Upload folder using huggingface_hub
Browse files- README.md +42 -0
- checkpoint-60/config.json +39 -0
- checkpoint-60/model.safetensors +3 -0
- checkpoint-60/optimizer.pt +3 -0
- checkpoint-60/rng_state.pth +3 -0
- checkpoint-60/scheduler.pt +3 -0
- checkpoint-60/trainer_state.json +711 -0
- checkpoint-60/training_args.bin +3 -0
- config.json +39 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -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-7pyp9-5fin2/autotrain-data
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metricsg
|
| 22 |
+
loss: 0.26788148283958435
|
| 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-60/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 5,
|
| 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": "calcetin",
|
| 14 |
+
"1": "camisa",
|
| 15 |
+
"2": "chaqueta",
|
| 16 |
+
"3": "pantalon",
|
| 17 |
+
"4": "vestido"
|
| 18 |
+
},
|
| 19 |
+
"image_size": 224,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"calcetin": 0,
|
| 24 |
+
"camisa": 1,
|
| 25 |
+
"chaqueta": 2,
|
| 26 |
+
"pantalon": 3,
|
| 27 |
+
"vestido": 4
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-12,
|
| 30 |
+
"model_type": "vit",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_channels": 3,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"patch_size": 16,
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"qkv_bias": true,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.38.1"
|
| 39 |
+
}
|
checkpoint-60/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8be692bdce769c2dac8b89145e22f7d1d4a861aa1f809403e2769901ea4c5817
|
| 3 |
+
size 343233204
|
checkpoint-60/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ee36207cafdba5e0c9d4cec9f7a6ba6cf735a7c4367d79523f78b3fafaccf74
|
| 3 |
+
size 686581690
|
checkpoint-60/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7fe7270b39d695527acad43e255827551756ddf01e691b03878945681278ac0
|
| 3 |
+
size 13990
|
checkpoint-60/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:974fb60062a9e094d57046984954545b807c1053a95415c6cb8cd6fd59c288ae
|
| 3 |
+
size 1064
|
checkpoint-60/trainer_state.json
ADDED
|
@@ -0,0 +1,711 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.26788148283958435,
|
| 3 |
+
"best_model_checkpoint": "autotrain-7pyp9-5fin2/checkpoint-60",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 60,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25,
|
| 13 |
+
"grad_norm": 9.696087837219238,
|
| 14 |
+
"learning_rate": 8.333333333333334e-06,
|
| 15 |
+
"loss": 1.6218,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5,
|
| 20 |
+
"grad_norm": 10.306160926818848,
|
| 21 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 22 |
+
"loss": 1.5261,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.75,
|
| 27 |
+
"grad_norm": 10.536490440368652,
|
| 28 |
+
"learning_rate": 2.5e-05,
|
| 29 |
+
"loss": 1.6076,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.0,
|
| 34 |
+
"grad_norm": 14.387479782104492,
|
| 35 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 36 |
+
"loss": 1.8423,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_accuracy": 0.2857142857142857,
|
| 42 |
+
"eval_f1_macro": 0.2333333333333333,
|
| 43 |
+
"eval_f1_micro": 0.2857142857142857,
|
| 44 |
+
"eval_f1_weighted": 0.23809523809523808,
|
| 45 |
+
