |
+
"101": "ear",
|
| 31 |
+
"102": "elbow",
|
| 32 |
+
"103": "elephant",
|
| 33 |
+
"104": "envelope",
|
| 34 |
+
"105": "eraser",
|
| 35 |
+
"106": "eye",
|
| 36 |
+
"107": "eyeglasses",
|
| 37 |
+
"108": "face",
|
| 38 |
+
"109": "fan",
|
| 39 |
+
"11": "axe",
|
| 40 |
+
"110": "feather",
|
| 41 |
+
"111": "fence",
|
| 42 |
+
"112": "finger",
|
| 43 |
+
"113": "fire hydrant",
|
| 44 |
+
"114": "fireplace",
|
| 45 |
+
"115": "firetruck",
|
| 46 |
+
"116": "fish",
|
| 47 |
+
"117": "flamingo",
|
| 48 |
+
"118": "flashlight",
|
| 49 |
+
"119": "flip flops",
|
| 50 |
+
"12": "backpack",
|
| 51 |
+
"120": "floor lamp",
|
| 52 |
+
"121": "flower",
|
| 53 |
+
"122": "flying saucer",
|
| 54 |
+
"123": "foot",
|
| 55 |
+
"124": "fork",
|
| 56 |
+
"125": "frog",
|
| 57 |
+
"126": "frying pan",
|
| 58 |
+
"127": "garden hose",
|
| 59 |
+
"128": "garden",
|
| 60 |
+
"129": "giraffe",
|
| 61 |
+
"13": "banana",
|
| 62 |
+
"130": "goatee",
|
| 63 |
+
"131": "golf club",
|
| 64 |
+
"132": "grapes",
|
| 65 |
+
"133": "grass",
|
| 66 |
+
"134": "guitar",
|
| 67 |
+
"135": "hamburger",
|
| 68 |
+
"136": "hammer",
|
| 69 |
+
"137": "hand",
|
| 70 |
+
"138": "harp",
|
| 71 |
+
"139": "hat",
|
| 72 |
+
"14": "bandage",
|
| 73 |
+
"140": "headphones",
|
| 74 |
+
"141": "hedgehog",
|
| 75 |
+
"142": "helicopter",
|
| 76 |
+
"143": "helmet",
|
| 77 |
+
"144": "hexagon",
|
| 78 |
+
"145": "hockey puck",
|
| 79 |
+
"146": "hockey stick",
|
| 80 |
+
"147": "horse",
|
| 81 |
+
"148": "hospital",
|
| 82 |
+
"149": "hot air balloon",
|
| 83 |
+
"15": "barn",
|
| 84 |
+
"150": "hot dog",
|
| 85 |
+
"151": "hot tub",
|
| 86 |
+
"152": "hourglass",
|
| 87 |
+
"153": "house plant",
|
| 88 |
+
"154": "house",
|
| 89 |
+
"155": "hurricane",
|
| 90 |
+
"156": "ice cream",
|
| 91 |
+
"157": "jacket",
|
| 92 |
+
"158": "jail",
|
| 93 |
+
"159": "kangaroo",
|
| 94 |
+
"16": "baseball bat",
|
| 95 |
+
"160": "key",
|
| 96 |
+
"161": "keyboard",
|
| 97 |
+
"162": "knee",
|
| 98 |
+
"163": "knife",
|
| 99 |
+
"164": "ladder",
|
| 100 |
+
"165": "lantern",
|
| 101 |
+
"166": "laptop",
|
| 102 |
+
"167": "leaf",
|
| 103 |
+
"168": "leg",
|
| 104 |
+
"169": "light bulb",
|
| 105 |
+
"17": "baseball",
|
| 106 |
+
"170": "lighter",
|
| 107 |
+
"171": "lighthouse",
|
| 108 |
+
"172": "lightning",
|
| 109 |
+
"173": "line",
|
| 110 |
+
"174": "lion",
|
| 111 |
+
"175": "lipstick",
|
| 112 |
+
"176": "lobster",
|
| 113 |
+
"177": "lollipop",
|
| 114 |
+
"178": "mailbox",
|
| 115 |
+
"179": "map",
|
| 116 |
+
"18": "basket",
|
| 117 |
+
"180": "marker",
|
| 118 |
+
"181": "matches",
|
| 119 |
+
"182": "megaphone",
|
| 120 |
+
"183": "mermaid",
|
| 121 |
+
"184": "microphone",
|
| 122 |
+
"185": "microwave",
|
| 123 |
+
"186": "monkey",
|
| 124 |
+
"187": "moon",
|
| 125 |
+
"188": "mosquito",
|
| 126 |
+
"189": "motorbike",
|
| 127 |
+
"19": "basketball",
|
| 128 |
+
"190": "mountain",
|
| 129 |
+
"191": "mouse",
|
| 130 |
+
"192": "moustache",
|
| 131 |
+
"193": "mouth",
|
| 132 |
+
"194": "mug",
|
| 133 |
+
"195": "mushroom",
|
| 134 |
+
"196": "nail",
|
| 135 |
+
"197": "necklace",
|
| 136 |
+
"198": "nose",
|
| 137 |
+
"199": "ocean",
|
| 138 |
+
"2": "alarm clock",
|
| 139 |
+
"20": "bat",
|
| 140 |
+
"200": "octagon",
|
| 141 |
+
"201": "octopus",
|
| 142 |
+
"202": "onion",
|
| 143 |
+
"203": "oven",
|
| 144 |
+
"204": "owl",
|
| 145 |
+
"205": "paint can",
|
| 146 |
+
"206": "paintbrush",
|
| 147 |
+
"207": "palm tree",
|
| 148 |
+
"208": "panda",
|
| 149 |
+
"209": "pants",
|
| 150 |
+
"21": "bathtub",
|
| 151 |
+
"210": "paper clip",
|
| 152 |
+
"211": "parachute",
|
| 153 |
+
"212": "parrot",
|
| 154 |
+
"213": "passport",
|
| 155 |
+
"214": "peanut",
|
| 156 |
+
"215": "pear",
|
| 157 |
+
"216": "peas",
|
| 158 |
+
"217": "pencil",
|
| 159 |
+
"218": "penguin",
|
| 160 |
+
"219": "piano",
|
| 161 |
+
"22": "beach",
|
| 162 |
+
"220": "pickup truck",
|
| 163 |
+
"221": "picture frame",
|
| 164 |
+
"222": "pig",
|
| 165 |
+
"223": "pillow",
|
| 166 |
+
"224": "pineapple",
|
| 167 |
+
"225": "pizza",
|
| 168 |
+
"226": "pliers",
|
| 169 |
+
"227": "police car",
|
| 170 |
+
"228": "pond",
|
| 171 |
+
"229": "pool",
|
| 172 |
+
"23": "bear",
|
| 173 |
+
"230": "popsicle",
|
| 174 |
+
"231": "postcard",
|
| 175 |
+
"232": "potato",
|
| 176 |
+
"233": "power outlet",
|
| 177 |
+
"234": "purse",
|
| 178 |
+
"235": "rabbit",
|
| 179 |
+
"236": "raccoon",
|
| 180 |
+
"237": "radio",
|
| 181 |
+
"238": "rain",
|
| 182 |
+
"239": "rainbow",
|
| 183 |
+
"24": "beard",
|
| 184 |
+
"240": "rake",
|
| 185 |
+
"241": "remote control",
|
| 186 |
+
"242": "rhinoceros",
|
| 187 |
+
"243": "rifle",
|
| 188 |
+
"244": "river",
|
| 189 |
+
"245": "roller coaster",
|
| 190 |
+
"246": "rollerskates",
|
| 191 |
+
"247": "sailboat",
|
| 192 |
+
