Upload folder using huggingface_hub
Browse files- README.md +42 -0
- checkpoint-494/config.json +35 -0
- checkpoint-494/model.safetensors +3 -0
- checkpoint-494/optimizer.pt +3 -0
- checkpoint-494/rng_state.pth +3 -0
- checkpoint-494/scheduler.pt +3 -0
- checkpoint-494/trainer_state.json +743 -0
- checkpoint-494/training_args.bin +3 -0
- config.json +35 -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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
- autotrain-3b9gd-7t9lc/autotrain-data
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metrics
|
| 22 |
+
loss: 0.0002666182699613273
|
| 23 |
+
|
| 24 |
+
f1_macro: 1.0
|
| 25 |
+
|
| 26 |
+
f1_micro: 1.0
|
| 27 |
+
|
| 28 |
+
f1_weighted: 1.0
|
| 29 |
+
|
| 30 |
+
precision_macro: 1.0
|
| 31 |
+
|
| 32 |
+
precision_micro: 1.0
|
| 33 |
+
|
| 34 |
+
precision_weighted: 1.0
|
| 35 |
+
|
| 36 |
+
recall_macro: 1.0
|
| 37 |
+
|
| 38 |
+
recall_micro: 1.0
|
| 39 |
+
|
| 40 |
+
recall_weighted: 1.0
|
| 41 |
+
|
| 42 |
+
accuracy: 1.0
|
checkpoint-494/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 3,
|
| 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": "paper",
|
| 14 |
+
"1": "rock",
|
| 15 |
+
"2": "scissors"
|
| 16 |
+
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"paper": 0,
|
| 22 |
+
"rock": 1,
|
| 23 |
+
"scissors": 2
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"model_type": "vit",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_channels": 3,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"patch_size": 16,
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"qkv_bias": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.39.0"
|
| 35 |
+
}
|
checkpoint-494/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e975fa2899815bd2b1c1592f380ccc9e57f2a202d1fa85037aac37928e8713
|
| 3 |
+
size 343227052
|
checkpoint-494/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8048094a4dd54565485f3b16a9c01c3f3d6af51987921a71542378c17c691127
|
| 3 |
+
size 686569402
|
checkpoint-494/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffcc0ee1f2a3a1d1a059b0a191a439f10a99e759c216fed227f7e4522bec391e
|
| 3 |
+
size 13990
|
checkpoint-494/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03b764c62e1310c6c04975d9ffd39413e945f85cc486b1586bfa13a2fc3005d9
|
| 3 |
+
size 1064
|
checkpoint-494/trainer_state.json
ADDED
|
@@ -0,0 +1,743 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0002666182699613273,
|
| 3 |
+
"best_model_checkpoint": "autotrain-3b9gd-7t9lc/checkpoint-494",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 494,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 8.240466117858887,
|
| 14 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 15 |
+
"loss": 1.1781,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"grad_norm": 14.987759590148926,
|
| 21 |
+
"learning_rate": 6.666666666666667e-06,
|
| 22 |
+
"loss": 1.1781,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06,
|
| 27 |
+
"grad_norm": 8.519774436950684,
|
| 28 |
+
"learning_rate": 1e-05,
|
| 29 |
+
"loss": 1.0057,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08,
|
| 34 |
+
"grad_norm": 6.639293193817139,
|
| 35 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 36 |
+
"loss": 0.909,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1,
|
| 41 |
+
"grad_norm": 8.727118492126465,
|
| 42 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 43 |
+
"loss": 0.8319,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"grad_norm": 7.4621148109436035,
|
| 49 |
+
"learning_rate": 2e-05,
|
| 50 |
+