"eval_loss": 1.4759962558746338,
|
| 46 |
+
"eval_precision_macro": 0.2,
|
| 47 |
+
"eval_precision_micro": 0.2857142857142857,
|
| 48 |
+
"eval_precision_weighted": 0.21428571428571427,
|
| 49 |
+
"eval_recall_macro": 0.3,
|
| 50 |
+
"eval_recall_micro": 0.2857142857142857,
|
| 51 |
+
"eval_recall_weighted": 0.2857142857142857,
|
| 52 |
+
"eval_runtime": 10.2566,
|
| 53 |
+
"eval_samples_per_second": 0.682,
|
| 54 |
+
"eval_steps_per_second": 0.097,
|
| 55 |
+
"step": 4
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.25,
|
| 59 |
+
"grad_norm": 10.712774276733398,
|
| 60 |
+
"learning_rate": 4.166666666666667e-05,
|
| 61 |
+
"loss": 1.4473,
|
| 62 |
+
"step": 5
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.5,
|
| 66 |
+
"grad_norm": 12.506595611572266,
|
| 67 |
+
"learning_rate": 5e-05,
|
| 68 |
+
"loss": 1.5484,
|
| 69 |
+
"step": 6
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.75,
|
| 73 |
+
"grad_norm": 9.017632484436035,
|
| 74 |
+
"learning_rate": 4.9074074074074075e-05,
|
| 75 |
+
"loss": 1.1466,
|
| 76 |
+
"step": 7
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.0,
|
| 80 |
+
"grad_norm": 13.27194595336914,
|
| 81 |
+
"learning_rate": 4.814814814814815e-05,
|
| 82 |
+
"loss": 1.582,
|
| 83 |
+
"step": 8
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.0,
|
| 87 |
+
"eval_accuracy": 0.5714285714285714,
|
| 88 |
+
"eval_f1_macro": 0.5666666666666667,
|
| 89 |
+
"eval_f1_micro": 0.5714285714285714,
|
| 90 |
+
"eval_f1_weighted": 0.49999999999999994,
|
| 91 |
+
"eval_loss": 1.188533902168274,
|
| 92 |
+
"eval_precision_macro": 0.5666666666666667,
|
| 93 |
+
"eval_precision_micro": 0.5714285714285714,
|
| 94 |
+
"eval_precision_weighted": 0.5476190476190476,
|
| 95 |
+
"eval_recall_macro": 0.7,
|
| 96 |
+
"eval_recall_micro": 0.5714285714285714,
|
| 97 |
+
"eval_recall_weighted": 0.5714285714285714,
|
| 98 |
+
"eval_runtime": 9.1717,
|
| 99 |
+
"eval_samples_per_second": 0.763,
|
| 100 |
+
"eval_steps_per_second": 0.109,
|
| 101 |
+
"step": 8
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.25,
|
| 105 |
+
"grad_norm": 8.264730453491211,
|
| 106 |
+
"learning_rate": 4.722222222222222e-05,
|
| 107 |
+
"loss": 0.989,
|
| 108 |
+
"step": 9
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.5,
|
| 112 |
+
"grad_norm": 9.464434623718262,
|
| 113 |
+
"learning_rate": 4.62962962962963e-05,
|
| 114 |
+
"loss": 1.1446,
|
| 115 |
+
"step": 10
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 2.75,
|
| 119 |
+
"grad_norm": 9.174596786499023,
|
| 120 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 121 |
+
"loss": 1.1437,
|
| 122 |
+
"step": 11
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.0,
|
| 126 |
+
"grad_norm": 8.549043655395508,
|
| 127 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 128 |
+
"loss": 0.7139,
|
| 129 |
+
"step": 12
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.0,
|
| 133 |
+
"eval_accuracy": 1.0,
|
| 134 |
+
"eval_f1_macro": 1.0,
|
| 135 |
+
"eval_f1_micro": 1.0,
|
| 136 |
+
"eval_f1_weighted": 1.0,
|
| 137 |
+
"eval_loss": 0.9490184187889099,
|
| 138 |
+
"eval_precision_macro": 1.0,
|
| 139 |
+
"eval_precision_micro": 1.0,
|
| 140 |
+
"eval_precision_weighted": 1.0,
|
| 141 |
+
"eval_recall_macro": 1.0,
|
| 142 |
+
"eval_recall_micro": 1.0,
|
| 143 |
+
"eval_recall_weighted": 1.0,