"248": "sandwich",
|
| 193 |
+
"249": "saw",
|
| 194 |
+
"25": "bed",
|
| 195 |
+
"250": "saxophone",
|
| 196 |
+
"251": "school bus",
|
| 197 |
+
"252": "scissors",
|
| 198 |
+
"253": "scorpion",
|
| 199 |
+
"254": "screwdriver",
|
| 200 |
+
"255": "sea turtle",
|
| 201 |
+
"256": "see saw",
|
| 202 |
+
"257": "shark",
|
| 203 |
+
"258": "sheep",
|
| 204 |
+
"259": "shoe",
|
| 205 |
+
"26": "bee",
|
| 206 |
+
"260": "shorts",
|
| 207 |
+
"261": "shovel",
|
| 208 |
+
"262": "sink",
|
| 209 |
+
"263": "skateboard",
|
| 210 |
+
"264": "skull",
|
| 211 |
+
"265": "skyscraper",
|
| 212 |
+
"266": "sleeping bag",
|
| 213 |
+
"267": "smiley face",
|
| 214 |
+
"268": "snail",
|
| 215 |
+
"269": "snake",
|
| 216 |
+
"27": "belt",
|
| 217 |
+
"270": "snorkel",
|
| 218 |
+
"271": "snowflake",
|
| 219 |
+
"272": "snowman",
|
| 220 |
+
"273": "soccer ball",
|
| 221 |
+
"274": "sock",
|
| 222 |
+
"275": "speedboat",
|
| 223 |
+
"276": "spider",
|
| 224 |
+
"277": "spoon",
|
| 225 |
+
"278": "spreadsheet",
|
| 226 |
+
"279": "square",
|
| 227 |
+
"28": "bench",
|
| 228 |
+
"280": "squiggle",
|
| 229 |
+
"281": "squirrel",
|
| 230 |
+
"282": "stairs",
|
| 231 |
+
"283": "star",
|
| 232 |
+
"284": "steak",
|
| 233 |
+
"285": "stereo",
|
| 234 |
+
"286": "stethoscope",
|
| 235 |
+
"287": "stitches",
|
| 236 |
+
"288": "stop sign",
|
| 237 |
+
"289": "stove",
|
| 238 |
+
"29": "bicycle",
|
| 239 |
+
"290": "strawberry",
|
| 240 |
+
"291": "streetlight",
|
| 241 |
+
"292": "string bean",
|
| 242 |
+
"293": "submarine",
|
| 243 |
+
"294": "suitcase",
|
| 244 |
+
"295": "sun",
|
| 245 |
+
"296": "swan",
|
| 246 |
+
"297": "sweater",
|
| 247 |
+
"298": "swing set",
|
| 248 |
+
"299": "sword",
|
| 249 |
+
"3": "ambulance",
|
| 250 |
+
"30": "binoculars",
|
| 251 |
+
"300": "syringe",
|
| 252 |
+
"301": "t-shirt",
|
| 253 |
+
"302": "table",
|
| 254 |
+
"303": "teapot",
|
| 255 |
+
"304": "teddy-bear",
|
| 256 |
+
"305": "telephone",
|
| 257 |
+
"306": "television",
|
| 258 |
+
"307": "tennis racquet",
|
| 259 |
+
"308": "tent",
|
| 260 |
+
"309": "The Eiffel Tower",
|
| 261 |
+
"31": "bird",
|
| 262 |
+
"310": "The Great Wall of China",
|
| 263 |
+
"311": "The Mona Lisa",
|
| 264 |
+
"312": "tiger",
|
| 265 |
+
"313": "toaster",
|
| 266 |
+
"314": "toe",
|
| 267 |
+
"315": "toilet",
|
| 268 |
+
"316": "tooth",
|
| 269 |
+
"317": "toothbrush",
|
| 270 |
+
"318": "toothpaste",
|
| 271 |
+
"319": "tornado",
|
| 272 |
+
"32": "birthday cake",
|
| 273 |
+
"320": "tractor",
|
| 274 |
+
"321": "traffic light",
|
| 275 |
+
"322": "train",
|
| 276 |
+
"323": "tree",
|
| 277 |
+
"324": "triangle",
|
| 278 |
+
"325": "trombone",
|
| 279 |
+
"326": "truck",
|
| 280 |
+
"327": "trumpet",
|
| 281 |
+
"328": "umbrella",
|
| 282 |
+
"329": "underwear",
|
| 283 |
+
"33": "blackberry",
|
| 284 |
+
"330": "van",
|
| 285 |
+
"331": "vase",
|
| 286 |
+
"332": "violin",
|
| 287 |
+
"333": "washing machine",
|
| 288 |
+
"334": "watermelon",
|
| 289 |
+
"335": "waterslide",
|
| 290 |
+
"336": "whale",
|
| 291 |
+
"337": "wheel",
|
| 292 |
+
"338": "windmill",
|
| 293 |
+
"339": "wine bottle",
|
| 294 |
+
"34": "blueberry",
|
| 295 |
+
"340": "wine glass",
|
| 296 |
+
"341": "wristwatch",
|
| 297 |
+
"342": "yoga",
|
| 298 |
+
"343": "zebra",
|
| 299 |
+
"344": "zigzag",
|
| 300 |
+
"35": "book",
|
| 301 |
+
"36": "boomerang",
|
| 302 |
+
"37": "bottlecap",
|
| 303 |
+
"38": "bowtie",
|
| 304 |
+
"39": "bracelet",
|
| 305 |
+
"4": "angel",
|
| 306 |
+
"40": "brain",
|
| 307 |
+
"41": "bread",
|
| 308 |
+
"42": "bridge",
|
| 309 |
+
"43": "broccoli",
|
| 310 |
+
"44": "broom",
|
| 311 |
+
"45": "bucket",
|
| 312 |
+
"46": "bulldozer",
|
| 313 |
+
"47": "bus",
|
| 314 |
+
"48": "bush",
|
| 315 |
+
"49": "butterfly",
|
| 316 |
+
"5": "animal migration",
|
| 317 |
+
"50": "cactus",
|
| 318 |
+
"51": "cake",
|
| 319 |
+
"52": "calculator",
|
| 320 |
+
"53": "calendar",
|
| 321 |
+
"54": "camel",
|
| 322 |
+
"55": "camera",
|
| 323 |
+
"56": "camouflage",
|
| 324 |
+
"57": "campfire",
|
| 325 |
+
"58": "candle",
|
| 326 |
+
"59": "cannon",
|
| 327 |
+
"6": "ant",
|
| 328 |
+
"60": "canoe",
|
| 329 |
+
"61": "car",
|
| 330 |
+
"62": "carrot",
|
| 331 |
+
"63": "castle",
|
| 332 |
+
"64": "cat",
|
| 333 |
+
"65": "ceiling fan",
|
| 334 |
+
"66": "cell phone",
|
| 335 |
+
"67": "cello",
|
| 336 |
+
"68": "chair",
|
| 337 |
+
"69": "chandelier",
|
| 338 |
+
"7": "anvil",
|
| 339 |
+
"70": "church",
|
| 340 |
+
"71": "circle",
|
| 341 |
+
"72": "clarinet",
|
| 342 |
+
"73": "clock",
|
| 343 |
+
"74": "cloud",
|
| 344 |
+
"75": "coffee cup",
|
| 345 |
+
"76": "compass",
|
| 346 |
+
"77": "computer",
|
| 347 |
+
"78": "cookie",
|
| 348 |
+
"79": "cooler",
|
| 349 |
+
"8": "apple",
|
| 350 |
+
"80": "couch",
|
| 351 |
+
"81": "cow",
|
| 352 |
+
"82": "crab",
