Upload folder using huggingface_hub
Browse files- README.md +41 -0
- checkpoint-168/config.json +35 -0
- checkpoint-168/model.safetensors +3 -0
- checkpoint-168/optimizer.pt +3 -0
- checkpoint-168/rng_state.pth +3 -0
- checkpoint-168/scheduler.pt +3 -0
- checkpoint-168/trainer_state.json +1470 -0
- checkpoint-168/training_args.bin +3 -0
- config.json +35 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Aug07_15-10-44_5a39e86fee3e/events.out.tfevents.1723043445.5a39e86fee3e.8439.0 +2 -2
- runs/Aug07_15-10-44_5a39e86fee3e/events.out.tfevents.1723043814.5a39e86fee3e.8439.1 +3 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- image-classification
|
| 6 |
+
base_model: google/vit-base-patch16-224
|
| 7 |
+
widget:
|
| 8 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
| 9 |
+
example_title: Tiger
|
| 10 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
| 11 |
+
example_title: Teapot
|
| 12 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
| 13 |
+
example_title: Palace
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# Model Trained Using AutoTrain
|
| 17 |
+
|
| 18 |
+
- Problem type: Image Classification
|
| 19 |
+
|
| 20 |
+
## Validation Metrics
|
| 21 |
+
loss: 0.004509058315306902
|
| 22 |
+
|
| 23 |
+
f1_macro: 1.0
|
| 24 |
+
|
| 25 |
+
f1_micro: 1.0
|
| 26 |
+
|
| 27 |
+
f1_weighted: 1.0
|
| 28 |
+
|
| 29 |
+
precision_macro: 1.0
|
| 30 |
+
|
| 31 |
+
precision_micro: 1.0
|
| 32 |
+
|
| 33 |
+
precision_weighted: 1.0
|
| 34 |
+
|
| 35 |
+
recall_macro: 1.0
|
| 36 |
+
|
| 37 |
+
recall_micro: 1.0
|
| 38 |
+
|
| 39 |
+
recall_weighted: 1.0
|
| 40 |
+
|
| 41 |
+
accuracy: 1.0
|
checkpoint-168/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": "BRVO",
|
| 14 |
+
"1": "DR2",
|
| 15 |
+
"2": "Normal"
|
| 16 |
+
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"BRVO": 0,
|
| 22 |
+
"DR2": 1,
|
| 23 |
+
"Normal": 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": "4.43.1"
|
| 35 |
+
}
|
checkpoint-168/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f81e44ad73aeace0af102c964f82a042668dc7efe78a3a379453382e4e3859ec
|
| 3 |
+
size 343227052
|
checkpoint-168/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8857d6414d61d7c4f0b0e13887a41d3e0765f7706b268ae0c7f08ecd63a14e21
|
| 3 |
+
size 686575034
|
checkpoint-168/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7440266609d5de99cd629304d7e75a20d2fef4bf2b198c869b3a5ce43cc8911d
|
| 3 |
+
size 14244
|
checkpoint-168/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4369253a549f99d3ca9160cc5d27060daf19d5fe133ed60970aa8d09664e1ae
|
| 3 |
+
size 1064
|
checkpoint-168/trainer_state.json
ADDED
|
@@ -0,0 +1,1470 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.004509058315306902,
|
| 3 |
+
"best_model_checkpoint": "autotrain-8oqr6-image0807-20/checkpoint-168",
|
| 4 |
+
"epoch": 14.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 168,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08333333333333333,
|
| 13 |
+
"grad_norm": Infinity,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"loss": 1.5603,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16666666666666666,
|
| 20 |
+
"grad_norm": 12.834511756896973,
|
| 21 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 22 |
+
"loss": 1.3929,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.25,
|
| 27 |
+
"grad_norm": 14.02276611328125,
|
| 28 |
+
"learning_rate": 4.166666666666667e-06,
|
| 29 |
+
"loss": 1.4694,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3333333333333333,
|
| 34 |
+
"grad_norm": 8.786632537841797,
|
| 35 |
+
"learning_rate": 6.25e-06,
|
| 36 |
+
"loss": 1.131,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4166666666666667,
|
| 41 |
+
"grad_norm": 8.789505004882812,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 1.0679,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5,
|
| 48 |
+
"grad_norm": 14.320700645446777,
|
| 49 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 50 |
+
"loss": 1.4058,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5833333333333334,
|
| 55 |
+
"grad_norm": 8.472625732421875,
|
| 56 |
+
"learning_rate": 1.25e-05,
|
| 57 |
+
"loss": 1.0877,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6666666666666666,
|
| 62 |
+
"grad_norm": 7.7828569412231445,
|
| 63 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 64 |
+
"loss": 1.0601,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.75,
|
| 69 |
+
"grad_norm": 7.590905666351318,
|
| 70 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 71 |
+
"loss": 0.8311,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8333333333333334,
|
| 76 |
+
"grad_norm": 7.066843509674072,
|
| 77 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 78 |
+
"loss": 0.7218,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.9166666666666666,
|
| 83 |
+
"grad_norm": 9.683036804199219,
|
| 84 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 85 |
+
"loss": 1.1176,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"grad_norm": 11.81384563446045,
|
| 91 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 92 |
+
"loss": 0.8141,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"eval_accuracy": 0.44,
|
| 98 |
+
"eval_f1_macro": 0.3730639730639731,
|
| 99 |
+
"eval_f1_micro": 0.44,
|
| 100 |
+
"eval_f1_weighted": 0.3794747474747474,
|
| 101 |
+
"eval_loss": 0.9374414086341858,
|
| 102 |
+
"eval_precision_macro": 0.6825396825396824,
|
| 103 |
+
"eval_precision_micro": 0.44,
|
| 104 |
+
"eval_precision_weighted": 0.6704761904761903,
|
| 105 |
+
"eval_recall_macro": 0.4212962962962963,
|
| 106 |
+
"eval_recall_micro": 0.44,
|
| 107 |
+
"eval_recall_weighted": 0.44,
|
| 108 |
+
"eval_runtime": 3.5485,
|
| 109 |
+
"eval_samples_per_second": 7.045,
|
| 110 |
+
"eval_steps_per_second": 0.564,
|
| 111 |
+
"step": 12
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.0833333333333333,
|
| 115 |
+
"grad_norm": 8.487566947937012,
|
| 116 |
+
"learning_rate": 2.5e-05,
|
| 117 |
+
"loss": 0.8732,
|
| 118 |
+
"step": 13
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.1666666666666667,
|
| 122 |
+
"grad_norm": 9.960497856140137,
|
| 123 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 124 |
+
"loss": 0.9684,
|
| 125 |
+
"step": 14
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.25,
|
| 129 |
+
"grad_norm": 11.692998886108398,
|
| 130 |
+
"learning_rate": 2.916666666666667e-05,
|
| 131 |
+
"loss": 1.019,
|
| 132 |
+
"step": 15