|
| 144 |
+
"eval_runtime": 10.7532,
|
| 145 |
+
"eval_samples_per_second": 0.651,
|
| 146 |
+
"eval_steps_per_second": 0.093,
|
| 147 |
+
"step": 12
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.25,
|
| 151 |
+
"grad_norm": 6.337627410888672,
|
| 152 |
+
"learning_rate": 4.351851851851852e-05,
|
| 153 |
+
"loss": 0.7327,
|
| 154 |
+
"step": 13
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.5,
|
| 158 |
+
"grad_norm": 7.614839553833008,
|
| 159 |
+
"learning_rate": 4.259259259259259e-05,
|
| 160 |
+
"loss": 0.7517,
|
| 161 |
+
"step": 14
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.75,
|
| 165 |
+
"grad_norm": 5.98110294342041,
|
| 166 |
+
"learning_rate": 4.166666666666667e-05,
|
| 167 |
+
"loss": 0.5506,
|
| 168 |
+
"step": 15
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 4.0,
|
| 172 |
+
"grad_norm": 10.03960132598877,
|
| 173 |
+
"learning_rate": 4.074074074074074e-05,
|
| 174 |
+
"loss": 0.7225,
|
| 175 |
+
"step": 16
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 4.0,
|
| 179 |
+
"eval_accuracy": 1.0,
|
| 180 |
+
"eval_f1_macro": 1.0,
|
| 181 |
+
"eval_f1_micro": 1.0,
|
| 182 |
+
"eval_f1_weighted": 1.0,
|
| 183 |
+
"eval_loss": 0.7890792489051819,
|
| 184 |
+
"eval_precision_macro": 1.0,
|
| 185 |
+
"eval_precision_micro": 1.0,
|
| 186 |
+
"eval_precision_weighted": 1.0,
|
| 187 |
+
"eval_recall_macro": 1.0,
|
| 188 |
+
"eval_recall_micro": 1.0,
|
| 189 |
+
"eval_recall_weighted": 1.0,
|
| 190 |
+
"eval_runtime": 10.5465,
|
| 191 |
+
"eval_samples_per_second": 0.664,
|
| 192 |
+
"eval_steps_per_second": 0.095,
|
| 193 |
+
"step": 16
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 4.25,
|
| 197 |
+
"grad_norm": 6.536053657531738,
|
| 198 |
+
"learning_rate": 3.981481481481482e-05,
|
| 199 |
+
"loss": 0.6645,
|
| 200 |
+
"step": 17
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.5,
|
| 204 |
+
"grad_norm": 4.258215427398682,
|
| 205 |
+
"learning_rate": 3.888888888888889e-05,
|
| 206 |
+
"loss": 0.4016,
|
| 207 |
+
"step": 18
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.75,
|
| 211 |
+
"grad_norm": 5.74752140045166,
|
| 212 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 213 |
+
"loss": 0.5753,
|
| 214 |
+
"step": 19
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 5.0,
|
| 218 |
+
"grad_norm": 9.975458145141602,
|
| 219 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 220 |
+
"loss": 0.5969,
|
| 221 |
+
"step": 20
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 5.0,
|
| 225 |
+
"eval_accuracy": 1.0,
|
| 226 |
+
"eval_f1_macro": 1.0,
|
| 227 |
+
"eval_f1_micro": 1.0,
|
| 228 |
+
"eval_f1_weighted": 1.0,
|
| 229 |
+
"eval_loss": 0.6536229252815247,
|
| 230 |
+
"eval_precision_macro": 1.0,
|
| 231 |
+
"eval_precision_micro": 1.0,
|
| 232 |
+
"eval_precision_weighted": 1.0,
|
| 233 |
+
"eval_recall_macro": 1.0,
|
| 234 |
+
"eval_recall_micro": 1.0,
|
| 235 |
+
"eval_recall_weighted": 1.0,
|
| 236 |
+
"eval_runtime": 10.0375,
|
| 237 |
+
"eval_samples_per_second": 0.697,
|
| 238 |
+
"eval_steps_per_second": 0.1,
|
| 239 |
+
"step": 20
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 5.25,
|
| 243 |
+
"grad_norm": 5.497837543487549,
|
| 244 |
+
"learning_rate": 3.611111111111111e-05,
|
| 245 |
+
"loss": 0.4362,
|
| 246 |
+
"step": 21
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.5,