|
| 353 |
+
"83": "crayon",
|
| 354 |
+
"84": "crocodile",
|
| 355 |
+
"85": "crown",
|
| 356 |
+
"86": "cruise ship",
|
| 357 |
+
"87": "cup",
|
| 358 |
+
"88": "diamond",
|
| 359 |
+
"89": "dishwasher",
|
| 360 |
+
"9": "arm",
|
| 361 |
+
"90": "diving board",
|
| 362 |
+
"91": "dog",
|
| 363 |
+
"92": "dolphin",
|
| 364 |
+
"93": "donut",
|
| 365 |
+
"94": "door",
|
| 366 |
+
"95": "dragon",
|
| 367 |
+
"96": "dresser",
|
| 368 |
+
"97": "drill",
|
| 369 |
+
"98": "drums",
|
| 370 |
+
"99": "duck"
|
| 371 |
+
},
|
| 372 |
+
"image_size": 28,
|
| 373 |
+
"initializer_range": 0.02,
|
| 374 |
+
"label2id": {
|
| 375 |
+
"The Eiffel Tower": "309",
|
| 376 |
+
"The Great Wall of China": "310",
|
| 377 |
+
"The Mona Lisa": "311",
|
| 378 |
+
"aircraft carrier": "0",
|
| 379 |
+
"airplane": "1",
|
| 380 |
+
"alarm clock": "2",
|
| 381 |
+
"ambulance": "3",
|
| 382 |
+
"angel": "4",
|
| 383 |
+
"animal migration": "5",
|
| 384 |
+
"ant": "6",
|
| 385 |
+
"anvil": "7",
|
| 386 |
+
"apple": "8",
|
| 387 |
+
"arm": "9",
|
| 388 |
+
"asparagus": "10",
|
| 389 |
+
"axe": "11",
|
| 390 |
+
"backpack": "12",
|
| 391 |
+
"banana": "13",
|
| 392 |
+
"bandage": "14",
|
| 393 |
+
"barn": "15",
|
| 394 |
+
"baseball": "17",
|
| 395 |
+
"baseball bat": "16",
|
| 396 |
+
"basket": "18",
|
| 397 |
+
"basketball": "19",
|
| 398 |
+
"bat": "20",
|
| 399 |
+
"bathtub": "21",
|
| 400 |
+
"beach": "22",
|
| 401 |
+
"bear": "23",
|
| 402 |
+
"beard": "24",
|
| 403 |
+
"bed": "25",
|
| 404 |
+
"bee": "26",
|
| 405 |
+
"belt": "27",
|
| 406 |
+
"bench": "28",
|
| 407 |
+
"bicycle": "29",
|
| 408 |
+
"binoculars": "30",
|
| 409 |
+
"bird": "31",
|
| 410 |
+
"birthday cake": "32",
|
| 411 |
+
"blackberry": "33",
|
| 412 |
+
"blueberry": "34",
|
| 413 |
+
"book": "35",
|
| 414 |
+
"boomerang": "36",
|
| 415 |
+
"bottlecap": "37",
|
| 416 |
+
"bowtie": "38",
|
| 417 |
+
"bracelet": "39",
|
| 418 |
+
"brain": "40",
|
| 419 |
+
"bread": "41",
|
| 420 |
+
"bridge": "42",
|
| 421 |
+
"broccoli": "43",
|
| 422 |
+
"broom": "44",
|
| 423 |
+
"bucket": "45",
|
| 424 |
+
"bulldozer": "46",
|
| 425 |
+
"bus": "47",
|
| 426 |
+
"bush": "48",
|
| 427 |
+
"butterfly": "49",
|
| 428 |
+
"cactus": "50",
|
| 429 |
+
"cake": "51",
|
| 430 |
+
"calculator": "52",
|
| 431 |
+
"calendar": "53",
|
| 432 |
+
"camel": "54",
|
| 433 |
+
"camera": "55",
|
| 434 |
+
"camouflage": "56",
|
| 435 |
+
"campfire": "57",
|
| 436 |
+
"candle": "58",
|
| 437 |
+
"cannon": "59",
|
| 438 |
+
"canoe": "60",
|
| 439 |
+
"car": "61",
|
| 440 |
+
"carrot": "62",
|
| 441 |
+
"castle": "63",
|
| 442 |
+
"cat": "64",
|
| 443 |
+
"ceiling fan": "65",
|
| 444 |
+
"cell phone": "66",
|
| 445 |
+
"cello": "67",
|
| 446 |
+
"chair": "68",
|
| 447 |
+
"chandelier": "69",
|
| 448 |
+
"church": "70",
|
| 449 |
+
"circle": "71",
|
| 450 |
+
"clarinet": "72",
|
| 451 |
+
"clock": "73",
|
| 452 |
+
"cloud": "74",
|
| 453 |
+
"coffee cup": "75",
|
| 454 |
+
"compass": "76",
|
| 455 |
+
"computer": "77",
|
| 456 |
+
"cookie": "78",
|
| 457 |
+
"cooler": "79",
|
| 458 |
+
"couch": "80",
|
| 459 |
+
"cow": "81",
|
| 460 |
+
"crab": "82",
|
| 461 |
+
"crayon": "83",
|
| 462 |
+
"crocodile": "84",
|
| 463 |
+
"crown": "85",
|
| 464 |
+
"cruise ship": "86",
|
| 465 |
+
"cup": "87",
|
| 466 |
+
"diamond": "88",
|
| 467 |
+
"dishwasher": "89",
|
| 468 |
+
"diving board": "90",
|
| 469 |
+
"dog": "91",
|
| 470 |
+
"dolphin": "92",
|
| 471 |
+
"donut": "93",
|
| 472 |
+
"door": "94",
|
| 473 |
+
"dragon": "95",
|
| 474 |
+
"dresser": "96",
|
| 475 |
+
"drill": "97",
|
| 476 |
+
"drums": "98",
|
| 477 |
+
"duck": "99",
|
| 478 |
+
"dumbbell": "100",
|
| 479 |
+
"ear": "101",
|
| 480 |
+
"elbow": "102",
|
| 481 |
+
"elephant": "103",
|
| 482 |
+
"envelope": "104",
|
| 483 |
+
"eraser": "105",
|
| 484 |
+
"eye": "106",
|
| 485 |
+
"eyeglasses": "107",
|
| 486 |
+
"face": "108",
|
| 487 |
+
"fan": "109",
|
| 488 |
+
"feather": "110",
|
| 489 |
+
"fence": "111",
|
| 490 |
+
"finger": "112",
|
| 491 |
+
"fire hydrant": "113",
|
| 492 |
+
"fireplace": "114",
|
| 493 |
+
"firetruck": "115",
|
| 494 |
+
"fish": "116",
|
| 495 |
+
"flamingo": "117",
|
| 496 |
+
"flashlight": "118",
|
| 497 |
+
"flip flops": "119",
|
| 498 |
+
"floor lamp": "120",
|
| 499 |
+
"flower": "121",
|
| 500 |
+
"flying saucer": "122",
|
| 501 |
+
"foot": "123",
|
| 502 |
+
"fork": "124",
|
| 503 |
+
"frog": "125",
|
| 504 |
+
"frying pan": "126",
|
| 505 |
+
"garden": "128",
|
| 506 |
+
"garden hose": "127",
|
| 507 |
+
"giraffe": "129",
|
| 508 |
+
"goatee": "130",
|
| 509 |
+
"golf club": "131",
|
| 510 |
+
"grapes": "132",
|
| 511 |
+
"grass": "133",
|
| 512 |
+
"guitar": "134",
|
| 513 |
+
"hamburger": "135",
|
| 514 |
+
"hammer": "136",
|
| 515 |
+
"hand": "137",
|
| 516 |
+
"harp": "138",
|
| 517 |
+
