Commit
•
492d843
1
Parent(s):
87d0f31
Upload folder using huggingface_hub
Browse files- README.md +32 -0
- checkpoint-210/config.json +33 -0
- checkpoint-210/model.safetensors +3 -0
- checkpoint-210/optimizer.pt +3 -0
- checkpoint-210/rng_state.pth +3 -0
- checkpoint-210/scheduler.pt +3 -0
- checkpoint-210/trainer_state.json +550 -0
- checkpoint-210/training_args.bin +3 -0
- config.json +33 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- image-classification
|
| 6 |
+
widget:
|
| 7 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
| 8 |
+
example_title: Tiger
|
| 9 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
| 10 |
+
example_title: Teapot
|
| 11 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
| 12 |
+
example_title: Palace
|
| 13 |
+
datasets:
|
| 14 |
+
- autotrain-xblock-twitter-1/autotrain-data
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metrics
|
| 22 |
+
loss: 0.3891792595386505
|
| 23 |
+
|
| 24 |
+
f1: 0.8878923766816144
|
| 25 |
+
|
| 26 |
+
precision: 0.8181818181818182
|
| 27 |
+
|
| 28 |
+
recall: 0.9705882352941176
|
| 29 |
+
|
| 30 |
+
auc: 0.8559883412824589
|
| 31 |
+
|
| 32 |
+
accuracy: 0.8201438848920863
|
checkpoint-210/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ViTForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"encoder_stride": 16,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "not-twitter",
|
| 14 |
+
"1": "twitter"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"not-twitter": 0,
|
| 21 |
+
"twitter": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"model_type": "vit",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_channels": 3,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"patch_size": 16,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qkv_bias": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.39.0"
|
| 33 |
+
}
|
checkpoint-210/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba19ed14288b9342dc16ad5a46cad2bf8fdccbd192bd312006e733ca6cecc961
|
| 3 |
+
size 343223968
|
checkpoint-210/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c7ff2eb0e09bc385d940572a8156badb0e5e7f4714507e2c640eef5ee268ce
|
| 3 |
+
size 686568890
|
checkpoint-210/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfdcb99695b32b58664d33569f7df569092977d4bfe5e8a9e4e5375c87dfda63
|
| 3 |
+
size 14244
|
checkpoint-210/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:644a039b0933011dc62600956f24498376f424bf1564e62cb7ce64e08540580a
|
| 3 |
+
size 1064
|
checkpoint-210/trainer_state.json
ADDED
|
@@ -0,0 +1,550 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3891792595386505,
|
| 3 |
+
"best_model_checkpoint": "autotrain-xblock-twitter-1/checkpoint-210",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 210,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 13.318061828613281,
|
| 14 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 15 |
+
"loss": 0.8613,
|
| 16 |
+
"step": 3
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09,
|
| 20 |
+
"grad_norm": 10.021459579467773,
|
| 21 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 22 |
+
"loss": 0.8653,
|
| 23 |
+
"step": 6
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13,
|
| 27 |
+
"grad_norm": 9.035711288452148,
|
| 28 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 29 |
+
"loss": 0.6439,
|
| 30 |
+
"step": 9
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.17,
|
| 34 |
+
"grad_norm": 6.433827877044678,
|
| 35 |