|
| 250 |
+
"grad_norm": 4.085073947906494,
|
| 251 |
+
"learning_rate": 3.518518518518519e-05,
|
| 252 |
+
"loss": 0.3137,
|
| 253 |
+
"step": 22
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 5.75,
|
| 257 |
+
"grad_norm": 2.8543953895568848,
|
| 258 |
+
"learning_rate": 3.425925925925926e-05,
|
| 259 |
+
"loss": 0.2236,
|
| 260 |
+
"step": 23
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.0,
|
| 264 |
+
"grad_norm": 5.734010219573975,
|
| 265 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 266 |
+
"loss": 0.3182,
|
| 267 |
+
"step": 24
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 6.0,
|
| 271 |
+
"eval_accuracy": 1.0,
|
| 272 |
+
"eval_f1_macro": 1.0,
|
| 273 |
+
"eval_f1_micro": 1.0,
|
| 274 |
+
"eval_f1_weighted": 1.0,
|
| 275 |
+
"eval_loss": 0.5447709560394287,
|
| 276 |
+
"eval_precision_macro": 1.0,
|
| 277 |
+
"eval_precision_micro": 1.0,
|
| 278 |
+
"eval_precision_weighted": 1.0,
|
| 279 |
+
"eval_recall_macro": 1.0,
|
| 280 |
+
"eval_recall_micro": 1.0,
|
| 281 |
+
"eval_recall_weighted": 1.0,
|
| 282 |
+
"eval_runtime": 8.8115,
|
| 283 |
+
"eval_samples_per_second": 0.794,
|
| 284 |
+
"eval_steps_per_second": 0.113,
|
| 285 |
+
"step": 24
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 6.25,
|
| 289 |
+
"grad_norm": 3.954059600830078,
|
| 290 |
+
"learning_rate": 3.240740740740741e-05,
|
| 291 |
+
"loss": 0.2692,
|
| 292 |
+
"step": 25
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 6.5,
|
| 296 |
+
"grad_norm": 3.87939190864563,
|
| 297 |
+
"learning_rate": 3.148148148148148e-05,
|
| 298 |
+
"loss": 0.3134,
|
| 299 |
+
"step": 26
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 6.75,
|
| 303 |
+
"grad_norm": 3.0751078128814697,
|
| 304 |
+
"learning_rate": 3.055555555555556e-05,
|
| 305 |
+
"loss": 0.2339,
|
| 306 |
+
"step": 27
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 7.0,
|
| 310 |
+
"grad_norm": 5.125020980834961,
|
| 311 |
+
"learning_rate": 2.962962962962963e-05,
|
| 312 |
+
"loss": 0.2783,
|
| 313 |
+
"step": 28
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 7.0,
|
| 317 |
+
"eval_accuracy": 1.0,
|
| 318 |
+
"eval_f1_macro": 1.0,
|
| 319 |
+
"eval_f1_micro": 1.0,
|
| 320 |
+
"eval_f1_weighted": 1.0,
|
| 321 |
+
"eval_loss": 0.45870572328567505,
|
| 322 |
+
"eval_precision_macro": 1.0,
|
| 323 |
+
"eval_precision_micro": 1.0,
|
| 324 |
+
"eval_precision_weighted": 1.0,
|
| 325 |
+
"eval_recall_macro": 1.0,
|
| 326 |
+
"eval_recall_micro": 1.0,
|
| 327 |
+
"eval_recall_weighted": 1.0,
|
| 328 |
+
"eval_runtime": 9.8873,
|
| 329 |
+
"eval_samples_per_second": 0.708,
|
| 330 |
+
"eval_steps_per_second": 0.101,
|
| 331 |
+
"step": 28
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.25,
|
| 335 |
+
"grad_norm": 3.748976469039917,
|
| 336 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 337 |
+
"loss": 0.257,
|
| 338 |
+
"step": 29
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.5,
|
| 342 |
+
"grad_norm": 2.7245848178863525,
|
| 343 |
+
"learning_rate": 2.777777777777778e-05,
|
| 344 |
+
"loss": 0.1804,
|
| 345 |
+
"step": 30
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.75,
|
| 349 |
+
"grad_norm": 4.93157958984375,
|
| 350 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 351 |
+
"loss": 0.3459,
|
| 352 |
+
"step": 31