"hat": "139",
|
| 518 |
+
"headphones": "140",
|
| 519 |
+
"hedgehog": "141",
|
| 520 |
+
"helicopter": "142",
|
| 521 |
+
"helmet": "143",
|
| 522 |
+
"hexagon": "144",
|
| 523 |
+
"hockey puck": "145",
|
| 524 |
+
"hockey stick": "146",
|
| 525 |
+
"horse": "147",
|
| 526 |
+
"hospital": "148",
|
| 527 |
+
"hot air balloon": "149",
|
| 528 |
+
"hot dog": "150",
|
| 529 |
+
"hot tub": "151",
|
| 530 |
+
"hourglass": "152",
|
| 531 |
+
"house": "154",
|
| 532 |
+
"house plant": "153",
|
| 533 |
+
"hurricane": "155",
|
| 534 |
+
"ice cream": "156",
|
| 535 |
+
"jacket": "157",
|
| 536 |
+
"jail": "158",
|
| 537 |
+
"kangaroo": "159",
|
| 538 |
+
"key": "160",
|
| 539 |
+
"keyboard": "161",
|
| 540 |
+
"knee": "162",
|
| 541 |
+
"knife": "163",
|
| 542 |
+
"ladder": "164",
|
| 543 |
+
"lantern": "165",
|
| 544 |
+
"laptop": "166",
|
| 545 |
+
"leaf": "167",
|
| 546 |
+
"leg": "168",
|
| 547 |
+
"light bulb": "169",
|
| 548 |
+
"lighter": "170",
|
| 549 |
+
"lighthouse": "171",
|
| 550 |
+
"lightning": "172",
|
| 551 |
+
"line": "173",
|
| 552 |
+
"lion": "174",
|
| 553 |
+
"lipstick": "175",
|
| 554 |
+
"lobster": "176",
|
| 555 |
+
"lollipop": "177",
|
| 556 |
+
"mailbox": "178",
|
| 557 |
+
"map": "179",
|
| 558 |
+
"marker": "180",
|
| 559 |
+
"matches": "181",
|
| 560 |
+
"megaphone": "182",
|
| 561 |
+
"mermaid": "183",
|
| 562 |
+
"microphone": "184",
|
| 563 |
+
"microwave": "185",
|
| 564 |
+
"monkey": "186",
|
| 565 |
+
"moon": "187",
|
| 566 |
+
"mosquito": "188",
|
| 567 |
+
"motorbike": "189",
|
| 568 |
+
"mountain": "190",
|
| 569 |
+
"mouse": "191",
|
| 570 |
+
"moustache": "192",
|
| 571 |
+
"mouth": "193",
|
| 572 |
+
"mug": "194",
|
| 573 |
+
"mushroom": "195",
|
| 574 |
+
"nail": "196",
|
| 575 |
+
"necklace": "197",
|
| 576 |
+
"nose": "198",
|
| 577 |
+
"ocean": "199",
|
| 578 |
+
"octagon": "200",
|
| 579 |
+
"octopus": "201",
|
| 580 |
+
"onion": "202",
|
| 581 |
+
"oven": "203",
|
| 582 |
+
"owl": "204",
|
| 583 |
+
"paint can": "205",
|
| 584 |
+
"paintbrush": "206",
|
| 585 |
+
"palm tree": "207",
|
| 586 |
+
"panda": "208",
|
| 587 |
+
"pants": "209",
|
| 588 |
+
"paper clip": "210",
|
| 589 |
+
"parachute": "211",
|
| 590 |
+
"parrot": "212",
|
| 591 |
+
"passport": "213",
|
| 592 |
+
"peanut": "214",
|
| 593 |
+
"pear": "215",
|
| 594 |
+
"peas": "216",
|
| 595 |
+
"pencil": "217",
|
| 596 |
+
"penguin": "218",
|
| 597 |
+
"piano": "219",
|
| 598 |
+
"pickup truck": "220",
|
| 599 |
+
"picture frame": "221",
|
| 600 |
+
"pig": "222",
|
| 601 |
+
"pillow": "223",
|
| 602 |
+
"pineapple": "224",
|
| 603 |
+
"pizza": "225",
|
| 604 |
+
"pliers": "226",
|
| 605 |
+
"police car": "227",
|
| 606 |
+
"pond": "228",
|
| 607 |
+
"pool": "229",
|
| 608 |
+
"popsicle": "230",
|
| 609 |
+
"postcard": "231",
|
| 610 |
+
"potato": "232",
|
| 611 |
+
"power outlet": "233",
|
| 612 |
+
"purse": "234",
|
| 613 |
+
"rabbit": "235",
|
| 614 |
+
"raccoon": "236",
|
| 615 |
+
"radio": "237",
|
| 616 |
+
"rain": "238",
|
| 617 |
+
"rainbow": "239",
|
| 618 |
+
"rake": "240",
|
| 619 |
+
"remote control": "241",
|
| 620 |
+
"rhinoceros": "242",
|
| 621 |
+
"rifle": "243",
|
| 622 |
+
"river": "244",
|
| 623 |
+
"roller coaster": "245",
|
| 624 |
+
"rollerskates": "246",
|
| 625 |
+
"sailboat": "247",
|
| 626 |
+
"sandwich": "248",
|
| 627 |
+
"saw": "249",
|
| 628 |
+
"saxophone": "250",
|
| 629 |
+
"school bus": "251",
|
| 630 |
+
"scissors": "252",
|
| 631 |
+
"scorpion": "253",
|
| 632 |
+
"screwdriver": "254",
|
| 633 |
+
"sea turtle": "255",
|
| 634 |
+
"see saw": "256",
|
| 635 |
+
"shark": "257",
|
| 636 |
+
"sheep": "258",
|
| 637 |
+
"shoe": "259",
|
| 638 |
+
"shorts": "260",
|
| 639 |
+
"shovel": "261",
|
| 640 |
+
"sink": "262",
|
| 641 |
+
"skateboard": "263",
|
| 642 |
+
"skull": "264",
|
| 643 |
+
"skyscraper": "265",
|
| 644 |
+
"sleeping bag": "266",
|
| 645 |
+
"smiley face": "267",
|
| 646 |
+
"snail": "268",
|
| 647 |
+
"snake": "269",
|
| 648 |
+
"snorkel": "270",
|
| 649 |
+
"snowflake": "271",
|
| 650 |
+
"snowman": "272",
|
| 651 |
+
"soccer ball": "273",
|
| 652 |
+
"sock": "274",
|
| 653 |
+
"speedboat": "275",
|
| 654 |
+
"spider": "276",
|
| 655 |
+
"spoon": "277",
|
| 656 |
+
"spreadsheet": "278",
|
| 657 |
+
"square": "279",
|
| 658 |
+
"squiggle": "280",
|
| 659 |
+
"squirrel": "281",
|
| 660 |
+
"stairs": "282",
|
| 661 |
+
"star": "283",
|
| 662 |
+
"steak": "284",
|
| 663 |
+
"stereo": "285",
|
| 664 |
+
"stethoscope": "286",
|
| 665 |
+
"stitches": "287",
|
| 666 |
+
"stop sign": "288",
|
| 667 |
+
"stove": "289",
|
| 668 |
+
"strawberry": "290",
|
| 669 |
+
"streetlight": "291",
|
| 670 |
+
"string bean": "292",
|
| 671 |
+
"submarine": "293",
|
| 672 |
+
"suitcase": "294",
|
| 673 |
+
"sun": "295",
|
| 674 |
+
"swan": "296",
|
| 675 |
+
"sweater": "297",