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.3333333333333333,
|
| 136 |
+
"grad_norm": 8.928894996643066,
|
| 137 |
+
"learning_rate": 3.125e-05,
|
| 138 |
+
"loss": 0.8229,
|
| 139 |
+
"step": 16
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.4166666666666667,
|
| 143 |
+
"grad_norm": 6.653351306915283,
|
| 144 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 145 |
+
"loss": 0.7085,
|
| 146 |
+
"step": 17
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.5,
|
| 150 |
+
"grad_norm": 8.878649711608887,
|
| 151 |
+
"learning_rate": 3.541666666666667e-05,
|
| 152 |
+
"loss": 0.8582,
|
| 153 |
+
"step": 18
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.5833333333333335,
|
| 157 |
+
"grad_norm": 11.552042007446289,
|
| 158 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 159 |
+
"loss": 0.8241,
|
| 160 |
+
"step": 19
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.6666666666666665,
|
| 164 |
+
"grad_norm": 7.981046676635742,
|
| 165 |
+
"learning_rate": 3.958333333333333e-05,
|
| 166 |
+
"loss": 0.6277,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.75,
|
| 171 |
+
"grad_norm": 6.3088059425354,
|
| 172 |
+
"learning_rate": 4.166666666666667e-05,
|
| 173 |
+
"loss": 0.7445,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.8333333333333335,
|
| 178 |
+
"grad_norm": 9.09092903137207,
|
| 179 |
+
"learning_rate": 4.375e-05,
|
| 180 |
+
"loss": 0.5661,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.9166666666666665,
|
| 185 |
+
"grad_norm": 11.548644065856934,
|
| 186 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 187 |
+
"loss": 0.7331,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.0,
|
| 192 |
+
"grad_norm": 7.976438999176025,
|
| 193 |
+
"learning_rate": 4.791666666666667e-05,
|
| 194 |
+
"loss": 0.3373,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.0,
|
| 199 |
+
"eval_accuracy": 0.92,
|
| 200 |
+
"eval_f1_macro": 0.9212962962962963,
|
| 201 |
+
"eval_f1_micro": 0.92,
|
| 202 |
+
"eval_f1_weighted": 0.9194444444444444,
|
| 203 |
+
"eval_loss": 0.45741942524909973,
|
| 204 |
+
"eval_precision_macro": 0.9333333333333332,
|
| 205 |
+
"eval_precision_micro": 0.92,
|
| 206 |
+
"eval_precision_weighted": 0.9359999999999999,
|
| 207 |
+
"eval_recall_macro": 0.9259259259259259,
|
| 208 |
+
"eval_recall_micro": 0.92,
|
| 209 |
+
"eval_recall_weighted": 0.92,
|
| 210 |
+
"eval_runtime": 3.3749,
|
| 211 |
+
"eval_samples_per_second": 7.408,
|
| 212 |
+
"eval_steps_per_second": 0.593,
|
| 213 |
+
"step": 24
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.0833333333333335,
|
| 217 |
+
"grad_norm": 5.952542304992676,
|
| 218 |
+
"learning_rate": 5e-05,
|
| 219 |
+
"loss": 0.3945,
|
| 220 |
+
"step": 25
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.1666666666666665,
|
| 224 |
+
"grad_norm": 6.794156551361084,
|
| 225 |
+
"learning_rate": 4.976851851851852e-05,
|
| 226 |
+
"loss": 0.3153,
|
| 227 |
+
"step": 26
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.25,
|
| 231 |
+
"grad_norm": 5.6115498542785645,
|
| 232 |
+
"learning_rate": 4.9537037037037035e-05,
|
| 233 |
+
"loss": 0.3932,
|
| 234 |
+
"step": 27
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.3333333333333335,
|
| 238 |
+
"grad_norm": 12.02769947052002,
|
| 239 |
+
"learning_rate": 4.930555555555556e-05,
|
| 240 |
+
"loss": 0.5081,
|
| 241 |
+
"step": 28
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.4166666666666665,
|
| 245 |
+
"grad_norm": 5.4335479736328125,
|
| 246 |
+
"learning_rate": 4.9074074074074075e-05,
|
| 247 |
+
"loss": 0.2765,
|
| 248 |
+
"step": 29
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.5,
|
| 252 |
+
"grad_norm": 4.830887317657471,
|
| 253 |
+
"learning_rate": 4.8842592592592595e-05,
|
| 254 |
+
"loss": 0.2758,
|
| 255 |
+
"step": 30
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.5833333333333335,
|
| 259 |
+
"grad_norm": 5.837632656097412,
|
| 260 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 261 |
+
"loss": 0.3722,
|
| 262 |
+
"step": 31
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.6666666666666665,
|
| 266 |
+
"grad_norm": 4.3202433586120605,
|
| 267 |
+
"learning_rate": 4.837962962962963e-05,
|
| 268 |
+
"loss": 0.1471,
|
| 269 |
+
"step": 32
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.75,
|
| 273 |
+
"grad_norm": 7.924596786499023,
|
| 274 |
+
"learning_rate": 4.814814814814815e-05,
|
| 275 |
+
"loss": 0.3441,
|
| 276 |
+
"step": 33
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.8333333333333335,
|
| 280 |
+
"grad_norm": 11.923328399658203,
|
| 281 |
+
"learning_rate": 4.791666666666667e-05,
|
| 282 |
+
"loss": 0.4311,
|
| 283 |
+
"step": 34
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.9166666666666665,
|
| 287 |
+
"grad_norm": 4.268110752105713,
|
| 288 |
+
"learning_rate": 4.768518518518519e-05,
|
| 289 |
+
"loss": 0.1997,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.0,
|
| 294 |
+
"grad_norm": 15.501004219055176,
|
| 295 |
+
"learning_rate": 4.745370370370371e-05,
|
| 296 |
+
"loss": 0.3458,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.0,
|
| 301 |
+
"eval_accuracy": 0.96,
|
| 302 |
+
"eval_f1_macro": 0.9607843137254902,
|
| 303 |
+
"eval_f1_micro": 0.96,
|
| 304 |
+
"eval_f1_weighted": 0.96,
|
| 305 |
+
"eval_loss": 0.11712707579135895,
|
| 306 |
+
"eval_precision_macro": 0.9629629629629629,
|
| 307 |
+
"eval_precision_micro": 0.96,
|
| 308 |
+
"eval_precision_weighted": 0.9644444444444444,
|
| 309 |
+
"eval_recall_macro": 0.9629629629629629,
|
| 310 |
+
"eval_recall_micro": 0.96,
|
| 311 |
+
"eval_recall_weighted": 0.96,
|
| 312 |
+
"eval_runtime": 4.8385,
|
| 313 |
+
"eval_samples_per_second": 5.167,
|
| 314 |
+
"eval_steps_per_second": 0.413,
|
| 315 |
+
"step": 36
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.0833333333333335,
|
| 319 |
+
"grad_norm": 2.344996452331543,
|
| 320 |
+
"learning_rate": 4.722222222222222e-05,
|
| 321 |
+
"loss": 0.0562,
|
| 322 |
+
"step": 37
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.1666666666666665,
|
| 326 |
+
"grad_norm": 15.16490364074707,
|
| 327 |
+
"learning_rate": 4.699074074074074e-05,
|
| 328 |
+
"loss": 0.6778,
|
| 329 |
+
"step": 38
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.25,
|
| 333 |
+
"grad_norm": 6.663646221160889,
|
| 334 |
+
"learning_rate": 4.675925925925926e-05,
|
| 335 |
+
"loss": 0.2276,
|
| 336 |
+
"step": 39
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 3.3333333333333335,
