Upload folder using huggingface_hub
Browse files- README.md +42 -0
- checkpoint-2253/config.json +37 -0
- checkpoint-2253/model.safetensors +3 -0
- checkpoint-2253/optimizer.pt +3 -0
- checkpoint-2253/rng_state.pth +3 -0
- checkpoint-2253/scheduler.pt +3 -0
- checkpoint-2253/trainer_state.json +705 -0
- checkpoint-2253/training_args.bin +3 -0
- config.json +37 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Apr13_15-42-12_496e75b93dc4/events.out.tfevents.1713022933.496e75b93dc4.14956.0 +2 -2
- runs/Apr13_15-42-12_496e75b93dc4/events.out.tfevents.1713025068.496e75b93dc4.14956.1 +3 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
- xblock-base-patch1-224/autotrain-data
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metrics
|
| 22 |
+
loss: 0.4469132423400879
|
| 23 |
+
|
| 24 |
+
f1_macro: 0.8236777117298302
|
| 25 |
+
|
| 26 |
+
f1_micro: 0.829560585885486
|
| 27 |
+
|
| 28 |
+
f1_weighted: 0.8289271724966029
|
| 29 |
+
|
| 30 |
+
precision_macro: 0.8243514221166717
|
| 31 |
+
|
| 32 |
+
precision_micro: 0.829560585885486
|
| 33 |
+
|
| 34 |
+
precision_weighted: 0.8313607282611274
|
| 35 |
+
|
| 36 |
+
recall_macro: 0.8260057947019868
|
| 37 |
+
|
| 38 |
+
recall_micro: 0.829560585885486
|
| 39 |
+
|
| 40 |
+
recall_weighted: 0.829560585885486
|
| 41 |
+
|
| 42 |
+
accuracy: 0.829560585885486
|
checkpoint-2253/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 4,
|
| 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": "bluesky",
|
| 14 |
+
"1": "not-screenshot",
|
| 15 |
+
"2": "other-screenshot",
|
| 16 |
+
"3": "twitter"
|
| 17 |
+
},
|
| 18 |
+
"image_size": 224,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"bluesky": 0,
|
| 23 |
+
"not-screenshot": 1,
|
| 24 |
+
"other-screenshot": 2,
|
| 25 |
+
"twitter": 3
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-12,
|
| 28 |
+
"model_type": "vit",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_channels": 3,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"patch_size": 16,
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"qkv_bias": true,
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.39.3"
|
| 37 |
+
}
|
checkpoint-2253/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2a08cc01c6691df5610d2b51a33f4e71cb0d8f4fc6c4c4590d3426bcfeac2b5
|
| 3 |
+
size 343230128
|
checkpoint-2253/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d209548fcb17fcfdb1fcc7410e235554da75dcabada7bef2fe2f17202e679e4e
|
| 3 |
+
size 686581178
|
checkpoint-2253/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74d3cc1ae6d69d8c7a072006439f13a37690d21eeeb7a2afa2b41e2b1af2b5ad
|
| 3 |
+
size 14244
|
checkpoint-2253/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec2d3b5a510a1471dab40fffcdac65fde77564ce4593287787898b7b9e31ec75
|
| 3 |
+
size 1064
|
checkpoint-2253/trainer_state.json
ADDED
|
@@ -0,0 +1,705 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4469132423400879,
|
| 3 |
+
"best_model_checkpoint": "xblock-base-patch1-224/checkpoint-2253",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2253,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 9.94556713104248,
|
| 14 |
+
"learning_rate": 5.088495575221239e-06,
|
| 15 |
+
"loss": 1.5614,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07,
|
| 20 |
+
"grad_norm": 9.733675956726074,
|
| 21 |
+
"learning_rate": 1.0619469026548673e-05,
|
| 22 |
+
"loss": 1.4735,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1,
|
| 27 |
+
"grad_norm": 9.123199462890625,
|
| 28 |
+
"learning_rate": 1.6150442477876106e-05,
|
| 29 |
+
"loss": 1.3293,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13,
|
| 34 |
+
"grad_norm": 10.894118309020996,
|
| 35 |
+