|
| 676 |
+
"swing set": "298",
|
| 677 |
+
"sword": "299",
|
| 678 |
+
"syringe": "300",
|
| 679 |
+
"t-shirt": "301",
|
| 680 |
+
"table": "302",
|
| 681 |
+
"teapot": "303",
|
| 682 |
+
"teddy-bear": "304",
|
| 683 |
+
"telephone": "305",
|
| 684 |
+
"television": "306",
|
| 685 |
+
"tennis racquet": "307",
|
| 686 |
+
"tent": "308",
|
| 687 |
+
"tiger": "312",
|
| 688 |
+
"toaster": "313",
|
| 689 |
+
"toe": "314",
|
| 690 |
+
"toilet": "315",
|
| 691 |
+
"tooth": "316",
|
| 692 |
+
"toothbrush": "317",
|
| 693 |
+
"toothpaste": "318",
|
| 694 |
+
"tornado": "319",
|
| 695 |
+
"tractor": "320",
|
| 696 |
+
"traffic light": "321",
|
| 697 |
+
"train": "322",
|
| 698 |
+
"tree": "323",
|
| 699 |
+
"triangle": "324",
|
| 700 |
+
"trombone": "325",
|
| 701 |
+
"truck": "326",
|
| 702 |
+
"trumpet": "327",
|
| 703 |
+
"umbrella": "328",
|
| 704 |
+
"underwear": "329",
|
| 705 |
+
"van": "330",
|
| 706 |
+
"vase": "331",
|
| 707 |
+
"violin": "332",
|
| 708 |
+
"washing machine": "333",
|
| 709 |
+
"watermelon": "334",
|
| 710 |
+
"waterslide": "335",
|
| 711 |
+
"whale": "336",
|
| 712 |
+
"wheel": "337",
|
| 713 |
+
"windmill": "338",
|
| 714 |
+
"wine bottle": "339",
|
| 715 |
+
"wine glass": "340",
|
| 716 |
+
"wristwatch": "341",
|
| 717 |
+
"yoga": "342",
|
| 718 |
+
"zebra": "343",
|
| 719 |
+
"zigzag": "344"
|
| 720 |
+
},
|
| 721 |
+
"layer_norm_eps": 1e-05,
|
| 722 |
+
"mlp_ratio": 2.0,
|
| 723 |
+
"model_type": "mobilevitv2",
|
| 724 |
+
"n_attn_blocks": [
|
| 725 |
+
2,
|
| 726 |
+
4,
|
| 727 |
+
3
|
| 728 |
+
],
|
| 729 |
+
"num_channels": 1,
|
| 730 |
+
"output_stride": 32,
|
| 731 |
+
"patch_size": 1,
|
| 732 |
+
"problem_type": "single_label_classification",
|
| 733 |
+
"semantic_loss_ignore_index": 255,
|
| 734 |
+
"torch_dtype": "float32",
|
| 735 |
+
"transformers_version": "4.40.2",
|
| 736 |
+
"width_multiplier": 2.0
|
| 737 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c300259576684c0af329b0d510a8dd074ad1ada0211eb793e5fde762ab68a616
|
| 3 |
+
size 71269504
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"segmentation_maps",
|
| 5 |
+
"do_resize",
|
| 6 |
+
"size",
|
| 7 |
+
"resample",
|
| 8 |
+
"do_rescale",
|
| 9 |
+
"rescale_factor",
|
| 10 |
+
"do_center_crop",
|
| 11 |
+
"crop_size",
|
| 12 |
+
"do_flip_channel_order",
|
| 13 |
+
"return_tensors",
|
| 14 |
+
"data_format",
|
| 15 |
+
"input_data_format"
|
| 16 |
+
],
|
| 17 |
+
"crop_size": {
|
| 18 |
+
"height": 28,
|
| 19 |
+
"width": 28
|
| 20 |
+
},
|
| 21 |
+
"do_center_crop": true,
|
| 22 |
+
"do_convert_rgb": false,
|
| 23 |
+
"do_flip_channel_order": false,
|
| 24 |
+
"do_rescale": true,
|
| 25 |
+
"do_resize": true,
|
| 26 |
+
"image_processor_type": "MobileViTImageProcessor",
|
| 27 |
+
"resample": 2,
|
| 28 |
+
"rescale_factor": 0.00392156862745098,
|
| 29 |
+
"size": {
|
| 30 |
+
"shortest_edge": 28
|
| 31 |
+
}
|
| 32 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.762224,
|
| 3 |
+
"eval_loss": 0.9670637845993042
|
| 4 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,505 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.262571103526735,
|
| 5 |
+
"eval_steps": 5000,
|
| 6 |
+
"global_step": 55048,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11376564277588168,
|
| 13 |
+
"grad_norm": 4.343299865722656,
|
| 14 |
+
"learning_rate": 7.960000000000001e-05,
|
| 15 |
+
"loss": 4.3757,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.22753128555176336,
|
| 20 |
+
"grad_norm": 3.4980385303497314,
|
| 21 |
+
"learning_rate": 0.0001596,
|
| 22 |
+
"loss": 1.7997,
|
| 23 |
+
"step": 2000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3412969283276451,
|
| 27 |
+
"grad_norm": 3.350770950317383,
|
| 28 |
+
"learning_rate": 0.0002396,
|
| 29 |
+
"loss": 1.4879,
|
| 30 |
+
"step": 3000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4550625711035267,
|
| 34 |
+
"grad_norm": 3.362269163131714,
|
| 35 |
+
"learning_rate": 0.0003196,
|
| 36 |
+
"loss": 1.3834,
|
| 37 |
+
"step": 4000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5688282138794084,
|
| 41 |
+
"grad_norm": 2.424733877182007,
|
| 42 |
+
"learning_rate": 0.0003996,
|
| 43 |
+
"loss": 1.3351,
|
| 44 |
+
"step": 5000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5688282138794084,
|
| 48 |
+
"eval_accuracy": 0.668216,
|
| 49 |
+
"eval_loss": 1.3343349695205688,
|
| 50 |
+
"eval_runtime": 15.5029,
|
| 51 |
+
"eval_samples_per_second": 16125.98,
|
| 52 |
+
"eval_steps_per_second": 31.542,
|
| 53 |
+
"step": 5000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.6825938566552902,
|
| 57 |
+
"grad_norm": 2.601680040359497,
|
| 58 |
+
"learning_rate": 0.00047960000000000006,
|
| 59 |
+
"loss": 1.3097,
|
| 60 |
+
"step": 6000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.7963594994311718,
|
