Commit ·
8888e5c
1
Parent(s): db00921
Add files
Browse files- all_results.json +16 -0
- checkpoint-28000/config.json +34 -0
- checkpoint-28000/optimizer.pt +3 -0
- checkpoint-28000/preprocessor_config.json +17 -0
- checkpoint-28000/pytorch_model.bin +3 -0
- checkpoint-28000/rng_state.pth +3 -0
- checkpoint-28000/scaler.pt +3 -0
- checkpoint-28000/scheduler.pt +3 -0
- checkpoint-28000/trainer_state.json +3516 -0
- checkpoint-28000/training_args.bin +3 -0
- checkpoint-30000/config.json +34 -0
- checkpoint-30000/optimizer.pt +3 -0
- checkpoint-30000/preprocessor_config.json +17 -0
- checkpoint-30000/pytorch_model.bin +3 -0
- checkpoint-30000/rng_state.pth +3 -0
- checkpoint-30000/scaler.pt +3 -0
- checkpoint-30000/scheduler.pt +3 -0
- checkpoint-30000/trainer_state.json +0 -0
- checkpoint-30000/training_args.bin +3 -0
- config.json +34 -0
- eval_results.json +12 -0
- preprocessor_config.json +17 -0
- pytorch_model.bin +3 -0
- runs/Jun29_00-57-15_ficino/1656457039.4100714/events.out.tfevents.1656457039.ficino.3045589.1 +3 -0
- runs/Jun29_00-57-15_ficino/events.out.tfevents.1656457039.ficino.3045589.0 +3 -0
- runs/Jun29_00-57-15_ficino/events.out.tfevents.1657055182.ficino.3045589.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 64.0,
|
| 3 |
+
"eval_accuracy": 0.9457035788509057,
|
| 4 |
+
"eval_f1": 0.9276842027293449,
|
| 5 |
+
"eval_loss": 0.14763057231903076,
|
| 6 |
+
"eval_matthews_correlation": 0.8879028981021795,
|
| 7 |
+
"eval_precision": 0.932791895372278,
|
| 8 |
+
"eval_recall": 0.9230343944305247,
|
| 9 |
+
"eval_runtime": 1043.6137,
|
| 10 |
+
"eval_samples_per_second": 58.555,
|
| 11 |
+
"eval_steps_per_second": 1.83,
|
| 12 |
+
"train_loss": 0.1566047928276214,
|
| 13 |
+
"train_runtime": 597098.8722,
|
| 14 |
+
"train_samples_per_second": 25.809,
|
| 15 |
+
"train_steps_per_second": 0.05
|
| 16 |
+
}
|
checkpoint-28000/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-384",
|
| 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": "Front",
|
| 13 |
+
"1": "Middle",
|
| 14 |
+
"2": "Back"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 384,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Back": "2",
|
| 21 |
+
"Front": "0",
|
| 22 |
+
"Middle": "1"
|
| 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": "4.20.0"
|
| 34 |
+
}
|
checkpoint-28000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92e44f29773990940a6ee484deaaa7d159495afbb0bdc69529b9ce94621330d5
|
| 3 |
+
size 688858465
|
checkpoint-28000/preprocessor_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_std": [
|
| 11 |
+
0.5,
|
| 12 |
+
0.5,
|
| 13 |
+
0.5
|
| 14 |
+
],
|
| 15 |
+
"resample": 2,
|
| 16 |
+
"size": 384
|
| 17 |
+
}
|
checkpoint-28000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7aeae6401eee261a920c4636609b82fc52762b4b566ab785089a4bb27c1d0cb
|
| 3 |
+
size 344437425
|
checkpoint-28000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a776feb5bb30ae56498d0b3c161acbc1b74bf481ba2a790baa01b5a88a1df305
|
| 3 |
+
size 14503
|
checkpoint-28000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec8e921f8503d7f4128558bb1c0ff0d25de6dfea42f98051387e4689fa3cf243
|
| 3 |
+
size 559
|
checkpoint-28000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d80178b31d11242832b8dac59294e6a975ca255697b7afdea0e8c6651ef7890c
|
| 3 |
+
size 623
|
checkpoint-28000/trainer_state.json
ADDED
|
@@ -0,0 +1,3516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.14763057231903076,
|
| 3 |
+
"best_model_checkpoint": "./vit-front-page-384-complete-v2/checkpoint-28000",
|
| 4 |
+
"epoch": 59.57408637873754,
|
| 5 |
+
"global_step": 28000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.21,
|
| 12 |
+
"learning_rate": 7e-08,
|
| 13 |
+
"loss": 1.0485,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.43,
|
| 18 |
+
"learning_rate": 1.4e-07,
|
| 19 |
+
"loss": 0.9833,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.43,
|
| 24 |
+
"eval_accuracy": 0.6194995827128573,
|
| 25 |
+
"eval_f1": 0.2849637284042793,
|
| 26 |
+
"eval_loss": 0.9414144158363342,
|
| 27 |
+
"eval_matthews_correlation": -0.046627386105974944,
|
| 28 |
+
"eval_precision": 0.28223649662424866,
|
| 29 |
+
"eval_recall": 0.3194839105028776,
|
| 30 |
+
"eval_runtime": 1120.0285,
|
| 31 |
+
"eval_samples_per_second": 54.56,
|
| 32 |
+
"eval_steps_per_second": 1.705,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.64,
|
| 37 |
+
"learning_rate": 2.0999999999999997e-07,
|
| 38 |
+
"loss": 0.9031,
|
| 39 |
+
"step": 300
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.85,
|
| 43 |
+
"learning_rate": 2.8e-07,
|
| 44 |
+
"loss": 0.8378,
|
| 45 |
+
"step": 400
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.85,
|
| 49 |
+
"eval_accuracy": 0.6742542015087793,
|
| 50 |
+
"eval_f1": 0.27318592449369794,
|
| 51 |
+
"eval_loss": 0.8087042570114136,
|
| 52 |
+
"eval_matthews_correlation": -0.008566496106974774,
|
| 53 |
+
"eval_precision": 0.33248655167577795,
|
| 54 |
+
"eval_recall": 0.3329403574518804,
|
| 55 |
+
"eval_runtime": 1146.8267,
|
| 56 |
+
"eval_samples_per_second": 53.285,
|
| 57 |
+
"eval_steps_per_second": 1.665,
|
| 58 |
+
"step": 400
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.06,
|
| 62 |
+
"learning_rate": 3.5e-07,
|
| 63 |
+
"loss": 0.7846,
|
| 64 |
+
"step": 500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.28,
|
| 68 |
+
"learning_rate": 4.1999999999999995e-07,
|
| 69 |
+
"loss": 0.725,
|
| 70 |
+
"step": 600
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.28,
|
| 74 |
+
"eval_accuracy": 0.7299906724050467,
|
| 75 |
+
"eval_f1": 0.45416361692283386,
|
| 76 |
+
"eval_loss": 0.6847068071365356,
|
| 77 |
+
"eval_matthews_correlation": 0.3478679528690636,
|
| 78 |
+
"eval_precision": 0.7356178375809365,
|
| 79 |
+
"eval_recall": 0.4490403016153819,
|
| 80 |
+
"eval_runtime": 1122.3931,
|
| 81 |
+
"eval_samples_per_second": 54.445,
|
| 82 |
+
"eval_steps_per_second": 1.702,
|
| 83 |
+
"step": 600
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.49,
|
| 87 |
+
"learning_rate": 4.9e-07,
|
| 88 |
+
"loss": 0.6452,
|
| 89 |
+
"step": 700
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.7,
|
| 93 |
+
"learning_rate": 5.6e-07,
|
| 94 |
+
"loss": 0.5769,
|
| 95 |
+
"step": 800
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.7,
|
| 99 |
+
"eval_accuracy": 0.7984093995974406,
|
| 100 |
+
"eval_f1": 0.6063804641618133,
|
| 101 |
+
"eval_loss": 0.5433278679847717,
|
| 102 |
+
"eval_matthews_correlation": 0.554774970478316,
|
| 103 |
+
"eval_precision": 0.782372439805869,
|
| 104 |
+
"eval_recall": 0.6092247400862097,
|
| 105 |
+
"eval_runtime": 1136.2592,
|
| 106 |
+
"eval_samples_per_second": 53.781,
|
| 107 |
+
"eval_steps_per_second": 1.681,
|
| 108 |
+
"step": 800
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.91,
|
| 112 |
+
"learning_rate": 6.3e-07,
|
| 113 |
+
"loss": 0.5208,
|
| 114 |
+
"step": 900
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.13,
|
| 118 |
+
"learning_rate": 7e-07,
|
| 119 |
+
"loss": 0.4706,
|
| 120 |
+
"step": 1000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.13,
|
| 124 |
+
"eval_accuracy": 0.8339688098316124,
|
| 125 |
+
"eval_f1": 0.6871318497564141,
|
| 126 |
+
"eval_loss": 0.4425855875015259,
|
| 127 |
+
"eval_matthews_correlation": 0.6440133138789277,
|
| 128 |
+
"eval_precision": 0.8172733311232007,
|
| 129 |
+
"eval_recall": 0.6865053904162712,
|
| 130 |
+
"eval_runtime": 1131.2502,
|
| 131 |
+
"eval_samples_per_second": 54.019,
|
| 132 |
+
"eval_steps_per_second": 1.688,
|
| 133 |
+
"step": 1000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.34,
|
| 137 |
+
"learning_rate": 6.975928473177441e-07,
|
| 138 |
+
"loss": 0.4247,
|
| 139 |
+
"step": 1100
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.55,
|
| 143 |
+
"learning_rate": 6.951856946354883e-07,
|
| 144 |
+
"loss": 0.3902,
|
| 145 |
+
"step": 1200
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.55,
|
| 149 |
+
"eval_accuracy": 0.8571732478031059,
|
| 150 |
+
"eval_f1": 0.7517270150716192,
|
| 151 |
+
"eval_loss": 0.3730458915233612,
|
| 152 |
+
"eval_matthews_correlation": 0.6959063906454223,
|
| 153 |
+
"eval_precision": 0.8447385961080253,
|
| 154 |
+
"eval_recall": 0.7349271721409717,
|
| 155 |
+
"eval_runtime": 1143.842,
|
| 156 |
+
"eval_samples_per_second": 53.424,
|
| 157 |
+
"eval_steps_per_second": 1.67,
|
| 158 |
+
"step": 1200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.77,
|
| 162 |
+
"learning_rate": 6.927785419532324e-07,
|
| 163 |
+
"loss": 0.3604,
|