"learning_rate": 2.1681415929203542e-05,
|
| 36 |
+
"loss": 1.2442,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.17,
|
| 41 |
+
"grad_norm": 8.819581985473633,
|
| 42 |
+
"learning_rate": 2.721238938053097e-05,
|
| 43 |
+
"loss": 1.0742,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2,
|
| 48 |
+
"grad_norm": 13.125239372253418,
|
| 49 |
+
"learning_rate": 3.274336283185841e-05,
|
| 50 |
+
"loss": 1.1571,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23,
|
| 55 |
+
"grad_norm": 8.423856735229492,
|
| 56 |
+
"learning_rate": 3.827433628318584e-05,
|
| 57 |
+
"loss": 1.1193,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.27,
|
| 62 |
+
"grad_norm": 11.360130310058594,
|
| 63 |
+
"learning_rate": 4.380530973451328e-05,
|
| 64 |
+
"loss": 1.0605,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3,
|
| 69 |
+
"grad_norm": 7.3759379386901855,
|
| 70 |
+
"learning_rate": 4.9336283185840707e-05,
|
| 71 |
+
"loss": 0.9883,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.33,
|
| 76 |
+
"grad_norm": 12.12755298614502,
|
| 77 |
+
"learning_rate": 4.9457326097681306e-05,
|
| 78 |
+
"loss": 0.9764,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.37,
|
| 83 |
+
"grad_norm": 5.0697712898254395,
|
| 84 |
+
"learning_rate": 4.884065120868278e-05,
|
| 85 |
+
"loss": 1.1213,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4,
|
| 90 |
+
"grad_norm": 8.178693771362305,
|
| 91 |
+
"learning_rate": 4.822397631968427e-05,
|
| 92 |
+
"loss": 0.9683,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.43,
|
| 97 |
+
"grad_norm": 7.6824846267700195,
|
| 98 |
+
"learning_rate": 4.7607301430685744e-05,
|
| 99 |
+
"loss": 1.0408,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.47,
|
| 104 |
+
"grad_norm": 10.855768203735352,
|
| 105 |
+
"learning_rate": 4.699062654168723e-05,
|
| 106 |
+
"loss": 0.9092,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5,
|
| 111 |
+
"grad_norm": 6.187016487121582,
|
| 112 |
+
"learning_rate": 4.6373951652688704e-05,
|
| 113 |
+
"loss": 1.0058,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.53,
|
| 118 |
+
"grad_norm": 8.00668716430664,
|
| 119 |
+
"learning_rate": 4.575727676369018e-05,
|
| 120 |
+
"loss": 0.8086,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.57,
|
| 125 |
+
"grad_norm": 5.1038336753845215,
|
| 126 |
+
"learning_rate": 4.5140601874691665e-05,
|
| 127 |
+
"loss": 0.9027,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6,
|
| 132 |
+
"grad_norm": 10.569095611572266,
|
| 133 |
+
"learning_rate": 4.452392698569314e-05,
|
| 134 |
+
"loss": 0.8234,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.63,
|
| 139 |
+
"grad_norm": 8.256200790405273,
|
| 140 |
+
"learning_rate": 4.3907252096694626e-05,
|
| 141 |
+
"loss": 0.9163,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.67,
|
| 146 |
+
"grad_norm": 11.042557716369629,
|
| 147 |
+
"learning_rate": 4.32905772076961e-05,
|
| 148 |
+
"loss": 0.8243,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7,
|
| 153 |
+
"grad_norm": 18.462459564208984,
|
| 154 |
+
"learning_rate": 4.267390231869759e-05,
|
| 155 |
+
"loss": 0.8703,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.73,
|
| 160 |
+
"grad_norm": 12.024648666381836,
|
| 161 |
+
"learning_rate": 4.2057227429699064e-05,
|
| 162 |
+
"loss": 0.991,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.77,
|
| 167 |
+
"grad_norm": 11.26354694366455,
|
| 168 |
+
"learning_rate": 4.144055254070055e-05,
|
| 169 |
+
"loss": 0.8402,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8,
|
| 174 |
+
"grad_norm": 8.839094161987305,
|
| 175 |
+
"learning_rate": 4.0823877651702024e-05,
|
| 176 |
+