+
"learning_rate": 2.6190476190476192e-05,
|
| 36 |
+
"loss": 0.6497,
|
| 37 |
+
"step": 12
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.21,
|
| 41 |
+
"grad_norm": NaN,
|
| 42 |
+
"learning_rate": 3.095238095238095e-05,
|
| 43 |
+
"loss": 0.6613,
|
| 44 |
+
"step": 15
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.26,
|
| 48 |
+
"grad_norm": 15.247386932373047,
|
| 49 |
+
"learning_rate": 3.809523809523809e-05,
|
| 50 |
+
"loss": 1.1368,
|
| 51 |
+
"step": 18
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3,
|
| 55 |
+
"grad_norm": 13.3652982711792,
|
| 56 |
+
"learning_rate": 4.523809523809524e-05,
|
| 57 |
+
"loss": 0.7526,
|
| 58 |
+
"step": 21
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.34,
|
| 62 |
+
"grad_norm": 5.259400367736816,
|
| 63 |
+
"learning_rate": 4.973544973544973e-05,
|
| 64 |
+
"loss": 0.6684,
|
| 65 |
+
"step": 24
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.39,
|
| 69 |
+
"grad_norm": 9.16520881652832,
|
| 70 |
+
"learning_rate": 4.894179894179895e-05,
|
| 71 |
+
"loss": 0.6681,
|
| 72 |
+
"step": 27
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.43,
|
| 76 |
+
"grad_norm": 6.597314357757568,
|
| 77 |
+
"learning_rate": 4.814814814814815e-05,
|
| 78 |
+
"loss": 0.4601,
|
| 79 |
+
"step": 30
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.47,
|
| 83 |
+
"grad_norm": 5.8065385818481445,
|
| 84 |
+
"learning_rate": 4.7354497354497356e-05,
|
| 85 |
+
"loss": 0.6782,
|
| 86 |
+
"step": 33
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.51,
|
| 90 |
+
"grad_norm": 5.5024566650390625,
|
| 91 |
+
"learning_rate": 4.656084656084656e-05,
|
| 92 |
+
"loss": 0.5565,
|
| 93 |
+
"step": 36
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.56,
|
| 97 |
+
"grad_norm": 6.190059661865234,
|
| 98 |
+
"learning_rate": 4.576719576719577e-05,
|
| 99 |
+
"loss": 0.52,
|
| 100 |
+
"step": 39
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6,
|
| 104 |
+
"grad_norm": 15.302659034729004,
|
| 105 |
+
"learning_rate": 4.4973544973544974e-05,
|
| 106 |
+
"loss": 0.7737,
|
| 107 |
+
"step": 42
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.64,
|
| 111 |
+
"grad_norm": 4.845982074737549,
|
| 112 |
+
"learning_rate": 4.417989417989418e-05,
|
| 113 |
+
"loss": 0.549,
|
| 114 |
+
"step": 45
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.69,
|
| 118 |
+
"grad_norm": 5.293482780456543,
|
| 119 |
+
"learning_rate": 4.3386243386243384e-05,
|
| 120 |
+
"loss": 0.7392,
|
| 121 |
+
"step": 48
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.73,
|
| 125 |
+
"grad_norm": 7.307839870452881,
|
| 126 |
+
"learning_rate": 4.259259259259259e-05,
|
| 127 |
+
"loss": 0.5303,
|
| 128 |
+
"step": 51
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.77,
|
| 132 |
+
"grad_norm": 6.7569661140441895,
|
| 133 |
+
"learning_rate": 4.17989417989418e-05,
|
| 134 |
+
"loss": 0.4638,
|
| 135 |
+
"step": 54
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.81,
|
| 139 |
+
"grad_norm": 6.70114803314209,
|
| 140 |
+
"learning_rate": 4.100529100529101e-05,
|
| 141 |
+
"loss": 0.4203,
|
| 142 |
+
"step": 57
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.86,
|
| 146 |
+
"grad_norm": 11.536452293395996,
|
| 147 |
+
"learning_rate": 4.021164021164021e-05,
|
| 148 |
+
"loss": 0.6686,
|
| 149 |
+
"step": 60
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9,
|
| 153 |
+
"grad_norm": 7.2152934074401855,
|
| 154 |
+