| 164 |
+
"step": 1300
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.98,
|
| 168 |
+
"learning_rate": 6.903713892709766e-07,
|
| 169 |
+
"loss": 0.3392,
|
| 170 |
+
"step": 1400
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.98,
|
| 174 |
+
"eval_accuracy": 0.8786430803973229,
|
| 175 |
+
"eval_f1": 0.8069413230330182,
|
| 176 |
+
"eval_loss": 0.32644152641296387,
|
| 177 |
+
"eval_matthews_correlation": 0.7428749706793645,
|
| 178 |
+
"eval_precision": 0.8632726130534206,
|
| 179 |
+
"eval_recall": 0.7855049543193654,
|
| 180 |
+
"eval_runtime": 1136.2051,
|
| 181 |
+
"eval_samples_per_second": 53.783,
|
| 182 |
+
"eval_steps_per_second": 1.681,
|
| 183 |
+
"step": 1400
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.19,
|
| 187 |
+
"learning_rate": 6.879642365887207e-07,
|
| 188 |
+
"loss": 0.3188,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.4,
|
| 193 |
+
"learning_rate": 6.855570839064649e-07,
|
| 194 |
+
"loss": 0.3044,
|
| 195 |
+
"step": 1600
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.4,
|
| 199 |
+
"eval_accuracy": 0.8894925461061383,
|
| 200 |
+
"eval_f1": 0.8329212820595306,
|
| 201 |
+
"eval_loss": 0.2972641587257385,
|
| 202 |
+
"eval_matthews_correlation": 0.7664388748302527,
|
| 203 |
+
"eval_precision": 0.8723203701164862,
|
| 204 |
+
"eval_recall": 0.8120687720492296,
|
| 205 |
+
"eval_runtime": 1138.2797,
|
| 206 |
+
"eval_samples_per_second": 53.685,
|
| 207 |
+
"eval_steps_per_second": 1.678,
|
| 208 |
+
"step": 1600
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 3.62,
|
| 212 |
+
"learning_rate": 6.83149931224209e-07,
|
| 213 |
+
"loss": 0.2943,
|
| 214 |
+
"step": 1700
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.83,
|
| 218 |
+
"learning_rate": 6.807427785419532e-07,
|
| 219 |
+
"loss": 0.2795,
|
| 220 |
+
"step": 1800
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.83,
|
| 224 |
+
"eval_accuracy": 0.8961691403884862,
|
| 225 |
+
"eval_f1": 0.8432760143718706,
|
| 226 |
+
"eval_loss": 0.2766903340816498,
|
| 227 |
+
"eval_matthews_correlation": 0.781173318686851,
|
| 228 |
+
"eval_precision": 0.8834852690618357,
|
| 229 |
+
"eval_recall": 0.8221927104856026,
|
| 230 |
+
"eval_runtime": 1109.6741,
|
| 231 |
+
"eval_samples_per_second": 55.069,
|
| 232 |
+
"eval_steps_per_second": 1.721,
|
| 233 |
+
"step": 1800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 4.04,
|
| 237 |
+
"learning_rate": 6.783356258596973e-07,
|
| 238 |
+
"loss": 0.2738,
|
| 239 |
+
"step": 1900
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 4.26,
|
| 243 |
+
"learning_rate": 6.759284731774416e-07,
|
| 244 |
+
"loss": 0.262,
|
| 245 |
+
"step": 2000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 4.26,
|
| 249 |
+
"eval_accuracy": 0.9019784319821957,
|
| 250 |
+
"eval_f1": 0.8550525638971442,
|
| 251 |
+
"eval_loss": 0.26178261637687683,
|
| 252 |
+
"eval_matthews_correlation": 0.7937491549035616,
|
| 253 |
+
"eval_precision": 0.8893566012052573,
|
| 254 |
+
"eval_recall": 0.8349244764526037,
|
| 255 |
+
"eval_runtime": 1138.053,
|
| 256 |
+
"eval_samples_per_second": 53.696,
|
| 257 |
+
"eval_steps_per_second": 1.678,
|
| 258 |
+
"step": 2000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 4.47,
|
| 262 |
+
"learning_rate": 6.735213204951857e-07,
|
| 263 |
+
"loss": 0.2567,
|
| 264 |
+
"step": 2100
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.68,
|
| 268 |
+
"learning_rate": 6.711141678129298e-07,
|
| 269 |
+
"loss": 0.2497,
|
| 270 |
+
"step": 2200
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.68,
|
| 274 |
+
"eval_accuracy": 0.9061185750053183,
|
| 275 |
+
"eval_f1": 0.8647877107942263,
|
| 276 |
+
"eval_loss": 0.25028473138809204,
|
| 277 |
+
"eval_matthews_correlation": 0.8031001323768835,
|
| 278 |
+
"eval_precision": 0.888845641786976,
|
| 279 |
+
"eval_recall": 0.8490665078134735,
|
| 280 |
+
"eval_runtime": 1128.8955,
|
| 281 |
+
"eval_samples_per_second": 54.132,
|
| 282 |
+
"eval_steps_per_second": 1.692,
|
| 283 |
+
"step": 2200
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.89,
|
| 287 |
+
"learning_rate": 6.68707015130674e-07,
|
| 288 |
+
"loss": 0.2444,
|
| 289 |
+
"step": 2300
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 5.11,
|
| 293 |
+
"learning_rate": 6.662998624484181e-07,
|
| 294 |
+
"loss": 0.2414,
|
| 295 |
+
"step": 2400
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 5.11,
|
| 299 |
+
"eval_accuracy": 0.908589569457854,
|
| 300 |
+
"eval_f1": 0.8705010060852946,
|
| 301 |
+
"eval_loss": 0.24158228933811188,
|
| 302 |
+
"eval_matthews_correlation": 0.808821805927799,
|
| 303 |
+
"eval_precision": 0.888714743861985,
|
| 304 |
+
"eval_recall": 0.8577216170630284,
|
| 305 |
+
"eval_runtime": 1121.8959,
|
| 306 |
+
"eval_samples_per_second": 54.469,
|
| 307 |
+
"eval_steps_per_second": 1.702,
|
| 308 |
+
"step": 2400
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 5.32,
|
| 312 |
+
"learning_rate": 6.638927097661623e-07,
|
| 313 |
+
"loss": 0.2321,
|
| 314 |
+
"step": 2500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 5.53,
|
| 318 |
+
"learning_rate": 6.614855570839064e-07,
|
| 319 |
+
"loss": 0.2356,
|
| 320 |
+
"step": 2600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 5.53,
|
| 324 |
+
"eval_accuracy": 0.9110441997087172,
|
| 325 |
+
"eval_f1": 0.8747151973222319,
|
| 326 |
+
"eval_loss": 0.23398438096046448,
|
| 327 |
+
"eval_matthews_correlation": 0.8139518481821442,
|
| 328 |
+
"eval_precision": 0.8928668344520597,
|
| 329 |
+
"eval_recall": 0.861416198724987,
|
| 330 |
+
"eval_runtime": 1133.6213,
|
| 331 |
+
"eval_samples_per_second": 53.906,
|
| 332 |
+
"eval_steps_per_second": 1.685,
|
| 333 |
+
"step": 2600
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 5.74,
|
| 337 |
+
"learning_rate": 6.590784044016506e-07,
|
| 338 |
+
"loss": 0.226,
|
| 339 |
+
"step": 2700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 5.96,
|
| 343 |
+
"learning_rate": 6.566712517193947e-07,
|
| 344 |
+
"loss": 0.2251,
|
| 345 |
+
"step": 2800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 5.96,
|
| 349 |
+
"eval_accuracy": 0.9136297435729598,
|
| 350 |
+
"eval_f1": 0.8786518904171384,
|
| 351 |
+
"eval_loss": 0.22776289284229279,
|
| 352 |
+
"eval_matthews_correlation": 0.8196091308971525,
|
| 353 |
+
"eval_precision": 0.8955149466291931,
|
| 354 |
+
"eval_recall": 0.8663159550061658,
|
| 355 |
+
"eval_runtime": 1128.8199,
|
| 356 |
+
"eval_samples_per_second": 54.135,
|
| 357 |
+
"eval_steps_per_second": 1.692,
|
| 358 |
+
"step": 2800
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 6.17,
|
| 362 |
+
"learning_rate": 6.542640990371389e-07,
|
| 363 |
+
"loss": 0.2216,
|
| 364 |
+
"step": 2900
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 6.38,
|
| 368 |
+
"learning_rate": 6.51856946354883e-07,
|
| 369 |
+
"loss": 0.217,
|
| 370 |
+
"step": 3000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 6.38,
|
| 374 |
+
"eval_accuracy": 0.915577083571978,
|
| 375 |
+
"eval_f1": 0.8816198142871025,
|
| 376 |
+
"eval_loss": 0.22265483438968658,
|
| 377 |
+
"eval_matthews_correlation": 0.8236394377439027,
|
| 378 |
+
"eval_precision": 0.8990606065527942,
|
| 379 |
+
"eval_recall": 0.8686464677513945,
|
| 380 |
+
"eval_runtime": 1127.8916,
|
| 381 |
+
"eval_samples_per_second": 54.18,
|
| 382 |
+
"eval_steps_per_second": 1.693,
|
| 383 |
+
"step": 3000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 6.6,
|
| 387 |
+
"learning_rate": 6.494497936726272e-07,
|
| 388 |
+
"loss": 0.2175,
|
| 389 |
+
"step": 3100
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 6.81,
|
| 393 |
+
"learning_rate": 6.470426409903714e-07,
|
| 394 |
+
"loss": 0.2133,
|
| 395 |
+
"step": 3200
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 6.81,
|
| 399 |
+
"eval_accuracy": 0.9171153185291856,
|
| 400 |
+
"eval_f1": 0.8827723003585022,
|
| 401 |
+
"eval_loss": 0.21786576509475708,
|
| 402 |
+
"eval_matthews_correlation": 0.8266852106519758,
|
| 403 |
+
"eval_precision": 0.9034666000752295,
|
| 404 |
+
"eval_recall": 0.8679497941871164,
|
| 405 |
+
"eval_runtime": 1129.6487,
|
| 406 |
+
"eval_samples_per_second": 54.096,
|
| 407 |
+
"eval_steps_per_second": 1.691,
|
| 408 |
+
"step": 3200
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 7.02,
|
| 412 |
+
"learning_rate": 6.446354883081155e-07,
|
| 413 |
+
"loss": 0.2117,
|
| 414 |
+
"step": 3300
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 7.23,
|
| 418 |
+
"learning_rate": 6.422283356258597e-07,
|
| 419 |
+