"loss": 0.7653,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.83,
|
| 181 |
+
"grad_norm": 10.799356460571289,
|
| 182 |
+
"learning_rate": 4.020720276270351e-05,
|
| 183 |
+
"loss": 0.7787,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.87,
|
| 188 |
+
"grad_norm": 12.935748100280762,
|
| 189 |
+
"learning_rate": 3.9590527873704985e-05,
|
| 190 |
+
"loss": 0.7738,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.9,
|
| 195 |
+
"grad_norm": 4.829887866973877,
|
| 196 |
+
"learning_rate": 3.897385298470647e-05,
|
| 197 |
+
"loss": 0.8329,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.93,
|
| 202 |
+
"grad_norm": 4.532620429992676,
|
| 203 |
+
"learning_rate": 3.8357178095707946e-05,
|
| 204 |
+
"loss": 0.9689,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.97,
|
| 209 |
+
"grad_norm": 8.8261079788208,
|
| 210 |
+
"learning_rate": 3.774050320670943e-05,
|
| 211 |
+
"loss": 0.7615,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0,
|
| 216 |
+
"grad_norm": 3.9906632900238037,
|
| 217 |
+
"learning_rate": 3.712382831771091e-05,
|
| 218 |
+
"loss": 0.8284,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0,
|
| 223 |
+
"eval_accuracy": 0.7503328894806924,
|
| 224 |
+
"eval_f1_macro": 0.7379493476306923,
|
| 225 |
+
"eval_f1_micro": 0.7503328894806925,
|
| 226 |
+
"eval_f1_weighted": 0.7478927601803307,
|
| 227 |
+
"eval_loss": 0.6315314769744873,
|
| 228 |
+
"eval_precision_macro": 0.7619988736851466,
|
| 229 |
+
"eval_precision_micro": 0.7503328894806924,
|
| 230 |
+
"eval_precision_weighted": 0.7668596523942972,
|
| 231 |
+
"eval_recall_macro": 0.7356084437086093,
|
| 232 |
+
"eval_recall_micro": 0.7503328894806924,
|
| 233 |
+
"eval_recall_weighted": 0.7503328894806924,
|
| 234 |
+
"eval_runtime": 103.3083,
|
| 235 |
+
"eval_samples_per_second": 14.539,
|
| 236 |
+
"eval_steps_per_second": 0.91,
|
| 237 |
+
"step": 751
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.03,
|
| 241 |
+
"grad_norm": 7.72317361831665,
|
| 242 |
+
"learning_rate": 3.650715342871239e-05,
|
| 243 |
+
"loss": 0.8196,
|
| 244 |
+
"step": 775
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.07,
|
| 248 |
+
"grad_norm": 6.5625152587890625,
|
| 249 |
+
"learning_rate": 3.589047853971386e-05,
|
| 250 |
+
"loss": 0.7794,
|
| 251 |
+
"step": 800
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.1,
|
| 255 |
+
"grad_norm": 5.599926948547363,
|
| 256 |
+
"learning_rate": 3.5273803650715344e-05,
|
| 257 |
+
"loss": 0.6632,
|
| 258 |
+
"step": 825
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.13,
|
| 262 |
+
"grad_norm": 9.425518989562988,
|
| 263 |
+
"learning_rate": 3.465712876171682e-05,
|
| 264 |
+
"loss": 0.7074,
|
| 265 |
+
"step": 850
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.17,
|
| 269 |
+
"grad_norm": 8.80082893371582,
|
| 270 |
+
"learning_rate": 3.4040453872718305e-05,
|
| 271 |
+
"loss": 0.7325,
|
| 272 |
+
"step": 875
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.2,
|
| 276 |
+
"grad_norm": 11.81970500946045,
|
| 277 |
+
"learning_rate": 3.342377898371978e-05,
|
| 278 |
+
"loss": 0.8574,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.23,
|
| 283 |
+
"grad_norm": 8.871489524841309,
|
| 284 |
+
"learning_rate": 3.2807104094721266e-05,
|
| 285 |
+
"loss": 0.8407,
|
| 286 |
+
"step": 925
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.26,
|
| 290 |
+
"grad_norm": 7.296131610870361,
|
| 291 |
+
"learning_rate": 3.219042920572274e-05,
|
| 292 |
+
"loss": 0.6962,
|
| 293 |
+
"step": 950
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.3,
|
| 297 |
+
"grad_norm": 8.161062240600586,
|
| 298 |
+
"learning_rate": 3.1573754316724227e-05,
|