"loss": 0.6461,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14,
|
| 55 |
+
"grad_norm": 6.218155860900879,
|
| 56 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 57 |
+
"loss": 0.5342,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16,
|
| 62 |
+
"grad_norm": 2.2607550621032715,
|
| 63 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 64 |
+
"loss": 0.3212,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18,
|
| 69 |
+
"grad_norm": 7.647438049316406,
|
| 70 |
+
"learning_rate": 3e-05,
|
| 71 |
+
"loss": 0.2912,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2,
|
| 76 |
+
"grad_norm": 3.327169418334961,
|
| 77 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 78 |
+
"loss": 0.1935,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.22,
|
| 83 |
+
"grad_norm": 10.839067459106445,
|
| 84 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 85 |
+
"loss": 0.2682,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.24,
|
| 90 |
+
"grad_norm": 5.581568717956543,
|
| 91 |
+
"learning_rate": 4e-05,
|
| 92 |
+
"loss": 0.3104,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.26,
|
| 97 |
+
"grad_norm": 8.139863967895508,
|
| 98 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 99 |
+
"loss": 0.1683,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.28,
|
| 104 |
+
"grad_norm": 7.741869926452637,
|
| 105 |
+
"learning_rate": 4.666666666666667e-05,
|
| 106 |
+
"loss": 0.4055,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3,
|
| 111 |
+
"grad_norm": 23.573352813720703,
|
| 112 |
+
"learning_rate": 5e-05,
|
| 113 |
+
"loss": 0.3234,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.32,
|
| 118 |
+
"grad_norm": 8.024917602539062,
|
| 119 |
+
"learning_rate": 4.9624624624624625e-05,
|
| 120 |
+
"loss": 0.5331,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.34,
|
| 125 |
+
"grad_norm": 0.1634410321712494,
|
| 126 |
+
"learning_rate": 4.9249249249249253e-05,
|
| 127 |
+
"loss": 0.0505,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.36,
|
| 132 |
+
"grad_norm": 1.8996868133544922,
|
| 133 |
+
"learning_rate": 4.8873873873873876e-05,
|
| 134 |
+
"loss": 0.1691,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.38,
|
| 139 |
+
"grad_norm": 6.981603622436523,
|
| 140 |
+
"learning_rate": 4.8498498498498504e-05,
|
| 141 |
+
"loss": 0.2798,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4,
|
| 146 |
+
"grad_norm": 5.159909248352051,
|
| 147 |
+
"learning_rate": 4.812312312312313e-05,
|
| 148 |
+
"loss": 0.2114,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.43,
|
| 153 |
+
"grad_norm": 4.676971435546875,
|
| 154 |
+
"learning_rate": 4.774774774774775e-05,
|
| 155 |
+
"loss": 0.2634,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.45,
|
| 160 |
+
"grad_norm": 6.247714042663574,
|
| 161 |
+
"learning_rate": 4.737237237237238e-05,
|
| 162 |
+
"loss": 0.1426,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.47,
|
| 167 |
+
"grad_norm": 1.8779627084732056,
|
| 168 |
+
"learning_rate": 4.6996996996997e-05,
|
| 169 |
+
"loss": 0.4049,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.49,
|
| 174 |
+
"grad_norm": 0.6359833478927612,
|
| 175 |
+
"learning_rate": 4.662162162162162e-05,
|
| 176 |
+
"loss": 0.0321,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.51,
|
| 181 |
+
"grad_norm": 0.4598715007305145,
|
| 182 |
+
"learning_rate": 4.624624624624625e-05,
|
| 183 |
+
"loss": 0.0668,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.53,
|
| 188 |
+
"grad_norm": 0.07359237223863602,
|
| 189 |
+
"learning_rate": 4.587087087087087e-05,
|
| 190 |
+