"learning_rate": 3.941798941798942e-05,
|
| 155 |
+
"loss": 0.596,
|
| 156 |
+
"step": 63
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.94,
|
| 160 |
+
"grad_norm": 4.001399040222168,
|
| 161 |
+
"learning_rate": 3.862433862433863e-05,
|
| 162 |
+
"loss": 0.3098,
|
| 163 |
+
"step": 66
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.99,
|
| 167 |
+
"grad_norm": 7.049214839935303,
|
| 168 |
+
"learning_rate": 3.7830687830687835e-05,
|
| 169 |
+
"loss": 0.5719,
|
| 170 |
+
"step": 69
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.0,
|
| 174 |
+
"eval_accuracy": 0.7050359712230215,
|
| 175 |
+
"eval_auc": 0.6505034446210917,
|
| 176 |
+
"eval_f1": 0.8144796380090497,
|
| 177 |
+
"eval_loss": 0.5788741111755371,
|
| 178 |
+
"eval_precision": 0.7563025210084033,
|
| 179 |
+
"eval_recall": 0.8823529411764706,
|
| 180 |
+
"eval_runtime": 5.1352,
|
| 181 |
+
"eval_samples_per_second": 27.068,
|
| 182 |
+
"eval_steps_per_second": 1.753,
|
| 183 |
+
"step": 70
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.03,
|
| 187 |
+
"grad_norm": 8.485621452331543,
|
| 188 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 189 |
+
"loss": 0.8083,
|
| 190 |
+
"step": 72
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.07,
|
| 194 |
+
"grad_norm": 8.083047866821289,
|
| 195 |
+
"learning_rate": 3.6243386243386245e-05,
|
| 196 |
+
"loss": 0.5378,
|
| 197 |
+
"step": 75
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.11,
|
| 201 |
+
"grad_norm": 4.286181926727295,
|
| 202 |
+
"learning_rate": 3.5449735449735446e-05,
|
| 203 |
+
"loss": 0.4745,
|
| 204 |
+
"step": 78
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.16,
|
| 208 |
+
"grad_norm": 6.330202579498291,
|
| 209 |
+
"learning_rate": 3.465608465608466e-05,
|
| 210 |
+
"loss": 0.4858,
|
| 211 |
+
"step": 81
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.2,
|
| 215 |
+
"grad_norm": 5.901049613952637,
|
| 216 |
+
"learning_rate": 3.386243386243386e-05,
|
| 217 |
+
"loss": 0.4534,
|
| 218 |
+
"step": 84
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.24,
|
| 222 |
+
"grad_norm": 4.458903789520264,
|
| 223 |
+
"learning_rate": 3.306878306878307e-05,
|
| 224 |
+
"loss": 0.4565,
|
| 225 |
+
"step": 87
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.29,
|
| 229 |
+
"grad_norm": 8.628113746643066,
|
| 230 |
+
"learning_rate": 3.227513227513227e-05,
|
| 231 |
+
"loss": 0.5021,
|
| 232 |
+
"step": 90
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.33,
|
| 236 |
+
"grad_norm": 12.450860023498535,
|
| 237 |
+
"learning_rate": 3.148148148148148e-05,
|
| 238 |
+
"loss": 0.6712,
|
| 239 |
+
"step": 93
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.37,
|
| 243 |
+
"grad_norm": 6.316427230834961,
|
| 244 |
+
"learning_rate": 3.068783068783069e-05,
|
| 245 |
+
"loss": 0.3929,
|
| 246 |
+
"step": 96
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.41,
|
| 250 |
+
"grad_norm": 7.734628200531006,
|
| 251 |
+
"learning_rate": 2.9894179894179897e-05,
|
| 252 |
+
"loss": 0.5408,
|
| 253 |
+
"step": 99
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.46,
|
| 257 |
+
"grad_norm": 6.100373268127441,
|
| 258 |
+
"learning_rate": 2.91005291005291e-05,
|
| 259 |
+
"loss": 0.6207,
|
| 260 |
+
"step": 102
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.5,
|
| 264 |
+
"grad_norm": 6.035886764526367,
|
| 265 |
+
"learning_rate": 2.830687830687831e-05,
|
| 266 |
+
"loss": 0.6811,
|
| 267 |
+
"step": 105
