Upload 8 files
Browse files- config.json +54 -0
- optimizer.pt +3 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1180 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/bit-50",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BitForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"conv_layer": "std_conv",
|
| 7 |
+
"depths": [
|
| 8 |
+
3,
|
| 9 |
+
4,
|
| 10 |
+
6,
|
| 11 |
+
3
|
| 12 |
+
],
|
| 13 |
+
"drop_path_rate": 0.0,
|
| 14 |
+
"embedding_dynamic_padding": false,
|
| 15 |
+
"embedding_size": 64,
|
| 16 |
+
"global_padding": null,
|
| 17 |
+
"hidden_act": "relu",
|
| 18 |
+
"hidden_sizes": [
|
| 19 |
+
256,
|
| 20 |
+
512,
|
| 21 |
+
1024,
|
| 22 |
+
2048
|
| 23 |
+
],
|
| 24 |
+
"id2label": {
|
| 25 |
+
"0": "Normal",
|
| 26 |
+
"1": "Pharyngitis"
|
| 27 |
+
},
|
| 28 |
+
"label2id": {
|
| 29 |
+
"Normal": 0,
|
| 30 |
+
"Pharyngitis": 1
|
| 31 |
+
},
|
| 32 |
+
"layer_type": "preactivation",
|
| 33 |
+
"model_type": "bit",
|
| 34 |
+
"num_channels": 3,
|
| 35 |
+
"num_groups": 32,
|
| 36 |
+
"out_features": [
|
| 37 |
+
"stage4"
|
| 38 |
+
],
|
| 39 |
+
"out_indices": [
|
| 40 |
+
4
|
| 41 |
+
],
|
| 42 |
+
"output_stride": 32,
|
| 43 |
+
"problem_type": "single_label_classification",
|
| 44 |
+
"stage_names": [
|
| 45 |
+
"stem",
|
| 46 |
+
"stage1",
|
| 47 |
+
"stage2",
|
| 48 |
+
"stage3",
|
| 49 |
+
"stage4"
|
| 50 |
+
],
|
| 51 |
+
"torch_dtype": "float32",
|
| 52 |
+
"transformers_version": "4.31.0",
|
| 53 |
+
"width_factor": 1
|
| 54 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10a6f2be9e9b90fa0086e696649cc382d557894cb4b7d3e18159ba21c1dc413c
|
| 3 |
+
size 188126085
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 448,
|
| 4 |
+
"width": 448
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "BitImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.5,
|
| 19 |
+
0.5,
|
| 20 |
+
0.5
|
| 21 |
+
],
|
| 22 |
+
"resample": 2,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"shortest_edge": 448
|
| 26 |
+
}
|
| 27 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bf3b96c3436625e41d0c0a5bbd64bcb4711113044756449997d7d1f2094a733
|
| 3 |
+
size 94069425
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b90e645f9aec8a283a49863bae8f4c4c680d791881542595f7c97077a6a04db5
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:728cfd753dc06fe9ef1b4dd63fe688c547f84c5a188dba8fe41a5eb8a4336ae2
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "bit-50-Pharyngitis\\checkpoint-36",
|
| 4 |
+
"epoch": 95.23809523809524,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.95,
|
| 12 |
+
"eval_accuracy": 0.7027027027027027,
|
| 13 |
+
"eval_loss": 0.6438681483268738,
|
| 14 |
+
"eval_runtime": 0.5883,
|
| 15 |
+
"eval_samples_per_second": 62.898,
|
| 16 |
+
"eval_steps_per_second": 5.1,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.9,
|
| 21 |
+
"learning_rate": 1e-05,
|
| 22 |
+
"loss": 0.6378,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.9,
|
| 27 |
+
"eval_accuracy": 0.8918918918918919,
|
| 28 |
+
"eval_loss": 0.4361162483692169,
|
| 29 |
+
"eval_runtime": 0.3774,
|
| 30 |
+
"eval_samples_per_second": 98.042,
|
| 31 |
+
"eval_steps_per_second": 7.949,
|
| 32 |
+
"step": 10
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.86,
|
| 36 |
+
"eval_accuracy": 0.972972972972973,
|
| 37 |
+
"eval_loss": 0.2754928469657898,
|
| 38 |
+
"eval_runtime": 0.3737,
|
| 39 |
+
"eval_samples_per_second": 99.02,
|
| 40 |
+
"eval_steps_per_second": 8.029,
|
| 41 |
+
"step": 15
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.81,
|
| 45 |
+
"learning_rate": 2e-05,
|
| 46 |
+
"loss": 0.4237,
|
| 47 |
+
"step": 20
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 4.0,
|
| 51 |
+
"eval_accuracy": 0.918918918918919,
|
| 52 |
+
"eval_loss": 0.21373549103736877,
|
| 53 |
+
"eval_runtime": 0.4065,
|
| 54 |
+
"eval_samples_per_second": 91.026,
|
| 55 |
+
"eval_steps_per_second": 7.381,
|
| 56 |
+
"step": 21
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.95,
|
| 60 |
+
"eval_accuracy": 0.9459459459459459,
|
| 61 |
+
"eval_loss": 0.1247631162405014,
|
| 62 |
+
"eval_runtime": 0.3977,
|
| 63 |
+
"eval_samples_per_second": 93.032,
|
| 64 |
+
"eval_steps_per_second": 7.543,
|
| 65 |
+
"step": 26
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 5.71,
|
| 69 |
+
"learning_rate": 3e-05,
|
| 70 |
+
"loss": 0.2592,
|
| 71 |
+
"step": 30
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.9,
|
| 75 |
+
"eval_accuracy": 0.972972972972973,
|
| 76 |
+
"eval_loss": 0.08167269825935364,
|
| 77 |
+
"eval_runtime": 0.3971,
|
| 78 |
+
"eval_samples_per_second": 93.166,
|
| 79 |
+
"eval_steps_per_second": 7.554,
|
| 80 |
+
"step": 31
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.86,
|
| 84 |
+
"eval_accuracy": 1.0,
|
| 85 |
+
"eval_loss": 0.06954346597194672,
|
| 86 |
+
"eval_runtime": 0.3842,
|
| 87 |
+
"eval_samples_per_second": 96.305,
|
| 88 |
+
"eval_steps_per_second": 7.809,
|
| 89 |
+
"step": 36
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 7.62,