"loss": 0.2098,
|
| 420 |
+
"step": 3400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 7.23,
|
| 424 |
+
"eval_accuracy": 0.9182935410495999,
|
| 425 |
+
"eval_f1": 0.884903972857821,
|
| 426 |
+
"eval_loss": 0.21342970430850983,
|
| 427 |
+
"eval_matthews_correlation": 0.8292988605784972,
|
| 428 |
+
"eval_precision": 0.9040958524512837,
|
| 429 |
+
"eval_recall": 0.870991653583178,
|
| 430 |
+
"eval_runtime": 1152.1924,
|
| 431 |
+
"eval_samples_per_second": 53.037,
|
| 432 |
+
"eval_steps_per_second": 1.658,
|
| 433 |
+
"step": 3400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 7.45,
|
| 437 |
+
"learning_rate": 6.398211829436038e-07,
|
| 438 |
+
"loss": 0.2021,
|
| 439 |
+
"step": 3500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 7.66,
|
| 443 |
+
"learning_rate": 6.37414030261348e-07,
|
| 444 |
+
"loss": 0.2062,
|
| 445 |
+
"step": 3600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 7.66,
|
| 449 |
+
"eval_accuracy": 0.9201754242419283,
|
| 450 |
+
"eval_f1": 0.8875922877918782,
|
| 451 |
+
"eval_loss": 0.20977966487407684,
|
| 452 |
+
"eval_matthews_correlation": 0.833123364179002,
|
| 453 |
+
"eval_precision": 0.9084794166339746,
|
| 454 |
+
"eval_recall": 0.872252852044762,
|
| 455 |
+
"eval_runtime": 1135.8312,
|
| 456 |
+
"eval_samples_per_second": 53.801,
|
| 457 |
+
"eval_steps_per_second": 1.682,
|
| 458 |
+
"step": 3600
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 7.87,
|
| 462 |
+
"learning_rate": 6.350068775790921e-07,
|
| 463 |
+
"loss": 0.2033,
|
| 464 |
+
"step": 3700
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 8.09,
|
| 468 |
+
"learning_rate": 6.325997248968363e-07,
|
| 469 |
+
"loss": 0.1982,
|
| 470 |
+
"step": 3800
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 8.09,
|
| 474 |
+
"eval_accuracy": 0.9213863751656876,
|
| 475 |
+
"eval_f1": 0.88930772340783,
|
| 476 |
+
"eval_loss": 0.20641230046749115,
|
| 477 |
+
"eval_matthews_correlation": 0.8357746010338397,
|
| 478 |
+
"eval_precision": 0.9095846117319936,
|
| 479 |
+
"eval_recall": 0.8745329047658825,
|
| 480 |
+
"eval_runtime": 1143.3313,
|
| 481 |
+
"eval_samples_per_second": 53.448,
|
| 482 |
+
"eval_steps_per_second": 1.671,
|
| 483 |
+
"step": 3800
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 8.3,
|
| 487 |
+
"learning_rate": 6.301925722145805e-07,
|
| 488 |
+
"loss": 0.196,
|
| 489 |
+
"step": 3900
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 8.51,
|
| 493 |
+
"learning_rate": 6.277854195323246e-07,
|
| 494 |
+
"loss": 0.1983,
|
| 495 |
+
"step": 4000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 8.51,
|
| 499 |
+
"eval_accuracy": 0.9222700420559983,
|
| 500 |
+
"eval_f1": 0.8900453287552592,
|
| 501 |
+
"eval_loss": 0.20386044681072235,
|
| 502 |
+
"eval_matthews_correlation": 0.837555384879415,
|
| 503 |
+
"eval_precision": 0.9123527733555781,
|
| 504 |
+
"eval_recall": 0.8740593137023058,
|
| 505 |
+
"eval_runtime": 1129.2304,
|
| 506 |
+
"eval_samples_per_second": 54.116,
|
| 507 |
+
"eval_steps_per_second": 1.691,
|
| 508 |
+
"step": 4000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 8.72,
|
| 512 |
+
"learning_rate": 6.253782668500687e-07,
|
| 513 |
+
"loss": 0.1965,
|
| 514 |
+
"step": 4100
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 8.94,
|
| 518 |
+
"learning_rate": 6.229711141678129e-07,
|
| 519 |
+
"loss": 0.1936,
|
| 520 |
+
"step": 4200
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 8.94,
|
| 524 |
+
"eval_accuracy": 0.9233828077697229,
|
| 525 |
+
"eval_f1": 0.8932485448536257,
|
| 526 |
+
"eval_loss": 0.20058760046958923,
|
| 527 |
+
"eval_matthews_correlation": 0.8401209500114148,
|
| 528 |
+
"eval_precision": 0.9107366418558472,
|
| 529 |
+
"eval_recall": 0.8798434624360084,
|
| 530 |
+
"eval_runtime": 1120.0565,
|
| 531 |
+
"eval_samples_per_second": 54.559,
|
| 532 |
+
"eval_steps_per_second": 1.705,
|
| 533 |
+
"step": 4200
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 9.15,
|
| 537 |
+
"learning_rate": 6.205880330123796e-07,
|
| 538 |
+
"loss": 0.1922,
|
| 539 |
+
"step": 4300
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 9.36,
|
| 543 |
+
"learning_rate": 6.181808803301237e-07,
|
| 544 |
+
"loss": 0.1953,
|
| 545 |
+
"step": 4400
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 9.36,
|
| 549 |
+
"eval_accuracy": 0.9238246412148783,
|
| 550 |
+
"eval_f1": 0.8951433768565843,
|
| 551 |
+
"eval_loss": 0.19883869588375092,
|
| 552 |
+
"eval_matthews_correlation": 0.8415676876590389,
|
| 553 |
+
"eval_precision": 0.9072146230906633,
|
| 554 |
+
"eval_recall": 0.885557435823166,
|
| 555 |
+
"eval_runtime": 1137.9471,
|
| 556 |
+
"eval_samples_per_second": 53.701,
|
| 557 |
+
"eval_steps_per_second": 1.678,
|
| 558 |
+
"step": 4400
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 9.57,
|
| 562 |
+
"learning_rate": 6.15773727647868e-07,
|
| 563 |
+
"loss": 0.1843,
|
| 564 |
+
"step": 4500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 9.79,
|
| 568 |
+
"learning_rate": 6.133665749656121e-07,
|
| 569 |
+
"loss": 0.1852,
|
| 570 |
+
"step": 4600
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 9.79,
|
| 574 |
+
"eval_accuracy": 0.9253792403737584,
|
| 575 |
+
"eval_f1": 0.8946482066160663,
|
| 576 |
+
"eval_loss": 0.19628000259399414,
|
| 577 |
+
"eval_matthews_correlation": 0.8441339816426117,
|
| 578 |
+
"eval_precision": 0.9173420280370865,
|
| 579 |
+
"eval_recall": 0.8782309033246154,
|
| 580 |
+
"eval_runtime": 1124.1932,
|
| 581 |
+
"eval_samples_per_second": 54.358,
|
| 582 |
+
"eval_steps_per_second": 1.699,
|
| 583 |
+
"step": 4600
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 10.0,
|
| 587 |
+
"learning_rate": 6.109594222833563e-07,
|
| 588 |
+
"loss": 0.1845,
|
| 589 |
+
"step": 4700
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 10.21,
|
| 593 |
+
"learning_rate": 6.085522696011004e-07,
|
| 594 |
+
"loss": 0.1839,
|
| 595 |
+
"step": 4800
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 10.21,
|
| 599 |
+
"eval_accuracy": 0.9258374380205862,
|
| 600 |
+
"eval_f1": 0.8972498157769592,
|
| 601 |
+
"eval_loss": 0.1933354139328003,
|
| 602 |
+
"eval_matthews_correlation": 0.8454266170310101,
|
| 603 |
+
"eval_precision": 0.9128401019975159,
|
| 604 |
+
"eval_recall": 0.8849382250200719,
|
| 605 |
+
"eval_runtime": 1122.9259,
|
| 606 |
+
"eval_samples_per_second": 54.419,
|
| 607 |
+
"eval_steps_per_second": 1.701,
|
| 608 |
+
"step": 4800
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 10.43,
|
| 612 |
+
"learning_rate": 6.061451169188445e-07,
|
| 613 |
+
"loss": 0.1845,
|
| 614 |
+
"step": 4900
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 10.64,
|
| 618 |
+
"learning_rate": 6.037379642365887e-07,
|
| 619 |
+
"loss": 0.1791,
|
| 620 |
+
"step": 5000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 10.64,
|
| 624 |
+
"eval_accuracy": 0.9267047407092245,
|
| 625 |
+
"eval_f1": 0.8983700490176202,
|
| 626 |
+
"eval_loss": 0.19171090424060822,
|
| 627 |
+
"eval_matthews_correlation": 0.8472176589659597,
|
| 628 |
+
"eval_precision": 0.9145474859208962,
|
| 629 |
+
"eval_recall": 0.8856752741366947,
|
| 630 |
+
"eval_runtime": 1134.0907,
|
| 631 |
+
"eval_samples_per_second": 53.884,
|
| 632 |
+
"eval_steps_per_second": 1.684,
|
| 633 |
+
"step": 5000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 10.85,
|
| 637 |
+
"learning_rate": 6.013308115543328e-07,
|
| 638 |
+
"loss": 0.182,
|
| 639 |
+
"step": 5100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 11.06,
|
| 643 |
+
"learning_rate": 5.98923658872077e-07,
|
| 644 |
+
"loss": 0.18,
|
| 645 |
+
"step": 5200
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 11.06,
|
| 649 |
+
"eval_accuracy": 0.9271138457510351,
|
| 650 |
+
"eval_f1": 0.8995050329011628,
|
| 651 |
+
"eval_loss": 0.1895856410264969,
|
| 652 |
+
"eval_matthews_correlation": 0.848294574832317,
|
| 653 |
+
"eval_precision": 0.9131718148389393,
|
| 654 |
+
"eval_recall": 0.8885987433408609,
|
| 655 |
+
"eval_runtime": 1126.9856,
|
| 656 |
+
"eval_samples_per_second": 54.223,
|
| 657 |
+
"eval_steps_per_second": 1.695,
|
| 658 |
+
"step": 5200
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 11.28,
|
| 662 |
+
"learning_rate": 5.965165061898212e-07,
|
| 663 |
+
"loss": 0.1763,
|
| 664 |
+
"step": 5300
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 11.49,
|
| 668 |
+
"learning_rate": 5.941093535075653e-07,
|
| 669 |
+
"loss": 0.1782,
|
| 670 |
+
"step": 5400
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 11.49,