| 64 |
+
"grad_norm": 1.9989418983459473,
|
| 65 |
+
"learning_rate": 0.0005596,
|
| 66 |
+
"loss": 1.2866,
|
| 67 |
+
"step": 7000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.9101251422070534,
|
| 71 |
+
"grad_norm": 1.8081185817718506,
|
| 72 |
+
"learning_rate": 0.0006396,
|
| 73 |
+
"loss": 1.2689,
|
| 74 |
+
"step": 8000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.023890784982935,
|
| 78 |
+
"grad_norm": 1.6405588388442993,
|
| 79 |
+
"learning_rate": 0.00071952,
|
| 80 |
+
"loss": 1.2487,
|
| 81 |
+
"step": 9000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.1376564277588168,
|
| 85 |
+
"grad_norm": 1.22613525390625,
|
| 86 |
+
"learning_rate": 0.00079952,
|
| 87 |
+
"loss": 1.2165,
|
| 88 |
+
"step": 10000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.1376564277588168,
|
| 92 |
+
"eval_accuracy": 0.686196,
|
| 93 |
+
"eval_loss": 1.2481120824813843,
|
| 94 |
+
"eval_runtime": 15.8446,
|
| 95 |
+
"eval_samples_per_second": 15778.257,
|
| 96 |
+
"eval_steps_per_second": 30.862,
|
| 97 |
+
"step": 10000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.2514220705346986,
|
| 101 |
+
"grad_norm": 1.2695167064666748,
|
| 102 |
+
"learning_rate": 0.0007996786565611985,
|
| 103 |
+
"loss": 1.2046,
|
| 104 |
+
"step": 11000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.36518771331058,
|
| 108 |
+
"grad_norm": 1.2521305084228516,
|
| 109 |
+
"learning_rate": 0.0007987086748436788,
|
| 110 |
+
"loss": 1.1849,
|
| 111 |
+
"step": 12000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.4789533560864618,
|
| 115 |
+
"grad_norm": 1.19619619846344,
|
| 116 |
+
"learning_rate": 0.0007970896788508052,
|
| 117 |
+
"loss": 1.1534,
|
| 118 |
+
"step": 13000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.5927189988623436,
|
| 122 |
+
"grad_norm": 1.0483107566833496,
|
| 123 |
+
"learning_rate": 0.0007948275336376884,
|
| 124 |
+
"loss": 1.1312,
|
| 125 |
+
"step": 14000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.7064846416382253,
|
| 129 |
+
"grad_norm": 1.3618515729904175,
|
| 130 |
+
"learning_rate": 0.0007919213896323948,
|
| 131 |
+
"loss": 1.112,
|
| 132 |
+
"step": 15000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.7064846416382253,
|
| 136 |
+
"eval_accuracy": 0.716556,
|
| 137 |
+
"eval_loss": 1.1176625490188599,
|
| 138 |
+
"eval_runtime": 15.2386,
|
| 139 |
+
"eval_samples_per_second": 16405.688,
|
| 140 |
+
"eval_steps_per_second": 32.09,
|
| 141 |
+
"step": 15000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.820250284414107,
|
| 145 |
+
"grad_norm": 0.9307771325111389,
|
| 146 |
+
"learning_rate": 0.0007883817747762077,
|
| 147 |
+
"loss": 1.0986,
|
| 148 |
+
"step": 16000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.9340159271899886,
|
| 152 |
+
"grad_norm": 0.9189246296882629,
|
| 153 |
+
"learning_rate": 0.0007842073597303121,
|
| 154 |
+
"loss": 1.0847,
|
| 155 |
+
"step": 17000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.04778156996587,
|
| 159 |
+
"grad_norm": 0.8016377687454224,
|
| 160 |
+
"learning_rate": 0.0007794081581686037,
|
| 161 |
+
"loss": 1.0506,
|
| 162 |
+
"step": 18000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.161547212741752,
|
| 166 |
+
"grad_norm": 0.9774219989776611,
|
| 167 |
+
"learning_rate": 0.0007739919744091065,
|
| 168 |
+
"loss": 1.0158,
|
| 169 |
+
"step": 19000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.2753128555176336,
|
| 173 |
+
"grad_norm": 0.8449124693870544,
|
| 174 |
+
"learning_rate": 0.0007679676160878387,
|
| 175 |
+
"loss": 1.0138,
|
| 176 |
+
"step": 20000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.2753128555176336,
|
| 180 |
+
"eval_accuracy": 0.732636,
|
| 181 |
+
"eval_loss": 1.052935242652893,
|
| 182 |
+
"eval_runtime": 15.2399,
|
| 183 |
+
"eval_samples_per_second": 16404.275,
|
| 184 |
+
"eval_steps_per_second": 32.087,
|
| 185 |
+
"step": 20000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.3890784982935154,
|
| 189 |
+
"grad_norm": 0.9211858510971069,
|
| 190 |
+
"learning_rate": 0.0007613448798360993,
|
| 191 |
+
"loss": 1.0113,
|
| 192 |
+
"step": 21000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.502844141069397,
|
| 196 |
+
"grad_norm": 0.7870326042175293,
|
| 197 |
+
"learning_rate": 0.0007541345353494786,
|
| 198 |
+
"loss": 1.0024,
|
| 199 |
+
"step": 22000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.616609783845279,
|
| 203 |
+
"grad_norm": 0.8683303594589233,
|
| 204 |
+
"learning_rate": 0.0007463483078745015,
|
| 205 |
+
"loss": 1.0032,
|
| 206 |
+
"step": 23000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.73037542662116,
|
| 210 |
+
"grad_norm": 1.031267523765564,
|
| 211 |
+
"learning_rate": 0.000738007485475254,
|
| 212 |
+
"loss": 0.9961,
|
| 213 |
+