|
| 93 |
+
"learning_rate": 4e-05,
|
| 94 |
+
"loss": 0.1775,
|
| 95 |
+
"step": 40
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 8.0,
|
| 99 |
+
"eval_accuracy": 0.918918918918919,
|
| 100 |
+
"eval_loss": 0.23191875219345093,
|
| 101 |
+
"eval_runtime": 0.3999,
|
| 102 |
+
"eval_samples_per_second": 92.518,
|
| 103 |
+
"eval_steps_per_second": 7.501,
|
| 104 |
+
"step": 42
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.95,
|
| 108 |
+
"eval_accuracy": 0.972972972972973,
|
| 109 |
+
"eval_loss": 0.052055422216653824,
|
| 110 |
+
"eval_runtime": 0.4011,
|
| 111 |
+
"eval_samples_per_second": 92.257,
|
| 112 |
+
"eval_steps_per_second": 7.48,
|
| 113 |
+
"step": 47
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 9.52,
|
| 117 |
+
"learning_rate": 5e-05,
|
| 118 |
+
"loss": 0.1805,
|
| 119 |
+
"step": 50
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 9.9,
|
| 123 |
+
"eval_accuracy": 1.0,
|
| 124 |
+
"eval_loss": 0.047812674194574356,
|
| 125 |
+
"eval_runtime": 0.3975,
|
| 126 |
+
"eval_samples_per_second": 93.076,
|
| 127 |
+
"eval_steps_per_second": 7.547,
|
| 128 |
+
"step": 52
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.86,
|
| 132 |
+
"eval_accuracy": 1.0,
|
| 133 |
+
"eval_loss": 0.04274846613407135,
|
| 134 |
+
"eval_runtime": 0.4052,
|
| 135 |
+
"eval_samples_per_second": 91.313,
|
| 136 |
+
"eval_steps_per_second": 7.404,
|
| 137 |
+
"step": 57
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 11.43,
|
| 141 |
+
"learning_rate": 4.888888888888889e-05,
|
| 142 |
+
"loss": 0.171,
|
| 143 |
+
"step": 60
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 12.0,
|
| 147 |
+
"eval_accuracy": 0.8918918918918919,
|
| 148 |
+
"eval_loss": 0.1753544956445694,
|
| 149 |
+
"eval_runtime": 0.4139,
|
| 150 |
+
"eval_samples_per_second": 89.385,
|
| 151 |
+
"eval_steps_per_second": 7.247,
|
| 152 |
+
"step": 63
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 12.95,
|
| 156 |
+
"eval_accuracy": 0.9459459459459459,
|
| 157 |
+
"eval_loss": 0.06655322760343552,
|
| 158 |
+
"eval_runtime": 0.3887,
|
| 159 |
+
"eval_samples_per_second": 95.191,
|
| 160 |
+
"eval_steps_per_second": 7.718,
|
| 161 |
+
"step": 68
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 13.33,
|
| 165 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 166 |
+
"loss": 0.089,
|
| 167 |
+
"step": 70
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 13.9,
|
| 171 |
+
"eval_accuracy": 1.0,
|
| 172 |
+
"eval_loss": 0.02494250051677227,
|
| 173 |
+
"eval_runtime": 0.4123,
|
| 174 |
+
"eval_samples_per_second": 89.751,
|
| 175 |
+
"eval_steps_per_second": 7.277,
|
| 176 |
+
"step": 73
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 14.86,
|
| 180 |
+
"eval_accuracy": 1.0,
|
| 181 |
+
"eval_loss": 0.019040122628211975,
|
| 182 |
+
"eval_runtime": 0.4396,
|
| 183 |
+
"eval_samples_per_second": 84.171,
|
| 184 |
+
"eval_steps_per_second": 6.825,
|
| 185 |
+
"step": 78
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 15.24,
|
| 189 |
+
"learning_rate": 4.666666666666667e-05,
|
| 190 |
+
"loss": 0.1093,
|
| 191 |
+
"step": 80
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 16.0,
|
| 195 |
+
"eval_accuracy": 0.9459459459459459,
|
| 196 |
+
"eval_loss": 0.06111358851194382,
|
| 197 |
+
"eval_runtime": 0.4317,
|
| 198 |
+
"eval_samples_per_second": 85.699,
|
| 199 |
+
"eval_steps_per_second": 6.949,
|
| 200 |
+
"step": 84
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 16.95,
|
| 204 |
+
"eval_accuracy": 0.918918918918919,
|
| 205 |
+
"eval_loss": 0.16683633625507355,
|
| 206 |
+
"eval_runtime": 0.394,
|
| 207 |
+
"eval_samples_per_second": 93.907,
|
| 208 |
+
"eval_steps_per_second": 7.614,
|
| 209 |
+
"step": 89
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 17.14,
|
| 213 |
+
"learning_rate": 4.555555555555556e-05,
|
| 214 |
+
"loss": 0.1025,
|
| 215 |
+
"step": 90
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 17.9,
|
| 219 |
+
"eval_accuracy": 0.972972972972973,
|
| 220 |
+
"eval_loss": 0.05101567134261131,
|
| 221 |
+
"eval_runtime": 0.3847,
|
| 222 |
+
"eval_samples_per_second": 96.177,
|
| 223 |
+
"eval_steps_per_second": 7.798,
|
| 224 |
+
"step": 94
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 18.86,
|
| 228 |
+
"eval_accuracy": 1.0,
|
| 229 |
+
"eval_loss": 0.010445931926369667,
|
| 230 |
+
"eval_runtime": 0.3987,
|
| 231 |
+
"eval_samples_per_second": 92.805,
|
| 232 |
+
"eval_steps_per_second": 7.525,
|
| 233 |
+
"step": 99
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 19.05,
|
| 237 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 238 |
+
"loss": 0.12,
|
| 239 |
+
"step": 100
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 20.0,
|
| 243 |
+
"eval_accuracy": 0.8918918918918919,
|
| 244 |
+
"eval_loss": 0.18418262898921967,
|
| 245 |
+
"eval_runtime": 0.391,
|
| 246 |
+
"eval_samples_per_second": 94.632,
|
| 247 |
+
"eval_steps_per_second": 7.673,
|
| 248 |
+
"step": 105