|
| 340 |
+
"grad_norm": 6.370706081390381,
|
| 341 |
+
"learning_rate": 4.652777777777778e-05,
|
| 342 |
+
"loss": 0.1726,
|
| 343 |
+
"step": 40
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 3.4166666666666665,
|
| 347 |
+
"grad_norm": 2.5982818603515625,
|
| 348 |
+
"learning_rate": 4.62962962962963e-05,
|
| 349 |
+
"loss": 0.0996,
|
| 350 |
+
"step": 41
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.5,
|
| 354 |
+
"grad_norm": 0.8788436651229858,
|
| 355 |
+
"learning_rate": 4.6064814814814814e-05,
|
| 356 |
+
"loss": 0.0327,
|
| 357 |
+
"step": 42
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.5833333333333335,
|
| 361 |
+
"grad_norm": 2.1129608154296875,
|
| 362 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 363 |
+
"loss": 0.0456,
|
| 364 |
+
"step": 43
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 3.6666666666666665,
|
| 368 |
+
"grad_norm": 0.5866346955299377,
|
| 369 |
+
"learning_rate": 4.5601851851851854e-05,
|
| 370 |
+
"loss": 0.0271,
|
| 371 |
+
"step": 44
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.75,
|
| 375 |
+
"grad_norm": 0.8767072558403015,
|
| 376 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 377 |
+
"loss": 0.0283,
|
| 378 |
+
"step": 45
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.8333333333333335,
|
| 382 |
+
"grad_norm": 15.523418426513672,
|
| 383 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 384 |
+
"loss": 0.4742,
|
| 385 |
+
"step": 46
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 3.9166666666666665,
|
| 389 |
+
"grad_norm": 11.548255920410156,
|
| 390 |
+
"learning_rate": 4.490740740740741e-05,
|
| 391 |
+
"loss": 0.4021,
|
| 392 |
+
"step": 47
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.0,
|
| 396 |
+
"grad_norm": 6.209399223327637,
|
| 397 |
+
"learning_rate": 4.467592592592593e-05,
|
| 398 |
+
"loss": 0.0824,
|
| 399 |
+
"step": 48
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.0,
|
| 403 |
+
"eval_accuracy": 0.96,
|
| 404 |
+
"eval_f1_macro": 0.9607843137254902,
|
| 405 |
+
"eval_f1_micro": 0.96,
|
| 406 |
+
"eval_f1_weighted": 0.96,
|
| 407 |
+
"eval_loss": 0.10311740636825562,
|
| 408 |
+
"eval_precision_macro": 0.9629629629629629,
|
| 409 |
+
"eval_precision_micro": 0.96,
|
| 410 |
+
"eval_precision_weighted": 0.9644444444444444,
|
| 411 |
+
"eval_recall_macro": 0.9629629629629629,
|
| 412 |
+
"eval_recall_micro": 0.96,
|
| 413 |
+
"eval_recall_weighted": 0.96,
|
| 414 |
+
"eval_runtime": 3.7242,
|
| 415 |
+
"eval_samples_per_second": 6.713,
|
| 416 |
+
"eval_steps_per_second": 0.537,
|
| 417 |
+
"step": 48
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.083333333333333,
|
| 421 |
+
"grad_norm": 0.3856086730957031,
|
| 422 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 423 |
+
"loss": 0.013,
|
| 424 |
+
"step": 49
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 4.166666666666667,
|
| 428 |
+
"grad_norm": 5.717906951904297,
|
| 429 |
+
"learning_rate": 4.4212962962962966e-05,
|
| 430 |
+
"loss": 0.1319,
|
| 431 |
+
"step": 50
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.25,
|
| 435 |
+
"grad_norm": 8.69568920135498,
|
| 436 |
+
"learning_rate": 4.3981481481481486e-05,
|
| 437 |
+
"loss": 0.2903,
|
| 438 |
+
"step": 51
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 4.333333333333333,
|
| 442 |
+
"grad_norm": 5.768003940582275,
|
| 443 |
+
"learning_rate": 4.375e-05,
|
| 444 |
+
"loss": 0.0858,
|
| 445 |
+
"step": 52
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 4.416666666666667,
|
| 449 |
+
"grad_norm": 7.638088703155518,
|
| 450 |
+
"learning_rate": 4.351851851851852e-05,
|
| 451 |
+
"loss": 0.1193,
|
| 452 |
+
"step": 53
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.5,
|
| 456 |
+
"grad_norm": 9.927226066589355,
|
| 457 |
+
"learning_rate": 4.328703703703704e-05,
|
| 458 |
+
"loss": 0.2348,
|
| 459 |
+
"step": 54
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.583333333333333,
|
| 463 |
+
"grad_norm": 1.2509145736694336,
|
| 464 |
+
"learning_rate": 4.305555555555556e-05,
|
| 465 |
+
"loss": 0.032,
|
| 466 |
+
"step": 55
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 4.666666666666667,
|
| 470 |
+
"grad_norm": 14.929356575012207,
|
| 471 |
+
"learning_rate": 4.282407407407408e-05,
|
| 472 |
+
"loss": 0.572,
|
| 473 |
+
"step": 56
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.75,
|
| 477 |
+
"grad_norm": 6.632589817047119,
|
| 478 |
+
"learning_rate": 4.259259259259259e-05,
|
| 479 |
+
"loss": 0.1317,
|
| 480 |
+
"step": 57
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 4.833333333333333,
|
| 484 |
+
"grad_norm": 1.4584470987319946,
|
| 485 |
+
"learning_rate": 4.236111111111111e-05,
|
| 486 |
+
"loss": 0.0205,
|
| 487 |
+
"step": 58
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 4.916666666666667,
|
| 491 |
+
"grad_norm": 1.1450552940368652,
|
| 492 |
+
"learning_rate": 4.212962962962963e-05,
|
| 493 |
+
"loss": 0.0214,
|
| 494 |
+
"step": 59
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.0,
|
| 498 |
+
"grad_norm": 0.27064746618270874,
|
| 499 |
+
"learning_rate": 4.1898148148148145e-05,
|
| 500 |
+
"loss": 0.0057,
|
| 501 |
+
"step": 60
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 5.0,
|
| 505 |
+
"eval_accuracy": 1.0,
|
| 506 |
+
"eval_f1_macro": 1.0,
|
| 507 |
+
"eval_f1_micro": 1.0,
|
| 508 |
+
"eval_f1_weighted": 1.0,
|
| 509 |
+
"eval_loss": 0.031145477667450905,
|
| 510 |
+
"eval_precision_macro": 1.0,
|
| 511 |
+
"eval_precision_micro": 1.0,
|
| 512 |
+
"eval_precision_weighted": 1.0,
|
| 513 |
+
"eval_recall_macro": 1.0,
|
| 514 |
+
"eval_recall_micro": 1.0,
|
| 515 |
+
"eval_recall_weighted": 1.0,
|
| 516 |
+
"eval_runtime": 3.5904,
|
| 517 |
+
"eval_samples_per_second": 6.963,
|
| 518 |
+
"eval_steps_per_second": 0.557,
|
| 519 |
+
"step": 60
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.083333333333333,
|
| 523 |
+
"grad_norm": 9.926855087280273,
|
| 524 |
+
"learning_rate": 4.166666666666667e-05,
|
| 525 |
+
"loss": 0.1684,
|
| 526 |
+
"step": 61
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 5.166666666666667,
|
| 530 |
+
"grad_norm": 11.866793632507324,
|
| 531 |
+
"learning_rate": 4.1435185185185185e-05,
|
| 532 |
+
"loss": 0.096,
|
| 533 |
+
"step": 62
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.25,
|
| 537 |
+
"grad_norm": 0.2823261320590973,
|
| 538 |
+
"learning_rate": 4.1203703703703705e-05,
|
| 539 |
+
