Upload folder using huggingface_hub
Browse files- config.json +34 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1204 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Benign",
|
| 13 |
+
"1": "Malignant",
|
| 14 |
+
"2": "NoTumor"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Benign": "0",
|
| 21 |
+
"Malignant": "1",
|
| 22 |
+
"NoTumor": "2"
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"model_type": "vit",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_channels": 3,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.31.0"
|
| 34 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc6dcb2db7a78f00b45605896aec0180d9a8a8061921b34b8312486d3a61702f
|
| 3 |
+
size 686525061
|
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": "ViTFeatureExtractor",
|
| 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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f291da0382777c2ad7bff355115390c76e789bf6bf2037ababcf6b50a4708405
|
| 3 |
+
size 343271789
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8839cdafbeb5ee30636918c46809ccb433603424aa23b658cf5ea835ffc00a1
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20a317f904da7d5fccd2ce998c858bbee363f4c0c196596f0a4d881e791b8e14
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.05584140494465828,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-960",
|
| 4 |
+
"epoch": 3.9130434782608696,
|
| 5 |
+
"global_step": 1440,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.0001986413043478261,
|
| 13 |
+
"loss": 0.5178,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 0.0001972826086956522,
|
| 19 |
+
"loss": 0.1889,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 0.00019592391304347828,
|
| 25 |
+
"loss": 0.1312,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 0.00019456521739130434,
|
| 31 |
+
"loss": 0.1188,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.11,
|
| 36 |
+
"eval_accuracy": 0.9645776566757494,
|
| 37 |
+
"eval_loss": 0.13658936321735382,
|
| 38 |
+
"eval_runtime": 16.3774,
|
| 39 |
+
"eval_samples_per_second": 44.818,
|
| 40 |
+
"eval_steps_per_second": 5.617,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.14,
|
| 45 |
+
"learning_rate": 0.00019320652173913046,
|
| 46 |
+
"loss": 0.2121,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.16,
|
| 51 |
+
"learning_rate": 0.00019184782608695653,
|
| 52 |
+
"loss": 0.1603,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.19,
|
| 57 |
+
"learning_rate": 0.00019048913043478262,
|
| 58 |
+
"loss": 0.0693,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22,
|
| 63 |
+
"learning_rate": 0.0001891304347826087,
|
| 64 |
+
"loss": 0.1173,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.22,
|
| 69 |
+
"eval_accuracy": 0.9686648501362398,
|
| 70 |
+
"eval_loss": 0.11560923606157303,
|
| 71 |
+
"eval_runtime": 17.9116,
|
| 72 |
+
"eval_samples_per_second": 40.979,
|
| 73 |
+
"eval_steps_per_second": 5.136,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.24,
|
| 78 |
+
"learning_rate": 0.0001877717391304348,
|
| 79 |
+
"loss": 0.1313,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.27,
|
| 84 |
+
"learning_rate": 0.0001864130434782609,
|
| 85 |
+
"loss": 0.07,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3,
|
| 90 |
+
"learning_rate": 0.00018505434782608698,
|
| 91 |
+
"loss": 0.0911,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.33,
|
| 96 |
+
"learning_rate": 0.00018369565217391304,
|
| 97 |
+
"loss": 0.1286,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.33,
|
| 102 |
+
"eval_accuracy": 0.9782016348773842,
|
| 103 |
+
"eval_loss": 0.08449282497167587,
|
| 104 |
+
"eval_runtime": 16.6099,
|
| 105 |
+
"eval_samples_per_second": 44.19,
|
| 106 |
+
"eval_steps_per_second": 5.539,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.35,
|
| 111 |
+
"learning_rate": 0.00018233695652173913,
|
| 112 |
+
"loss": 0.0904,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.38,
|
| 117 |
+
"learning_rate": 0.00018097826086956522,
|
| 118 |
+
"loss": 0.145,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.41,
|
| 123 |
+
"learning_rate": 0.0001796195652173913,
|
| 124 |
+
"loss": 0.0803,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.43,
|
| 129 |
+
"learning_rate": 0.0001782608695652174,
|
| 130 |
+
"loss": 0.0715,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.43,
|
| 135 |
+
"eval_accuracy": 0.9754768392370572,
|
| 136 |
+