"loss": 0.2143,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.55,
|
| 195 |
+
"grad_norm": 8.209424018859863,
|
| 196 |
+
"learning_rate": 4.54954954954955e-05,
|
| 197 |
+
"loss": 0.1671,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.57,
|
| 202 |
+
"grad_norm": 0.7971270084381104,
|
| 203 |
+
"learning_rate": 4.5120120120120124e-05,
|
| 204 |
+
"loss": 0.2135,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.59,
|
| 209 |
+
"grad_norm": 12.232625961303711,
|
| 210 |
+
"learning_rate": 4.4744744744744746e-05,
|
| 211 |
+
"loss": 0.1478,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.61,
|
| 216 |
+
"grad_norm": 13.341341972351074,
|
| 217 |
+
"learning_rate": 4.4369369369369375e-05,
|
| 218 |
+
"loss": 0.3675,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.63,
|
| 223 |
+
"grad_norm": 22.468730926513672,
|
| 224 |
+
"learning_rate": 4.3993993993994e-05,
|
| 225 |
+
"loss": 0.1616,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.65,
|
| 230 |
+
"grad_norm": 6.675795078277588,
|
| 231 |
+
"learning_rate": 4.3618618618618626e-05,
|
| 232 |
+
"loss": 0.1661,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.67,
|
| 237 |
+
"grad_norm": 1.265025019645691,
|
| 238 |
+
"learning_rate": 4.324324324324325e-05,
|
| 239 |
+
"loss": 0.1427,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.69,
|
| 244 |
+
"grad_norm": 0.23774471879005432,
|
| 245 |
+
"learning_rate": 4.286786786786787e-05,
|
| 246 |
+
"loss": 0.0339,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.71,
|
| 251 |
+
"grad_norm": 9.141915321350098,
|
| 252 |
+
"learning_rate": 4.24924924924925e-05,
|
| 253 |
+
"loss": 0.4787,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.73,
|
| 258 |
+
"grad_norm": 14.628870964050293,
|
| 259 |
+
"learning_rate": 4.2117117117117115e-05,
|
| 260 |
+
"loss": 0.0911,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.75,
|
| 265 |
+
"grad_norm": 8.062237739562988,
|
| 266 |
+
"learning_rate": 4.1741741741741744e-05,
|
| 267 |
+
"loss": 0.0447,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.77,
|
| 272 |
+
"grad_norm": 16.428728103637695,
|
| 273 |
+
"learning_rate": 4.1366366366366366e-05,
|
| 274 |
+
"loss": 0.3648,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.79,
|
| 279 |
+
"grad_norm": 0.037159789353609085,
|
| 280 |
+
"learning_rate": 4.099099099099099e-05,
|
| 281 |
+
"loss": 0.249,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.81,
|
| 286 |
+
"grad_norm": 8.085445404052734,
|
| 287 |
+
"learning_rate": 4.061561561561562e-05,
|
| 288 |
+
"loss": 0.0837,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.83,
|
| 293 |
+
"grad_norm": 2.010667085647583,
|
| 294 |
+
"learning_rate": 4.024024024024024e-05,
|
| 295 |
+
"loss": 0.0347,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.85,
|
| 300 |
+
"grad_norm": 0.7477858662605286,
|
| 301 |
+
"learning_rate": 3.986486486486487e-05,
|
| 302 |
+
"loss": 0.1399,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.87,
|
| 307 |
+
"grad_norm": 7.963656425476074,
|
| 308 |
+
"learning_rate": 3.948948948948949e-05,
|
| 309 |
+
"loss": 0.09,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.89,
|
| 314 |
+
"grad_norm": 0.43208637833595276,
|
| 315 |
+
"learning_rate": 3.911411411411411e-05,
|
| 316 |
+
"loss": 0.1049,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.91,
|
| 321 |
+
"grad_norm": 5.871271133422852,
|
| 322 |
+
"learning_rate": 3.873873873873874e-05,
|
| 323 |
+
"loss": 0.322,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.93,
|
| 328 |
+
"grad_norm": 0.027932079508900642,