|
| 674 |
+
"eval_accuracy": 0.9275556791961904,
|
| 675 |
+
"eval_f1": 0.9002696190246419,
|
| 676 |
+
"eval_loss": 0.18787473440170288,
|
| 677 |
+
"eval_matthews_correlation": 0.84921482512736,
|
| 678 |
+
"eval_precision": 0.9139059903894043,
|
| 679 |
+
"eval_recall": 0.88930836639531,
|
| 680 |
+
"eval_runtime": 1128.4943,
|
| 681 |
+
"eval_samples_per_second": 54.151,
|
| 682 |
+
"eval_steps_per_second": 1.693,
|
| 683 |
+
"step": 5400
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 11.7,
|
| 687 |
+
"learning_rate": 5.917022008253094e-07,
|
| 688 |
+
"loss": 0.1788,
|
| 689 |
+
"step": 5500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 11.91,
|
| 693 |
+
"learning_rate": 5.892950481430536e-07,
|
| 694 |
+
"loss": 0.1712,
|
| 695 |
+
"step": 5600
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 11.91,
|
| 699 |
+
"eval_accuracy": 0.9287175375149324,
|
| 700 |
+
"eval_f1": 0.9011964058613507,
|
| 701 |
+
"eval_loss": 0.1861330270767212,
|
| 702 |
+
"eval_matthews_correlation": 0.8514678062818634,
|
| 703 |
+
"eval_precision": 0.9173976756930257,
|
| 704 |
+
"eval_recall": 0.8884787278098573,
|
| 705 |
+
"eval_runtime": 1120.0822,
|
| 706 |
+
"eval_samples_per_second": 54.558,
|
| 707 |
+
"eval_steps_per_second": 1.705,
|
| 708 |
+
"step": 5600
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 12.13,
|
| 712 |
+
"learning_rate": 5.868878954607978e-07,
|
| 713 |
+
"loss": 0.172,
|
| 714 |
+
"step": 5700
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 12.34,
|
| 718 |
+
"learning_rate": 5.84480742778542e-07,
|
| 719 |
+
"loss": 0.1737,
|
| 720 |
+
"step": 5800
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 12.34,
|
| 724 |
+
"eval_accuracy": 0.9296993896152776,
|
| 725 |
+
"eval_f1": 0.9010626619953944,
|
| 726 |
+
"eval_loss": 0.18573108315467834,
|
| 727 |
+
"eval_matthews_correlation": 0.8533347114503049,
|
| 728 |
+
"eval_precision": 0.9231173958750271,
|
| 729 |
+
"eval_recall": 0.8849159091550628,
|
| 730 |
+
"eval_runtime": 1156.0243,
|
| 731 |
+
"eval_samples_per_second": 52.861,
|
| 732 |
+
"eval_steps_per_second": 1.652,
|
| 733 |
+
"step": 5800
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 12.55,
|
| 737 |
+
"learning_rate": 5.820735900962861e-07,
|
| 738 |
+
"loss": 0.1726,
|
| 739 |
+
"step": 5900
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 12.77,
|
| 743 |
+
"learning_rate": 5.796664374140302e-07,
|
| 744 |
+
"loss": 0.1696,
|
| 745 |
+
"step": 6000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 12.77,
|
| 749 |
+
"eval_accuracy": 0.930026673648726,
|
| 750 |
+
"eval_f1": 0.9031918377265686,
|
| 751 |
+
"eval_loss": 0.1828816682100296,
|
| 752 |
+
"eval_matthews_correlation": 0.8542309647721633,
|
| 753 |
+
"eval_precision": 0.9192960205580971,
|
| 754 |
+
"eval_recall": 0.8904958440603054,
|
| 755 |
+
"eval_runtime": 1124.8361,
|
| 756 |
+
"eval_samples_per_second": 54.327,
|
| 757 |
+
"eval_steps_per_second": 1.698,
|
| 758 |
+
"step": 6000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 12.98,
|
| 762 |
+
"learning_rate": 5.772592847317744e-07,
|
| 763 |
+
"loss": 0.1682,
|
| 764 |
+
"step": 6100
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 13.19,
|
| 768 |
+
"learning_rate": 5.748521320495185e-07,
|
| 769 |
+
"loss": 0.1698,
|
| 770 |
+
"step": 6200
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 13.19,
|
| 774 |
+
"eval_accuracy": 0.9302885008754848,
|
| 775 |
+
"eval_f1": 0.9048186507788922,
|
| 776 |
+
"eval_loss": 0.18205700814723969,
|
| 777 |
+
"eval_matthews_correlation": 0.8551184049776112,
|
| 778 |
+
"eval_precision": 0.9164794554225942,
|
| 779 |
+
"eval_recall": 0.8951361110635792,
|
| 780 |
+
"eval_runtime": 1130.5739,
|
| 781 |
+
"eval_samples_per_second": 54.051,
|
| 782 |
+
"eval_steps_per_second": 1.689,
|
| 783 |
+
"step": 6200
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 13.4,
|
| 787 |
+
"learning_rate": 5.724449793672627e-07,
|
| 788 |
+
"loss": 0.1682,
|
| 789 |
+
"step": 6300
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 13.62,
|
| 793 |
+
"learning_rate": 5.700378266850069e-07,
|
| 794 |
+
"loss": 0.1667,
|
| 795 |
+
"step": 6400
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 13.62,
|
| 799 |
+
"eval_accuracy": 0.9303048650771573,
|
| 800 |
+
"eval_f1": 0.9056480109419961,
|
| 801 |
+
"eval_loss": 0.18090908229351044,
|
| 802 |
+
"eval_matthews_correlation": 0.855428359187355,
|
| 803 |
+
"eval_precision": 0.9147426706946558,
|
| 804 |
+
"eval_recall": 0.8978667208863417,
|
| 805 |
+
"eval_runtime": 1113.9498,
|
| 806 |
+
"eval_samples_per_second": 54.858,
|
| 807 |
+
"eval_steps_per_second": 1.715,
|
| 808 |
+
"step": 6400
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 13.83,
|
| 812 |
+
"learning_rate": 5.67630674002751e-07,
|
| 813 |
+
"loss": 0.1673,
|
| 814 |
+
"step": 6500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 14.04,
|
| 818 |
+
"learning_rate": 5.652235213204951e-07,
|
| 819 |
+
"loss": 0.1651,
|
| 820 |
+
"step": 6600
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 14.04,
|
| 824 |
+
"eval_accuracy": 0.9307794269256574,
|
| 825 |
+
"eval_f1": 0.90568642496187,
|
| 826 |
+
"eval_loss": 0.17903146147727966,
|
| 827 |
+
"eval_matthews_correlation": 0.8562905390552094,
|
| 828 |
+
"eval_precision": 0.9160847482436384,
|
| 829 |
+
"eval_recall": 0.8970366589757913,
|
| 830 |
+
"eval_runtime": 1123.7851,
|
| 831 |
+
"eval_samples_per_second": 54.378,
|
| 832 |
+
"eval_steps_per_second": 1.7,
|
| 833 |
+
"step": 6600
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 14.26,
|
| 837 |
+
"learning_rate": 5.628163686382393e-07,
|
| 838 |
+
"loss": 0.1638,
|
| 839 |
+
"step": 6700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 14.47,
|
| 843 |
+
"learning_rate": 5.604092159559834e-07,
|
| 844 |
+
"loss": 0.1614,
|
| 845 |
+
"step": 6800
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 14.47,
|
| 849 |
+
"eval_accuracy": 0.9319412852443993,
|
| 850 |
+
"eval_f1": 0.9062846542418327,
|
| 851 |
+
"eval_loss": 0.17761486768722534,
|
| 852 |
+
"eval_matthews_correlation": 0.8583632583058451,
|
| 853 |
+
"eval_precision": 0.9210761772993599,
|
| 854 |
+
"eval_recall": 0.8945216174285454,
|
| 855 |
+
"eval_runtime": 1135.9567,
|
| 856 |
+
"eval_samples_per_second": 53.795,
|
| 857 |
+
"eval_steps_per_second": 1.681,
|
| 858 |
+
"step": 6800
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 14.68,
|
| 862 |
+
"learning_rate": 5.580261348005502e-07,
|
| 863 |
+
"loss": 0.1629,
|
| 864 |
+
"step": 6900
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 14.89,
|
| 868 |
+
"learning_rate": 5.556189821182944e-07,
|
| 869 |
+
"loss": 0.16,
|
| 870 |
+
"step": 7000
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 14.89,
|
| 874 |
+
"eval_accuracy": 0.9323667544878823,
|
| 875 |
+
"eval_f1": 0.9057483267194343,
|
| 876 |
+
"eval_loss": 0.177241712808609,
|
| 877 |
+
"eval_matthews_correlation": 0.8590673404186833,
|
| 878 |
+
"eval_precision": 0.9249219537323391,
|
| 879 |
+
"eval_recall": 0.8912560253961389,
|
| 880 |
+
"eval_runtime": 1147.9689,
|
| 881 |
+
"eval_samples_per_second": 53.232,
|
| 882 |
+
"eval_steps_per_second": 1.664,
|
| 883 |
+
"step": 7000
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 15.11,
|
| 887 |
+
"learning_rate": 5.532118294360385e-07,
|
| 888 |
+
"loss": 0.1622,
|
| 889 |
+
"step": 7100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 15.32,
|
| 893 |
+
"learning_rate": 5.508046767537827e-07,
|
| 894 |
+
"loss": 0.1591,
|
| 895 |
+
"step": 7200
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 15.32,
|
| 899 |
+
"eval_accuracy": 0.9334467917982622,
|
| 900 |
+
"eval_f1": 0.90852409435722,
|
| 901 |
+
"eval_loss": 0.17550112307071686,
|
| 902 |
+
"eval_matthews_correlation": 0.8615051567396046,
|
| 903 |
+
"eval_precision": 0.9232173166653612,
|
| 904 |
+
"eval_recall": 0.8966351633696954,
|
| 905 |
+
"eval_runtime": 1144.6322,
|
| 906 |
+
"eval_samples_per_second": 53.387,
|
| 907 |
+
"eval_steps_per_second": 1.669,
|
| 908 |
+
"step": 7200
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 15.53,
|
| 912 |
+
"learning_rate": 5.483975240715268e-07,
|
| 913 |
+
"loss": 0.16,
|
| 914 |
+
"step": 7300
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 15.74,
|
| 918 |
+
"learning_rate": 5.45990371389271e-07,
|
| 919 |
+
"loss": 0.1601,
|
| 920 |
+
"step": 7400
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 15.74,
|
| 924 |
+
"eval_accuracy": 0.9333322423865552,
|
| 925 |
+