"eval_loss": 0.08169694244861603,
|
| 137 |
+
"eval_runtime": 16.7496,
|
| 138 |
+
"eval_samples_per_second": 43.822,
|
| 139 |
+
"eval_steps_per_second": 5.493,
|
| 140 |
+
"step": 160
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.46,
|
| 144 |
+
"learning_rate": 0.0001769021739130435,
|
| 145 |
+
"loss": 0.1404,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.49,
|
| 150 |
+
"learning_rate": 0.00017554347826086956,
|
| 151 |
+
"loss": 0.2379,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.52,
|
| 156 |
+
"learning_rate": 0.00017418478260869567,
|
| 157 |
+
"loss": 0.1005,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.54,
|
| 162 |
+
"learning_rate": 0.00017282608695652174,
|
| 163 |
+
"loss": 0.131,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.54,
|
| 168 |
+
"eval_accuracy": 0.9564032697547684,
|
| 169 |
+
"eval_loss": 0.17271830141544342,
|
| 170 |
+
"eval_runtime": 17.335,
|
| 171 |
+
"eval_samples_per_second": 42.342,
|
| 172 |
+
"eval_steps_per_second": 5.307,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.57,
|
| 177 |
+
"learning_rate": 0.00017146739130434783,
|
| 178 |
+
"loss": 0.0959,
|
| 179 |
+
"step": 210
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.6,
|
| 183 |
+
"learning_rate": 0.00017010869565217392,
|
| 184 |
+
"loss": 0.0672,
|
| 185 |
+
"step": 220
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.62,
|
| 189 |
+
"learning_rate": 0.00016875,
|
| 190 |
+
"loss": 0.1202,
|
| 191 |
+
"step": 230
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.65,
|
| 195 |
+
"learning_rate": 0.0001673913043478261,
|
| 196 |
+
"loss": 0.1347,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.65,
|
| 201 |
+
"eval_accuracy": 0.9782016348773842,
|
| 202 |
+
"eval_loss": 0.08324442058801651,
|
| 203 |
+
"eval_runtime": 17.0177,
|
| 204 |
+
"eval_samples_per_second": 43.132,
|
| 205 |
+
"eval_steps_per_second": 5.406,
|
| 206 |
+
"step": 240
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.68,
|
| 210 |
+
"learning_rate": 0.0001660326086956522,
|
| 211 |
+
"loss": 0.0863,
|
| 212 |
+
"step": 250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.71,
|
| 216 |
+
"learning_rate": 0.00016467391304347828,
|
| 217 |
+
"loss": 0.1664,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.73,
|
| 222 |
+
"learning_rate": 0.00016331521739130434,
|
| 223 |
+
"loss": 0.1342,
|
| 224 |
+
"step": 270
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.76,
|
| 228 |
+
"learning_rate": 0.00016195652173913046,
|
| 229 |
+
"loss": 0.1421,
|
| 230 |
+
"step": 280
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.76,
|
| 234 |
+
"eval_accuracy": 0.9686648501362398,
|
| 235 |
+
"eval_loss": 0.10627246648073196,
|
| 236 |
+
"eval_runtime": 17.0559,
|
| 237 |
+
"eval_samples_per_second": 43.035,
|
| 238 |
+
"eval_steps_per_second": 5.394,
|
| 239 |
+
"step": 280
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.79,
|
| 243 |
+
"learning_rate": 0.00016059782608695652,
|
| 244 |
+
"loss": 0.087,
|
| 245 |
+
"step": 290
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.82,
|
| 249 |
+
"learning_rate": 0.00015923913043478262,
|
| 250 |
+
"loss": 0.1118,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.84,
|
| 255 |
+
"learning_rate": 0.0001578804347826087,
|
| 256 |
+
"loss": 0.1376,
|
| 257 |
+
"step": 310
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.87,
|
| 261 |
+
"learning_rate": 0.0001565217391304348,
|
| 262 |
+
"loss": 0.0761,
|
| 263 |
+
"step": 320
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.87,
|
| 267 |
+
"eval_accuracy": 0.9754768392370572,
|
| 268 |
+
"eval_loss": 0.09320751577615738,
|
| 269 |
+
"eval_runtime": 16.7943,
|
| 270 |
+
"eval_samples_per_second": 43.705,
|
| 271 |
+
"eval_steps_per_second": 5.478,
|
| 272 |
+
"step": 320
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.9,
|
| 276 |
+
"learning_rate": 0.00015516304347826086,
|
| 277 |
+
"loss": 0.0989,
|
| 278 |
+
"step": 330
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.92,
|
| 282 |
+
"learning_rate": 0.00015380434782608698,
|
| 283 |
+
"loss": 0.0366,
|
| 284 |
+
"step": 340
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.95,
|
| 288 |
+
"learning_rate": 0.00015244565217391304,
|
| 289 |
+
"loss": 0.1462,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.98,
|
| 294 |
+
"learning_rate": 0.00015108695652173913,
|
| 295 |
+
"loss": 0.0823,
|
| 296 |
+
"step": 360