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 8.0,
|
| 356 |
+
"grad_norm": 2.705587863922119,
|
| 357 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 358 |
+
"loss": 0.1309,
|
| 359 |
+
"step": 32
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.0,
|
| 363 |
+
"eval_accuracy": 1.0,
|
| 364 |
+
"eval_f1_macro": 1.0,
|
| 365 |
+
"eval_f1_micro": 1.0,
|
| 366 |
+
"eval_f1_weighted": 1.0,
|
| 367 |
+
"eval_loss": 0.3977826237678528,
|
| 368 |
+
"eval_precision_macro": 1.0,
|
| 369 |
+
"eval_precision_micro": 1.0,
|
| 370 |
+
"eval_precision_weighted": 1.0,
|
| 371 |
+
"eval_recall_macro": 1.0,
|
| 372 |
+
"eval_recall_micro": 1.0,
|
| 373 |
+
"eval_recall_weighted": 1.0,
|
| 374 |
+
"eval_runtime": 10.2924,
|
| 375 |
+
"eval_samples_per_second": 0.68,
|
| 376 |
+
"eval_steps_per_second": 0.097,
|
| 377 |
+
"step": 32
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 8.25,
|
| 381 |
+
"grad_norm": 3.3278110027313232,
|
| 382 |
+
"learning_rate": 2.5e-05,
|
| 383 |
+
"loss": 0.1971,
|
| 384 |
+
"step": 33
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.5,
|
| 388 |
+
"grad_norm": 4.389842510223389,
|
| 389 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 390 |
+
"loss": 0.2652,
|
| 391 |
+
"step": 34
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 8.75,
|
| 395 |
+
"grad_norm": 3.1025760173797607,
|
| 396 |
+
"learning_rate": 2.314814814814815e-05,
|
| 397 |
+
"loss": 0.2182,
|
| 398 |
+
"step": 35
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 9.0,
|
| 402 |
+
"grad_norm": 6.207980632781982,
|
| 403 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 404 |
+
"loss": 0.2985,
|
| 405 |
+
"step": 36
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 9.0,
|
| 409 |
+
"eval_accuracy": 1.0,
|
| 410 |
+
"eval_f1_macro": 1.0,
|
| 411 |
+
"eval_f1_micro": 1.0,
|
| 412 |
+
"eval_f1_weighted": 1.0,
|
| 413 |
+
"eval_loss": 0.3642716109752655,
|
| 414 |
+
"eval_precision_macro": 1.0,
|
| 415 |
+
"eval_precision_micro": 1.0,
|
| 416 |
+
"eval_precision_weighted": 1.0,
|
| 417 |
+
"eval_recall_macro": 1.0,
|
| 418 |
+
"eval_recall_micro": 1.0,
|
| 419 |
+
"eval_recall_weighted": 1.0,
|
| 420 |
+
"eval_runtime": 9.4469,
|
| 421 |
+
"eval_samples_per_second": 0.741,
|
| 422 |
+
"eval_steps_per_second": 0.106,
|
| 423 |
+
"step": 36
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 9.25,
|
| 427 |
+
"grad_norm": 2.031935453414917,
|
| 428 |
+
"learning_rate": 2.1296296296296296e-05,
|
| 429 |
+
"loss": 0.1189,
|
| 430 |
+
"step": 37
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 9.5,
|
| 434 |
+
"grad_norm": 2.120398759841919,
|
| 435 |
+
"learning_rate": 2.037037037037037e-05,
|
| 436 |
+
"loss": 0.1298,
|
| 437 |
+
"step": 38
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 9.75,
|
| 441 |
+
"grad_norm": 2.0307655334472656,
|
| 442 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 443 |
+
"loss": 0.1268,
|
| 444 |
+
"step": 39
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.0,
|
| 448 |
+
"grad_norm": 0.8479315638542175,
|
| 449 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 450 |
+
"loss": 0.0475,
|
| 451 |
+
"step": 40
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 10.0,
|
| 455 |
+
"eval_accuracy": 1.0,
|
| 456 |
+
"eval_f1_macro": 1.0,
|
| 457 |
+
"eval_f1_micro": 1.0,
|
| 458 |
+