"step": 24000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.8441410693970424,
|
| 217 |
+
"grad_norm": 0.8440726399421692,
|
| 218 |
+
"learning_rate": 0.0007291089356699791,
|
| 219 |
+
"loss": 0.9909,
|
| 220 |
+
"step": 25000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.8441410693970424,
|
| 224 |
+
"eval_accuracy": 0.741524,
|
| 225 |
+
"eval_loss": 1.0143921375274658,
|
| 226 |
+
"eval_runtime": 14.9299,
|
| 227 |
+
"eval_samples_per_second": 16744.96,
|
| 228 |
+
"eval_steps_per_second": 32.753,
|
| 229 |
+
"step": 25000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.9579067121729237,
|
| 233 |
+
"grad_norm": 0.708281934261322,
|
| 234 |
+
"learning_rate": 0.0007196848947861554,
|
| 235 |
+
"loss": 0.9832,
|
| 236 |
+
"step": 26000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.0716723549488054,
|
| 240 |
+
"grad_norm": 0.692997395992279,
|
| 241 |
+
"learning_rate": 0.000709742030952583,
|
| 242 |
+
"loss": 0.9383,
|
| 243 |
+
"step": 27000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.185437997724687,
|
| 247 |
+
"grad_norm": 0.8190609216690063,
|
| 248 |
+
"learning_rate": 0.0006992857783851634,
|
| 249 |
+
"loss": 0.9193,
|
| 250 |
+
"step": 28000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 3.299203640500569,
|
| 254 |
+
"grad_norm": 0.7791016697883606,
|
| 255 |
+
"learning_rate": 0.0006883428362373026,
|
| 256 |
+
"loss": 0.9197,
|
| 257 |
+
"step": 29000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.4129692832764507,
|
| 261 |
+
"grad_norm": 0.6834008693695068,
|
| 262 |
+
"learning_rate": 0.0006769309995941914,
|
| 263 |
+
"loss": 0.9236,
|
| 264 |
+
"step": 30000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.4129692832764507,
|
| 268 |
+
"eval_accuracy": 0.748324,
|
| 269 |
+
"eval_loss": 0.9886829257011414,
|
| 270 |
+
"eval_runtime": 14.8544,
|
| 271 |
+
"eval_samples_per_second": 16830.07,
|
| 272 |
+
"eval_steps_per_second": 32.92,
|
| 273 |
+
"step": 30000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.526734926052332,
|
| 277 |
+
"grad_norm": 0.7945353388786316,
|
| 278 |
+
"learning_rate": 0.0006650809067991791,
|
| 279 |
+
"loss": 0.9259,
|
| 280 |
+
"step": 31000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 3.640500568828214,
|
| 284 |
+
"grad_norm": 0.7771942019462585,
|
| 285 |
+
"learning_rate": 0.000652788107427868,
|
| 286 |
+
"loss": 0.924,
|
| 287 |
+
"step": 32000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.7542662116040955,
|
| 291 |
+
"grad_norm": 0.7232080101966858,
|
| 292 |
+
"learning_rate": 0.0006400842315977677,
|
| 293 |
+
"loss": 0.9149,
|
| 294 |
+
"step": 33000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.868031854379977,
|
| 298 |
+
"grad_norm": 0.6129056215286255,
|
| 299 |
+
"learning_rate": 0.0006270032202430253,
|
| 300 |
+
"loss": 0.9142,
|
| 301 |
+
"step": 34000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 3.981797497155859,
|
| 305 |
+
"grad_norm": 0.7053471803665161,
|
| 306 |
+
"learning_rate": 0.0006135401606551002,
|
| 307 |
+
"loss": 0.914,
|
| 308 |
+
"step": 35000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.981797497155859,
|
| 312 |
+
"eval_accuracy": 0.754936,
|
| 313 |
+
"eval_loss": 0.9585933089256287,
|
| 314 |
+
"eval_runtime": 15.1971,
|
| 315 |
+
"eval_samples_per_second": 16450.463,
|
| 316 |
+
"eval_steps_per_second": 32.177,
|
| 317 |
+
"step": 35000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.09556313993174,
|
| 321 |
+
"grad_norm": 0.7185536623001099,
|
| 322 |
+
"learning_rate": 0.0005997438247807972,
|
| 323 |
+
"loss": 0.8508,
|
| 324 |
+
"step": 36000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.2093287827076225,
|
| 328 |
+
"grad_norm": 0.7729761600494385,
|
| 329 |
+
"learning_rate": 0.0005856090312640852,
|
| 330 |
+
"loss": 0.8434,
|
| 331 |
+
"step": 37000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.323094425483504,
|
| 335 |
+
"grad_norm": 0.8405170440673828,
|
| 336 |
+
"learning_rate": 0.0005711724058927512,
|
| 337 |
+
"loss": 0.8442,
|
| 338 |
+
"step": 38000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.436860068259386,
|
| 342 |
+
"grad_norm": 0.6555745005607605,
|
| 343 |
+
"learning_rate": 0.0005564574250751392,
|
| 344 |
+
"loss": 0.852,
|
| 345 |
+
"step": 39000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.550625711035267,
|
| 349 |
+
"grad_norm": 0.6500961184501648,
|
| 350 |
+
"learning_rate": 0.0005415031062964693,
|
| 351 |
+
"loss": 0.849,
|
| 352 |
+
"step": 40000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.550625711035267,
|
| 356 |
+
"eval_accuracy": 0.758092,
|
| 357 |
+
"eval_loss": 0.9504426121711731,
|
| 358 |
+
"eval_runtime": 14.8523,
|
| 359 |
+
"eval_samples_per_second": 16832.413,
|
| 360 |
+
"eval_steps_per_second": 32.924,
|
| 361 |
+