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 20.95,
|
| 252 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 253 |
+
"loss": 0.0996,
|
| 254 |
+
"step": 110
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 20.95,
|
| 258 |
+
"eval_accuracy": 1.0,
|
| 259 |
+
"eval_loss": 0.011865493841469288,
|
| 260 |
+
"eval_runtime": 0.3899,
|
| 261 |
+
"eval_samples_per_second": 94.901,
|
| 262 |
+
"eval_steps_per_second": 7.695,
|
| 263 |
+
"step": 110
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 21.9,
|
| 267 |
+
"eval_accuracy": 0.972972972972973,
|
| 268 |
+
"eval_loss": 0.03581492602825165,
|
| 269 |
+
"eval_runtime": 0.4047,
|
| 270 |
+
"eval_samples_per_second": 91.415,
|
| 271 |
+
"eval_steps_per_second": 7.412,
|
| 272 |
+
"step": 115
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 22.86,
|
| 276 |
+
"learning_rate": 4.222222222222222e-05,
|
| 277 |
+
"loss": 0.0933,
|
| 278 |
+
"step": 120
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 22.86,
|
| 282 |
+
"eval_accuracy": 0.9459459459459459,
|
| 283 |
+
"eval_loss": 0.11507910490036011,
|
| 284 |
+
"eval_runtime": 0.4091,
|
| 285 |
+
"eval_samples_per_second": 90.451,
|
| 286 |
+
"eval_steps_per_second": 7.334,
|
| 287 |
+
"step": 120
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 24.0,
|
| 291 |
+
"eval_accuracy": 0.972972972972973,
|
| 292 |
+
"eval_loss": 0.08254072815179825,
|
| 293 |
+
"eval_runtime": 0.3864,
|
| 294 |
+
"eval_samples_per_second": 95.759,
|
| 295 |
+
"eval_steps_per_second": 7.764,
|
| 296 |
+
"step": 126
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 24.76,
|
| 300 |
+
"learning_rate": 4.111111111111111e-05,
|
| 301 |
+
"loss": 0.1118,
|
| 302 |
+
"step": 130
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 24.95,
|
| 306 |
+
"eval_accuracy": 0.972972972972973,
|
| 307 |
+
"eval_loss": 0.08668244630098343,
|
| 308 |
+
"eval_runtime": 0.3898,
|
| 309 |
+
"eval_samples_per_second": 94.932,
|
| 310 |
+
"eval_steps_per_second": 7.697,
|
| 311 |
+
"step": 131
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 25.9,
|
| 315 |
+
"eval_accuracy": 1.0,
|
| 316 |
+
"eval_loss": 0.009897518903017044,
|
| 317 |
+
"eval_runtime": 0.4036,
|
| 318 |
+
"eval_samples_per_second": 91.68,
|
| 319 |
+
"eval_steps_per_second": 7.434,
|
| 320 |
+
"step": 136
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 26.67,
|
| 324 |
+
"learning_rate": 4e-05,
|
| 325 |
+
"loss": 0.0471,
|
| 326 |
+
"step": 140
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 26.86,
|
| 330 |
+
"eval_accuracy": 1.0,
|
| 331 |
+
"eval_loss": 0.019395073875784874,
|
| 332 |
+
"eval_runtime": 0.3954,
|
| 333 |
+
"eval_samples_per_second": 93.584,
|
| 334 |
+
"eval_steps_per_second": 7.588,
|
| 335 |
+
"step": 141
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 28.0,
|
| 339 |
+
"eval_accuracy": 1.0,
|
| 340 |
+
"eval_loss": 0.0031759734265506268,
|
| 341 |
+
"eval_runtime": 0.3912,
|
| 342 |
+
"eval_samples_per_second": 94.57,
|
| 343 |
+
"eval_steps_per_second": 7.668,
|
| 344 |
+
"step": 147
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 28.57,
|
| 348 |
+
"learning_rate": 3.888888888888889e-05,
|
| 349 |
+
"loss": 0.0686,
|
| 350 |
+
"step": 150
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 28.95,
|
| 354 |
+
"eval_accuracy": 1.0,
|
| 355 |
+
"eval_loss": 0.0057038371451199055,
|
| 356 |
+
"eval_runtime": 0.3906,
|
| 357 |
+
"eval_samples_per_second": 94.728,
|
| 358 |
+
"eval_steps_per_second": 7.681,
|
| 359 |
+
"step": 152
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 29.9,
|
| 363 |
+
"eval_accuracy": 1.0,
|
| 364 |
+
"eval_loss": 0.0014269119128584862,
|
| 365 |
+
"eval_runtime": 0.3905,
|
| 366 |
+
"eval_samples_per_second": 94.751,
|
| 367 |
+
"eval_steps_per_second": 7.682,
|
| 368 |
+
"step": 157
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 30.48,
|
| 372 |
+
"learning_rate": 3.777777777777778e-05,
|
| 373 |
+
"loss": 0.0692,
|
| 374 |
+
"step": 160
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 30.86,
|
| 378 |
+
"eval_accuracy": 0.918918918918919,
|
| 379 |
+
"eval_loss": 0.34027108550071716,
|
| 380 |
+
"eval_runtime": 0.4009,
|
| 381 |
+
"eval_samples_per_second": 92.295,
|
| 382 |
+
"eval_steps_per_second": 7.483,
|
| 383 |
+
"step": 162
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 32.0,
|
| 387 |
+
"eval_accuracy": 1.0,
|
| 388 |
+
"eval_loss": 0.011479969136416912,
|
| 389 |
+
"eval_runtime": 0.4005,
|
| 390 |
+
"eval_samples_per_second": 92.395,
|
| 391 |
+
"eval_steps_per_second": 7.491,
|
| 392 |
+
"step": 168
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 32.38,
|
| 396 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 397 |
+
"loss": 0.0912,
|
| 398 |
+
"step": 170
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 32.95,
|
| 402 |
+
"eval_accuracy": 0.9459459459459459,
|
| 403 |
+
"eval_loss": 0.0989471897482872,
|
| 404 |
+
"eval_runtime": 0.4052,
|
| 405 |
+
"eval_samples_per_second": 91.323,
|
| 406 |
+
"eval_steps_per_second": 7.405,