"eval_f1_weighted": 1.0,
|
| 459 |
+
"eval_loss": 0.3392049968242645,
|
| 460 |
+
"eval_precision_macro": 1.0,
|
| 461 |
+
"eval_precision_micro": 1.0,
|
| 462 |
+
"eval_precision_weighted": 1.0,
|
| 463 |
+
"eval_recall_macro": 1.0,
|
| 464 |
+
"eval_recall_micro": 1.0,
|
| 465 |
+
"eval_recall_weighted": 1.0,
|
| 466 |
+
"eval_runtime": 7.7433,
|
| 467 |
+
"eval_samples_per_second": 0.904,
|
| 468 |
+
"eval_steps_per_second": 0.129,
|
| 469 |
+
"step": 40
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 10.25,
|
| 473 |
+
"grad_norm": 2.031165361404419,
|
| 474 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 475 |
+
"loss": 0.1097,
|
| 476 |
+
"step": 41
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 10.5,
|
| 480 |
+
"grad_norm": 3.5009922981262207,
|
| 481 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 482 |
+
"loss": 0.2108,
|
| 483 |
+
"step": 42
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 10.75,
|
| 487 |
+
"grad_norm": 2.418134927749634,
|
| 488 |
+
"learning_rate": 1.574074074074074e-05,
|
| 489 |
+
"loss": 0.1351,
|
| 490 |
+
"step": 43
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 11.0,
|
| 494 |
+
"grad_norm": 2.964043617248535,
|
| 495 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 496 |
+
"loss": 0.1048,
|
| 497 |
+
"step": 44
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 11.0,
|
| 501 |
+
"eval_accuracy": 1.0,
|
| 502 |
+
"eval_f1_macro": 1.0,
|
| 503 |
+
"eval_f1_micro": 1.0,
|
| 504 |
+
"eval_f1_weighted": 1.0,
|
| 505 |
+
"eval_loss": 0.31069040298461914,
|
| 506 |
+
"eval_precision_macro": 1.0,
|
| 507 |
+
"eval_precision_micro": 1.0,
|
| 508 |
+
"eval_precision_weighted": 1.0,
|
| 509 |
+
"eval_recall_macro": 1.0,
|
| 510 |
+
"eval_recall_micro": 1.0,
|
| 511 |
+
"eval_recall_weighted": 1.0,
|
| 512 |
+
"eval_runtime": 12.0672,
|
| 513 |
+
"eval_samples_per_second": 0.58,
|
| 514 |
+
"eval_steps_per_second": 0.083,
|
| 515 |
+
"step": 44
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 11.25,
|
| 519 |
+
"grad_norm": 1.4578193426132202,
|
| 520 |
+
"learning_rate": 1.388888888888889e-05,
|
| 521 |
+
"loss": 0.09,
|
| 522 |
+
"step": 45
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 11.5,
|
| 526 |
+
"grad_norm": 1.4886540174484253,
|
| 527 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 528 |
+
"loss": 0.0873,
|
| 529 |
+
"step": 46
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 11.75,
|
| 533 |
+
"grad_norm": 4.489426612854004,
|
| 534 |
+
"learning_rate": 1.2037037037037037e-05,
|
| 535 |
+
"loss": 0.244,
|
| 536 |
+
"step": 47
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 12.0,
|
| 540 |
+
"grad_norm": 7.104702949523926,
|
| 541 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 542 |
+
"loss": 0.2115,
|
| 543 |
+
"step": 48
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 12.0,
|
| 547 |
+
"eval_accuracy": 1.0,
|
| 548 |
+
"eval_f1_macro": 1.0,
|
| 549 |
+
"eval_f1_micro": 1.0,
|
| 550 |
+
"eval_f1_weighted": 1.0,
|
| 551 |
+
"eval_loss": 0.2882018983364105,
|
| 552 |
+
"eval_precision_macro": 1.0,
|
| 553 |
+
"eval_precision_micro": 1.0,
|
| 554 |
+
"eval_precision_weighted": 1.0,
|
| 555 |
+
"eval_recall_macro": 1.0,
|
| 556 |
+
"eval_recall_micro": 1.0,
|
| 557 |
+
"eval_recall_weighted": 1.0,
|
| 558 |
+
"eval_runtime": 6.9001,
|