"loss": 0.0077,
|
| 540 |
+
"step": 63
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 5.333333333333333,
|
| 544 |
+
"grad_norm": 0.13144320249557495,
|
| 545 |
+
"learning_rate": 4.0972222222222225e-05,
|
| 546 |
+
"loss": 0.0042,
|
| 547 |
+
"step": 64
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.416666666666667,
|
| 551 |
+
"grad_norm": 1.130588412284851,
|
| 552 |
+
"learning_rate": 4.074074074074074e-05,
|
| 553 |
+
"loss": 0.018,
|
| 554 |
+
"step": 65
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 5.5,
|
| 558 |
+
"grad_norm": 2.605109691619873,
|
| 559 |
+
"learning_rate": 4.0509259259259265e-05,
|
| 560 |
+
"loss": 0.0231,
|
| 561 |
+
"step": 66
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 5.583333333333333,
|
| 565 |
+
"grad_norm": 1.1471952199935913,
|
| 566 |
+
"learning_rate": 4.027777777777778e-05,
|
| 567 |
+
"loss": 0.0158,
|
| 568 |
+
"step": 67
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 5.666666666666667,
|
| 572 |
+
"grad_norm": 1.1078166961669922,
|
| 573 |
+
"learning_rate": 4.00462962962963e-05,
|
| 574 |
+
"loss": 0.0165,
|
| 575 |
+
"step": 68
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.75,
|
| 579 |
+
"grad_norm": 1.1546205282211304,
|
| 580 |
+
"learning_rate": 3.981481481481482e-05,
|
| 581 |
+
"loss": 0.0129,
|
| 582 |
+
"step": 69
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 5.833333333333333,
|
| 586 |
+
"grad_norm": 0.3603000044822693,
|
| 587 |
+
"learning_rate": 3.958333333333333e-05,
|
| 588 |
+
"loss": 0.0059,
|
| 589 |
+
"step": 70
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.916666666666667,
|
| 593 |
+
"grad_norm": 0.8429247736930847,
|
| 594 |
+
"learning_rate": 3.935185185185186e-05,
|
| 595 |
+
"loss": 0.0105,
|
| 596 |
+
"step": 71
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 6.0,
|
| 600 |
+
"grad_norm": 0.3156064450740814,
|
| 601 |
+
"learning_rate": 3.912037037037037e-05,
|
| 602 |
+
"loss": 0.0059,
|
| 603 |
+
"step": 72
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 6.0,
|
| 607 |
+
"eval_accuracy": 1.0,
|
| 608 |
+
"eval_f1_macro": 1.0,
|
| 609 |
+
"eval_f1_micro": 1.0,
|
| 610 |
+
"eval_f1_weighted": 1.0,
|
| 611 |
+
"eval_loss": 0.018539924174547195,
|
| 612 |
+
"eval_precision_macro": 1.0,
|
| 613 |
+
"eval_precision_micro": 1.0,
|
| 614 |
+
"eval_precision_weighted": 1.0,
|
| 615 |
+
"eval_recall_macro": 1.0,
|
| 616 |
+
"eval_recall_micro": 1.0,
|
| 617 |
+
"eval_recall_weighted": 1.0,
|
| 618 |
+
"eval_runtime": 4.594,
|
| 619 |
+
"eval_samples_per_second": 5.442,
|
| 620 |
+
"eval_steps_per_second": 0.435,
|
| 621 |
+
"step": 72
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 6.083333333333333,
|
| 625 |
+
"grad_norm": 0.1072208359837532,
|
| 626 |
+
"learning_rate": 3.888888888888889e-05,
|
| 627 |
+
"loss": 0.003,
|
| 628 |
+
"step": 73
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 6.166666666666667,
|
| 632 |
+
"grad_norm": 6.890180587768555,
|
| 633 |
+
"learning_rate": 3.865740740740741e-05,
|
| 634 |
+
"loss": 0.098,
|
| 635 |
+
"step": 74
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 6.25,
|
| 639 |
+
"grad_norm": 0.08405998349189758,
|
| 640 |
+
"learning_rate": 3.8425925925925924e-05,
|
| 641 |
+
"loss": 0.0028,
|
| 642 |
+
"step": 75
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 6.333333333333333,
|
| 646 |
+
"grad_norm": 0.3140483796596527,
|
| 647 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 648 |
+
"loss": 0.0074,
|
| 649 |
+
"step": 76
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 6.416666666666667,
|
| 653 |
+
"grad_norm": 13.510580062866211,
|
| 654 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 655 |
+
"loss": 0.337,
|
| 656 |
+
"step": 77
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 6.5,
|
| 660 |
+
"grad_norm": 3.8720881938934326,
|
| 661 |
+
"learning_rate": 3.7731481481481484e-05,
|
| 662 |
+
"loss": 0.038,
|
| 663 |
+
"step": 78
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 6.583333333333333,
|
| 667 |
+
"grad_norm": 17.56529998779297,
|
| 668 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 669 |
+
"loss": 0.7544,
|
| 670 |
+
"step": 79
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 6.666666666666667,
|
| 674 |
+
"grad_norm": 17.980655670166016,
|
| 675 |
+
"learning_rate": 3.726851851851852e-05,
|
| 676 |
+
"loss": 0.3827,
|
| 677 |
+
"step": 80
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 6.75,
|
| 681 |
+
"grad_norm": 8.608877182006836,
|
| 682 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 683 |
+
"loss": 0.0761,
|
| 684 |
+
"step": 81
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 6.833333333333333,
|
| 688 |
+
"grad_norm": 13.063497543334961,
|
| 689 |
+
"learning_rate": 3.6805555555555556e-05,
|
| 690 |
+
"loss": 0.1506,
|
| 691 |
+
"step": 82
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 6.916666666666667,
|
| 695 |
+
"grad_norm": 2.446282148361206,
|
| 696 |
+
"learning_rate": 3.6574074074074076e-05,
|
| 697 |
+
"loss": 0.0203,
|
| 698 |
+
"step": 83
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 7.0,
|
| 702 |
+
"grad_norm": 0.17822924256324768,
|
| 703 |
+
"learning_rate": 3.6342592592592596e-05,
|
| 704 |
+
"loss": 0.0034,
|
| 705 |
+
"step": 84
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 7.0,
|
| 709 |
+
"eval_accuracy": 0.92,
|
| 710 |
+
"eval_f1_macro": 0.9212962962962963,
|
| 711 |
+
"eval_f1_micro": 0.92,
|
| 712 |
+
"eval_f1_weighted": 0.9194444444444444,
|
| 713 |
+
"eval_loss": 0.2091759443283081,
|
| 714 |
+
"eval_precision_macro": 0.9333333333333332,
|
| 715 |
+
"eval_precision_micro": 0.92,
|
| 716 |
+
"eval_precision_weighted": 0.9359999999999999,
|
| 717 |
+
"eval_recall_macro": 0.9259259259259259,
|
| 718 |
+
"eval_recall_micro": 0.92,
|
| 719 |
+
"eval_recall_weighted": 0.92,
|
| 720 |
+
"eval_runtime": 3.4699,
|
| 721 |
+
"eval_samples_per_second": 7.205,
|
| 722 |
+
"eval_steps_per_second": 0.576,
|
| 723 |
+
"step": 84
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 7.083333333333333,
|
| 727 |
+
"grad_norm": 32.10905456542969,
|
| 728 |
+
"learning_rate": 3.611111111111111e-05,
|
| 729 |
+
"loss": 0.329,
|
| 730 |
+
"step": 85
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 7.166666666666667,
|
| 734 |
+
"grad_norm": 11.40704345703125,
|
| 735 |
+
"learning_rate": 3.587962962962963e-05,
|
| 736 |
+
"loss": 0.0685,
|
| 737 |
+
"step": 86
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 7.25,