|
| 407 |
+
"step": 173
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 33.9,
|
| 411 |
+
"eval_accuracy": 0.9459459459459459,
|
| 412 |
+
"eval_loss": 0.10641559958457947,
|
| 413 |
+
"eval_runtime": 0.3889,
|
| 414 |
+
"eval_samples_per_second": 95.131,
|
| 415 |
+
"eval_steps_per_second": 7.713,
|
| 416 |
+
"step": 178
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 34.29,
|
| 420 |
+
"learning_rate": 3.555555555555556e-05,
|
| 421 |
+
"loss": 0.0994,
|
| 422 |
+
"step": 180
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 34.86,
|
| 426 |
+
"eval_accuracy": 0.972972972972973,
|
| 427 |
+
"eval_loss": 0.09466935694217682,
|
| 428 |
+
"eval_runtime": 0.3912,
|
| 429 |
+
"eval_samples_per_second": 94.569,
|
| 430 |
+
"eval_steps_per_second": 7.668,
|
| 431 |
+
"step": 183
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 36.0,
|
| 435 |
+
"eval_accuracy": 0.9459459459459459,
|
| 436 |
+
"eval_loss": 0.10136424005031586,
|
| 437 |
+
"eval_runtime": 0.4255,
|
| 438 |
+
"eval_samples_per_second": 86.966,
|
| 439 |
+
"eval_steps_per_second": 7.051,
|
| 440 |
+
"step": 189
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 36.19,
|
| 444 |
+
"learning_rate": 3.444444444444445e-05,
|
| 445 |
+
"loss": 0.0561,
|
| 446 |
+
"step": 190
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 36.95,
|
| 450 |
+
"eval_accuracy": 0.972972972972973,
|
| 451 |
+
"eval_loss": 0.0519096776843071,
|
| 452 |
+
"eval_runtime": 0.4107,
|
| 453 |
+
"eval_samples_per_second": 90.096,
|
| 454 |
+
"eval_steps_per_second": 7.305,
|
| 455 |
+
"step": 194
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 37.9,
|
| 459 |
+
"eval_accuracy": 0.918918918918919,
|
| 460 |
+
"eval_loss": 0.16669504344463348,
|
| 461 |
+
"eval_runtime": 0.4065,
|
| 462 |
+
"eval_samples_per_second": 91.027,
|
| 463 |
+
"eval_steps_per_second": 7.381,
|
| 464 |
+
"step": 199
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 38.1,
|
| 468 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 469 |
+
"loss": 0.0516,
|
| 470 |
+
"step": 200
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 38.86,
|
| 474 |
+
"eval_accuracy": 0.918918918918919,
|
| 475 |
+
"eval_loss": 0.3604719936847687,
|
| 476 |
+
"eval_runtime": 0.3971,
|
| 477 |
+
"eval_samples_per_second": 93.183,
|
| 478 |
+
"eval_steps_per_second": 7.555,
|
| 479 |
+
"step": 204
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 40.0,
|
| 483 |
+
"learning_rate": 3.222222222222223e-05,
|
| 484 |
+
"loss": 0.0535,
|
| 485 |
+
"step": 210
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 40.0,
|
| 489 |
+
"eval_accuracy": 0.972972972972973,
|
| 490 |
+
"eval_loss": 0.044684119522571564,
|
| 491 |
+
"eval_runtime": 0.3775,
|
| 492 |
+
"eval_samples_per_second": 98.002,
|
| 493 |
+
"eval_steps_per_second": 7.946,
|
| 494 |
+
"step": 210
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 40.95,
|
| 498 |
+
"eval_accuracy": 0.918918918918919,
|
| 499 |
+
"eval_loss": 0.1711174100637436,
|
| 500 |
+
"eval_runtime": 0.3876,
|
| 501 |
+
"eval_samples_per_second": 95.468,
|
| 502 |
+
"eval_steps_per_second": 7.741,
|
| 503 |
+
"step": 215
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 41.9,
|
| 507 |
+
"learning_rate": 3.111111111111111e-05,
|
| 508 |
+
"loss": 0.0475,
|
| 509 |
+
"step": 220
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 41.9,
|
| 513 |
+
"eval_accuracy": 0.9459459459459459,
|
| 514 |
+
"eval_loss": 0.10387804359197617,
|
| 515 |
+
"eval_runtime": 0.3953,
|
| 516 |
+
"eval_samples_per_second": 93.597,
|
| 517 |
+
"eval_steps_per_second": 7.589,
|
| 518 |
+
"step": 220
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 42.86,
|
| 522 |
+
"eval_accuracy": 1.0,
|
| 523 |
+
"eval_loss": 0.029212407767772675,
|
| 524 |
+
"eval_runtime": 0.3915,
|
| 525 |
+
"eval_samples_per_second": 94.5,
|
| 526 |
+
"eval_steps_per_second": 7.662,
|
| 527 |
+
"step": 225
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 43.81,
|
| 531 |
+
"learning_rate": 3e-05,
|
| 532 |
+
"loss": 0.0504,
|
| 533 |
+
"step": 230
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 44.0,
|
| 537 |
+
"eval_accuracy": 1.0,
|
| 538 |
+
"eval_loss": 0.014002898707985878,
|
| 539 |
+
"eval_runtime": 0.3889,
|
| 540 |
+
"eval_samples_per_second": 95.145,
|
| 541 |
+
"eval_steps_per_second": 7.714,
|
| 542 |
+
"step": 231
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 44.95,
|
| 546 |
+
"eval_accuracy": 0.8918918918918919,
|
| 547 |
+
"eval_loss": 0.27451202273368835,
|
| 548 |
+
"eval_runtime": 0.4255,
|
| 549 |
+
"eval_samples_per_second": 86.962,
|
| 550 |
+
"eval_steps_per_second": 7.051,
|
| 551 |
+
"step": 236
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 45.71,
|
| 555 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 556 |
+
"loss": 0.0432,
|
| 557 |
+
"step": 240
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 45.9,
|
| 561 |
+
"eval_accuracy": 1.0,
|
| 562 |
+
"eval_loss": 0.002892308635637164,
|
| 563 |
+