"step": 40000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.664391353811149,
|
| 365 |
+
"grad_norm": 0.6345399618148804,
|
| 366 |
+
"learning_rate": 0.0005263038333083039,
|
| 367 |
+
"loss": 0.8493,
|
| 368 |
+
"step": 41000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.778156996587031,
|
| 372 |
+
"grad_norm": 0.7285176515579224,
|
| 373 |
+
"learning_rate": 0.0005108991688044689,
|
| 374 |
+
"loss": 0.8505,
|
| 375 |
+
"step": 42000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.891922639362912,
|
| 379 |
+
"grad_norm": 0.7443712949752808,
|
| 380 |
+
"learning_rate": 0.000495314163389589,
|
| 381 |
+
"loss": 0.8515,
|
| 382 |
+
"step": 43000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 5.005688282138794,
|
| 386 |
+
"grad_norm": 0.6659076809883118,
|
| 387 |
+
"learning_rate": 0.0004795899698565036,
|
| 388 |
+
"loss": 0.8403,
|
| 389 |
+
"step": 44000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 5.1194539249146755,
|
| 393 |
+
"grad_norm": 0.7172214984893799,
|
| 394 |
+
"learning_rate": 0.00046372068282238195,
|
| 395 |
+
"loss": 0.7614,
|
| 396 |
+
"step": 45000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.1194539249146755,
|
| 400 |
+
"eval_accuracy": 0.761088,
|
| 401 |
+
"eval_loss": 0.9495302438735962,
|
| 402 |
+
"eval_runtime": 15.3396,
|
| 403 |
+
"eval_samples_per_second": 16297.69,
|
| 404 |
+
"eval_steps_per_second": 31.878,
|
| 405 |
+
"step": 45000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 5.233219567690558,
|
| 409 |
+
"grad_norm": 0.8739346861839294,
|
| 410 |
+
"learning_rate": 0.0004477477751198958,
|
| 411 |
+
"loss": 0.767,
|
| 412 |
+
"step": 46000
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 5.346985210466439,
|
| 416 |
+
"grad_norm": 0.8742613196372986,
|
| 417 |
+
"learning_rate": 0.0004316972214137623,
|
| 418 |
+
"loss": 0.7723,
|
| 419 |
+
"step": 47000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.460750853242321,
|
| 423 |
+
"grad_norm": 0.7512331604957581,
|
| 424 |
+
"learning_rate": 0.00041559512263430705,
|
| 425 |
+
"loss": 0.7738,
|
| 426 |
+
"step": 48000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.5745164960182025,
|
| 430 |
+
"grad_norm": 0.7592815160751343,
|
| 431 |
+
"learning_rate": 0.00039948379493191056,
|
| 432 |
+
"loss": 0.7735,
|
| 433 |
+
"step": 49000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.688282138794084,
|
| 437 |
+
"grad_norm": 0.6751989722251892,
|
| 438 |
+
"learning_rate": 0.00038335718753151784,
|
| 439 |
+
"loss": 0.7726,
|
| 440 |
+
"step": 50000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.688282138794084,
|
| 444 |
+
"eval_accuracy": 0.763736,
|
| 445 |
+
"eval_loss": 0.9361330270767212,
|
| 446 |
+
"eval_runtime": 17.5361,
|
| 447 |
+
"eval_samples_per_second": 14256.306,
|
| 448 |
+
"eval_steps_per_second": 27.885,
|
| 449 |
+
"step": 50000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.802047781569966,
|
| 453 |
+
"grad_norm": 0.7502247095108032,
|
| 454 |
+
"learning_rate": 0.0003672737214802269,
|
| 455 |
+
"loss": 0.7735,
|
| 456 |
+
"step": 51000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 5.915813424345847,
|
| 460 |
+
"grad_norm": 0.7880488038063049,
|
| 461 |
+
"learning_rate": 0.000351227356466713,
|
| 462 |
+
"loss": 0.7736,
|
| 463 |
+
"step": 52000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 6.0295790671217295,
|
| 467 |
+
"grad_norm": 0.7424056529998779,
|
| 468 |
+
"learning_rate": 0.0003352762228480271,
|
| 469 |
+
"loss": 0.7455,
|
| 470 |
+
"step": 53000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.143344709897611,
|
| 474 |
+
"grad_norm": 0.8073525428771973,
|
| 475 |
+
"learning_rate": 0.0003194143300116524,
|
| 476 |
+
"loss": 0.6797,
|
| 477 |
+
"step": 54000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 6.257110352673493,
|
| 481 |
+
"grad_norm": 0.7268177270889282,
|
| 482 |
+
"learning_rate": 0.00030369914003658996,
|
| 483 |
+
"loss": 0.6867,
|
| 484 |
+
"step": 55000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 6.257110352673493,
|
| 488 |
+
"eval_accuracy": 0.763196,
|
| 489 |
+
"eval_loss": 0.9648858308792114,
|
| 490 |
+
"eval_runtime": 15.5355,
|
| 491 |
+
"eval_samples_per_second": 16092.147,
|
| 492 |
+
"eval_steps_per_second": 31.476,
|
| 493 |
+
"step": 55000
|
| 494 |
+
}
|
| 495 |
+
],
|
| 496 |
+
"logging_steps": 1000,
|
| 497 |
+
"max_steps": 87900,
|
| 498 |
+
"num_input_tokens_seen": 0,
|
| 499 |
+
"num_train_epochs": 10,
|
| 500 |
+
"save_steps": 5000,
|
| 501 |
+
"total_flos": 2.354556845700649e+18,
|
| 502 |
+
"train_batch_size": 512,
|
| 503 |
+
"trial_name": null,
|
| 504 |
+
"trial_params": null
|
| 505 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e81425bdd4b3dd187b8b983f0ce75f0cc40038a6f6a10437dab22b47c9c3c8c
|
| 3 |
+
size 4984
|