| 299 |
+
"loss": 0.8163,
|
| 300 |
+
"step": 975
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.33,
|
| 304 |
+
"grad_norm": 14.00735092163086,
|
| 305 |
+
"learning_rate": 3.0957079427725704e-05,
|
| 306 |
+
"loss": 0.6706,
|
| 307 |
+
"step": 1000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.36,
|
| 311 |
+
"grad_norm": 10.980608940124512,
|
| 312 |
+
"learning_rate": 3.0340404538727184e-05,
|
| 313 |
+
"loss": 0.6639,
|
| 314 |
+
"step": 1025
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.4,
|
| 318 |
+
"grad_norm": 6.72366189956665,
|
| 319 |
+
"learning_rate": 2.9723729649728664e-05,
|
| 320 |
+
"loss": 0.7,
|
| 321 |
+
"step": 1050
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.43,
|
| 325 |
+
"grad_norm": 24.283390045166016,
|
| 326 |
+
"learning_rate": 2.9107054760730145e-05,
|
| 327 |
+
"loss": 0.7156,
|
| 328 |
+
"step": 1075
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.46,
|
| 332 |
+
"grad_norm": 4.696579933166504,
|
| 333 |
+
"learning_rate": 2.8490379871731625e-05,
|
| 334 |
+
"loss": 0.5984,
|
| 335 |
+
"step": 1100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.5,
|
| 339 |
+
"grad_norm": 6.687375545501709,
|
| 340 |
+
"learning_rate": 2.7873704982733105e-05,
|
| 341 |
+
"loss": 0.6752,
|
| 342 |
+
"step": 1125
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.53,
|
| 346 |
+
"grad_norm": 12.651863098144531,
|
| 347 |
+
"learning_rate": 2.7257030093734586e-05,
|
| 348 |
+
"loss": 0.8265,
|
| 349 |
+
"step": 1150
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.56,
|
| 353 |
+
"grad_norm": 5.703587532043457,
|
| 354 |
+
"learning_rate": 2.6640355204736066e-05,
|
| 355 |
+
"loss": 0.6061,
|
| 356 |
+
"step": 1175
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.6,
|
| 360 |
+
"grad_norm": 12.219403266906738,
|
| 361 |
+
"learning_rate": 2.6023680315737543e-05,
|
| 362 |
+
"loss": 0.5414,
|
| 363 |
+
"step": 1200
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.63,
|
| 367 |
+
"grad_norm": 13.479424476623535,
|
| 368 |
+
"learning_rate": 2.5407005426739024e-05,
|
| 369 |
+
"loss": 0.6115,
|
| 370 |
+
"step": 1225
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.66,
|
| 374 |
+
"grad_norm": 2.6645803451538086,
|
| 375 |
+
"learning_rate": 2.4790330537740504e-05,
|
| 376 |
+
"loss": 0.7061,
|
| 377 |
+
"step": 1250
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.7,
|
| 381 |
+
"grad_norm": 7.649036884307861,
|
| 382 |
+
"learning_rate": 2.4173655648741984e-05,
|
| 383 |
+
"loss": 0.5908,
|
| 384 |
+
"step": 1275
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.73,
|
| 388 |
+
"grad_norm": 7.877263069152832,
|
| 389 |
+
"learning_rate": 2.3556980759743465e-05,
|
| 390 |
+
"loss": 0.5877,
|
| 391 |
+
"step": 1300
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.76,
|
| 395 |
+
"grad_norm": 3.582003355026245,
|
| 396 |
+
"learning_rate": 2.2940305870744945e-05,
|
| 397 |
+
"loss": 0.6062,
|
| 398 |
+
"step": 1325
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.8,
|
| 402 |
+
"grad_norm": 11.514890670776367,
|
| 403 |
+
"learning_rate": 2.2323630981746425e-05,
|
| 404 |
+
"loss": 0.5983,
|
| 405 |
+
"step": 1350
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.83,
|
| 409 |
+
"grad_norm": 14.150575637817383,
|
| 410 |
+
"learning_rate": 2.1706956092747906e-05,
|
| 411 |
+
"loss": 0.6691,
|
| 412 |
+
"step": 1375
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.86,
|
| 416 |
+
"grad_norm": 5.117061138153076,
|
| 417 |
+
"learning_rate": 2.1090281203749386e-05,
|
| 418 |
+
"loss": 0.6876,
|
| 419 |
+
"step": 1400
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.9,
|
| 423 |
+