|
| 741 |
+
"grad_norm": 0.05015498399734497,
|
| 742 |
+
"learning_rate": 3.564814814814815e-05,
|
| 743 |
+
"loss": 0.0017,
|
| 744 |
+
"step": 87
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 7.333333333333333,
|
| 748 |
+
"grad_norm": 6.359123229980469,
|
| 749 |
+
"learning_rate": 3.541666666666667e-05,
|
| 750 |
+
"loss": 0.0544,
|
| 751 |
+
"step": 88
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 7.416666666666667,
|
| 755 |
+
"grad_norm": 0.08459993451833725,
|
| 756 |
+
"learning_rate": 3.518518518518519e-05,
|
| 757 |
+
"loss": 0.0024,
|
| 758 |
+
"step": 89
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 7.5,
|
| 762 |
+
"grad_norm": 10.152039527893066,
|
| 763 |
+
"learning_rate": 3.49537037037037e-05,
|
| 764 |
+
"loss": 0.4355,
|
| 765 |
+
"step": 90
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 7.583333333333333,
|
| 769 |
+
"grad_norm": 9.866460800170898,
|
| 770 |
+
"learning_rate": 3.472222222222222e-05,
|
| 771 |
+
"loss": 0.2072,
|
| 772 |
+
"step": 91
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 7.666666666666667,
|
| 776 |
+
"grad_norm": 0.9173619747161865,
|
| 777 |
+
"learning_rate": 3.449074074074074e-05,
|
| 778 |
+
"loss": 0.0077,
|
| 779 |
+
"step": 92
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 7.75,
|
| 783 |
+
"grad_norm": 38.00164031982422,
|
| 784 |
+
"learning_rate": 3.425925925925926e-05,
|
| 785 |
+
"loss": 0.6829,
|
| 786 |
+
"step": 93
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 7.833333333333333,
|
| 790 |
+
"grad_norm": 16.044174194335938,
|
| 791 |
+
"learning_rate": 3.402777777777778e-05,
|
| 792 |
+
"loss": 0.3129,
|
| 793 |
+
"step": 94
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 7.916666666666667,
|
| 797 |
+
"grad_norm": 13.979844093322754,
|
| 798 |
+
"learning_rate": 3.3796296296296295e-05,
|
| 799 |
+
"loss": 0.2296,
|
| 800 |
+
"step": 95
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 8.0,
|
| 804 |
+
"grad_norm": 0.6512384414672852,
|
| 805 |
+
"learning_rate": 3.3564814814814815e-05,
|
| 806 |
+
"loss": 0.0127,
|
| 807 |
+
"step": 96
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 8.0,
|
| 811 |
+
"eval_accuracy": 0.92,
|
| 812 |
+
"eval_f1_macro": 0.9212962962962963,
|
| 813 |
+
"eval_f1_micro": 0.92,
|
| 814 |
+
"eval_f1_weighted": 0.9194444444444444,
|
| 815 |
+
"eval_loss": 0.07724393159151077,
|
| 816 |
+
"eval_precision_macro": 0.9333333333333332,
|
| 817 |
+
"eval_precision_micro": 0.92,
|
| 818 |
+
"eval_precision_weighted": 0.9359999999999999,
|
| 819 |
+
"eval_recall_macro": 0.9259259259259259,
|
| 820 |
+
"eval_recall_micro": 0.92,
|
| 821 |
+
"eval_recall_weighted": 0.92,
|
| 822 |
+
"eval_runtime": 4.6803,
|
| 823 |
+
"eval_samples_per_second": 5.342,
|
| 824 |
+
"eval_steps_per_second": 0.427,
|
| 825 |
+
"step": 96
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 8.083333333333334,
|
| 829 |
+
"grad_norm": 0.6132311224937439,
|
| 830 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 831 |
+
"loss": 0.0133,
|
| 832 |
+
"step": 97
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 8.166666666666666,
|
| 836 |
+
"grad_norm": 0.09633371978998184,
|
| 837 |
+
"learning_rate": 3.3101851851851855e-05,
|
| 838 |
+
"loss": 0.0031,
|
| 839 |
+
"step": 98
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 8.25,
|
| 843 |
+
"grad_norm": 1.8075445890426636,
|
| 844 |
+
"learning_rate": 3.2870370370370375e-05,
|
| 845 |
+
"loss": 0.0159,
|
| 846 |
+
"step": 99
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 8.333333333333334,
|
| 850 |
+
"grad_norm": 0.10686684399843216,
|
| 851 |
+
"learning_rate": 3.263888888888889e-05,
|
| 852 |
+
"loss": 0.0024,
|
| 853 |
+
"step": 100
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 8.416666666666666,
|
| 857 |
+
"grad_norm": 21.682884216308594,
|
| 858 |
+
"learning_rate": 3.240740740740741e-05,
|
| 859 |
+
"loss": 0.6049,
|
| 860 |
+
"step": 101
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 8.5,
|
| 864 |
+
"grad_norm": 0.352243572473526,
|
| 865 |
+
"learning_rate": 3.217592592592593e-05,
|
| 866 |
+
"loss": 0.0084,
|
| 867 |
+
"step": 102
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 8.583333333333334,
|
| 871 |
+
"grad_norm": 2.671285390853882,
|
| 872 |
+
"learning_rate": 3.194444444444444e-05,
|
| 873 |
+
"loss": 0.0195,
|
| 874 |
+
"step": 103
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 8.666666666666666,
|
| 878 |
+
"grad_norm": 0.13619431853294373,
|
| 879 |
+
"learning_rate": 3.171296296296297e-05,
|
| 880 |
+
"loss": 0.0032,
|
| 881 |
+
"step": 104
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 8.75,
|
| 885 |
+
"grad_norm": 12.125520706176758,
|
| 886 |
+
"learning_rate": 3.148148148148148e-05,
|
| 887 |
+
"loss": 0.2758,
|
| 888 |
+
"step": 105
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 8.833333333333334,
|
| 892 |
+
"grad_norm": 2.413362503051758,
|
| 893 |
+
"learning_rate": 3.125e-05,
|
| 894 |
+
"loss": 0.0481,
|
| 895 |
+
"step": 106
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 8.916666666666666,
|
| 899 |
+
"grad_norm": 0.030400389805436134,
|
| 900 |
+
"learning_rate": 3.101851851851852e-05,
|
| 901 |
+
"loss": 0.0009,
|
| 902 |
+
"step": 107
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 9.0,
|
| 906 |
+
"grad_norm": 0.14056330919265747,
|
| 907 |
+
"learning_rate": 3.0787037037037034e-05,
|
| 908 |
+
"loss": 0.0022,
|
| 909 |
+
"step": 108
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 9.0,
|
| 913 |
+
"eval_accuracy": 1.0,
|
| 914 |
+
"eval_f1_macro": 1.0,
|
| 915 |
+
"eval_f1_micro": 1.0,
|
| 916 |
+
"eval_f1_weighted": 1.0,
|
| 917 |
+
"eval_loss": 0.022804124280810356,
|
| 918 |
+
"eval_precision_macro": 1.0,
|
| 919 |
+
"eval_precision_micro": 1.0,
|
| 920 |
+
"eval_precision_weighted": 1.0,
|
| 921 |
+
"eval_recall_macro": 1.0,
|
| 922 |
+
"eval_recall_micro": 1.0,
|
| 923 |
+
"eval_recall_weighted": 1.0,
|
| 924 |
+
"eval_runtime": 3.4813,
|
| 925 |
+
"eval_samples_per_second": 7.181,
|
| 926 |
+
"eval_steps_per_second": 0.575,
|
| 927 |
+
"step": 108
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 9.083333333333334,
|
| 931 |
+
"grad_norm": 0.2784619629383087,
|
| 932 |
+
"learning_rate": 3.055555555555556e-05,
|
| 933 |
+
"loss": 0.0047,
|
| 934 |
+
"step": 109
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 9.166666666666666,
|
| 938 |
+
"grad_norm": 2.1104135513305664,
|
| 939 |