"eval_runtime": 0.3957,
|
| 564 |
+
"eval_samples_per_second": 93.507,
|
| 565 |
+
"eval_steps_per_second": 7.582,
|
| 566 |
+
"step": 241
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 46.86,
|
| 570 |
+
"eval_accuracy": 0.8648648648648649,
|
| 571 |
+
"eval_loss": 0.4316161274909973,
|
| 572 |
+
"eval_runtime": 0.4242,
|
| 573 |
+
"eval_samples_per_second": 87.218,
|
| 574 |
+
"eval_steps_per_second": 7.072,
|
| 575 |
+
"step": 246
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 47.62,
|
| 579 |
+
"learning_rate": 2.777777777777778e-05,
|
| 580 |
+
"loss": 0.0992,
|
| 581 |
+
"step": 250
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 48.0,
|
| 585 |
+
"eval_accuracy": 1.0,
|
| 586 |
+
"eval_loss": 0.015067849308252335,
|
| 587 |
+
"eval_runtime": 0.3902,
|
| 588 |
+
"eval_samples_per_second": 94.825,
|
| 589 |
+
"eval_steps_per_second": 7.688,
|
| 590 |
+
"step": 252
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 48.95,
|
| 594 |
+
"eval_accuracy": 1.0,
|
| 595 |
+
"eval_loss": 0.00749516487121582,
|
| 596 |
+
"eval_runtime": 0.3915,
|
| 597 |
+
"eval_samples_per_second": 94.506,
|
| 598 |
+
"eval_steps_per_second": 7.663,
|
| 599 |
+
"step": 257
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 49.52,
|
| 603 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 604 |
+
"loss": 0.1531,
|
| 605 |
+
"step": 260
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 49.9,
|
| 609 |
+
"eval_accuracy": 0.8648648648648649,
|
| 610 |
+
"eval_loss": 0.3624305725097656,
|
| 611 |
+
"eval_runtime": 0.4028,
|
| 612 |
+
"eval_samples_per_second": 91.854,
|
| 613 |
+
"eval_steps_per_second": 7.448,
|
| 614 |
+
"step": 262
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 50.86,
|
| 618 |
+
"eval_accuracy": 0.972972972972973,
|
| 619 |
+
"eval_loss": 0.036536574363708496,
|
| 620 |
+
"eval_runtime": 0.3932,
|
| 621 |
+
"eval_samples_per_second": 94.091,
|
| 622 |
+
"eval_steps_per_second": 7.629,
|
| 623 |
+
"step": 267
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 51.43,
|
| 627 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 628 |
+
"loss": 0.0622,
|
| 629 |
+
"step": 270
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 52.0,
|
| 633 |
+
"eval_accuracy": 0.972972972972973,
|
| 634 |
+
"eval_loss": 0.20016101002693176,
|
| 635 |
+
"eval_runtime": 0.4002,
|
| 636 |
+
"eval_samples_per_second": 92.444,
|
| 637 |
+
"eval_steps_per_second": 7.495,
|
| 638 |
+
"step": 273
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 52.95,
|
| 642 |
+
"eval_accuracy": 0.972972972972973,
|
| 643 |
+
"eval_loss": 0.12544459104537964,
|
| 644 |
+
"eval_runtime": 0.4119,
|
| 645 |
+
"eval_samples_per_second": 89.837,
|
| 646 |
+
"eval_steps_per_second": 7.284,
|
| 647 |
+
"step": 278
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 53.33,
|
| 651 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 652 |
+
"loss": 0.0432,
|
| 653 |
+
"step": 280
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 53.9,
|
| 657 |
+
"eval_accuracy": 0.9459459459459459,
|
| 658 |
+
"eval_loss": 0.0909779816865921,
|
| 659 |
+
"eval_runtime": 0.3955,
|
| 660 |
+
"eval_samples_per_second": 93.545,
|
| 661 |
+
"eval_steps_per_second": 7.585,
|
| 662 |
+
"step": 283
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 54.86,
|
| 666 |
+
"eval_accuracy": 0.8918918918918919,
|
| 667 |
+
"eval_loss": 0.3727685809135437,
|
| 668 |
+
"eval_runtime": 0.3993,
|
| 669 |
+
"eval_samples_per_second": 92.669,
|
| 670 |
+
"eval_steps_per_second": 7.514,
|
| 671 |
+
"step": 288
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 55.24,
|
| 675 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 676 |
+
"loss": 0.0531,
|
| 677 |
+
"step": 290
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 56.0,
|
| 681 |
+
"eval_accuracy": 0.9459459459459459,
|
| 682 |
+
"eval_loss": 0.10307420045137405,
|
| 683 |
+
"eval_runtime": 0.3958,
|
| 684 |
+
"eval_samples_per_second": 93.478,
|
| 685 |
+
"eval_steps_per_second": 7.579,
|
| 686 |
+
"step": 294
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 56.95,
|
| 690 |
+
"eval_accuracy": 1.0,
|
| 691 |
+
"eval_loss": 0.002981973346322775,
|
| 692 |
+
"eval_runtime": 0.3986,
|
| 693 |
+
"eval_samples_per_second": 92.827,
|
| 694 |
+
"eval_steps_per_second": 7.526,
|
| 695 |
+
"step": 299
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 57.14,
|
| 699 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 700 |
+
"loss": 0.0731,
|
| 701 |
+
"step": 300
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 57.9,
|
| 705 |
+
"eval_accuracy": 0.9459459459459459,
|
| 706 |
+
"eval_loss": 0.2001199871301651,
|
| 707 |
+
"eval_runtime": 0.4153,
|
| 708 |
+
"eval_samples_per_second": 89.082,
|
| 709 |
+
"eval_steps_per_second": 7.223,
|
| 710 |
+
"step": 304
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 58.86,
|
| 714 |
+
"eval_accuracy": 0.918918918918919,
|
| 715 |
+
"eval_loss": 0.2389511615037918,
|
| 716 |
+
"eval_runtime": 0.3911,
|
| 717 |