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.54,
|
| 271 |
+
"grad_norm": 5.461982250213623,
|
| 272 |
+
"learning_rate": 2.7513227513227512e-05,
|
| 273 |
+
"loss": 0.5054,
|
| 274 |
+
"step": 108
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.59,
|
| 278 |
+
"grad_norm": 8.910785675048828,
|
| 279 |
+
"learning_rate": 2.6719576719576723e-05,
|
| 280 |
+
"loss": 0.6739,
|
| 281 |
+
"step": 111
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.63,
|
| 285 |
+
"grad_norm": 4.59702205657959,
|
| 286 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 287 |
+
"loss": 0.4551,
|
| 288 |
+
"step": 114
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.67,
|
| 292 |
+
"grad_norm": 2.666771173477173,
|
| 293 |
+
"learning_rate": 2.5132275132275137e-05,
|
| 294 |
+
"loss": 0.3917,
|
| 295 |
+
"step": 117
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.71,
|
| 299 |
+
"grad_norm": 3.653053045272827,
|
| 300 |
+
"learning_rate": 2.4338624338624338e-05,
|
| 301 |
+
"loss": 0.4881,
|
| 302 |
+
"step": 120
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.76,
|
| 306 |
+
"grad_norm": 1.8620728254318237,
|
| 307 |
+
"learning_rate": 2.3544973544973546e-05,
|
| 308 |
+
"loss": 0.2256,
|
| 309 |
+
"step": 123
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.8,
|
| 313 |
+
"grad_norm": 15.068528175354004,
|
| 314 |
+
"learning_rate": 2.275132275132275e-05,
|
| 315 |
+
"loss": 0.8185,
|
| 316 |
+
"step": 126
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.84,
|
| 320 |
+
"grad_norm": 2.865483045578003,
|
| 321 |
+
"learning_rate": 2.1957671957671956e-05,
|
| 322 |
+
"loss": 0.6451,
|
| 323 |
+
"step": 129
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.89,
|
| 327 |
+
"grad_norm": 1.9436465501785278,
|
| 328 |
+
"learning_rate": 2.1164021164021164e-05,
|
| 329 |
+
"loss": 0.294,
|
| 330 |
+
"step": 132
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.93,
|
| 334 |
+
"grad_norm": 2.666163921356201,
|
| 335 |
+
"learning_rate": 2.037037037037037e-05,
|
| 336 |
+
"loss": 0.4637,
|
| 337 |
+
"step": 135
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.97,
|
| 341 |
+
"grad_norm": 3.914135217666626,
|
| 342 |
+
"learning_rate": 1.9576719576719577e-05,
|
| 343 |
+
"loss": 0.4303,
|
| 344 |
+
"step": 138
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.0,
|
| 348 |
+
"eval_accuracy": 0.7841726618705036,
|
| 349 |
+
"eval_auc": 0.8285638579756226,
|
| 350 |
+
"eval_f1": 0.8684210526315789,
|
| 351 |
+
"eval_loss": 0.4182623028755188,
|
| 352 |
+
"eval_precision": 0.7857142857142857,
|
| 353 |
+
"eval_recall": 0.9705882352941176,
|
| 354 |
+
"eval_runtime": 5.2653,
|
| 355 |
+
"eval_samples_per_second": 26.399,
|
| 356 |
+
"eval_steps_per_second": 1.709,
|
| 357 |
+
"step": 140
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.01,
|
| 361 |
+
"grad_norm": 6.129709243774414,
|
| 362 |
+
"learning_rate": 1.8783068783068782e-05,
|
| 363 |
+
"loss": 0.5329,
|
| 364 |
+
"step": 141
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.06,
|
| 368 |
+
"grad_norm": 6.085241317749023,
|
| 369 |
+
"learning_rate": 1.798941798941799e-05,
|
| 370 |
+
"loss": 0.4188,
|
| 371 |
+
"step": 144
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.1,
|
| 375 |
+
"grad_norm": 7.526946067810059,
|
| 376 |
+
"learning_rate": 1.7195767195767195e-05,
|
| 377 |
+
"loss": 0.4073,
|
| 378 |
+
"step": 147
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.14,
|
| 382 |
+