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.98,
|
| 300 |
+
"eval_accuracy": 0.9782016348773842,
|
| 301 |
+
"eval_loss": 0.07622215896844864,
|
| 302 |
+
"eval_runtime": 16.6368,
|
| 303 |
+
"eval_samples_per_second": 44.119,
|
| 304 |
+
"eval_steps_per_second": 5.53,
|
| 305 |
+
"step": 360
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.01,
|
| 309 |
+
"learning_rate": 0.00014972826086956522,
|
| 310 |
+
"loss": 0.0875,
|
| 311 |
+
"step": 370
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.03,
|
| 315 |
+
"learning_rate": 0.0001483695652173913,
|
| 316 |
+
"loss": 0.0605,
|
| 317 |
+
"step": 380
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.06,
|
| 321 |
+
"learning_rate": 0.0001470108695652174,
|
| 322 |
+
"loss": 0.1191,
|
| 323 |
+
"step": 390
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.09,
|
| 327 |
+
"learning_rate": 0.0001456521739130435,
|
| 328 |
+
"loss": 0.0961,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.09,
|
| 333 |
+
"eval_accuracy": 0.9782016348773842,
|
| 334 |
+
"eval_loss": 0.07835610955953598,
|
| 335 |
+
"eval_runtime": 16.8911,
|
| 336 |
+
"eval_samples_per_second": 43.455,
|
| 337 |
+
"eval_steps_per_second": 5.447,
|
| 338 |
+
"step": 400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.11,
|
| 342 |
+
"learning_rate": 0.00014429347826086956,
|
| 343 |
+
"loss": 0.1104,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.14,
|
| 348 |
+
"learning_rate": 0.00014293478260869567,
|
| 349 |
+
"loss": 0.0785,
|
| 350 |
+
"step": 420
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.17,
|
| 354 |
+
"learning_rate": 0.00014157608695652174,
|
| 355 |
+
"loss": 0.1137,
|
| 356 |
+
"step": 430
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.2,
|
| 360 |
+
"learning_rate": 0.00014021739130434783,
|
| 361 |
+
"loss": 0.099,
|
| 362 |
+
"step": 440
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.2,
|
| 366 |
+
"eval_accuracy": 0.9550408719346049,
|
| 367 |
+
"eval_loss": 0.15678562223911285,
|
| 368 |
+
"eval_runtime": 16.7723,
|
| 369 |
+
"eval_samples_per_second": 43.763,
|
| 370 |
+
"eval_steps_per_second": 5.485,
|
| 371 |
+
"step": 440
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.22,
|
| 375 |
+
"learning_rate": 0.00013885869565217392,
|
| 376 |
+
"loss": 0.0959,
|
| 377 |
+
"step": 450
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.25,
|
| 381 |
+
"learning_rate": 0.0001375,
|
| 382 |
+
"loss": 0.0755,
|
| 383 |
+
"step": 460
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.28,
|
| 387 |
+
"learning_rate": 0.0001361413043478261,
|
| 388 |
+
"loss": 0.0629,
|
| 389 |
+
"step": 470
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.3,
|
| 393 |
+
"learning_rate": 0.0001347826086956522,
|
| 394 |
+
"loss": 0.054,
|
| 395 |
+
"step": 480
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.3,
|
| 399 |
+
"eval_accuracy": 0.9782016348773842,
|
| 400 |
+
"eval_loss": 0.07049289345741272,
|
| 401 |
+
"eval_runtime": 17.2374,
|
| 402 |
+
"eval_samples_per_second": 42.582,
|
| 403 |
+
"eval_steps_per_second": 5.337,
|
| 404 |
+
"step": 480
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.33,
|
| 408 |
+
"learning_rate": 0.00013342391304347828,
|
| 409 |
+
"loss": 0.0202,
|
| 410 |
+
"step": 490
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.36,
|
| 414 |
+
"learning_rate": 0.00013206521739130434,
|
| 415 |
+
"loss": 0.0476,
|
| 416 |
+
"step": 500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.39,
|
| 420 |
+
"learning_rate": 0.00013070652173913046,
|
| 421 |
+
"loss": 0.0309,
|
| 422 |
+
"step": 510
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.41,
|
| 426 |
+
"learning_rate": 0.00012934782608695652,
|
| 427 |
+
"loss": 0.0876,
|
| 428 |
+
"step": 520
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.41,
|
| 432 |
+
"eval_accuracy": 0.9782016348773842,
|
| 433 |
+
"eval_loss": 0.07148320972919464,
|
| 434 |
+
"eval_runtime": 16.6678,
|
| 435 |
+
"eval_samples_per_second": 44.037,
|
| 436 |
+
"eval_steps_per_second": 5.52,
|
| 437 |
+
"step": 520
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.44,
|
| 441 |
+
"learning_rate": 0.00012798913043478261,
|
| 442 |
+
"loss": 0.0667,
|
| 443 |
+
"step": 530
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.47,
|
| 447 |
+
"learning_rate": 0.0001266304347826087,
|
| 448 |
+
"loss": 0.0504,
|
| 449 |
+
"step": 540
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.49,