"grad_norm": 6.246029376983643,
|
| 424 |
+
"learning_rate": 2.0473606314750867e-05,
|
| 425 |
+
"loss": 0.6186,
|
| 426 |
+
"step": 1425
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.93,
|
| 430 |
+
"grad_norm": 8.04295825958252,
|
| 431 |
+
"learning_rate": 1.9856931425752347e-05,
|
| 432 |
+
"loss": 0.7033,
|
| 433 |
+
"step": 1450
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.96,
|
| 437 |
+
"grad_norm": 6.798038482666016,
|
| 438 |
+
"learning_rate": 1.9240256536753827e-05,
|
| 439 |
+
"loss": 0.6698,
|
| 440 |
+
"step": 1475
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.0,
|
| 444 |
+
"grad_norm": 7.464223384857178,
|
| 445 |
+
"learning_rate": 1.8623581647755304e-05,
|
| 446 |
+
"loss": 0.6421,
|
| 447 |
+
"step": 1500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.0,
|
| 451 |
+
"eval_accuracy": 0.8062583222370173,
|
| 452 |
+
"eval_f1_macro": 0.8030885441145199,
|
| 453 |
+
"eval_f1_micro": 0.8062583222370173,
|
| 454 |
+
"eval_f1_weighted": 0.8081177448606712,
|
| 455 |
+
"eval_loss": 0.49981948733329773,
|
| 456 |
+
"eval_precision_macro": 0.8105725964724615,
|
| 457 |
+
"eval_precision_micro": 0.8062583222370173,
|
| 458 |
+
"eval_precision_weighted": 0.8226218541008891,
|
| 459 |
+
"eval_recall_macro": 0.8098096026490066,
|
| 460 |
+
"eval_recall_micro": 0.8062583222370173,
|
| 461 |
+
"eval_recall_weighted": 0.8062583222370173,
|
| 462 |
+
"eval_runtime": 108.6859,
|
| 463 |
+
"eval_samples_per_second": 13.82,
|
| 464 |
+
"eval_steps_per_second": 0.865,
|
| 465 |
+
"step": 1502
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.03,
|
| 469 |
+
"grad_norm": 7.260876655578613,
|
| 470 |
+
"learning_rate": 1.8006906758756785e-05,
|
| 471 |
+
"loss": 0.6168,
|
| 472 |
+
"step": 1525
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.06,
|
| 476 |
+
"grad_norm": 10.966588973999023,
|
| 477 |
+
"learning_rate": 1.7390231869758265e-05,
|
| 478 |
+
"loss": 0.6235,
|
| 479 |
+
"step": 1550
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.1,
|
| 483 |
+
"grad_norm": 7.024848937988281,
|
| 484 |
+
"learning_rate": 1.6773556980759745e-05,
|
| 485 |
+
"loss": 0.5583,
|
| 486 |
+
"step": 1575
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.13,
|
| 490 |
+
"grad_norm": 7.464731693267822,
|
| 491 |
+
"learning_rate": 1.6156882091761226e-05,
|
| 492 |
+
"loss": 0.5755,
|
| 493 |
+
"step": 1600
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.16,
|
| 497 |
+
"grad_norm": 3.144723892211914,
|
| 498 |
+
"learning_rate": 1.5540207202762706e-05,
|
| 499 |
+
"loss": 0.5972,
|
| 500 |
+
"step": 1625
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.2,
|
| 504 |
+
"grad_norm": 10.064537048339844,
|
| 505 |
+
"learning_rate": 1.4923532313764185e-05,
|
| 506 |
+
"loss": 0.583,
|
| 507 |
+
"step": 1650
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.23,
|
| 511 |
+
"grad_norm": 8.008367538452148,
|
| 512 |
+
"learning_rate": 1.4306857424765665e-05,
|
| 513 |
+
"loss": 0.5201,
|
| 514 |
+
"step": 1675
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.26,
|
| 518 |
+
"grad_norm": 6.358066082000732,
|
| 519 |
+
"learning_rate": 1.3690182535767144e-05,
|
| 520 |
+
"loss": 0.5662,
|
| 521 |
+
"step": 1700
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.3,
|
| 525 |
+
"grad_norm": 6.239820957183838,
|
| 526 |
+
"learning_rate": 1.3073507646768624e-05,
|
| 527 |
+
"loss": 0.5854,
|
| 528 |
+
"step": 1725
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.33,
|
| 532 |
+
"grad_norm": 6.083053112030029,
|
| 533 |
+
"learning_rate": 1.2456832757770105e-05,
|
| 534 |
+
"loss": 0.5655,
|
| 535 |
+
"step": 1750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.36,