| 559 |
+
"eval_samples_per_second": 1.014,
|
| 560 |
+
"eval_steps_per_second": 0.145,
|
| 561 |
+
"step": 48
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 12.25,
|
| 565 |
+
"grad_norm": 2.515641927719116,
|
| 566 |
+
"learning_rate": 1.0185185185185185e-05,
|
| 567 |
+
"loss": 0.103,
|
| 568 |
+
"step": 49
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 12.5,
|
| 572 |
+
"grad_norm": 0.9495440721511841,
|
| 573 |
+
"learning_rate": 9.259259259259259e-06,
|
| 574 |
+
"loss": 0.06,
|
| 575 |
+
"step": 50
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 12.75,
|
| 579 |
+
"grad_norm": 1.0977874994277954,
|
| 580 |
+
"learning_rate": 8.333333333333334e-06,
|
| 581 |
+
"loss": 0.0636,
|
| 582 |
+
"step": 51
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 13.0,
|
| 586 |
+
"grad_norm": 0.6637537479400635,
|
| 587 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 588 |
+
"loss": 0.0286,
|
| 589 |
+
"step": 52
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 13.0,
|
| 593 |
+
"eval_accuracy": 1.0,
|
| 594 |
+
"eval_f1_macro": 1.0,
|
| 595 |
+
"eval_f1_micro": 1.0,
|
| 596 |
+
"eval_f1_weighted": 1.0,
|
| 597 |
+
"eval_loss": 0.27626922726631165,
|
| 598 |
+
"eval_precision_macro": 1.0,
|
| 599 |
+
"eval_precision_micro": 1.0,
|
| 600 |
+
"eval_precision_weighted": 1.0,
|
| 601 |
+
"eval_recall_macro": 1.0,
|
| 602 |
+
"eval_recall_micro": 1.0,
|
| 603 |
+
"eval_recall_weighted": 1.0,
|
| 604 |
+
"eval_runtime": 11.2321,
|
| 605 |
+
"eval_samples_per_second": 0.623,
|
| 606 |
+
"eval_steps_per_second": 0.089,
|
| 607 |
+
"step": 52
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 13.25,
|
| 611 |
+
"grad_norm": 1.2230528593063354,
|
| 612 |
+
"learning_rate": 6.481481481481481e-06,
|
| 613 |
+
"loss": 0.0676,
|
| 614 |
+
"step": 53
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 13.5,
|
| 618 |
+
"grad_norm": 2.4814634323120117,
|
| 619 |
+
"learning_rate": 5.555555555555556e-06,
|
| 620 |
+
"loss": 0.1172,
|
| 621 |
+
"step": 54
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 13.75,
|
| 625 |
+
"grad_norm": 0.5611864328384399,
|
| 626 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 627 |
+
"loss": 0.0363,
|
| 628 |
+
"step": 55
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 14.0,
|
| 632 |
+
"grad_norm": 1.0584659576416016,
|
| 633 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 634 |
+
"loss": 0.0455,
|
| 635 |
+
"step": 56
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 14.0,
|
| 639 |
+
"eval_accuracy": 1.0,
|
| 640 |
+
"eval_f1_macro": 1.0,
|
| 641 |
+
"eval_f1_micro": 1.0,
|
| 642 |
+
"eval_f1_weighted": 1.0,
|
| 643 |
+
"eval_loss": 0.27015116810798645,
|
| 644 |
+
"eval_precision_macro": 1.0,
|
| 645 |
+
"eval_precision_micro": 1.0,
|
| 646 |
+
"eval_precision_weighted": 1.0,
|
| 647 |
+
"eval_recall_macro": 1.0,
|
| 648 |
+
"eval_recall_micro": 1.0,
|
| 649 |
+
"eval_recall_weighted": 1.0,
|
| 650 |
+
"eval_runtime": 10.6957,
|
| 651 |
+
"eval_samples_per_second": 0.654,
|
| 652 |
+
"eval_steps_per_second": 0.093,
|
| 653 |
+
"step": 56
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 14.25,
|
| 657 |
+
"grad_norm": 1.4141819477081299,
|
| 658 |
+
"learning_rate": 2.777777777777778e-06,
|
| 659 |
+
"loss": 0.068,
|
| 660 |
+
"step": 57
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 14.5,