|
| 453 |
+
"learning_rate": 0.0001252717391304348,
|
| 454 |
+
"loss": 0.086,
|
| 455 |
+
"step": 550
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.52,
|
| 459 |
+
"learning_rate": 0.00012391304347826086,
|
| 460 |
+
"loss": 0.0454,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.52,
|
| 465 |
+
"eval_accuracy": 0.9782016348773842,
|
| 466 |
+
"eval_loss": 0.07060308009386063,
|
| 467 |
+
"eval_runtime": 16.826,
|
| 468 |
+
"eval_samples_per_second": 43.623,
|
| 469 |
+
"eval_steps_per_second": 5.468,
|
| 470 |
+
"step": 560
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.55,
|
| 474 |
+
"learning_rate": 0.00012255434782608698,
|
| 475 |
+
"loss": 0.0976,
|
| 476 |
+
"step": 570
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.58,
|
| 480 |
+
"learning_rate": 0.00012119565217391304,
|
| 481 |
+
"loss": 0.0721,
|
| 482 |
+
"step": 580
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.6,
|
| 486 |
+
"learning_rate": 0.00011983695652173914,
|
| 487 |
+
"loss": 0.0632,
|
| 488 |
+
"step": 590
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.63,
|
| 492 |
+
"learning_rate": 0.00011847826086956522,
|
| 493 |
+
"loss": 0.0645,
|
| 494 |
+
"step": 600
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.63,
|
| 498 |
+
"eval_accuracy": 0.9768392370572208,
|
| 499 |
+
"eval_loss": 0.06225130707025528,
|
| 500 |
+
"eval_runtime": 16.7524,
|
| 501 |
+
"eval_samples_per_second": 43.815,
|
| 502 |
+
"eval_steps_per_second": 5.492,
|
| 503 |
+
"step": 600
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.66,
|
| 507 |
+
"learning_rate": 0.00011711956521739131,
|
| 508 |
+
"loss": 0.0651,
|
| 509 |
+
"step": 610
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.68,
|
| 513 |
+
"learning_rate": 0.00011576086956521739,
|
| 514 |
+
"loss": 0.1066,
|
| 515 |
+
"step": 620
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.71,
|
| 519 |
+
"learning_rate": 0.00011440217391304349,
|
| 520 |
+
"loss": 0.0589,
|
| 521 |
+
"step": 630
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.74,
|
| 525 |
+
"learning_rate": 0.00011304347826086956,
|
| 526 |
+
"loss": 0.1375,
|
| 527 |
+
"step": 640
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.74,
|
| 531 |
+
"eval_accuracy": 0.9591280653950953,
|
| 532 |
+
"eval_loss": 0.08669634163379669,
|
| 533 |
+
"eval_runtime": 16.6315,
|
| 534 |
+
"eval_samples_per_second": 44.133,
|
| 535 |
+
"eval_steps_per_second": 5.532,
|
| 536 |
+
"step": 640
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.77,
|
| 540 |
+
"learning_rate": 0.00011168478260869566,
|
| 541 |
+
"loss": 0.0579,
|
| 542 |
+
"step": 650
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.79,
|
| 546 |
+
"learning_rate": 0.00011032608695652174,
|
| 547 |
+
"loss": 0.085,
|
| 548 |
+
"step": 660
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.82,
|
| 552 |
+
"learning_rate": 0.00010896739130434783,
|
| 553 |
+
"loss": 0.0802,
|
| 554 |
+
"step": 670
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.85,
|
| 558 |
+
"learning_rate": 0.0001076086956521739,
|
| 559 |
+
"loss": 0.0702,
|
| 560 |
+
"step": 680
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.85,
|
| 564 |
+
"eval_accuracy": 0.9782016348773842,
|
| 565 |
+
"eval_loss": 0.06121528893709183,
|
| 566 |
+
"eval_runtime": 17.1568,
|
| 567 |
+
"eval_samples_per_second": 42.782,
|
| 568 |
+
"eval_steps_per_second": 5.362,
|
| 569 |
+
"step": 680
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.88,
|
| 573 |
+
"learning_rate": 0.00010625000000000001,
|
| 574 |
+
"loss": 0.0445,
|
| 575 |
+
"step": 690
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.9,
|
| 579 |
+
"learning_rate": 0.0001048913043478261,
|
| 580 |
+
"loss": 0.0917,
|
| 581 |
+
"step": 700
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.93,
|
| 585 |
+
"learning_rate": 0.00010353260869565218,
|
| 586 |
+
"loss": 0.0758,
|
| 587 |
+
"step": 710
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.96,
|
| 591 |
+
"learning_rate": 0.00010217391304347828,
|
| 592 |
+
"loss": 0.1081,
|
| 593 |
+
"step": 720
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.96,
|
| 597 |
+
"eval_accuracy": 0.9782016348773842,
|
| 598 |
+
"eval_loss": 0.05692754313349724,
|
| 599 |
+
"eval_runtime": 16.578,
|
| 600 |
+
"eval_samples_per_second": 44.275,
|
| 601 |
+
"eval_steps_per_second": 5.55,
|
| 602 |
+
"step": 720