+
"eval_samples_per_second": 94.615,
|
| 718 |
+
"eval_steps_per_second": 7.672,
|
| 719 |
+
"step": 309
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 59.05,
|
| 723 |
+
"learning_rate": 2.111111111111111e-05,
|
| 724 |
+
"loss": 0.0529,
|
| 725 |
+
"step": 310
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 60.0,
|
| 729 |
+
"eval_accuracy": 0.9459459459459459,
|
| 730 |
+
"eval_loss": 0.13383528590202332,
|
| 731 |
+
"eval_runtime": 0.3898,
|
| 732 |
+
"eval_samples_per_second": 94.919,
|
| 733 |
+
"eval_steps_per_second": 7.696,
|
| 734 |
+
"step": 315
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 60.95,
|
| 738 |
+
"learning_rate": 2e-05,
|
| 739 |
+
"loss": 0.0203,
|
| 740 |
+
"step": 320
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 60.95,
|
| 744 |
+
"eval_accuracy": 0.9459459459459459,
|
| 745 |
+
"eval_loss": 0.22631436586380005,
|
| 746 |
+
"eval_runtime": 0.3946,
|
| 747 |
+
"eval_samples_per_second": 93.757,
|
| 748 |
+
"eval_steps_per_second": 7.602,
|
| 749 |
+
"step": 320
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 61.9,
|
| 753 |
+
"eval_accuracy": 0.9459459459459459,
|
| 754 |
+
"eval_loss": 0.16640439629554749,
|
| 755 |
+
"eval_runtime": 0.3813,
|
| 756 |
+
"eval_samples_per_second": 97.045,
|
| 757 |
+
"eval_steps_per_second": 7.868,
|
| 758 |
+
"step": 325
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 62.86,
|
| 762 |
+
"learning_rate": 1.888888888888889e-05,
|
| 763 |
+
"loss": 0.0345,
|
| 764 |
+
"step": 330
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 62.86,
|
| 768 |
+
"eval_accuracy": 1.0,
|
| 769 |
+
"eval_loss": 0.006216500885784626,
|
| 770 |
+
"eval_runtime": 0.3909,
|
| 771 |
+
"eval_samples_per_second": 94.661,
|
| 772 |
+
"eval_steps_per_second": 7.675,
|
| 773 |
+
"step": 330
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 64.0,
|
| 777 |
+
"eval_accuracy": 1.0,
|
| 778 |
+
"eval_loss": 0.0056242975406348705,
|
| 779 |
+
"eval_runtime": 0.4048,
|
| 780 |
+
"eval_samples_per_second": 91.408,
|
| 781 |
+
"eval_steps_per_second": 7.411,
|
| 782 |
+
"step": 336
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 64.76,
|
| 786 |
+
"learning_rate": 1.777777777777778e-05,
|
| 787 |
+
"loss": 0.0595,
|
| 788 |
+
"step": 340
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 64.95,
|
| 792 |
+
"eval_accuracy": 1.0,
|
| 793 |
+
"eval_loss": 0.022064007818698883,
|
| 794 |
+
"eval_runtime": 0.3988,
|
| 795 |
+
"eval_samples_per_second": 92.779,
|
| 796 |
+
"eval_steps_per_second": 7.523,
|
| 797 |
+
"step": 341
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 65.9,
|
| 801 |
+
"eval_accuracy": 1.0,
|
| 802 |
+
"eval_loss": 0.01646520011126995,
|
| 803 |
+
"eval_runtime": 0.4012,
|
| 804 |
+
"eval_samples_per_second": 92.225,
|
| 805 |
+
"eval_steps_per_second": 7.478,
|
| 806 |
+
"step": 346
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 66.67,
|
| 810 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 811 |
+
"loss": 0.0278,
|
| 812 |
+
"step": 350
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 66.86,
|
| 816 |
+
"eval_accuracy": 1.0,
|
| 817 |
+
"eval_loss": 0.01749444752931595,
|
| 818 |
+
"eval_runtime": 0.404,
|
| 819 |
+
"eval_samples_per_second": 91.579,
|
| 820 |
+
"eval_steps_per_second": 7.425,
|
| 821 |
+
"step": 351
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 68.0,
|
| 825 |
+
"eval_accuracy": 1.0,
|
| 826 |
+
"eval_loss": 0.017633311450481415,
|
| 827 |
+
"eval_runtime": 0.3933,
|
| 828 |
+
"eval_samples_per_second": 94.074,
|
| 829 |
+
"eval_steps_per_second": 7.628,
|
| 830 |
+
"step": 357
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 68.57,
|
| 834 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 835 |
+
"loss": 0.1035,
|
| 836 |
+
"step": 360
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 68.95,
|
| 840 |
+
"eval_accuracy": 0.918918918918919,
|
| 841 |
+
"eval_loss": 0.15788349509239197,
|
| 842 |
+
"eval_runtime": 0.3978,
|
| 843 |
+
"eval_samples_per_second": 93.022,
|
| 844 |
+
"eval_steps_per_second": 7.542,
|
| 845 |
+
"step": 362
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 69.9,
|
| 849 |
+
"eval_accuracy": 0.972972972972973,
|
| 850 |
+
"eval_loss": 0.06550092250108719,
|
| 851 |
+
"eval_runtime": 0.3834,
|
| 852 |
+
"eval_samples_per_second": 96.515,
|
| 853 |
+
"eval_steps_per_second": 7.826,
|
| 854 |
+
"step": 367
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 70.48,
|
| 858 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 859 |
+
"loss": 0.0466,
|
| 860 |
+
"step": 370
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 70.86,
|
| 864 |
+
"eval_accuracy": 1.0,
|
| 865 |
+
"eval_loss": 0.00981216412037611,
|
| 866 |
+
"eval_runtime": 0.4023,
|
| 867 |
+
"eval_samples_per_second": 91.96,
|
| 868 |
+
"eval_steps_per_second": 7.456,
|
| 869 |
+
"step": 372
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 72.0,
|
| 873 |
+
"eval_accuracy": 0.9459459459459459,
|
| 874 |
+
"eval_loss": 0.0761876329779625,