|
| 329 |
+
"learning_rate": 3.836336336336336e-05,
|
| 330 |
+
"loss": 0.0024,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.95,
|
| 335 |
+
"grad_norm": 0.017657727003097534,
|
| 336 |
+
"learning_rate": 3.7987987987987985e-05,
|
| 337 |
+
"loss": 0.1332,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.97,
|
| 342 |
+
"grad_norm": 0.7482669949531555,
|
| 343 |
+
"learning_rate": 3.7612612612612614e-05,
|
| 344 |
+
"loss": 0.0361,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.99,
|
| 349 |
+
"grad_norm": 0.05272696912288666,
|
| 350 |
+
"learning_rate": 3.7237237237237236e-05,
|
| 351 |
+
"loss": 0.0071,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.0,
|
| 356 |
+
"eval_accuracy": 0.9954128440366973,
|
| 357 |
+
"eval_f1_macro": 0.9953370832314339,
|
| 358 |
+
"eval_f1_micro": 0.9954128440366973,
|
| 359 |
+
"eval_f1_weighted": 0.9954123953053728,
|
| 360 |
+
"eval_loss": 0.008562826551496983,
|
| 361 |
+
"eval_precision_macro": 0.9954337899543378,
|
| 362 |
+
"eval_precision_micro": 0.9954128440366973,
|
| 363 |
+
"eval_precision_weighted": 0.9954756817896192,
|
| 364 |
+
"eval_recall_macro": 0.9953051643192489,
|
| 365 |
+
"eval_recall_micro": 0.9954128440366973,
|
| 366 |
+
"eval_recall_weighted": 0.9954128440366973,
|
| 367 |
+
"eval_runtime": 61.5673,
|
| 368 |
+
"eval_samples_per_second": 3.541,
|
| 369 |
+
"eval_steps_per_second": 0.227,
|
| 370 |
+
"step": 247
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.01,
|
| 374 |
+
"grad_norm": 2.773138999938965,
|
| 375 |
+
"learning_rate": 3.6861861861861865e-05,
|
| 376 |
+
"loss": 0.257,
|
| 377 |
+
"step": 250
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.03,
|
| 381 |
+
"grad_norm": 4.275286674499512,
|
| 382 |
+
"learning_rate": 3.648648648648649e-05,
|
| 383 |
+
"loss": 0.382,
|
| 384 |
+
"step": 255
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.05,
|
| 388 |
+
"grad_norm": 24.60214614868164,
|
| 389 |
+
"learning_rate": 3.611111111111111e-05,
|
| 390 |
+
"loss": 0.3858,
|
| 391 |
+
"step": 260
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.07,
|
| 395 |
+
"grad_norm": 8.784448623657227,
|
| 396 |
+
"learning_rate": 3.573573573573574e-05,
|
| 397 |
+
"loss": 0.5298,
|
| 398 |
+
"step": 265
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.09,
|
| 402 |
+
"grad_norm": 1.1353392601013184,
|
| 403 |
+
"learning_rate": 3.536036036036036e-05,
|
| 404 |
+
"loss": 0.153,
|
| 405 |
+
"step": 270
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.11,
|
| 409 |
+
"grad_norm": 0.023551814258098602,
|
| 410 |
+
"learning_rate": 3.498498498498499e-05,
|
| 411 |
+
"loss": 0.0052,
|
| 412 |
+
"step": 275
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.13,
|
| 416 |
+
"grad_norm": 0.15712416172027588,
|
| 417 |
+
"learning_rate": 3.460960960960961e-05,
|
| 418 |
+
"loss": 0.3094,
|
| 419 |
+
"step": 280
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.15,
|
| 423 |
+
"grad_norm": 0.023001644760370255,
|
| 424 |
+
"learning_rate": 3.4234234234234234e-05,
|
| 425 |
+
"loss": 0.0407,
|
| 426 |
+
"step": 285
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.17,
|
| 430 |
+
"grad_norm": 0.011525897309184074,
|
| 431 |
+
"learning_rate": 3.385885885885886e-05,
|
| 432 |
+
"loss": 0.0422,
|
| 433 |
+
"step": 290
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.19,
|
| 437 |
+
"grad_norm": 0.9765132665634155,
|
| 438 |
+
"learning_rate": 3.3483483483483485e-05,
|
| 439 |
+
"loss": 0.1107,
|
| 440 |
+
"step": 295
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.21,
|