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.98,
|
| 606 |
+
"learning_rate": 0.00010081521739130436,
|
| 607 |
+
"loss": 0.0587,
|
| 608 |
+
"step": 730
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.01,
|
| 612 |
+
"learning_rate": 9.945652173913043e-05,
|
| 613 |
+
"loss": 0.079,
|
| 614 |
+
"step": 740
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.04,
|
| 618 |
+
"learning_rate": 9.809782608695652e-05,
|
| 619 |
+
"loss": 0.0371,
|
| 620 |
+
"step": 750
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.07,
|
| 624 |
+
"learning_rate": 9.673913043478261e-05,
|
| 625 |
+
"loss": 0.0594,
|
| 626 |
+
"step": 760
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.07,
|
| 630 |
+
"eval_accuracy": 0.9700272479564033,
|
| 631 |
+
"eval_loss": 0.06466467678546906,
|
| 632 |
+
"eval_runtime": 16.8988,
|
| 633 |
+
"eval_samples_per_second": 43.435,
|
| 634 |
+
"eval_steps_per_second": 5.444,
|
| 635 |
+
"step": 760
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.09,
|
| 639 |
+
"learning_rate": 9.538043478260869e-05,
|
| 640 |
+
"loss": 0.0905,
|
| 641 |
+
"step": 770
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.12,
|
| 645 |
+
"learning_rate": 9.402173913043478e-05,
|
| 646 |
+
"loss": 0.0642,
|
| 647 |
+
"step": 780
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.15,
|
| 651 |
+
"learning_rate": 9.266304347826087e-05,
|
| 652 |
+
"loss": 0.0939,
|
| 653 |
+
"step": 790
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.17,
|
| 657 |
+
"learning_rate": 9.130434782608696e-05,
|
| 658 |
+
"loss": 0.0541,
|
| 659 |
+
"step": 800
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.17,
|
| 663 |
+
"eval_accuracy": 0.9741144414168937,
|
| 664 |
+
"eval_loss": 0.08268817514181137,
|
| 665 |
+
"eval_runtime": 17.3128,
|
| 666 |
+
"eval_samples_per_second": 42.396,
|
| 667 |
+
"eval_steps_per_second": 5.314,
|
| 668 |
+
"step": 800
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.2,
|
| 672 |
+
"learning_rate": 8.994565217391305e-05,
|
| 673 |
+
"loss": 0.0772,
|
| 674 |
+
"step": 810
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.23,
|
| 678 |
+
"learning_rate": 8.858695652173914e-05,
|
| 679 |
+
"loss": 0.0625,
|
| 680 |
+
"step": 820
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.26,
|
| 684 |
+
"learning_rate": 8.722826086956522e-05,
|
| 685 |
+
"loss": 0.0259,
|
| 686 |
+
"step": 830
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.28,
|
| 690 |
+
"learning_rate": 8.586956521739131e-05,
|
| 691 |
+
"loss": 0.0257,
|
| 692 |
+
"step": 840
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.28,
|
| 696 |
+
"eval_accuracy": 0.9782016348773842,
|
| 697 |
+
"eval_loss": 0.10866793990135193,
|
| 698 |
+
"eval_runtime": 16.7914,
|
| 699 |
+
"eval_samples_per_second": 43.713,
|
| 700 |
+
"eval_steps_per_second": 5.479,
|
| 701 |
+
"step": 840
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 2.31,
|
| 705 |
+
"learning_rate": 8.45108695652174e-05,
|
| 706 |
+
"loss": 0.1028,
|
| 707 |
+
"step": 850
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.34,
|
| 711 |
+
"learning_rate": 8.315217391304349e-05,
|
| 712 |
+
"loss": 0.0372,
|
| 713 |
+
"step": 860
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.36,
|
| 717 |
+
"learning_rate": 8.179347826086957e-05,
|
| 718 |
+
"loss": 0.1126,
|
| 719 |
+
"step": 870
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.39,
|
| 723 |
+
"learning_rate": 8.043478260869566e-05,
|
| 724 |
+
"loss": 0.0532,
|
| 725 |
+
"step": 880
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.39,
|
| 729 |
+
"eval_accuracy": 0.9686648501362398,
|
| 730 |
+
"eval_loss": 0.05911888927221298,
|
| 731 |
+
"eval_runtime": 17.5644,
|
| 732 |
+
"eval_samples_per_second": 41.789,
|
| 733 |
+
"eval_steps_per_second": 5.238,
|
| 734 |
+
"step": 880
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.42,
|
| 738 |
+
"learning_rate": 7.907608695652175e-05,
|
| 739 |
+
"loss": 0.0423,
|
| 740 |
+
"step": 890
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.45,
|
| 744 |
+
"learning_rate": 7.771739130434783e-05,
|
| 745 |
+
"loss": 0.0261,
|
| 746 |
+
"step": 900
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.47,
|
| 750 |
+
"learning_rate": 7.635869565217392e-05,
|
| 751 |
+
"loss": 0.0879,
|
| 752 |
+
"step": 910
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.5,
|
| 756 |
+
"learning_rate": 7.500000000000001e-05,
|
| 757 |
+
"loss": 0.0858,
|
| 758 |