"eval_f1": 0.9088120224095171,
|
| 926 |
+
"eval_loss": 0.17453713715076447,
|
| 927 |
+
"eval_matthews_correlation": 0.8613787118816909,
|
| 928 |
+
"eval_precision": 0.9218305477922321,
|
| 929 |
+
"eval_recall": 0.8980828107442319,
|
| 930 |
+
"eval_runtime": 1143.4792,
|
| 931 |
+
"eval_samples_per_second": 53.441,
|
| 932 |
+
"eval_steps_per_second": 1.67,
|
| 933 |
+
"step": 7400
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 15.96,
|
| 937 |
+
"learning_rate": 5.435832187070151e-07,
|
| 938 |
+
"loss": 0.1584,
|
| 939 |
+
"step": 7500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 16.17,
|
| 943 |
+
"learning_rate": 5.411760660247592e-07,
|
| 944 |
+
"loss": 0.1558,
|
| 945 |
+
"step": 7600
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 16.17,
|
| 949 |
+
"eval_accuracy": 0.9338395326384002,
|
| 950 |
+
"eval_f1": 0.9096298761981343,
|
| 951 |
+
"eval_loss": 0.17321471869945526,
|
| 952 |
+
"eval_matthews_correlation": 0.8625748894777745,
|
| 953 |
+
"eval_precision": 0.9213568402254939,
|
| 954 |
+
"eval_recall": 0.8999913944640027,
|
| 955 |
+
"eval_runtime": 1116.2047,
|
| 956 |
+
"eval_samples_per_second": 54.747,
|
| 957 |
+
"eval_steps_per_second": 1.711,
|
| 958 |
+
"step": 7600
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 16.38,
|
| 962 |
+
"learning_rate": 5.387689133425034e-07,
|
| 963 |
+
"loss": 0.1544,
|
| 964 |
+
"step": 7700
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 16.6,
|
| 968 |
+
"learning_rate": 5.363617606602475e-07,
|
| 969 |
+
"loss": 0.1552,
|
| 970 |
+
"step": 7800
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 16.6,
|
| 974 |
+
"eval_accuracy": 0.9334631559999346,
|
| 975 |
+
"eval_f1": 0.9101663960284817,
|
| 976 |
+
"eval_loss": 0.17314866185188293,
|
| 977 |
+
"eval_matthews_correlation": 0.8621017254091837,
|
| 978 |
+
"eval_precision": 0.9185625631174649,
|
| 979 |
+
"eval_recall": 0.9029180840503908,
|
| 980 |
+
"eval_runtime": 1134.8054,
|
| 981 |
+
"eval_samples_per_second": 53.85,
|
| 982 |
+
"eval_steps_per_second": 1.683,
|
| 983 |
+
"step": 7800
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 16.81,
|
| 987 |
+
"learning_rate": 5.339546079779917e-07,
|
| 988 |
+
"loss": 0.1571,
|
| 989 |
+
"step": 7900
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 17.02,
|
| 993 |
+
"learning_rate": 5.315474552957359e-07,
|
| 994 |
+
"loss": 0.1526,
|
| 995 |
+
"step": 8000
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 17.02,
|
| 999 |
+
"eval_accuracy": 0.9340849956634866,
|
| 1000 |
+
"eval_f1": 0.9110344713781423,
|
| 1001 |
+
"eval_loss": 0.17203205823898315,
|
| 1002 |
+
"eval_matthews_correlation": 0.8634918058087261,
|
| 1003 |
+
"eval_precision": 0.9187082054219985,
|
| 1004 |
+
"eval_recall": 0.9044161914490357,
|
| 1005 |
+
"eval_runtime": 1153.6876,
|
| 1006 |
+
"eval_samples_per_second": 52.968,
|
| 1007 |
+
"eval_steps_per_second": 1.656,
|
| 1008 |
+
"step": 8000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 17.23,
|
| 1012 |
+
"learning_rate": 5.2914030261348e-07,
|
| 1013 |
+
"loss": 0.1485,
|
| 1014 |
+
"step": 8100
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 17.45,
|
| 1018 |
+
"learning_rate": 5.267331499312242e-07,
|
| 1019 |
+
"loss": 0.1532,
|
| 1020 |
+
"step": 8200
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 17.45,
|
| 1024 |
+
"eval_accuracy": 0.9346741069236937,
|
| 1025 |
+
"eval_f1": 0.9117218687868994,
|
| 1026 |
+
"eval_loss": 0.17076529562473297,
|
| 1027 |
+
"eval_matthews_correlation": 0.8646272156128906,
|
| 1028 |
+
"eval_precision": 0.9201726149656478,
|
| 1029 |
+
"eval_recall": 0.9044721170341236,
|
| 1030 |
+
"eval_runtime": 1135.1604,
|
| 1031 |
+
"eval_samples_per_second": 53.833,
|
| 1032 |
+
"eval_steps_per_second": 1.683,
|
| 1033 |
+
"step": 8200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 17.66,
|
| 1037 |
+
"learning_rate": 5.243259972489684e-07,
|
| 1038 |
+
"loss": 0.1551,
|
| 1039 |
+
"step": 8300
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 17.87,
|
| 1043 |
+
"learning_rate": 5.219188445667125e-07,
|
| 1044 |
+
"loss": 0.1539,
|
| 1045 |
+
"step": 8400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 17.87,
|
| 1049 |
+
"eval_accuracy": 0.9351159403688492,
|
| 1050 |
+
"eval_f1": 0.911610683009681,
|
| 1051 |
+
"eval_loss": 0.1695307195186615,
|
| 1052 |
+
"eval_matthews_correlation": 0.865289074877206,
|
| 1053 |
+
"eval_precision": 0.9226978459827032,
|
| 1054 |
+
"eval_recall": 0.9023554489680277,
|
| 1055 |
+
"eval_runtime": 1122.959,
|
| 1056 |
+
"eval_samples_per_second": 54.418,
|
| 1057 |
+
"eval_steps_per_second": 1.701,
|
| 1058 |
+
"step": 8400
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 18.09,
|
| 1062 |
+
"learning_rate": 5.195116918844567e-07,
|
| 1063 |
+
"loss": 0.1477,
|
| 1064 |
+
"step": 8500
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 18.3,
|
| 1068 |
+
"learning_rate": 5.171045392022008e-07,
|
| 1069 |
+
"loss": 0.1483,
|
| 1070 |
+
"step": 8600
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 18.3,
|
| 1074 |
+
"eval_accuracy": 0.9356723232257115,
|
| 1075 |
+
"eval_f1": 0.9116987398295661,
|
| 1076 |
+
"eval_loss": 0.16896899044513702,
|
| 1077 |
+
"eval_matthews_correlation": 0.8662695435076357,
|
| 1078 |
+
"eval_precision": 0.9255532080817271,
|
| 1079 |
+
"eval_recall": 0.9005543243181938,
|
| 1080 |
+
"eval_runtime": 1135.8593,
|
| 1081 |
+
"eval_samples_per_second": 53.8,
|
| 1082 |
+
"eval_steps_per_second": 1.682,
|
| 1083 |
+
"step": 8600
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 18.51,
|
| 1087 |
+
"learning_rate": 5.146973865199449e-07,
|
| 1088 |
+
"loss": 0.1489,
|
| 1089 |
+
"step": 8700
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 18.72,
|
| 1093 |
+
"learning_rate": 5.122902338376891e-07,
|
| 1094 |
+
"loss": 0.1469,
|
| 1095 |
+
"step": 8800
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 18.72,
|
| 1099 |
+
"eval_accuracy": 0.9358032368390908,
|
| 1100 |
+
"eval_f1": 0.9135814294302561,
|
| 1101 |
+
"eval_loss": 0.16858318448066711,
|
| 1102 |
+
"eval_matthews_correlation": 0.8670812623876053,
|
| 1103 |
+
"eval_precision": 0.9210624088966272,
|
| 1104 |
+
"eval_recall": 0.907023142033475,
|
| 1105 |
+
"eval_runtime": 1122.9881,
|
| 1106 |
+
"eval_samples_per_second": 54.416,
|
| 1107 |
+
"eval_steps_per_second": 1.701,
|
| 1108 |
+
"step": 8800
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 18.94,
|
| 1112 |
+
"learning_rate": 5.099071526822558e-07,
|
| 1113 |
+
"loss": 0.1507,
|
| 1114 |
+
"step": 8900
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 19.15,
|
| 1118 |
+
"learning_rate": 5.075e-07,
|
| 1119 |
+
"loss": 0.1461,
|
| 1120 |
+
"step": 9000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 19.15,
|
| 1124 |
+
"eval_accuracy": 0.9359177862507978,
|
| 1125 |
+
"eval_f1": 0.9125886359052826,
|
| 1126 |
+
"eval_loss": 0.16734813153743744,
|
| 1127 |
+
"eval_matthews_correlation": 0.8668498402291797,
|
| 1128 |
+
"eval_precision": 0.9249962574783411,
|
| 1129 |
+
"eval_recall": 0.9022824765643582,
|
| 1130 |
+
"eval_runtime": 1124.669,
|
| 1131 |
+
"eval_samples_per_second": 54.335,
|
| 1132 |
+
"eval_steps_per_second": 1.698,
|
| 1133 |
+
"step": 9000
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 19.36,
|
| 1137 |
+
"learning_rate": 5.050928473177441e-07,
|
| 1138 |
+
"loss": 0.1453,
|
| 1139 |
+
"step": 9100
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 19.57,
|
| 1143 |
+
"learning_rate": 5.026856946354882e-07,
|
| 1144 |
+
"loss": 0.1487,
|
| 1145 |
+
"step": 9200
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 19.57,
|
| 1149 |
+
"eval_accuracy": 0.936588718519367,
|
| 1150 |
+
"eval_f1": 0.9144201514784519,
|
| 1151 |
+
"eval_loss": 0.16664335131645203,
|
| 1152 |
+
"eval_matthews_correlation": 0.8685701549851123,
|
| 1153 |
+
"eval_precision": 0.9231788402692221,
|
| 1154 |
+
"eval_recall": 0.9068124874405709,
|
| 1155 |
+
"eval_runtime": 1132.0219,
|
| 1156 |
+
"eval_samples_per_second": 53.982,
|
| 1157 |
+
"eval_steps_per_second": 1.687,
|
| 1158 |
+
"step": 9200
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 19.79,
|
| 1162 |
+
"learning_rate": 5.00302613480055e-07,
|
| 1163 |
+
"loss": 0.1499,
|
| 1164 |
+
"step": 9300
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 20.0,
|
| 1168 |
+
"learning_rate": 4.978954607977991e-07,
|
| 1169 |
+
"loss": 0.1433,
|
| 1170 |
+
"step": 9400
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 20.0,
|
| 1174 |
+
"eval_accuracy": 0.9369978235611776,