| 444 |
+
"grad_norm": 0.193386971950531,
|
| 445 |
+
"learning_rate": 3.310810810810811e-05,
|
| 446 |
+
"loss": 0.1098,
|
| 447 |
+
"step": 300
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.23,
|
| 451 |
+
"grad_norm": 0.0348842591047287,
|
| 452 |
+
"learning_rate": 3.2732732732732736e-05,
|
| 453 |
+
"loss": 0.0901,
|
| 454 |
+
"step": 305
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.26,
|
| 458 |
+
"grad_norm": 0.02413288690149784,
|
| 459 |
+
"learning_rate": 3.235735735735736e-05,
|
| 460 |
+
"loss": 0.0014,
|
| 461 |
+
"step": 310
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.28,
|
| 465 |
+
"grad_norm": 1.470839023590088,
|
| 466 |
+
"learning_rate": 3.198198198198199e-05,
|
| 467 |
+
"loss": 0.0368,
|
| 468 |
+
"step": 315
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.3,
|
| 472 |
+
"grad_norm": 0.6575441360473633,
|
| 473 |
+
"learning_rate": 3.160660660660661e-05,
|
| 474 |
+
"loss": 0.3384,
|
| 475 |
+
"step": 320
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.32,
|
| 479 |
+
"grad_norm": 0.11603262275457382,
|
| 480 |
+
"learning_rate": 3.123123123123123e-05,
|
| 481 |
+
"loss": 0.2287,
|
| 482 |
+
"step": 325
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.34,
|
| 486 |
+
"grad_norm": 0.09468206018209457,
|
| 487 |
+
"learning_rate": 3.085585585585586e-05,
|
| 488 |
+
"loss": 0.0053,
|
| 489 |
+
"step": 330
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.36,
|
| 493 |
+
"grad_norm": 0.18447920680046082,
|
| 494 |
+
"learning_rate": 3.0480480480480482e-05,
|
| 495 |
+
"loss": 0.0894,
|
| 496 |
+
"step": 335
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.38,
|
| 500 |
+
"grad_norm": 22.559310913085938,
|
| 501 |
+
"learning_rate": 3.0105105105105108e-05,
|
| 502 |
+
"loss": 0.2127,
|
| 503 |
+
"step": 340
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.4,
|
| 507 |
+
"grad_norm": 0.36875221133232117,
|
| 508 |
+
"learning_rate": 2.9729729729729733e-05,
|
| 509 |
+
"loss": 0.0123,
|
| 510 |
+
"step": 345
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.42,
|
| 514 |
+
"grad_norm": 0.3973434269428253,
|
| 515 |
+
"learning_rate": 2.935435435435436e-05,
|
| 516 |
+
"loss": 0.0268,
|
| 517 |
+
"step": 350
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.44,
|
| 521 |
+
"grad_norm": 0.054519250988960266,
|
| 522 |
+
"learning_rate": 2.897897897897898e-05,
|
| 523 |
+
"loss": 0.1053,
|
| 524 |
+
"step": 355
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.46,
|
| 528 |
+
"grad_norm": 5.856131076812744,
|
| 529 |
+
"learning_rate": 2.8603603603603606e-05,
|
| 530 |
+
"loss": 0.105,
|
| 531 |
+
"step": 360
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.48,
|
| 535 |
+
"grad_norm": 2.6053731441497803,
|
| 536 |
+
"learning_rate": 2.8228228228228232e-05,
|
| 537 |
+
"loss": 0.0072,
|
| 538 |
+
"step": 365
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.5,
|
| 542 |
+
"grad_norm": 14.849920272827148,
|
| 543 |
+
"learning_rate": 2.7852852852852857e-05,
|
| 544 |
+
"loss": 0.256,
|
| 545 |
+
"step": 370
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.52,
|
| 549 |
+
"grad_norm": 0.036322303116321564,
|
| 550 |
+
"learning_rate": 2.7477477477477483e-05,
|
| 551 |
+
"loss": 0.1195,
|
| 552 |
+
"step": 375
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.54,
|
| 556 |
+
"grad_norm": 7.0286431312561035,
|
| 557 |
+
"learning_rate": 2.7102102102102105e-05,
|
| 558 |
+
"loss": 0.2874,
|
| 559 |
+
"step": 380
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.56,
|
| 563 |
+
"grad_norm": 0.007908895611763,