|
| 875 |
+
"eval_runtime": 0.3968,
|
| 876 |
+
"eval_samples_per_second": 93.24,
|
| 877 |
+
"eval_steps_per_second": 7.56,
|
| 878 |
+
"step": 378
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 72.38,
|
| 882 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 883 |
+
"loss": 0.0719,
|
| 884 |
+
"step": 380
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 72.95,
|
| 888 |
+
"eval_accuracy": 0.9459459459459459,
|
| 889 |
+
"eval_loss": 0.26816752552986145,
|
| 890 |
+
"eval_runtime": 0.4037,
|
| 891 |
+
"eval_samples_per_second": 91.659,
|
| 892 |
+
"eval_steps_per_second": 7.432,
|
| 893 |
+
"step": 383
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 73.9,
|
| 897 |
+
"eval_accuracy": 0.972972972972973,
|
| 898 |
+
"eval_loss": 0.03098950907588005,
|
| 899 |
+
"eval_runtime": 0.3999,
|
| 900 |
+
"eval_samples_per_second": 92.524,
|
| 901 |
+
"eval_steps_per_second": 7.502,
|
| 902 |
+
"step": 388
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 74.29,
|
| 906 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 907 |
+
"loss": 0.0144,
|
| 908 |
+
"step": 390
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 74.86,
|
| 912 |
+
"eval_accuracy": 1.0,
|
| 913 |
+
"eval_loss": 0.0038737300783395767,
|
| 914 |
+
"eval_runtime": 0.4143,
|
| 915 |
+
"eval_samples_per_second": 89.311,
|
| 916 |
+
"eval_steps_per_second": 7.241,
|
| 917 |
+
"step": 393
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 76.0,
|
| 921 |
+
"eval_accuracy": 0.972972972972973,
|
| 922 |
+
"eval_loss": 0.055370986461639404,
|
| 923 |
+
"eval_runtime": 0.387,
|
| 924 |
+
"eval_samples_per_second": 95.603,
|
| 925 |
+
"eval_steps_per_second": 7.752,
|
| 926 |
+
"step": 399
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 76.19,
|
| 930 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 931 |
+
"loss": 0.0613,
|
| 932 |
+
"step": 400
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 76.95,
|
| 936 |
+
"eval_accuracy": 0.972972972972973,
|
| 937 |
+
"eval_loss": 0.05363788455724716,
|
| 938 |
+
"eval_runtime": 0.3953,
|
| 939 |
+
"eval_samples_per_second": 93.59,
|
| 940 |
+
"eval_steps_per_second": 7.588,
|
| 941 |
+
"step": 404
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 77.9,
|
| 945 |
+
"eval_accuracy": 0.972972972972973,
|
| 946 |
+
"eval_loss": 0.03543579578399658,
|
| 947 |
+
"eval_runtime": 0.4021,
|
| 948 |
+
"eval_samples_per_second": 92.01,
|
| 949 |
+
"eval_steps_per_second": 7.46,
|
| 950 |
+
"step": 409
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 78.1,
|
| 954 |
+
"learning_rate": 1e-05,
|
| 955 |
+
"loss": 0.0307,
|
| 956 |
+
"step": 410
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 78.86,
|
| 960 |
+
"eval_accuracy": 0.972972972972973,
|
| 961 |
+
"eval_loss": 0.02702740766108036,
|
| 962 |
+
"eval_runtime": 0.4203,
|
| 963 |
+
"eval_samples_per_second": 88.032,
|
| 964 |
+
"eval_steps_per_second": 7.138,
|
| 965 |
+
"step": 414
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 80.0,
|
| 969 |
+
"learning_rate": 8.88888888888889e-06,
|
| 970 |
+
"loss": 0.0253,
|
| 971 |
+
"step": 420
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 80.0,
|
| 975 |
+
"eval_accuracy": 1.0,
|
| 976 |
+
"eval_loss": 0.005909389816224575,
|
| 977 |
+
"eval_runtime": 0.3856,
|
| 978 |
+
"eval_samples_per_second": 95.942,
|
| 979 |
+
"eval_steps_per_second": 7.779,
|
| 980 |
+
"step": 420
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 80.95,
|
| 984 |
+
"eval_accuracy": 1.0,
|
| 985 |
+
"eval_loss": 0.01845603436231613,
|
| 986 |
+
"eval_runtime": 0.3966,
|
| 987 |
+
"eval_samples_per_second": 93.298,
|
| 988 |
+
"eval_steps_per_second": 7.565,
|
| 989 |
+
"step": 425
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 81.9,
|
| 993 |
+
"learning_rate": 7.777777777777777e-06,
|
| 994 |
+
"loss": 0.0311,
|
| 995 |
+
"step": 430
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 81.9,
|
| 999 |
+
"eval_accuracy": 0.972972972972973,
|
| 1000 |
+
"eval_loss": 0.02441835217177868,
|
| 1001 |
+
"eval_runtime": 0.4215,
|
| 1002 |
+
"eval_samples_per_second": 87.778,
|
| 1003 |
+
"eval_steps_per_second": 7.117,
|
| 1004 |
+
"step": 430
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 82.86,
|
| 1008 |
+
"eval_accuracy": 0.972972972972973,
|
| 1009 |
+
"eval_loss": 0.030215006321668625,
|
| 1010 |
+
"eval_runtime": 0.4009,
|
| 1011 |
+
"eval_samples_per_second": 92.283,
|
| 1012 |
+
"eval_steps_per_second": 7.482,
|
| 1013 |
+
"step": 435
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 83.81,
|
| 1017 |
+
"learning_rate": 6.666666666666667e-06,
|
| 1018 |
+
"loss": 0.0189,
|
| 1019 |
+
"step": 440
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 84.0,
|
| 1023 |
+
"eval_accuracy": 1.0,
|
| 1024 |
+
"eval_loss": 0.00978150311857462,
|
| 1025 |
+
"eval_runtime": 0.4039,
|
| 1026 |
+
"eval_samples_per_second": 91.607,
|
| 1027 |
+
"eval_steps_per_second": 7.428,
|
| 1028 |
+
"step": 441
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 84.95,