|
| 1175 |
+
"eval_f1": 0.91467275197079,
|
| 1176 |
+
"eval_loss": 0.16577279567718506,
|
| 1177 |
+
"eval_matthews_correlation": 0.8693728793586808,
|
| 1178 |
+
"eval_precision": 0.924099137774855,
|
| 1179 |
+
"eval_recall": 0.9066503727608389,
|
| 1180 |
+
"eval_runtime": 1144.9998,
|
| 1181 |
+
"eval_samples_per_second": 53.37,
|
| 1182 |
+
"eval_steps_per_second": 1.668,
|
| 1183 |
+
"step": 9400
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 20.21,
|
| 1187 |
+
"learning_rate": 4.954883081155432e-07,
|
| 1188 |
+
"loss": 0.144,
|
| 1189 |
+
"step": 9500
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 20.43,
|
| 1193 |
+
"learning_rate": 4.930811554332874e-07,
|
| 1194 |
+
"loss": 0.1437,
|
| 1195 |
+
"step": 9600
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 20.43,
|
| 1199 |
+
"eval_accuracy": 0.9370796445695396,
|
| 1200 |
+
"eval_f1": 0.9143506341308217,
|
| 1201 |
+
"eval_loss": 0.1650729477405548,
|
| 1202 |
+
"eval_matthews_correlation": 0.8693576464491103,
|
| 1203 |
+
"eval_precision": 0.9258633996979286,
|
| 1204 |
+
"eval_recall": 0.9047199267971502,
|
| 1205 |
+
"eval_runtime": 1124.1861,
|
| 1206 |
+
"eval_samples_per_second": 54.358,
|
| 1207 |
+
"eval_steps_per_second": 1.699,
|
| 1208 |
+
"step": 9600
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 20.64,
|
| 1212 |
+
"learning_rate": 4.906740027510316e-07,
|
| 1213 |
+
"loss": 0.1419,
|
| 1214 |
+
"step": 9700
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 20.85,
|
| 1218 |
+
"learning_rate": 4.882668500687758e-07,
|
| 1219 |
+
"loss": 0.1434,
|
| 1220 |
+
"step": 9800
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 20.85,
|
| 1224 |
+
"eval_accuracy": 0.9370796445695396,
|
| 1225 |
+
"eval_f1": 0.9154200976052094,
|
| 1226 |
+
"eval_loss": 0.1648997962474823,
|
| 1227 |
+
"eval_matthews_correlation": 0.8697098635796452,
|
| 1228 |
+
"eval_precision": 0.9230816943100145,
|
| 1229 |
+
"eval_recall": 0.9086611768001123,
|
| 1230 |
+
"eval_runtime": 1148.703,
|
| 1231 |
+
"eval_samples_per_second": 53.198,
|
| 1232 |
+
"eval_steps_per_second": 1.663,
|
| 1233 |
+
"step": 9800
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 21.06,
|
| 1237 |
+
"learning_rate": 4.8585969738652e-07,
|
| 1238 |
+
"loss": 0.1439,
|
| 1239 |
+
"step": 9900
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 21.28,
|
| 1243 |
+
"learning_rate": 4.834525447042641e-07,
|
| 1244 |
+
"loss": 0.1421,
|
| 1245 |
+
"step": 10000
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 21.28,
|
| 1249 |
+
"eval_accuracy": 0.9374232928046605,
|
| 1250 |
+
"eval_f1": 0.9159962475642537,
|
| 1251 |
+
"eval_loss": 0.16433577239513397,
|
| 1252 |
+
"eval_matthews_correlation": 0.8705984477158324,
|
| 1253 |
+
"eval_precision": 0.9223208386659031,
|
| 1254 |
+
"eval_recall": 0.9104375438916276,
|
| 1255 |
+
"eval_runtime": 1138.7887,
|
| 1256 |
+
"eval_samples_per_second": 53.661,
|
| 1257 |
+
"eval_steps_per_second": 1.677,
|
| 1258 |
+
"step": 10000
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 21.49,
|
| 1262 |
+
"learning_rate": 4.810453920220083e-07,
|
| 1263 |
+
"loss": 0.1386,
|
| 1264 |
+
"step": 10100
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 21.7,
|
| 1268 |
+
"learning_rate": 4.786382393397524e-07,
|
| 1269 |
+
"loss": 0.1383,
|
| 1270 |
+
"step": 10200
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 21.7,
|
| 1274 |
+
"eval_accuracy": 0.9377669410397814,
|
| 1275 |
+
"eval_f1": 0.9154593212298457,
|
| 1276 |
+
"eval_loss": 0.16332927346229553,
|
| 1277 |
+
"eval_matthews_correlation": 0.8708321918919477,
|
| 1278 |
+
"eval_precision": 0.9264808218886014,
|
| 1279 |
+
"eval_recall": 0.9061723895970233,
|
| 1280 |
+
"eval_runtime": 1130.5862,
|
| 1281 |
+
"eval_samples_per_second": 54.051,
|
| 1282 |
+
"eval_steps_per_second": 1.689,
|
| 1283 |
+
"step": 10200
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 21.91,
|
| 1287 |
+
"learning_rate": 4.7623108665749656e-07,
|
| 1288 |
+
"loss": 0.144,
|
| 1289 |
+
"step": 10300
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 22.13,
|
| 1293 |
+
"learning_rate": 4.7382393397524066e-07,
|
| 1294 |
+
"loss": 0.137,
|
| 1295 |
+
"step": 10400
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 22.13,
|
| 1299 |
+
"eval_accuracy": 0.937325107594626,
|
| 1300 |
+
"eval_f1": 0.9155487613959368,
|
| 1301 |
+
"eval_loss": 0.1631198674440384,
|
| 1302 |
+
"eval_matthews_correlation": 0.8701584028013903,
|
| 1303 |
+
"eval_precision": 0.9238303074503852,
|
| 1304 |
+
"eval_recall": 0.9083409162157898,
|
| 1305 |
+
"eval_runtime": 1138.2164,
|
| 1306 |
+
"eval_samples_per_second": 53.688,
|
| 1307 |
+
"eval_steps_per_second": 1.678,
|
| 1308 |
+
"step": 10400
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 22.34,
|
| 1312 |
+
"learning_rate": 4.714167812929848e-07,
|
| 1313 |
+
"loss": 0.1446,
|
| 1314 |
+
"step": 10500
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 22.55,
|
| 1318 |
+
"learning_rate": 4.69009628610729e-07,
|
| 1319 |
+
"loss": 0.1387,
|
| 1320 |
+
"step": 10600
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 22.55,
|
| 1324 |
+
"eval_accuracy": 0.9385851511234025,
|
| 1325 |
+
"eval_f1": 0.9166627207954582,
|
| 1326 |
+
"eval_loss": 0.1620563566684723,
|
| 1327 |
+
"eval_matthews_correlation": 0.8725817378443448,
|
| 1328 |
+
"eval_precision": 0.9271811452031979,
|
| 1329 |
+
"eval_recall": 0.9077409974100349,
|
| 1330 |
+
"eval_runtime": 1145.5718,
|
| 1331 |
+
"eval_samples_per_second": 53.344,
|
| 1332 |
+
"eval_steps_per_second": 1.667,
|
| 1333 |
+
"step": 10600
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 22.77,
|
| 1337 |
+
"learning_rate": 4.6660247592847314e-07,
|
| 1338 |
+
"loss": 0.1367,
|
| 1339 |
+
"step": 10700
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 22.98,
|
| 1343 |
+
"learning_rate": 4.641953232462173e-07,
|
| 1344 |
+
"loss": 0.1369,
|
| 1345 |
+
"step": 10800
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 22.98,
|
| 1349 |
+
"eval_accuracy": 0.9383396880983161,
|
| 1350 |
+
"eval_f1": 0.9172324787033365,
|
| 1351 |
+
"eval_loss": 0.1618376225233078,
|
| 1352 |
+
"eval_matthews_correlation": 0.8723936452197988,
|
| 1353 |
+
"eval_precision": 0.9243962275737605,
|
| 1354 |
+
"eval_recall": 0.9109134783912377,
|
| 1355 |
+
"eval_runtime": 1141.2693,
|
| 1356 |
+
"eval_samples_per_second": 53.545,
|
| 1357 |
+
"eval_steps_per_second": 1.674,
|
| 1358 |
+
"step": 10800
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 23.19,
|
| 1362 |
+
"learning_rate": 4.617881705639615e-07,
|
| 1363 |
+
"loss": 0.1348,
|
| 1364 |
+
"step": 10900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 23.4,
|
| 1368 |
+
"learning_rate": 4.5938101788170567e-07,
|
| 1369 |
+
"loss": 0.1378,
|
| 1370 |
+
"step": 11000
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 23.4,
|
| 1374 |
+
"eval_accuracy": 0.9388797067535061,
|
| 1375 |
+
"eval_f1": 0.9170030704594044,
|
| 1376 |
+
"eval_loss": 0.16103394329547882,
|
| 1377 |
+
"eval_matthews_correlation": 0.8732414480101915,
|
| 1378 |
+
"eval_precision": 0.9272751714823327,
|
| 1379 |
+
"eval_recall": 0.908404227472793,
|
| 1380 |
+
"eval_runtime": 1131.6065,
|
| 1381 |
+
"eval_samples_per_second": 54.002,
|
| 1382 |
+
"eval_steps_per_second": 1.688,
|
| 1383 |
+
"step": 11000
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 23.62,
|
| 1387 |
+
"learning_rate": 4.569738651994498e-07,
|
| 1388 |
+
"loss": 0.1375,
|
| 1389 |
+
"step": 11100
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 23.83,
|
| 1393 |
+
"learning_rate": 4.5456671251719393e-07,
|
| 1394 |
+
"loss": 0.1366,
|
| 1395 |
+
"step": 11200
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 23.83,
|
| 1399 |
+
"eval_accuracy": 0.9389451635601958,
|
| 1400 |
+
"eval_f1": 0.9178736477228994,
|
| 1401 |
+
"eval_loss": 0.16072671115398407,
|
| 1402 |
+
"eval_matthews_correlation": 0.8736416443228668,
|
| 1403 |
+
"eval_precision": 0.9252270842575737,
|
| 1404 |
+
"eval_recall": 0.9114700960342543,
|
| 1405 |
+
"eval_runtime": 1137.3148,
|
| 1406 |
+
"eval_samples_per_second": 53.731,
|
| 1407 |
+
"eval_steps_per_second": 1.679,
|
| 1408 |
+
"step": 11200
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 24.04,
|
| 1412 |
+
"learning_rate": 4.521595598349381e-07,
|
| 1413 |
+
"loss": 0.1356,
|
| 1414 |
+
"step": 11300
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 24.26,
|
| 1418 |
+
"learning_rate": 4.4975240715268225e-07,
|
| 1419 |
+
"loss": 0.1348,
|
| 1420 |
+