|
| 664 |
+
"grad_norm": 0.8392394781112671,
|
| 665 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 666 |
+
"loss": 0.0545,
|
| 667 |
+
"step": 58
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 14.75,
|
| 671 |
+
"grad_norm": 1.3628590106964111,
|
| 672 |
+
"learning_rate": 9.259259259259259e-07,
|
| 673 |
+
"loss": 0.0644,
|
| 674 |
+
"step": 59
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 15.0,
|
| 678 |
+
"grad_norm": 1.1704597473144531,
|
| 679 |
+
"learning_rate": 0.0,
|
| 680 |
+
"loss": 0.0503,
|
| 681 |
+
"step": 60
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 15.0,
|
| 685 |
+
"eval_accuracy": 1.0,
|
| 686 |
+
"eval_f1_macro": 1.0,
|
| 687 |
+
"eval_f1_micro": 1.0,
|
| 688 |
+
"eval_f1_weighted": 1.0,
|
| 689 |
+
"eval_loss": 0.26788148283958435,
|
| 690 |
+
"eval_precision_macro": 1.0,
|
| 691 |
+
"eval_precision_micro": 1.0,
|
| 692 |
+
"eval_precision_weighted": 1.0,
|
| 693 |
+
"eval_recall_macro": 1.0,
|
| 694 |
+
"eval_recall_micro": 1.0,
|
| 695 |
+
"eval_recall_weighted": 1.0,
|
| 696 |
+
"eval_runtime": 9.3784,
|
| 697 |
+
"eval_samples_per_second": 0.746,
|
| 698 |
+
"eval_steps_per_second": 0.107,
|
| 699 |
+
"step": 60
|
| 700 |
+
}
|
| 701 |
+
],
|
| 702 |
+
"logging_steps": 1,
|
| 703 |
+
"max_steps": 60,
|
| 704 |
+
"num_input_tokens_seen": 0,
|
| 705 |
+
"num_train_epochs": 15,
|
| 706 |
+
"save_steps": 500,
|
| 707 |
+
"total_flos": 3.254751075373056e+16,
|
| 708 |
+
"train_batch_size": 8,
|
| 709 |
+
"trial_name": null,
|
| 710 |
+
"trial_params": null
|
| 711 |
+
}
|
checkpoint-60/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1c25b9ff5c4f73a1504132fbe92f8bf1cd0a75080019e66b8605f7e0c88ed80
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 5,
|
| 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": "calcetin",
|
| 14 |
+
"1": "camisa",
|
| 15 |
+
"2": "chaqueta",
|
| 16 |
+
"3": "pantalon",
|
| 17 |
+
"4": "vestido"
|
| 18 |
+
},
|
| 19 |
+
"image_size": 224,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"calcetin": 0,
|
| 24 |
+
"camisa": 1,
|
| 25 |
+
"chaqueta": 2,
|
| 26 |
+
"pantalon": 3,
|
| 27 |
+
"vestido": 4
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-12,
|
| 30 |
+
"model_type": "vit",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_channels": 3,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"patch_size": 16,
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"qkv_bias": true,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.38.1"
|
| 39 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8be692bdce769c2dac8b89145e22f7d1d4a861aa1f809403e2769901ea4c5817
|
| 3 |
+
size 343233204
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1c25b9ff5c4f73a1504132fbe92f8bf1cd0a75080019e66b8605f7e0c88ed80
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-7pyp9-5fin2/autotrain-data",
|
| 3 |
+
"model": "google/vit-base-patch16-224",
|
| 4 |
+
"username": "yuleysi",
|
| 5 |
+
"lr": 5e-05,
|
| 6 |
+
"epochs": 15,
|
| 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-7pyp9-5fin2",
|
| 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": "yuleysi/autotrain-7pyp9-5fin2",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "autotrain_image",
|
| 27 |
+
"target_column": "autotrain_label",
|
| 28 |
+
"log": "none"
|
| 29 |
+
}
|