|
| 539 |
+
"grad_norm": 17.246747970581055,
|
| 540 |
+
"learning_rate": 1.1840157868771585e-05,
|
| 541 |
+
"loss": 0.6351,
|
| 542 |
+
"step": 1775
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.4,
|
| 546 |
+
"grad_norm": 11.279265403747559,
|
| 547 |
+
"learning_rate": 1.1223482979773065e-05,
|
| 548 |
+
"loss": 0.5639,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.43,
|
| 553 |
+
"grad_norm": 6.290694713592529,
|
| 554 |
+
"learning_rate": 1.0606808090774544e-05,
|
| 555 |
+
"loss": 0.5125,
|
| 556 |
+
"step": 1825
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.46,
|
| 560 |
+
"grad_norm": 12.703798294067383,
|
| 561 |
+
"learning_rate": 9.990133201776024e-06,
|
| 562 |
+
"loss": 0.6839,
|
| 563 |
+
"step": 1850
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.5,
|
| 567 |
+
"grad_norm": 5.460929870605469,
|
| 568 |
+
"learning_rate": 9.373458312777505e-06,
|
| 569 |
+
"loss": 0.5766,
|
| 570 |
+
"step": 1875
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.53,
|
| 574 |
+
"grad_norm": 8.471376419067383,
|
| 575 |
+
"learning_rate": 8.756783423778985e-06,
|
| 576 |
+
"loss": 0.5011,
|
| 577 |
+
"step": 1900
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.56,
|
| 581 |
+
"grad_norm": 5.83112096786499,
|
| 582 |
+
"learning_rate": 8.140108534780466e-06,
|
| 583 |
+
"loss": 0.4984,
|
| 584 |
+
"step": 1925
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.6,
|
| 588 |
+
"grad_norm": 7.202915668487549,
|
| 589 |
+
"learning_rate": 7.523433645781943e-06,
|
| 590 |
+
"loss": 0.6013,
|
| 591 |
+
"step": 1950
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.63,
|
| 595 |
+
"grad_norm": 7.630007266998291,
|
| 596 |
+
"learning_rate": 6.906758756783424e-06,
|
| 597 |
+
"loss": 0.4976,
|
| 598 |
+
"step": 1975
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.66,
|
| 602 |
+
"grad_norm": 2.946850061416626,
|
| 603 |
+
"learning_rate": 6.290083867784904e-06,
|
| 604 |
+
"loss": 0.4218,
|
| 605 |
+
"step": 2000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.7,
|
| 609 |
+
"grad_norm": 12.109963417053223,
|
| 610 |
+
"learning_rate": 5.6734089787863845e-06,
|
| 611 |
+
"loss": 0.5818,
|
| 612 |
+
"step": 2025
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.73,
|
| 616 |
+
"grad_norm": 12.913744926452637,
|
| 617 |
+
"learning_rate": 5.056734089787865e-06,
|
| 618 |
+
"loss": 0.5638,
|
| 619 |
+
"step": 2050
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.76,
|
| 623 |
+
"grad_norm": 21.241952896118164,
|
| 624 |
+
"learning_rate": 4.464726196349285e-06,
|
| 625 |
+
"loss": 0.6451,
|
| 626 |
+
"step": 2075
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.8,
|
| 630 |
+
"grad_norm": 10.033452987670898,
|
| 631 |
+
"learning_rate": 3.848051307350765e-06,
|
| 632 |
+
"loss": 0.5067,
|
| 633 |
+
"step": 2100
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.83,
|
| 637 |
+
"grad_norm": 15.357681274414062,
|
| 638 |
+
"learning_rate": 3.231376418352245e-06,
|
| 639 |
+
"loss": 0.6292,
|
| 640 |
+
"step": 2125
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.86,
|
| 644 |
+
"grad_norm": 10.886502265930176,
|
| 645 |
+
"learning_rate": 2.614701529353725e-06,
|
| 646 |
+
"loss": 0.6365,
|
| 647 |
+
"step": 2150
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.9,
|
| 651 |
+
"grad_norm": 6.1179986000061035,
|
| 652 |
+
"learning_rate": 1.998026640355205e-06,
|
| 653 |
+
"loss": 0.5717,
|
| 654 |
+
"step": 2175
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.93,
|
| 658 |
+
"grad_norm": 8.245763778686523,
|
| 659 |
+
"learning_rate": 1.381351751356685e-06,
|
| 660 |
+
"loss": 0.5669,
|
| 661 |
+