+
"step": 920
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.5,
|
| 762 |
+
"eval_accuracy": 0.9673024523160763,
|
| 763 |
+
"eval_loss": 0.07639381289482117,
|
| 764 |
+
"eval_runtime": 16.7842,
|
| 765 |
+
"eval_samples_per_second": 43.732,
|
| 766 |
+
"eval_steps_per_second": 5.481,
|
| 767 |
+
"step": 920
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.53,
|
| 771 |
+
"learning_rate": 7.364130434782608e-05,
|
| 772 |
+
"loss": 0.0465,
|
| 773 |
+
"step": 930
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.55,
|
| 777 |
+
"learning_rate": 7.228260869565217e-05,
|
| 778 |
+
"loss": 0.1374,
|
| 779 |
+
"step": 940
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.58,
|
| 783 |
+
"learning_rate": 7.092391304347826e-05,
|
| 784 |
+
"loss": 0.0491,
|
| 785 |
+
"step": 950
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 2.61,
|
| 789 |
+
"learning_rate": 6.956521739130436e-05,
|
| 790 |
+
"loss": 0.0619,
|
| 791 |
+
"step": 960
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.61,
|
| 795 |
+
"eval_accuracy": 0.9782016348773842,
|
| 796 |
+
"eval_loss": 0.05584140494465828,
|
| 797 |
+
"eval_runtime": 16.6696,
|
| 798 |
+
"eval_samples_per_second": 44.032,
|
| 799 |
+
"eval_steps_per_second": 5.519,
|
| 800 |
+
"step": 960
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.64,
|
| 804 |
+
"learning_rate": 6.820652173913043e-05,
|
| 805 |
+
"loss": 0.0465,
|
| 806 |
+
"step": 970
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.66,
|
| 810 |
+
"learning_rate": 6.684782608695652e-05,
|
| 811 |
+
"loss": 0.0398,
|
| 812 |
+
"step": 980
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.69,
|
| 816 |
+
"learning_rate": 6.548913043478261e-05,
|
| 817 |
+
"loss": 0.0594,
|
| 818 |
+
"step": 990
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.72,
|
| 822 |
+
"learning_rate": 6.413043478260869e-05,
|
| 823 |
+
"loss": 0.0371,
|
| 824 |
+
"step": 1000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.72,
|
| 828 |
+
"eval_accuracy": 0.9782016348773842,
|
| 829 |
+
"eval_loss": 0.05662958696484566,
|
| 830 |
+
"eval_runtime": 17.4938,
|
| 831 |
+
"eval_samples_per_second": 41.958,
|
| 832 |
+
"eval_steps_per_second": 5.259,
|
| 833 |
+
"step": 1000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.74,
|
| 837 |
+
"learning_rate": 6.277173913043478e-05,
|
| 838 |
+
"loss": 0.0546,
|
| 839 |
+
"step": 1010
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 2.77,
|
| 843 |
+
"learning_rate": 6.141304347826087e-05,
|
| 844 |
+
"loss": 0.0603,
|
| 845 |
+
"step": 1020
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.8,
|
| 849 |
+
"learning_rate": 6.0054347826086955e-05,
|
| 850 |
+
"loss": 0.0592,
|
| 851 |
+
"step": 1030
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.83,
|
| 855 |
+
"learning_rate": 5.869565217391305e-05,
|
| 856 |
+
"loss": 0.037,
|
| 857 |
+
"step": 1040
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.83,
|
| 861 |
+
"eval_accuracy": 0.9782016348773842,
|
| 862 |
+
"eval_loss": 0.061389077454805374,
|
| 863 |
+
"eval_runtime": 16.7472,
|
| 864 |
+
"eval_samples_per_second": 43.828,
|
| 865 |
+
"eval_steps_per_second": 5.493,
|
| 866 |
+
"step": 1040
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.85,
|
| 870 |
+
"learning_rate": 5.7336956521739136e-05,
|
| 871 |
+
"loss": 0.0693,
|
| 872 |
+
"step": 1050
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.88,
|
| 876 |
+
"learning_rate": 5.5978260869565226e-05,
|
| 877 |
+
"loss": 0.0781,
|
| 878 |
+
"step": 1060
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.91,
|
| 882 |
+
"learning_rate": 5.461956521739131e-05,
|
| 883 |
+
"loss": 0.0662,
|
| 884 |
+
"step": 1070
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.93,
|
| 888 |
+
"learning_rate": 5.32608695652174e-05,
|
| 889 |
+
"loss": 0.0492,
|
| 890 |
+
"step": 1080
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.93,
|
| 894 |
+
"eval_accuracy": 0.9782016348773842,
|
| 895 |
+
"eval_loss": 0.05865919589996338,
|
| 896 |
+
"eval_runtime": 16.6677,
|
| 897 |
+
"eval_samples_per_second": 44.037,
|
| 898 |
+
"eval_steps_per_second": 5.52,
|
| 899 |
+
"step": 1080
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.96,
|
| 903 |
+
"learning_rate": 5.1902173913043484e-05,
|
| 904 |
+
"loss": 0.0518,
|
| 905 |
+
"step": 1090
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.99,
|
| 909 |
+
"learning_rate": 5.054347826086957e-05,