|
| 564 |
+
"learning_rate": 2.672672672672673e-05,
|
| 565 |
+
"loss": 0.1749,
|
| 566 |
+
"step": 385
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.58,
|
| 570 |
+
"grad_norm": 0.2694431245326996,
|
| 571 |
+
"learning_rate": 2.635135135135135e-05,
|
| 572 |
+
"loss": 0.0078,
|
| 573 |
+
"step": 390
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.6,
|
| 577 |
+
"grad_norm": 14.261417388916016,
|
| 578 |
+
"learning_rate": 2.5975975975975975e-05,
|
| 579 |
+
"loss": 0.0251,
|
| 580 |
+
"step": 395
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.62,
|
| 584 |
+
"grad_norm": 0.8614434003829956,
|
| 585 |
+
"learning_rate": 2.56006006006006e-05,
|
| 586 |
+
"loss": 0.01,
|
| 587 |
+
"step": 400
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.64,
|
| 591 |
+
"grad_norm": 10.162217140197754,
|
| 592 |
+
"learning_rate": 2.5225225225225222e-05,
|
| 593 |
+
"loss": 0.0645,
|
| 594 |
+
"step": 405
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.66,
|
| 598 |
+
"grad_norm": 0.010031257756054401,
|
| 599 |
+
"learning_rate": 2.484984984984985e-05,
|
| 600 |
+
"loss": 0.1714,
|
| 601 |
+
"step": 410
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.68,
|
| 605 |
+
"grad_norm": 1.1147041320800781,
|
| 606 |
+
"learning_rate": 2.4474474474474477e-05,
|
| 607 |
+
"loss": 0.062,
|
| 608 |
+
"step": 415
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.7,
|
| 612 |
+
"grad_norm": 14.216385841369629,
|
| 613 |
+
"learning_rate": 2.4099099099099102e-05,
|
| 614 |
+
"loss": 0.2521,
|
| 615 |
+
"step": 420
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.72,
|
| 619 |
+
"grad_norm": 5.073903560638428,
|
| 620 |
+
"learning_rate": 2.3723723723723725e-05,
|
| 621 |
+
"loss": 0.1764,
|
| 622 |
+
"step": 425
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.74,
|
| 626 |
+
"grad_norm": 0.5860055088996887,
|
| 627 |
+
"learning_rate": 2.334834834834835e-05,
|
| 628 |
+
"loss": 0.0095,
|
| 629 |
+
"step": 430
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.76,
|
| 633 |
+
"grad_norm": 6.916937828063965,
|
| 634 |
+
"learning_rate": 2.2972972972972976e-05,
|
| 635 |
+
"loss": 0.2236,
|
| 636 |
+
"step": 435
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.78,
|
| 640 |
+
"grad_norm": 0.4593968689441681,
|
| 641 |
+
"learning_rate": 2.2597597597597598e-05,
|
| 642 |
+
"loss": 0.2062,
|
| 643 |
+
"step": 440
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.8,
|
| 647 |
+
"grad_norm": 10.855243682861328,
|
| 648 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 649 |
+
"loss": 0.0295,
|
| 650 |
+
"step": 445
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.82,
|
| 654 |
+
"grad_norm": 8.221331596374512,
|
| 655 |
+
"learning_rate": 2.1846846846846845e-05,
|
| 656 |
+
"loss": 0.2937,
|
| 657 |
+
"step": 450
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.84,
|
| 661 |
+
"grad_norm": 5.3991265296936035,
|
| 662 |
+
"learning_rate": 2.147147147147147e-05,
|
| 663 |
+
"loss": 0.1518,
|
| 664 |
+
"step": 455
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.86,
|
| 668 |
+
"grad_norm": 2.2880308628082275,
|
| 669 |
+
"learning_rate": 2.1096096096096096e-05,
|
| 670 |
+
"loss": 0.0107,
|
| 671 |
+
"step": 460
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.88,
|
| 675 |
+
"grad_norm": 0.38851749897003174,
|
| 676 |
+
"learning_rate": 2.0720720720720722e-05,
|
| 677 |
+
"loss": 0.0047,
|
| 678 |
+
"step": 465
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.9,
|
| 682 |
+
"grad_norm": 0.007677082903683186,
|
| 683 |
+