"step": 2200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.96,
|
| 665 |
+
"grad_norm": 9.85698413848877,
|
| 666 |
+
"learning_rate": 7.646768623581648e-07,
|
| 667 |
+
"loss": 0.4571,
|
| 668 |
+
"step": 2225
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.0,
|
| 672 |
+
"grad_norm": 16.406970977783203,
|
| 673 |
+
"learning_rate": 1.480019733596448e-07,
|
| 674 |
+
"loss": 0.5549,
|
| 675 |
+
"step": 2250
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.0,
|
| 679 |
+
"eval_accuracy": 0.829560585885486,
|
| 680 |
+
"eval_f1_macro": 0.8236777117298302,
|
| 681 |
+
"eval_f1_micro": 0.829560585885486,
|
| 682 |
+
"eval_f1_weighted": 0.8289271724966029,
|
| 683 |
+
"eval_loss": 0.4469132423400879,
|
| 684 |
+
"eval_precision_macro": 0.8243514221166717,
|
| 685 |
+
"eval_precision_micro": 0.829560585885486,
|
| 686 |
+
"eval_precision_weighted": 0.8313607282611274,
|
| 687 |
+
"eval_recall_macro": 0.8260057947019868,
|
| 688 |
+
"eval_recall_micro": 0.829560585885486,
|
| 689 |
+
"eval_recall_weighted": 0.829560585885486,
|
| 690 |
+
"eval_runtime": 107.4762,
|
| 691 |
+
"eval_samples_per_second": 13.975,
|
| 692 |
+
"eval_steps_per_second": 0.875,
|
| 693 |
+
"step": 2253
|
| 694 |
+
}
|
| 695 |
+
],
|
| 696 |
+
"logging_steps": 25,
|
| 697 |
+
"max_steps": 2253,
|
| 698 |
+
"num_input_tokens_seen": 0,
|
| 699 |
+
"num_train_epochs": 3,
|
| 700 |
+
"save_steps": 500,
|
| 701 |
+
"total_flos": 1.3962756971819336e+18,
|
| 702 |
+
"train_batch_size": 8,
|
| 703 |
+
"trial_name": null,
|
| 704 |
+
"trial_params": null
|
| 705 |
+
}
|
checkpoint-2253/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be321081e73ffc6cae63799360a414dee56067b5572ebec02c8d8764fa8bed69
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 4,
|
| 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": "bluesky",
|
| 14 |
+
"1": "not-screenshot",
|
| 15 |
+
"2": "other-screenshot",
|
| 16 |
+
"3": "twitter"
|
| 17 |
+
},
|
| 18 |
+
"image_size": 224,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"bluesky": 0,
|
| 23 |
+
"not-screenshot": 1,
|
| 24 |
+
"other-screenshot": 2,
|
| 25 |
+
"twitter": 3
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-12,
|
| 28 |
+
"model_type": "vit",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_channels": 3,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"patch_size": 16,
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"qkv_bias": true,
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.39.3"
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2a08cc01c6691df5610d2b51a33f4e71cb0d8f4fc6c4c4590d3426bcfeac2b5
|
| 3 |
+
size 343230128
|
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 |
+
}
|
runs/Apr13_15-42-12_496e75b93dc4/events.out.tfevents.1713022933.496e75b93dc4.14956.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82bc4a387eb423c9031f591b17e56e6100e6cedc9e7bb157e8cee4239edb5c70
|
| 3 |
+
size 26565
|
runs/Apr13_15-42-12_496e75b93dc4/events.out.tfevents.1713025068.496e75b93dc4.14956.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aecec5609fc2621ffa17acea597de88036d30f75d0b184a60a7ac45af6e3da44
|
| 3 |
+
size 921
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be321081e73ffc6cae63799360a414dee56067b5572ebec02c8d8764fa8bed69
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "xblock-base-patch1-224/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": "xblock-base-patch1-224",
|
| 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/xblock-base-patch1-224",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "autotrain_image",
|
| 27 |
+
"target_column": "autotrain_label",
|
| 28 |
+
"log": "tensorboard"
|
| 29 |
+
}
|