|
| 910 |
+
"loss": 0.0237,
|
| 911 |
+
"step": 1100
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.02,
|
| 915 |
+
"learning_rate": 4.918478260869566e-05,
|
| 916 |
+
"loss": 0.047,
|
| 917 |
+
"step": 1110
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.04,
|
| 921 |
+
"learning_rate": 4.782608695652174e-05,
|
| 922 |
+
"loss": 0.0497,
|
| 923 |
+
"step": 1120
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.04,
|
| 927 |
+
"eval_accuracy": 0.9782016348773842,
|
| 928 |
+
"eval_loss": 0.05894890055060387,
|
| 929 |
+
"eval_runtime": 17.4733,
|
| 930 |
+
"eval_samples_per_second": 42.007,
|
| 931 |
+
"eval_steps_per_second": 5.265,
|
| 932 |
+
"step": 1120
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.07,
|
| 936 |
+
"learning_rate": 4.646739130434783e-05,
|
| 937 |
+
"loss": 0.0302,
|
| 938 |
+
"step": 1130
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.1,
|
| 942 |
+
"learning_rate": 4.5108695652173916e-05,
|
| 943 |
+
"loss": 0.0536,
|
| 944 |
+
"step": 1140
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.12,
|
| 948 |
+
"learning_rate": 4.375e-05,
|
| 949 |
+
"loss": 0.0477,
|
| 950 |
+
"step": 1150
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 3.15,
|
| 954 |
+
"learning_rate": 4.239130434782609e-05,
|
| 955 |
+
"loss": 0.0399,
|
| 956 |
+
"step": 1160
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 3.15,
|
| 960 |
+
"eval_accuracy": 0.9782016348773842,
|
| 961 |
+
"eval_loss": 0.07955215126276016,
|
| 962 |
+
"eval_runtime": 16.6976,
|
| 963 |
+
"eval_samples_per_second": 43.958,
|
| 964 |
+
"eval_steps_per_second": 5.51,
|
| 965 |
+
"step": 1160
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.18,
|
| 969 |
+
"learning_rate": 4.1032608695652174e-05,
|
| 970 |
+
"loss": 0.0466,
|
| 971 |
+
"step": 1170
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.21,
|
| 975 |
+
"learning_rate": 3.9673913043478264e-05,
|
| 976 |
+
"loss": 0.0554,
|
| 977 |
+
"step": 1180
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.23,
|
| 981 |
+
"learning_rate": 3.831521739130435e-05,
|
| 982 |
+
"loss": 0.0568,
|
| 983 |
+
"step": 1190
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 3.26,
|
| 987 |
+
"learning_rate": 3.695652173913043e-05,
|
| 988 |
+
"loss": 0.0436,
|
| 989 |
+
"step": 1200
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.26,
|
| 993 |
+
"eval_accuracy": 0.9782016348773842,
|
| 994 |
+
"eval_loss": 0.05998248606920242,
|
| 995 |
+
"eval_runtime": 16.8038,
|
| 996 |
+
"eval_samples_per_second": 43.68,
|
| 997 |
+
"eval_steps_per_second": 5.475,
|
| 998 |
+
"step": 1200
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.29,
|
| 1002 |
+
"learning_rate": 3.559782608695653e-05,
|
| 1003 |
+
"loss": 0.0393,
|
| 1004 |
+
"step": 1210
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 3.32,
|
| 1008 |
+
"learning_rate": 3.423913043478261e-05,
|
| 1009 |
+
"loss": 0.0575,
|
| 1010 |
+
"step": 1220
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.34,
|
| 1014 |
+
"learning_rate": 3.2880434782608696e-05,
|
| 1015 |
+
"loss": 0.0526,
|
| 1016 |
+
"step": 1230
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.37,
|
| 1020 |
+
"learning_rate": 3.152173913043479e-05,
|
| 1021 |
+
"loss": 0.0514,
|
| 1022 |
+
"step": 1240
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.37,
|
| 1026 |
+
"eval_accuracy": 0.9686648501362398,
|
| 1027 |
+
"eval_loss": 0.06500357389450073,
|
| 1028 |
+
"eval_runtime": 16.7999,
|
| 1029 |
+
"eval_samples_per_second": 43.691,
|
| 1030 |
+
"eval_steps_per_second": 5.476,
|
| 1031 |
+
"step": 1240
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.4,
|
| 1035 |
+
"learning_rate": 3.016304347826087e-05,
|
| 1036 |
+
"loss": 0.0571,
|
| 1037 |
+
"step": 1250
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 3.42,
|
| 1041 |
+
"learning_rate": 2.8804347826086957e-05,
|
| 1042 |
+
"loss": 0.0567,
|
| 1043 |
+
"step": 1260
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 3.45,
|
| 1047 |
+
"learning_rate": 2.7445652173913044e-05,
|
| 1048 |
+
"loss": 0.0537,
|
| 1049 |
+
"step": 1270
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.48,
|
| 1053 |
+
"learning_rate": 2.608695652173913e-05,
|
| 1054 |
+
"loss": 0.0594,
|
| 1055 |
+
"step": 1280
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 3.48,
|
| 1059 |
+
"eval_accuracy": 0.9686648501362398,
|
| 1060 |
+
"eval_loss": 0.07097260653972626,
|
| 1061 |
+