"grad_norm": 3.7981059551239014,
|
| 383 |
+
"learning_rate": 1.6402116402116404e-05,
|
| 384 |
+
"loss": 0.3207,
|
| 385 |
+
"step": 150
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.19,
|
| 389 |
+
"grad_norm": 5.229352951049805,
|
| 390 |
+
"learning_rate": 1.560846560846561e-05,
|
| 391 |
+
"loss": 0.5247,
|
| 392 |
+
"step": 153
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.23,
|
| 396 |
+
"grad_norm": 3.7582530975341797,
|
| 397 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 398 |
+
"loss": 0.2936,
|
| 399 |
+
"step": 156
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.27,
|
| 403 |
+
"grad_norm": 6.107592582702637,
|
| 404 |
+
"learning_rate": 1.4021164021164022e-05,
|
| 405 |
+
"loss": 0.4513,
|
| 406 |
+
"step": 159
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.31,
|
| 410 |
+
"grad_norm": 8.501120567321777,
|
| 411 |
+
"learning_rate": 1.3227513227513228e-05,
|
| 412 |
+
"loss": 0.4808,
|
| 413 |
+
"step": 162
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.36,
|
| 417 |
+
"grad_norm": 3.4457428455352783,
|
| 418 |
+
"learning_rate": 1.2433862433862433e-05,
|
| 419 |
+
"loss": 0.27,
|
| 420 |
+
"step": 165
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.4,
|
| 424 |
+
"grad_norm": 5.215019702911377,
|
| 425 |
+
"learning_rate": 1.164021164021164e-05,
|
| 426 |
+
"loss": 0.3364,
|
| 427 |
+
"step": 168
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.44,
|
| 431 |
+
"grad_norm": 6.2070794105529785,
|
| 432 |
+
"learning_rate": 1.0846560846560846e-05,
|
| 433 |
+
"loss": 0.4075,
|
| 434 |
+
"step": 171
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.49,
|
| 438 |
+
"grad_norm": 5.491907119750977,
|
| 439 |
+
"learning_rate": 1.0052910052910053e-05,
|
| 440 |
+
"loss": 0.5218,
|
| 441 |
+
"step": 174
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.53,
|
| 445 |
+
"grad_norm": 7.795518398284912,
|
| 446 |
+
"learning_rate": 9.259259259259259e-06,
|
| 447 |
+
"loss": 0.329,
|
| 448 |
+
"step": 177
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.57,
|
| 452 |
+
"grad_norm": 3.6145973205566406,
|
| 453 |
+
"learning_rate": 8.465608465608466e-06,
|
| 454 |
+
"loss": 0.3696,
|
| 455 |
+
"step": 180
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.61,
|
| 459 |
+
"grad_norm": 5.689661502838135,
|
| 460 |
+
"learning_rate": 7.671957671957672e-06,
|
| 461 |
+
"loss": 0.6274,
|
| 462 |
+
"step": 183
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.66,
|
| 466 |
+
"grad_norm": 4.555980682373047,
|
| 467 |
+
"learning_rate": 6.878306878306878e-06,
|
| 468 |
+
"loss": 0.3477,
|
| 469 |
+
"step": 186
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.7,
|
| 473 |
+
"grad_norm": 6.758476257324219,
|
| 474 |
+
"learning_rate": 6.0846560846560845e-06,
|
| 475 |
+
"loss": 0.3809,
|
| 476 |
+
"step": 189
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.74,
|
| 480 |
+
"grad_norm": 3.1286351680755615,
|
| 481 |
+
"learning_rate": 5.291005291005291e-06,
|
| 482 |
+
"loss": 0.35,
|
| 483 |
+
"step": 192
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.79,
|
| 487 |
+
"grad_norm": 8.514357566833496,
|
| 488 |
+
"learning_rate": 4.497354497354498e-06,
|
| 489 |
+
"loss": 0.5799,
|
| 490 |
+
"step": 195
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.83,
|
| 494 |
+
"grad_norm": 4.899698734283447,
|
| 495 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 496 |
+
"loss": 0.5754,
|
| 497 |
+
"step": 198