"step": 11400
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 24.26,
|
| 1424 |
+
"eval_accuracy": 0.9389287993585232,
|
| 1425 |
+
"eval_f1": 0.9184615824628515,
|
| 1426 |
+
"eval_loss": 0.16080142557621002,
|
| 1427 |
+
"eval_matthews_correlation": 0.8739011778237431,
|
| 1428 |
+
"eval_precision": 0.9233816839860781,
|
| 1429 |
+
"eval_recall": 0.9140549878602235,
|
| 1430 |
+
"eval_runtime": 1135.8462,
|
| 1431 |
+
"eval_samples_per_second": 53.8,
|
| 1432 |
+
"eval_steps_per_second": 1.682,
|
| 1433 |
+
"step": 11400
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 24.47,
|
| 1437 |
+
"learning_rate": 4.4734525447042636e-07,
|
| 1438 |
+
"loss": 0.1331,
|
| 1439 |
+
"step": 11500
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 24.68,
|
| 1443 |
+
"learning_rate": 4.449381017881705e-07,
|
| 1444 |
+
"loss": 0.1318,
|
| 1445 |
+
"step": 11600
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 24.68,
|
| 1449 |
+
"eval_accuracy": 0.9396324600304374,
|
| 1450 |
+
"eval_f1": 0.9179972413838614,
|
| 1451 |
+
"eval_loss": 0.1595466136932373,
|
| 1452 |
+
"eval_matthews_correlation": 0.874736229093411,
|
| 1453 |
+
"eval_precision": 0.9290778467923758,
|
| 1454 |
+
"eval_recall": 0.9086960867914774,
|
| 1455 |
+
"eval_runtime": 1138.0648,
|
| 1456 |
+
"eval_samples_per_second": 53.696,
|
| 1457 |
+
"eval_steps_per_second": 1.678,
|
| 1458 |
+
"step": 11600
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 24.89,
|
| 1462 |
+
"learning_rate": 4.425309491059147e-07,
|
| 1463 |
+
"loss": 0.133,
|
| 1464 |
+
"step": 11700
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 25.11,
|
| 1468 |
+
"learning_rate": 4.4012379642365883e-07,
|
| 1469 |
+
"loss": 0.133,
|
| 1470 |
+
"step": 11800
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 25.11,
|
| 1474 |
+
"eval_accuracy": 0.9398942872571961,
|
| 1475 |
+
"eval_f1": 0.9190977119048673,
|
| 1476 |
+
"eval_loss": 0.1590360403060913,
|
| 1477 |
+
"eval_matthews_correlation": 0.8755172814743742,
|
| 1478 |
+
"eval_precision": 0.9272724566504644,
|
| 1479 |
+
"eval_recall": 0.9119361728726462,
|
| 1480 |
+
"eval_runtime": 1134.5021,
|
| 1481 |
+
"eval_samples_per_second": 53.864,
|
| 1482 |
+
"eval_steps_per_second": 1.684,
|
| 1483 |
+
"step": 11800
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 25.32,
|
| 1487 |
+
"learning_rate": 4.37716643741403e-07,
|
| 1488 |
+
"loss": 0.1335,
|
| 1489 |
+
"step": 11900
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 25.53,
|
| 1493 |
+
"learning_rate": 4.353094910591472e-07,
|
| 1494 |
+
"loss": 0.1314,
|
| 1495 |
+
"step": 12000
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 25.53,
|
| 1499 |
+
"eval_accuracy": 0.9395015464170581,
|
| 1500 |
+
"eval_f1": 0.9190581177761091,
|
| 1501 |
+
"eval_loss": 0.1591825634241104,
|
| 1502 |
+
"eval_matthews_correlation": 0.8750075920131161,
|
| 1503 |
+
"eval_precision": 0.9245997125950819,
|
| 1504 |
+
"eval_recall": 0.9141288069140882,
|
| 1505 |
+
"eval_runtime": 1127.6358,
|
| 1506 |
+
"eval_samples_per_second": 54.192,
|
| 1507 |
+
"eval_steps_per_second": 1.694,
|
| 1508 |
+
"step": 12000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 25.74,
|
| 1512 |
+
"learning_rate": 4.3290233837689136e-07,
|
| 1513 |
+
"loss": 0.1312,
|
| 1514 |
+
"step": 12100
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 25.96,
|
| 1518 |
+
"learning_rate": 4.30519257221458e-07,
|
| 1519 |
+
"loss": 0.1321,
|
| 1520 |
+
"step": 12200
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 25.96,
|
| 1524 |
+
"eval_accuracy": 0.9405324911224205,
|
| 1525 |
+
"eval_f1": 0.9189856286227304,
|
| 1526 |
+
"eval_loss": 0.1582149714231491,
|
| 1527 |
+
"eval_matthews_correlation": 0.8765464055444899,
|
| 1528 |
+
"eval_precision": 0.9312260325323165,
|
| 1529 |
+
"eval_recall": 0.9088528341675056,
|
| 1530 |
+
"eval_runtime": 1128.8638,
|
| 1531 |
+
"eval_samples_per_second": 54.133,
|
| 1532 |
+
"eval_steps_per_second": 1.692,
|
| 1533 |
+
"step": 12200
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 26.17,
|
| 1537 |
+
"learning_rate": 4.2811210453920216e-07,
|
| 1538 |
+
"loss": 0.1296,
|
| 1539 |
+
"step": 12300
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 26.38,
|
| 1543 |
+
"learning_rate": 4.257049518569464e-07,
|
| 1544 |
+
"loss": 0.129,
|
| 1545 |
+
"step": 12400
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 26.38,
|
| 1549 |
+
"eval_accuracy": 0.9404997627190758,
|
| 1550 |
+
"eval_f1": 0.9200009556213352,
|
| 1551 |
+
"eval_loss": 0.15780366957187653,
|
| 1552 |
+
"eval_matthews_correlation": 0.8768428582724813,
|
| 1553 |
+
"eval_precision": 0.9276058379537663,
|
| 1554 |
+
"eval_recall": 0.9133484566347269,
|
| 1555 |
+
"eval_runtime": 1119.4943,
|
| 1556 |
+
"eval_samples_per_second": 54.586,
|
| 1557 |
+
"eval_steps_per_second": 1.706,
|
| 1558 |
+
"step": 12400
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 26.6,
|
| 1562 |
+
"learning_rate": 4.2329779917469053e-07,
|
| 1563 |
+
"loss": 0.1322,
|
| 1564 |
+
"step": 12500
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 26.81,
|
| 1568 |
+
"learning_rate": 4.2089064649243464e-07,
|
| 1569 |
+
"loss": 0.1274,
|
| 1570 |
+
"step": 12600
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 26.81,
|
| 1574 |
+
"eval_accuracy": 0.9409579603659035,
|
| 1575 |
+
"eval_f1": 0.9200809083075646,
|
| 1576 |
+
"eval_loss": 0.15745599567890167,
|
| 1577 |
+
"eval_matthews_correlation": 0.8775856097831178,
|
| 1578 |
+
"eval_precision": 0.9300727450861266,
|
| 1579 |
+
"eval_recall": 0.9115769049685479,
|
| 1580 |
+
"eval_runtime": 1129.8115,
|
| 1581 |
+
"eval_samples_per_second": 54.088,
|
| 1582 |
+
"eval_steps_per_second": 1.691,
|
| 1583 |
+
"step": 12600
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 27.02,
|
| 1587 |
+
"learning_rate": 4.184834938101788e-07,
|
| 1588 |
+
"loss": 0.1298,
|
| 1589 |
+
"step": 12700
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 27.23,
|
| 1593 |
+
"learning_rate": 4.1607634112792296e-07,
|
| 1594 |
+
"loss": 0.1229,
|
| 1595 |
+
"step": 12800
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 27.23,
|
| 1599 |
+
"eval_accuracy": 0.9406797689374724,
|
| 1600 |
+
"eval_f1": 0.9207006984009518,
|
| 1601 |
+
"eval_loss": 0.15740837156772614,
|
| 1602 |
+
"eval_matthews_correlation": 0.8774253242767724,
|
| 1603 |
+
"eval_precision": 0.9264401397553,
|
| 1604 |
+
"eval_recall": 0.915588980453698,
|
| 1605 |
+
"eval_runtime": 1120.579,
|
| 1606 |
+
"eval_samples_per_second": 54.533,
|
| 1607 |
+
"eval_steps_per_second": 1.704,
|
| 1608 |
+
"step": 12800
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 27.45,
|
| 1612 |
+
"learning_rate": 4.136691884456671e-07,
|
| 1613 |
+
"loss": 0.1288,
|
| 1614 |
+
"step": 12900
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 27.66,
|
| 1618 |
+
"learning_rate": 4.112620357634113e-07,
|
| 1619 |
+
"loss": 0.1297,
|
| 1620 |
+
"step": 13000
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 27.66,
|
| 1624 |
+
"eval_accuracy": 0.9410070529709208,
|
| 1625 |
+
"eval_f1": 0.9195664023927276,
|
| 1626 |
+
"eval_loss": 0.15692035853862762,
|
| 1627 |
+
"eval_matthews_correlation": 0.8774949999573018,
|
| 1628 |
+
"eval_precision": 0.9325444450940837,
|
| 1629 |
+
"eval_recall": 0.9088784383760194,
|
| 1630 |
+
"eval_runtime": 1122.3792,
|
| 1631 |
+
"eval_samples_per_second": 54.446,
|
| 1632 |
+
"eval_steps_per_second": 1.702,
|
| 1633 |
+
"step": 13000
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 27.87,
|
| 1637 |
+
"learning_rate": 4.088548830811554e-07,
|
| 1638 |
+
"loss": 0.1294,
|
| 1639 |
+
"step": 13100
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 28.09,
|
| 1643 |
+
"learning_rate": 4.0644773039889954e-07,
|
| 1644 |
+
"loss": 0.127,
|
| 1645 |
+
"step": 13200
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 28.09,
|
| 1649 |
+
"eval_accuracy": 0.9410725097776105,
|
| 1650 |
+
"eval_f1": 0.9215107403838404,
|
| 1651 |
+
"eval_loss": 0.15686339139938354,
|
| 1652 |
+
"eval_matthews_correlation": 0.8783377225875042,
|
| 1653 |
+
"eval_precision": 0.9264187923955762,
|
| 1654 |
+
"eval_recall": 0.9170523743755302,
|
| 1655 |
+
"eval_runtime": 1130.091,
|
| 1656 |
+
"eval_samples_per_second": 54.074,
|
| 1657 |
+
"eval_steps_per_second": 1.69,
|
| 1658 |
+
"step": 13200
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 28.3,
|
| 1662 |
+
"learning_rate": 4.040405777166437e-07,
|
| 1663 |
+
"loss": 0.1283,
|
| 1664 |
+
"step": 13300
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 28.51,