"eval_runtime": 16.7073,
|
| 1062 |
+
"eval_samples_per_second": 43.933,
|
| 1063 |
+
"eval_steps_per_second": 5.507,
|
| 1064 |
+
"step": 1280
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.51,
|
| 1068 |
+
"learning_rate": 2.472826086956522e-05,
|
| 1069 |
+
"loss": 0.0405,
|
| 1070 |
+
"step": 1290
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.53,
|
| 1074 |
+
"learning_rate": 2.3369565217391306e-05,
|
| 1075 |
+
"loss": 0.0681,
|
| 1076 |
+
"step": 1300
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.56,
|
| 1080 |
+
"learning_rate": 2.2010869565217393e-05,
|
| 1081 |
+
"loss": 0.057,
|
| 1082 |
+
"step": 1310
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 3.59,
|
| 1086 |
+
"learning_rate": 2.065217391304348e-05,
|
| 1087 |
+
"loss": 0.0623,
|
| 1088 |
+
"step": 1320
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.59,
|
| 1092 |
+
"eval_accuracy": 0.9673024523160763,
|
| 1093 |
+
"eval_loss": 0.060318876057863235,
|
| 1094 |
+
"eval_runtime": 17.1669,
|
| 1095 |
+
"eval_samples_per_second": 42.757,
|
| 1096 |
+
"eval_steps_per_second": 5.359,
|
| 1097 |
+
"step": 1320
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.61,
|
| 1101 |
+
"learning_rate": 1.9293478260869567e-05,
|
| 1102 |
+
"loss": 0.0284,
|
| 1103 |
+
"step": 1330
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 3.64,
|
| 1107 |
+
"learning_rate": 1.793478260869565e-05,
|
| 1108 |
+
"loss": 0.047,
|
| 1109 |
+
"step": 1340
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.67,
|
| 1113 |
+
"learning_rate": 1.6576086956521738e-05,
|
| 1114 |
+
"loss": 0.0393,
|
| 1115 |
+
"step": 1350
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.7,
|
| 1119 |
+
"learning_rate": 1.5217391304347828e-05,
|
| 1120 |
+
"loss": 0.0497,
|
| 1121 |
+
"step": 1360
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 3.7,
|
| 1125 |
+
"eval_accuracy": 0.9645776566757494,
|
| 1126 |
+
"eval_loss": 0.06646621227264404,
|
| 1127 |
+
"eval_runtime": 17.3679,
|
| 1128 |
+
"eval_samples_per_second": 42.262,
|
| 1129 |
+
"eval_steps_per_second": 5.297,
|
| 1130 |
+
"step": 1360
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.72,
|
| 1134 |
+
"learning_rate": 1.3858695652173914e-05,
|
| 1135 |
+
"loss": 0.0718,
|
| 1136 |
+
"step": 1370
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.75,
|
| 1140 |
+
"learning_rate": 1.25e-05,
|
| 1141 |
+
"loss": 0.0455,
|
| 1142 |
+
"step": 1380
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 3.78,
|
| 1146 |
+
"learning_rate": 1.1141304347826088e-05,
|
| 1147 |
+
"loss": 0.0492,
|
| 1148 |
+
"step": 1390
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.8,
|
| 1152 |
+
"learning_rate": 9.782608695652175e-06,
|
| 1153 |
+
"loss": 0.0453,
|
| 1154 |
+
"step": 1400
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 3.8,
|
| 1158 |
+
"eval_accuracy": 0.9591280653950953,
|
| 1159 |
+
"eval_loss": 0.06604766100645065,
|
| 1160 |
+
"eval_runtime": 16.9729,
|
| 1161 |
+
"eval_samples_per_second": 43.246,
|
| 1162 |
+
"eval_steps_per_second": 5.42,
|
| 1163 |
+
"step": 1400
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 3.83,
|
| 1167 |
+
"learning_rate": 8.423913043478262e-06,
|
| 1168 |
+
"loss": 0.0627,
|
| 1169 |
+
"step": 1410
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 3.86,
|
| 1173 |
+
"learning_rate": 7.065217391304347e-06,
|
| 1174 |
+
"loss": 0.048,
|
| 1175 |
+
"step": 1420
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 3.89,
|
| 1179 |
+
"learning_rate": 5.706521739130435e-06,
|
| 1180 |
+
"loss": 0.0465,
|
| 1181 |
+
"step": 1430
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 3.91,
|
| 1185 |
+
"learning_rate": 4.347826086956522e-06,
|
| 1186 |
+
"loss": 0.0292,
|
| 1187 |
+
"step": 1440
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 3.91,
|
| 1191 |
+
"eval_accuracy": 0.9754768392370572,
|
| 1192 |
+
"eval_loss": 0.06895896792411804,
|
| 1193 |
+
"eval_runtime": 16.756,
|
| 1194 |
+
"eval_samples_per_second": 43.805,
|
| 1195 |
+
"eval_steps_per_second": 5.491,
|
| 1196 |
+
"step": 1440
|
| 1197 |
+
}
|
| 1198 |
+
],
|
| 1199 |
+
"max_steps": 1472,
|
| 1200 |
+
"num_train_epochs": 4,
|
| 1201 |
+
"total_flos": 1.781944272047278e+18,
|
| 1202 |
+
"trial_name": null,
|
| 1203 |
+
"trial_params": null
|
| 1204 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1798fce6b0d8dd1d5f03040dd3346140df5facb73133c871501b1c3a4bdcc7f7
|
| 3 |
+
size 3963
|