+
"learning_rate": 3.0324074074074077e-05,
|
| 940 |
+
"loss": 0.0248,
|
| 941 |
+
"step": 110
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 9.25,
|
| 945 |
+
"grad_norm": 15.935175895690918,
|
| 946 |
+
"learning_rate": 3.0092592592592593e-05,
|
| 947 |
+
"loss": 0.405,
|
| 948 |
+
"step": 111
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 9.333333333333334,
|
| 952 |
+
"grad_norm": 0.09212371706962585,
|
| 953 |
+
"learning_rate": 2.9861111111111113e-05,
|
| 954 |
+
"loss": 0.0028,
|
| 955 |
+
"step": 112
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 9.416666666666666,
|
| 959 |
+
"grad_norm": 0.849100649356842,
|
| 960 |
+
"learning_rate": 2.962962962962963e-05,
|
| 961 |
+
"loss": 0.0199,
|
| 962 |
+
"step": 113
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 9.5,
|
| 966 |
+
"grad_norm": 0.06665942072868347,
|
| 967 |
+
"learning_rate": 2.9398148148148146e-05,
|
| 968 |
+
"loss": 0.0018,
|
| 969 |
+
"step": 114
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 9.583333333333334,
|
| 973 |
+
"grad_norm": 0.07332099974155426,
|
| 974 |
+
"learning_rate": 2.916666666666667e-05,
|
| 975 |
+
"loss": 0.0018,
|
| 976 |
+
"step": 115
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 9.666666666666666,
|
| 980 |
+
"grad_norm": 3.6126911640167236,
|
| 981 |
+
"learning_rate": 2.8935185185185186e-05,
|
| 982 |
+
"loss": 0.0237,
|
| 983 |
+
"step": 116
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 9.75,
|
| 987 |
+
"grad_norm": 0.03336139768362045,
|
| 988 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 989 |
+
"loss": 0.0011,
|
| 990 |
+
"step": 117
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 9.833333333333334,
|
| 994 |
+
"grad_norm": 0.48148787021636963,
|
| 995 |
+
"learning_rate": 2.8472222222222223e-05,
|
| 996 |
+
"loss": 0.0067,
|
| 997 |
+
"step": 118
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 9.916666666666666,
|
| 1001 |
+
"grad_norm": 1.039989948272705,
|
| 1002 |
+
"learning_rate": 2.824074074074074e-05,
|
| 1003 |
+
"loss": 0.007,
|
| 1004 |
+
"step": 119
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 10.0,
|
| 1008 |
+
"grad_norm": 20.5938720703125,
|
| 1009 |
+
"learning_rate": 2.8009259259259263e-05,
|
| 1010 |
+
"loss": 0.1696,
|
| 1011 |
+
"step": 120
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 10.0,
|
| 1015 |
+
"eval_accuracy": 1.0,
|
| 1016 |
+
"eval_f1_macro": 1.0,
|
| 1017 |
+
"eval_f1_micro": 1.0,
|
| 1018 |
+
"eval_f1_weighted": 1.0,
|
| 1019 |
+
"eval_loss": 0.00790230743587017,
|
| 1020 |
+
"eval_precision_macro": 1.0,
|
| 1021 |
+
"eval_precision_micro": 1.0,
|
| 1022 |
+
"eval_precision_weighted": 1.0,
|
| 1023 |
+
"eval_recall_macro": 1.0,
|
| 1024 |
+
"eval_recall_micro": 1.0,
|
| 1025 |
+
"eval_recall_weighted": 1.0,
|
| 1026 |
+
"eval_runtime": 4.1594,
|
| 1027 |
+
"eval_samples_per_second": 6.011,
|
| 1028 |
+
"eval_steps_per_second": 0.481,
|
| 1029 |
+
"step": 120
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 10.083333333333334,
|
| 1033 |
+
"grad_norm": 0.11963392049074173,
|
| 1034 |
+
"learning_rate": 2.777777777777778e-05,
|
| 1035 |
+
"loss": 0.0029,
|
| 1036 |
+
"step": 121
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 10.166666666666666,
|
| 1040 |
+
"grad_norm": 13.877823829650879,
|
| 1041 |
+
"learning_rate": 2.75462962962963e-05,
|
| 1042 |
+
"loss": 0.3927,
|
| 1043 |
+
"step": 122
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 10.25,
|
| 1047 |
+
"grad_norm": 0.14195731282234192,
|
| 1048 |
+
"learning_rate": 2.7314814814814816e-05,
|
| 1049 |
+
"loss": 0.0021,
|
| 1050 |
+
"step": 123
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 10.333333333333334,
|
| 1054 |
+
"grad_norm": 0.7948401570320129,
|
| 1055 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 1056 |
+
"loss": 0.0112,
|
| 1057 |
+
"step": 124
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 10.416666666666666,
|
| 1061 |
+
"grad_norm": 13.389975547790527,
|
| 1062 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 1063 |
+
"loss": 0.1986,
|
| 1064 |
+
"step": 125
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 10.5,
|
| 1068 |
+
"grad_norm": 15.158964157104492,
|
| 1069 |
+
"learning_rate": 2.6620370370370372e-05,
|
| 1070 |
+
"loss": 0.7039,
|
| 1071 |
+
"step": 126
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 10.583333333333334,
|
| 1075 |
+
"grad_norm": 12.282134056091309,
|
| 1076 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 1077 |
+
"loss": 0.4762,
|
| 1078 |
+
"step": 127
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 10.666666666666666,
|
| 1082 |
+
"grad_norm": 23.414642333984375,
|
| 1083 |
+
"learning_rate": 2.615740740740741e-05,
|
| 1084 |
+
"loss": 0.3377,
|
| 1085 |
+
"step": 128
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 10.75,
|
| 1089 |
+
"grad_norm": 16.485862731933594,
|
| 1090 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 1091 |
+
"loss": 0.1597,
|
| 1092 |
+
"step": 129
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 10.833333333333334,
|
| 1096 |
+
"grad_norm": 0.08321473002433777,
|
| 1097 |
+
"learning_rate": 2.5694444444444445e-05,
|
| 1098 |
+
"loss": 0.0017,
|
| 1099 |
+
"step": 130
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 10.916666666666666,
|
| 1103 |
+
"grad_norm": 1.5314733982086182,
|
| 1104 |
+
"learning_rate": 2.5462962962962965e-05,
|
| 1105 |
+
"loss": 0.02,
|
| 1106 |
+
"step": 131
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 11.0,
|
| 1110 |
+
"grad_norm": 0.03295975551009178,
|
| 1111 |
+
"learning_rate": 2.5231481481481485e-05,
|
| 1112 |
+
"loss": 0.0011,
|
| 1113 |
+
"step": 132
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 11.0,
|
| 1117 |
+
"eval_accuracy": 1.0,
|
| 1118 |
+
"eval_f1_macro": 1.0,
|
| 1119 |
+
"eval_f1_micro": 1.0,
|
| 1120 |
+
"eval_f1_weighted": 1.0,
|
| 1121 |
+
"eval_loss": 0.02397926338016987,
|
| 1122 |
+
"eval_precision_macro": 1.0,
|
| 1123 |
+
"eval_precision_micro": 1.0,
|
| 1124 |
+
"eval_precision_weighted": 1.0,
|
| 1125 |
+
"eval_recall_macro": 1.0,
|
| 1126 |
+
"eval_recall_micro": 1.0,
|
| 1127 |
+
"eval_recall_weighted": 1.0,
|
| 1128 |
+
"eval_runtime": 3.5683,
|
| 1129 |
+
"eval_samples_per_second": 7.006,
|
| 1130 |
+
"eval_steps_per_second": 0.56,
|
| 1131 |
+
"step": 132
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 11.083333333333334,
|
| 1135 |
+
"grad_norm": 0.39047297835350037,
|
| 1136 |
+