"learning_rate": 2.0345345345345344e-05,
|
| 684 |
+
"loss": 0.1443,
|
| 685 |
+
"step": 470
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.92,
|
| 689 |
+
"grad_norm": 0.004121085163205862,
|
| 690 |
+
"learning_rate": 1.996996996996997e-05,
|
| 691 |
+
"loss": 0.0866,
|
| 692 |
+
"step": 475
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.94,
|
| 696 |
+
"grad_norm": 4.384052276611328,
|
| 697 |
+
"learning_rate": 1.9594594594594595e-05,
|
| 698 |
+
"loss": 0.1988,
|
| 699 |
+
"step": 480
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.96,
|
| 703 |
+
"grad_norm": 13.786602973937988,
|
| 704 |
+
"learning_rate": 1.921921921921922e-05,
|
| 705 |
+
"loss": 0.2474,
|
| 706 |
+
"step": 485
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.98,
|
| 710 |
+
"grad_norm": 0.005240537691861391,
|
| 711 |
+
"learning_rate": 1.8843843843843846e-05,
|
| 712 |
+
"loss": 0.0088,
|
| 713 |
+
"step": 490
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.0,
|
| 717 |
+
"eval_accuracy": 1.0,
|
| 718 |
+
"eval_f1_macro": 1.0,
|
| 719 |
+
"eval_f1_micro": 1.0,
|
| 720 |
+
"eval_f1_weighted": 1.0,
|
| 721 |
+
"eval_loss": 0.0002666182699613273,
|
| 722 |
+
"eval_precision_macro": 1.0,
|
| 723 |
+
"eval_precision_micro": 1.0,
|
| 724 |
+
"eval_precision_weighted": 1.0,
|
| 725 |
+
"eval_recall_macro": 1.0,
|
| 726 |
+
"eval_recall_micro": 1.0,
|
| 727 |
+
"eval_recall_weighted": 1.0,
|
| 728 |
+
"eval_runtime": 57.4601,
|
| 729 |
+
"eval_samples_per_second": 3.794,
|
| 730 |
+
"eval_steps_per_second": 0.244,
|
| 731 |
+
"step": 494
|
| 732 |
+
}
|
| 733 |
+
],
|
| 734 |
+
"logging_steps": 5,
|
| 735 |
+
"max_steps": 741,
|
| 736 |
+
"num_input_tokens_seen": 0,
|
| 737 |
+
"num_train_epochs": 3,
|
| 738 |
+
"save_steps": 500,
|
| 739 |
+
"total_flos": 3.0532117555408896e+17,
|
| 740 |
+
"train_batch_size": 8,
|
| 741 |
+
"trial_name": null,
|
| 742 |
+
"trial_params": null
|
| 743 |
+
}
|
checkpoint-494/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eba6754d811577f53c39320d7cd3739ba0da6d17008290fce51faa263bf7ee4c
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 3,
|
| 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": "paper",
|
| 14 |
+
"1": "rock",
|
| 15 |
+
"2": "scissors"
|
| 16 |
+
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"paper": 0,
|
| 22 |
+
"rock": 1,
|
| 23 |
+
"scissors": 2
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"model_type": "vit",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_channels": 3,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"patch_size": 16,
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"qkv_bias": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.39.0"
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e975fa2899815bd2b1c1592f380ccc9e57f2a202d1fa85037aac37928e8713
|
| 3 |
+
size 343227052
|
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:eba6754d811577f53c39320d7cd3739ba0da6d17008290fce51faa263bf7ee4c
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-3b9gd-7t9lc/autotrain-data",
|
| 3 |
+
"model": "google/vit-base-patch16-224",
|
| 4 |
+
"username": "alien2048",
|
| 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-3b9gd-7t9lc",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": null,
|
| 21 |
+
"save_total_limit": 1,
|
| 22 |
+
"save_strategy": "epoch",
|
| 23 |
+
"push_to_hub": true,
|
| 24 |
+
"repo_id": "alien2048/autotrain-3b9gd-7t9lc",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "autotrain_image",
|
| 27 |
+
"target_column": "autotrain_label",
|
| 28 |
+
"log": "none"
|
| 29 |
+
}
|