|
| 1032 |
+
"eval_accuracy": 1.0,
|
| 1033 |
+
"eval_loss": 0.004685988184064627,
|
| 1034 |
+
"eval_runtime": 0.3893,
|
| 1035 |
+
"eval_samples_per_second": 95.039,
|
| 1036 |
+
"eval_steps_per_second": 7.706,
|
| 1037 |
+
"step": 446
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 85.71,
|
| 1041 |
+
"learning_rate": 5.555555555555556e-06,
|
| 1042 |
+
"loss": 0.0235,
|
| 1043 |
+
"step": 450
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 85.9,
|
| 1047 |
+
"eval_accuracy": 1.0,
|
| 1048 |
+
"eval_loss": 0.010029388591647148,
|
| 1049 |
+
"eval_runtime": 0.4017,
|
| 1050 |
+
"eval_samples_per_second": 92.114,
|
| 1051 |
+
"eval_steps_per_second": 7.469,
|
| 1052 |
+
"step": 451
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 86.86,
|
| 1056 |
+
"eval_accuracy": 1.0,
|
| 1057 |
+
"eval_loss": 0.01385235320776701,
|
| 1058 |
+
"eval_runtime": 0.409,
|
| 1059 |
+
"eval_samples_per_second": 90.473,
|
| 1060 |
+
"eval_steps_per_second": 7.336,
|
| 1061 |
+
"step": 456
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 87.62,
|
| 1065 |
+
"learning_rate": 4.444444444444445e-06,
|
| 1066 |
+
"loss": 0.014,
|
| 1067 |
+
"step": 460
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 88.0,
|
| 1071 |
+
"eval_accuracy": 1.0,
|
| 1072 |
+
"eval_loss": 0.013605994172394276,
|
| 1073 |
+
"eval_runtime": 0.4002,
|
| 1074 |
+
"eval_samples_per_second": 92.454,
|
| 1075 |
+
"eval_steps_per_second": 7.496,
|
| 1076 |
+
"step": 462
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 88.95,
|
| 1080 |
+
"eval_accuracy": 0.972972972972973,
|
| 1081 |
+
"eval_loss": 0.030411923304200172,
|
| 1082 |
+
"eval_runtime": 0.3929,
|
| 1083 |
+
"eval_samples_per_second": 94.163,
|
| 1084 |
+
"eval_steps_per_second": 7.635,
|
| 1085 |
+
"step": 467
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 89.52,
|
| 1089 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 1090 |
+
"loss": 0.0197,
|
| 1091 |
+
"step": 470
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 89.9,
|
| 1095 |
+
"eval_accuracy": 0.972972972972973,
|
| 1096 |
+
"eval_loss": 0.04400445148348808,
|
| 1097 |
+
"eval_runtime": 0.4094,
|
| 1098 |
+
"eval_samples_per_second": 90.379,
|
| 1099 |
+
"eval_steps_per_second": 7.328,
|
| 1100 |
+
"step": 472
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 90.86,
|
| 1104 |
+
"eval_accuracy": 0.972972972972973,
|
| 1105 |
+
"eval_loss": 0.059370577335357666,
|
| 1106 |
+
"eval_runtime": 0.4037,
|
| 1107 |
+
"eval_samples_per_second": 91.649,
|
| 1108 |
+
"eval_steps_per_second": 7.431,
|
| 1109 |
+
"step": 477
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 91.43,
|
| 1113 |
+
"learning_rate": 2.2222222222222225e-06,
|
| 1114 |
+
"loss": 0.0309,
|
| 1115 |
+
"step": 480
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 92.0,
|
| 1119 |
+
"eval_accuracy": 0.972972972972973,
|
| 1120 |
+
"eval_loss": 0.048442043364048004,
|
| 1121 |
+
"eval_runtime": 0.3924,
|
| 1122 |
+
"eval_samples_per_second": 94.293,
|
| 1123 |
+
"eval_steps_per_second": 7.645,
|
| 1124 |
+
"step": 483
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 92.95,
|
| 1128 |
+
"eval_accuracy": 0.972972972972973,
|
| 1129 |
+
"eval_loss": 0.031032495200634003,
|
| 1130 |
+
"eval_runtime": 0.3937,
|
| 1131 |
+
"eval_samples_per_second": 93.991,
|
| 1132 |
+
"eval_steps_per_second": 7.621,
|
| 1133 |
+
"step": 488
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 93.33,
|
| 1137 |
+
"learning_rate": 1.1111111111111112e-06,
|
| 1138 |
+
"loss": 0.0197,
|
| 1139 |
+
"step": 490
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 93.9,
|
| 1143 |
+
"eval_accuracy": 1.0,
|
| 1144 |
+
"eval_loss": 0.019568899646401405,
|
| 1145 |
+
"eval_runtime": 0.4189,
|
| 1146 |
+
"eval_samples_per_second": 88.319,
|
| 1147 |
+
"eval_steps_per_second": 7.161,
|
| 1148 |
+
"step": 493
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 94.86,
|
| 1152 |
+
"eval_accuracy": 1.0,
|
| 1153 |
+
"eval_loss": 0.014562019146978855,
|
| 1154 |
+
"eval_runtime": 0.3925,
|
| 1155 |
+
"eval_samples_per_second": 94.275,
|
| 1156 |
+
"eval_steps_per_second": 7.644,
|
| 1157 |
+
"step": 498
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 95.24,
|
| 1161 |
+
"learning_rate": 0.0,
|
| 1162 |
+
"loss": 0.0106,
|
| 1163 |
+
"step": 500
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 95.24,
|
| 1167 |
+
"eval_accuracy": 1.0,
|
| 1168 |
+
"eval_loss": 0.014045949093997478,
|
| 1169 |
+
"eval_runtime": 0.394,
|
| 1170 |
+
"eval_samples_per_second": 93.898,
|
| 1171 |
+
"eval_steps_per_second": 7.613,
|
| 1172 |
+
"step": 500
|
| 1173 |
+
}
|
| 1174 |
+
],
|
| 1175 |
+
"max_steps": 500,
|
| 1176 |
+
"num_train_epochs": 100,
|
| 1177 |
+
"total_flos": 2.628508796024832e+18,
|
| 1178 |
+
"trial_name": null,
|
| 1179 |
+
"trial_params": null
|
| 1180 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acc8b7bab1ade4e0d6424a1f941b7718a67193b5aabf7db3f59c7627598a8dc3
|
| 3 |
+
size 4027
|