"learning_rate": 2.5e-05,
|
| 1137 |
+
"loss": 0.0055,
|
| 1138 |
+
"step": 133
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 11.166666666666666,
|
| 1142 |
+
"grad_norm": 1.087671160697937,
|
| 1143 |
+
"learning_rate": 2.4768518518518518e-05,
|
| 1144 |
+
"loss": 0.0201,
|
| 1145 |
+
"step": 134
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 11.25,
|
| 1149 |
+
"grad_norm": 0.26571857929229736,
|
| 1150 |
+
"learning_rate": 2.4537037037037038e-05,
|
| 1151 |
+
"loss": 0.0032,
|
| 1152 |
+
"step": 135
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 11.333333333333334,
|
| 1156 |
+
"grad_norm": 0.030041467398405075,
|
| 1157 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 1158 |
+
"loss": 0.001,
|
| 1159 |
+
"step": 136
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 11.416666666666666,
|
| 1163 |
+
"grad_norm": 0.10694663971662521,
|
| 1164 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 1165 |
+
"loss": 0.0023,
|
| 1166 |
+
"step": 137
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 11.5,
|
| 1170 |
+
"grad_norm": 0.1390959620475769,
|
| 1171 |
+
"learning_rate": 2.3842592592592594e-05,
|
| 1172 |
+
"loss": 0.0027,
|
| 1173 |
+
"step": 138
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 11.583333333333334,
|
| 1177 |
+
"grad_norm": 2.7979471683502197,
|
| 1178 |
+
"learning_rate": 2.361111111111111e-05,
|
| 1179 |
+
"loss": 0.027,
|
| 1180 |
+
"step": 139
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 11.666666666666666,
|
| 1184 |
+
"grad_norm": 0.1279616802930832,
|
| 1185 |
+
"learning_rate": 2.337962962962963e-05,
|
| 1186 |
+
"loss": 0.0026,
|
| 1187 |
+
"step": 140
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 11.75,
|
| 1191 |
+
"grad_norm": 2.4742202758789062,
|
| 1192 |
+
"learning_rate": 2.314814814814815e-05,
|
| 1193 |
+
"loss": 0.0204,
|
| 1194 |
+
"step": 141
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 11.833333333333334,
|
| 1198 |
+
"grad_norm": 0.8710950613021851,
|
| 1199 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 1200 |
+
"loss": 0.0138,
|
| 1201 |
+
"step": 142
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 11.916666666666666,
|
| 1205 |
+
"grad_norm": 9.07259464263916,
|
| 1206 |
+
"learning_rate": 2.2685185185185187e-05,
|
| 1207 |
+
"loss": 0.8974,
|
| 1208 |
+
"step": 143
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 12.0,
|
| 1212 |
+
"grad_norm": 0.030301809310913086,
|
| 1213 |
+
"learning_rate": 2.2453703703703703e-05,
|
| 1214 |
+
"loss": 0.0009,
|
| 1215 |
+
"step": 144
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 12.0,
|
| 1219 |
+
"eval_accuracy": 1.0,
|
| 1220 |
+
"eval_f1_macro": 1.0,
|
| 1221 |
+
"eval_f1_micro": 1.0,
|
| 1222 |
+
"eval_f1_weighted": 1.0,
|
| 1223 |
+
"eval_loss": 0.007570595946162939,
|
| 1224 |
+
"eval_precision_macro": 1.0,
|
| 1225 |
+
"eval_precision_micro": 1.0,
|
| 1226 |
+
"eval_precision_weighted": 1.0,
|
| 1227 |
+
"eval_recall_macro": 1.0,
|
| 1228 |
+
"eval_recall_micro": 1.0,
|
| 1229 |
+
"eval_recall_weighted": 1.0,
|
| 1230 |
+
"eval_runtime": 4.7114,
|
| 1231 |
+
"eval_samples_per_second": 5.306,
|
| 1232 |
+
"eval_steps_per_second": 0.424,
|
| 1233 |
+
"step": 144
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 12.083333333333334,
|
| 1237 |
+
"grad_norm": 0.7027904391288757,
|
| 1238 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1239 |
+
"loss": 0.0086,
|
| 1240 |
+
"step": 145
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 12.166666666666666,
|
| 1244 |
+
"grad_norm": 0.17031855881214142,
|
| 1245 |
+
"learning_rate": 2.1990740740740743e-05,
|
| 1246 |
+
"loss": 0.0018,
|
| 1247 |
+
"step": 146
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 12.25,
|
| 1251 |
+
"grad_norm": 6.612548828125,
|
| 1252 |
+
"learning_rate": 2.175925925925926e-05,
|
| 1253 |
+
"loss": 0.0484,
|
| 1254 |
+
"step": 147
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 12.333333333333334,
|
| 1258 |
+
"grad_norm": 15.77225112915039,
|
| 1259 |
+
"learning_rate": 2.152777777777778e-05,
|
| 1260 |
+
"loss": 0.355,
|
| 1261 |
+
"step": 148
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 12.416666666666666,
|
| 1265 |
+
"grad_norm": 0.06656526029109955,
|
| 1266 |
+
"learning_rate": 2.1296296296296296e-05,
|
| 1267 |
+
"loss": 0.0014,
|
| 1268 |
+
"step": 149
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 12.5,
|
| 1272 |
+
"grad_norm": 0.07425399124622345,
|
| 1273 |
+
"learning_rate": 2.1064814814814816e-05,
|
| 1274 |
+
"loss": 0.0018,
|
| 1275 |
+
"step": 150
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 12.583333333333334,
|
| 1279 |
+
"grad_norm": 0.058514680713415146,
|
| 1280 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 1281 |
+
"loss": 0.0013,
|
| 1282 |
+
"step": 151
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 12.666666666666666,
|
| 1286 |
+
"grad_norm": 12.347506523132324,
|
| 1287 |
+
"learning_rate": 2.0601851851851853e-05,
|
| 1288 |
+
"loss": 0.1189,
|
| 1289 |
+
"step": 152
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 12.75,
|
| 1293 |
+
"grad_norm": 1.8030519485473633,
|
| 1294 |
+
"learning_rate": 2.037037037037037e-05,
|
| 1295 |
+
"loss": 0.014,
|
| 1296 |
+
"step": 153
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 12.833333333333334,
|
| 1300 |
+
"grad_norm": 0.0552341565489769,
|
| 1301 |
+
"learning_rate": 2.013888888888889e-05,
|
| 1302 |
+
"loss": 0.0014,
|
| 1303 |
+
"step": 154
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 12.916666666666666,
|
| 1307 |
+
"grad_norm": 0.10470353066921234,
|
| 1308 |
+
"learning_rate": 1.990740740740741e-05,
|
| 1309 |
+
"loss": 0.0026,
|
| 1310 |
+
"step": 155
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 13.0,
|
| 1314 |
+
"grad_norm": 0.028571682050824165,
|
| 1315 |
+
"learning_rate": 1.967592592592593e-05,
|
| 1316 |
+
"loss": 0.0008,
|
| 1317 |
+
"step": 156
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 13.0,
|
| 1321 |
+
"eval_accuracy": 1.0,
|
| 1322 |
+
"eval_f1_macro": 1.0,
|
| 1323 |
+
"eval_f1_micro": 1.0,
|
| 1324 |
+
"eval_f1_weighted": 1.0,
|
| 1325 |
+
"eval_loss": 0.005100989248603582,
|
| 1326 |
+
"eval_precision_macro": 1.0,
|
| 1327 |
+
"eval_precision_micro": 1.0,
|
| 1328 |
+
"eval_precision_weighted": 1.0,
|
| 1329 |
+
"eval_recall_macro": 1.0,
|
| 1330 |
+
"eval_recall_micro": 1.0,
|
| 1331 |
+
"eval_recall_weighted": 1.0,
|
| 1332 |
+
"eval_runtime": 3.4909,
|