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.87,
|
| 501 |
+
"grad_norm": 9.083395004272461,
|
| 502 |
+
"learning_rate": 2.91005291005291e-06,
|
| 503 |
+
"loss": 0.3895,
|
| 504 |
+
"step": 201
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.91,
|
| 508 |
+
"grad_norm": 2.1063151359558105,
|
| 509 |
+
"learning_rate": 2.1164021164021164e-06,
|
| 510 |
+
"loss": 0.2194,
|
| 511 |
+
"step": 204
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.96,
|
| 515 |
+
"grad_norm": 5.722929954528809,
|
| 516 |
+
"learning_rate": 1.3227513227513228e-06,
|
| 517 |
+
"loss": 0.2762,
|
| 518 |
+
"step": 207
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.0,
|
| 522 |
+
"grad_norm": 1.7745004892349243,
|
| 523 |
+
"learning_rate": 5.291005291005291e-07,
|
| 524 |
+
"loss": 0.1982,
|
| 525 |
+
"step": 210
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.0,
|
| 529 |
+
"eval_accuracy": 0.8201438848920863,
|
| 530 |
+
"eval_auc": 0.8559883412824589,
|
| 531 |
+
"eval_f1": 0.8878923766816144,
|
| 532 |
+
"eval_loss": 0.3891792595386505,
|
| 533 |
+
"eval_precision": 0.8181818181818182,
|
| 534 |
+
"eval_recall": 0.9705882352941176,
|
| 535 |
+
"eval_runtime": 5.0466,
|
| 536 |
+
"eval_samples_per_second": 27.543,
|
| 537 |
+
"eval_steps_per_second": 1.783,
|
| 538 |
+
"step": 210
|
| 539 |
+
}
|
| 540 |
+
],
|
| 541 |
+
"logging_steps": 3,
|
| 542 |
+
"max_steps": 210,
|
| 543 |
+
"num_input_tokens_seen": 0,
|
| 544 |
+
"num_train_epochs": 3,
|
| 545 |
+
"save_steps": 500,
|
| 546 |
+
"total_flos": 1.2925663867713946e+17,
|
| 547 |
+
"train_batch_size": 8,
|
| 548 |
+
"trial_name": null,
|
| 549 |
+
"trial_params": null
|
| 550 |
+
}
|
checkpoint-210/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68f1ce4f99753813b853d204957f32d65a2dc4e4ba503412914d3cf246ba64c9
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ViTForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"encoder_stride": 16,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "not-twitter",
|
| 14 |
+
"1": "twitter"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"not-twitter": 0,
|
| 21 |
+
"twitter": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"model_type": "vit",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_channels": 3,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"patch_size": 16,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qkv_bias": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.39.0"
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba19ed14288b9342dc16ad5a46cad2bf8fdccbd192bd312006e733ca6cecc961
|
| 3 |
+
size 343223968
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68f1ce4f99753813b853d204957f32d65a2dc4e4ba503412914d3cf246ba64c9
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-xblock-twitter-1/autotrain-data",
|
| 3 |
+
"model": "google/vit-base-patch16-224",
|
| 4 |
+
"username": "howdyaendra",
|
| 5 |
+
"lr": 5e-05,
|
| 6 |
+
"epochs": 3,
|
| 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 |
+
"logging_steps": -1,
|
| 18 |
+
"project_name": "autotrain-xblock-twitter-1",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": "fp16",
|
| 21 |
+
"save_total_limit": 1,
|
| 22 |
+
"save_strategy": "epoch",
|
| 23 |
+
"push_to_hub": true,
|
| 24 |
+
"repo_id": "howdyaendra/autotrain-xblock-twitter-1",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "autotrain_image",
|
| 27 |
+
"target_column": "autotrain_label",
|
| 28 |
+
"log": "none"
|
| 29 |
+
}
|