| 1333 |
+
"eval_samples_per_second": 7.161,
|
| 1334 |
+
"eval_steps_per_second": 0.573,
|
| 1335 |
+
"step": 156
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 13.083333333333334,
|
| 1339 |
+
"grad_norm": 0.0461936816573143,
|
| 1340 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 1341 |
+
"loss": 0.0009,
|
| 1342 |
+
"step": 157
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 13.166666666666666,
|
| 1346 |
+
"grad_norm": 1.239888310432434,
|
| 1347 |
+
"learning_rate": 1.9212962962962962e-05,
|
| 1348 |
+
"loss": 0.0104,
|
| 1349 |
+
"step": 158
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 13.25,
|
| 1353 |
+
"grad_norm": 0.8754599094390869,
|
| 1354 |
+
"learning_rate": 1.8981481481481482e-05,
|
| 1355 |
+
"loss": 0.0103,
|
| 1356 |
+
"step": 159
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 13.333333333333334,
|
| 1360 |
+
"grad_norm": 9.688822746276855,
|
| 1361 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 1362 |
+
"loss": 0.0821,
|
| 1363 |
+
"step": 160
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 13.416666666666666,
|
| 1367 |
+
"grad_norm": 0.11708085983991623,
|
| 1368 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1369 |
+
"loss": 0.0021,
|
| 1370 |
+
"step": 161
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 13.5,
|
| 1374 |
+
"grad_norm": 0.47828805446624756,
|
| 1375 |
+
"learning_rate": 1.8287037037037038e-05,
|
| 1376 |
+
"loss": 0.0081,
|
| 1377 |
+
"step": 162
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 13.583333333333334,
|
| 1381 |
+
"grad_norm": 0.35925403237342834,
|
| 1382 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 1383 |
+
"loss": 0.0044,
|
| 1384 |
+
"step": 163
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 13.666666666666666,
|
| 1388 |
+
"grad_norm": 0.023463550955057144,
|
| 1389 |
+
"learning_rate": 1.7824074074074075e-05,
|
| 1390 |
+
"loss": 0.0007,
|
| 1391 |
+
"step": 164
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 13.75,
|
| 1395 |
+
"grad_norm": 0.03341836482286453,
|
| 1396 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 1397 |
+
"loss": 0.001,
|
| 1398 |
+
"step": 165
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 13.833333333333334,
|
| 1402 |
+
"grad_norm": 0.016831809654831886,
|
| 1403 |
+
"learning_rate": 1.736111111111111e-05,
|
| 1404 |
+
"loss": 0.0006,
|
| 1405 |
+
"step": 166
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 13.916666666666666,
|
| 1409 |
+
"grad_norm": 0.045966170728206635,
|
| 1410 |
+
"learning_rate": 1.712962962962963e-05,
|
| 1411 |
+
"loss": 0.0011,
|
| 1412 |
+
"step": 167
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 14.0,
|
| 1416 |
+
"grad_norm": 3.7905242443084717,
|
| 1417 |
+
"learning_rate": 1.6898148148148148e-05,
|
| 1418 |
+
"loss": 0.0383,
|
| 1419 |
+
"step": 168
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 14.0,
|
| 1423 |
+
"eval_accuracy": 1.0,
|
| 1424 |
+
"eval_f1_macro": 1.0,
|
| 1425 |
+
"eval_f1_micro": 1.0,
|
| 1426 |
+
"eval_f1_weighted": 1.0,
|
| 1427 |
+
"eval_loss": 0.004509058315306902,
|
| 1428 |
+
"eval_precision_macro": 1.0,
|
| 1429 |
+
"eval_precision_micro": 1.0,
|
| 1430 |
+
"eval_precision_weighted": 1.0,
|
| 1431 |
+
"eval_recall_macro": 1.0,
|
| 1432 |
+
"eval_recall_micro": 1.0,
|
| 1433 |
+
"eval_recall_weighted": 1.0,
|
| 1434 |
+
"eval_runtime": 3.5993,
|
| 1435 |
+
"eval_samples_per_second": 6.946,
|
| 1436 |
+
"eval_steps_per_second": 0.556,
|
| 1437 |
+
"step": 168
|
| 1438 |
+
}
|
| 1439 |
+
],
|
| 1440 |
+
"logging_steps": 1,
|
| 1441 |
+
"max_steps": 240,
|
| 1442 |
+
"num_input_tokens_seen": 0,
|
| 1443 |
+
"num_train_epochs": 20,
|
| 1444 |
+
"save_steps": 500,
|
| 1445 |
+
"stateful_callbacks": {
|
| 1446 |
+
"EarlyStoppingCallback": {
|
| 1447 |
+
"args": {
|
| 1448 |
+
"early_stopping_patience": 5,
|
| 1449 |
+
"early_stopping_threshold": 0.01
|
| 1450 |
+
},
|
| 1451 |
+
"attributes": {
|
| 1452 |
+
"early_stopping_patience_counter": 0
|
| 1453 |
+
}
|
| 1454 |
+
},
|
| 1455 |
+
"TrainerControl": {
|
| 1456 |
+
"args": {
|
| 1457 |
+
"should_epoch_stop": false,
|
| 1458 |
+
"should_evaluate": false,
|
| 1459 |
+
"should_log": false,
|
| 1460 |
+
"should_save": true,
|
| 1461 |
+
"should_training_stop": false
|
| 1462 |
+
},
|
| 1463 |
+
"attributes": {}
|
| 1464 |
+
}
|
| 1465 |
+
},
|
| 1466 |
+
"total_flos": 9.872567960809882e+16,
|
| 1467 |
+
"train_batch_size": 8,
|
| 1468 |
+
"trial_name": null,
|
| 1469 |
+
"trial_params": null
|
| 1470 |
+
}
|
checkpoint-168/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa2807ebc10a9fec435fb03cff015649272c8afb43485e38c7a54fda64707b5d
|
| 3 |
+
size 5240
|
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": "BRVO",
|
| 14 |
+
"1": "DR2",
|
| 15 |
+
"2": "Normal"
|
| 16 |
+
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"BRVO": 0,
|
| 22 |
+
"DR2": 1,
|
| 23 |
+
"Normal": 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": "4.43.1"
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f81e44ad73aeace0af102c964f82a042668dc7efe78a3a379453382e4e3859ec
|
| 3 |
+
size 343227052
|
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 |
+
}
|
runs/Aug07_15-10-44_5a39e86fee3e/events.out.tfevents.1723043445.5a39e86fee3e.8439.0
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 sha256:6f50ad6e8e41821bf4f1a3df64c9dca5a2cb9cd09450caa8e5b29913f69e094a
|
| 3 |
+
size 55152
|
runs/Aug07_15-10-44_5a39e86fee3e/events.out.tfevents.1723043814.5a39e86fee3e.8439.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:233d97fc1eca4a34c6c1c495d2ac65cb54614ed7cfaa5aafc51d958be2425921
|
| 3 |
+
size 921
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa2807ebc10a9fec435fb03cff015649272c8afb43485e38c7a54fda64707b5d
|
| 3 |
+
size 5240
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-8oqr6-image0807-20/autotrain-data",
|
| 3 |
+
"model": "google/vit-base-patch16-224",
|
| 4 |
+
"username": "SPJohn",
|
| 5 |
+
"lr": 5e-05,
|
| 6 |
+
"epochs": 20,
|
| 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-8oqr6-image0807-20",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": "fp16",
|
| 21 |
+
"save_total_limit": 1,
|
| 22 |
+
"push_to_hub": true,
|
| 23 |
+
"eval_strategy": "epoch",
|
| 24 |
+
"image_column": "autotrain_image",
|
| 25 |
+
"target_column": "autotrain_label",
|
| 26 |
+
"log": "tensorboard",
|
| 27 |
+
"early_stopping_patience": 5,
|
| 28 |
+
"early_stopping_threshold": 0.01
|
| 29 |
+
}
|