|
| 1668 |
+
"learning_rate": 4.0163342503438786e-07,
|
| 1669 |
+
"loss": 0.1277,
|
| 1670 |
+
"step": 13400
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 28.51,
|
| 1674 |
+
"eval_accuracy": 0.9413343370043692,
|
| 1675 |
+
"eval_f1": 0.9206744312110247,
|
| 1676 |
+
"eval_loss": 0.15601210296154022,
|
| 1677 |
+
"eval_matthews_correlation": 0.8783752668296679,
|
| 1678 |
+
"eval_precision": 0.9305381948772499,
|
| 1679 |
+
"eval_recall": 0.9122284555164281,
|
| 1680 |
+
"eval_runtime": 1130.3041,
|
| 1681 |
+
"eval_samples_per_second": 54.064,
|
| 1682 |
+
"eval_steps_per_second": 1.69,
|
| 1683 |
+
"step": 13400
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 28.72,
|
| 1687 |
+
"learning_rate": 3.9922627235213207e-07,
|
| 1688 |
+
"loss": 0.1253,
|
| 1689 |
+
"step": 13500
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 28.94,
|
| 1693 |
+
"learning_rate": 3.9681911966987623e-07,
|
| 1694 |
+
"loss": 0.1207,
|
| 1695 |
+
"step": 13600
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 28.94,
|
| 1699 |
+
"eval_accuracy": 0.9411379665843002,
|
| 1700 |
+
"eval_f1": 0.9214834197039864,
|
| 1701 |
+
"eval_loss": 0.1558128446340561,
|
| 1702 |
+
"eval_matthews_correlation": 0.8783956105526514,
|
| 1703 |
+
"eval_precision": 0.926977605882486,
|
| 1704 |
+
"eval_recall": 0.9164881442500526,
|
| 1705 |
+
"eval_runtime": 1129.013,
|
| 1706 |
+
"eval_samples_per_second": 54.126,
|
| 1707 |
+
"eval_steps_per_second": 1.692,
|
| 1708 |
+
"step": 13600
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 29.15,
|
| 1712 |
+
"learning_rate": 3.9441196698762033e-07,
|
| 1713 |
+
"loss": 0.126,
|
| 1714 |
+
"step": 13700
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 29.36,
|
| 1718 |
+
"learning_rate": 3.920048143053645e-07,
|
| 1719 |
+
"loss": 0.1233,
|
| 1720 |
+
"step": 13800
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 29.36,
|
| 1724 |
+
"eval_accuracy": 0.9414652506177487,
|
| 1725 |
+
"eval_f1": 0.9214108705582076,
|
| 1726 |
+
"eval_loss": 0.155442476272583,
|
| 1727 |
+
"eval_matthews_correlation": 0.8788308394514168,
|
| 1728 |
+
"eval_precision": 0.9290811733963565,
|
| 1729 |
+
"eval_recall": 0.9146004475707356,
|
| 1730 |
+
"eval_runtime": 1139.9159,
|
| 1731 |
+
"eval_samples_per_second": 53.608,
|
| 1732 |
+
"eval_steps_per_second": 1.676,
|
| 1733 |
+
"step": 13800
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 29.57,
|
| 1737 |
+
"learning_rate": 3.8959766162310865e-07,
|
| 1738 |
+
"loss": 0.1231,
|
| 1739 |
+
"step": 13900
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 29.79,
|
| 1743 |
+
"learning_rate": 3.871905089408528e-07,
|
| 1744 |
+
"loss": 0.1263,
|
| 1745 |
+
"step": 14000
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 29.79,
|
| 1749 |
+
"eval_accuracy": 0.9417598062478522,
|
| 1750 |
+
"eval_f1": 0.9216422791525614,
|
| 1751 |
+
"eval_loss": 0.15486527979373932,
|
| 1752 |
+
"eval_matthews_correlation": 0.8794389554648475,
|
| 1753 |
+
"eval_precision": 0.9295396447855918,
|
| 1754 |
+
"eval_recall": 0.9147710213831234,
|
| 1755 |
+
"eval_runtime": 1125.9339,
|
| 1756 |
+
"eval_samples_per_second": 54.274,
|
| 1757 |
+
"eval_steps_per_second": 1.696,
|
| 1758 |
+
"step": 14000
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 30.0,
|
| 1762 |
+
"learning_rate": 3.8478335625859697e-07,
|
| 1763 |
+
"loss": 0.1245,
|
| 1764 |
+
"step": 14100
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 30.21,
|
| 1768 |
+
"learning_rate": 3.823762035763411e-07,
|
| 1769 |
+
"loss": 0.1237,
|
| 1770 |
+
"step": 14200
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 30.21,
|
| 1774 |
+
"eval_accuracy": 0.9416288926344728,
|
| 1775 |
+
"eval_f1": 0.9223605864239737,
|
| 1776 |
+
"eval_loss": 0.15512850880622864,
|
| 1777 |
+
"eval_matthews_correlation": 0.8795357475488215,
|
| 1778 |
+
"eval_precision": 0.9269163530437144,
|
| 1779 |
+
"eval_recall": 0.9182071872279179,
|
| 1780 |
+
"eval_runtime": 1104.6568,
|
| 1781 |
+
"eval_samples_per_second": 55.319,
|
| 1782 |
+
"eval_steps_per_second": 1.729,
|
| 1783 |
+
"step": 14200
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 30.43,
|
| 1787 |
+
"learning_rate": 3.7996905089408523e-07,
|
| 1788 |
+
"loss": 0.1227,
|
| 1789 |
+
"step": 14300
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 30.64,
|
| 1793 |
+
"learning_rate": 3.775618982118294e-07,
|
| 1794 |
+
"loss": 0.1223,
|
| 1795 |
+
"step": 14400
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 30.64,
|
| 1799 |
+
"eval_accuracy": 0.9419725408695937,
|
| 1800 |
+
"eval_f1": 0.9224586705089605,
|
| 1801 |
+
"eval_loss": 0.1544523686170578,
|
| 1802 |
+
"eval_matthews_correlation": 0.8800542555052714,
|
| 1803 |
+
"eval_precision": 0.9285558015982011,
|
| 1804 |
+
"eval_recall": 0.9169498289882058,
|
| 1805 |
+
"eval_runtime": 1103.5815,
|
| 1806 |
+
"eval_samples_per_second": 55.373,
|
| 1807 |
+
"eval_steps_per_second": 1.731,
|
| 1808 |
+
"step": 14400
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 30.85,
|
| 1812 |
+
"learning_rate": 3.7515474552957355e-07,
|
| 1813 |
+
"loss": 0.122,
|
| 1814 |
+
"step": 14500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 31.06,
|
| 1818 |
+
"learning_rate": 3.7274759284731776e-07,
|
| 1819 |
+
"loss": 0.1223,
|
| 1820 |
+
"step": 14600
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 31.06,
|
| 1824 |
+
"eval_accuracy": 0.9423980101130767,
|
| 1825 |
+
"eval_f1": 0.9223331133049456,
|
| 1826 |
+
"eval_loss": 0.15414074063301086,
|
| 1827 |
+
"eval_matthews_correlation": 0.8806243664613724,
|
| 1828 |
+
"eval_precision": 0.9317093562981557,
|
| 1829 |
+
"eval_recall": 0.9142028224825047,
|
| 1830 |
+
"eval_runtime": 1127.3394,
|
| 1831 |
+
"eval_samples_per_second": 54.206,
|
| 1832 |
+
"eval_steps_per_second": 1.694,
|
| 1833 |
+
"step": 14600
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 31.28,
|
| 1837 |
+
"learning_rate": 3.703404401650619e-07,
|
| 1838 |
+
"loss": 0.1222,
|
| 1839 |
+
"step": 14700
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 31.49,
|
| 1843 |
+
"learning_rate": 3.6795735900962856e-07,
|
| 1844 |
+
"loss": 0.121,
|
| 1845 |
+
"step": 14800
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 31.49,
|
| 1849 |
+
"eval_accuracy": 0.9424143743147491,
|
| 1850 |
+
"eval_f1": 0.9226743391675636,
|
| 1851 |
+
"eval_loss": 0.15365062654018402,
|
| 1852 |
+
"eval_matthews_correlation": 0.8807922676782367,
|
| 1853 |
+
"eval_precision": 0.9305864010842684,
|
| 1854 |
+
"eval_recall": 0.9157406855938447,
|
| 1855 |
+
"eval_runtime": 1096.9802,
|
| 1856 |
+
"eval_samples_per_second": 55.707,
|
| 1857 |
+
"eval_steps_per_second": 1.741,
|
| 1858 |
+
"step": 14800
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 31.7,
|
| 1862 |
+
"learning_rate": 3.655502063273727e-07,
|
| 1863 |
+
"loss": 0.1198,
|
| 1864 |
+
"step": 14900
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 31.91,
|
| 1868 |
+
"learning_rate": 3.6314305364511693e-07,
|
| 1869 |
+
"loss": 0.1198,
|
| 1870 |
+
"step": 15000
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 31.91,
|
| 1874 |
+
"eval_accuracy": 0.9423652817097318,
|
| 1875 |
+
"eval_f1": 0.9218109899084128,
|
| 1876 |
+
"eval_loss": 0.15379200875759125,
|
| 1877 |
+
"eval_matthews_correlation": 0.8804685582055614,
|
| 1878 |
+
"eval_precision": 0.9326720200447173,
|
| 1879 |
+
"eval_recall": 0.9126828528399417,
|
| 1880 |
+
"eval_runtime": 1105.4205,
|
| 1881 |
+
"eval_samples_per_second": 55.281,
|
| 1882 |
+
"eval_steps_per_second": 1.728,
|
| 1883 |
+
"step": 15000
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 32.13,
|
| 1887 |
+
"learning_rate": 3.607359009628611e-07,
|
| 1888 |
+
"loss": 0.1193,
|
| 1889 |
+
"step": 15100
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 32.34,
|
| 1893 |
+
"learning_rate": 3.5832874828060525e-07,
|
| 1894 |
+
"loss": 0.1193,
|
| 1895 |
+
"step": 15200
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 32.34,
|
| 1899 |
+
"eval_accuracy": 0.9424961953231111,
|
| 1900 |
+
"eval_f1": 0.9231857675285348,
|
| 1901 |
+
"eval_loss": 0.15343151986598969,
|
| 1902 |
+
"eval_matthews_correlation": 0.8811431437323947,
|
| 1903 |
+
"eval_precision": 0.9293213427686996,
|
| 1904 |
+
"eval_recall": 0.9176996310804476,
|
| 1905 |
+
"eval_runtime": 1124.2062,
|
| 1906 |
+
"eval_samples_per_second": 54.357,
|
| 1907 |
+
"eval_steps_per_second": 1.699,
|
| 1908 |
+
"step": 15200
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 32.55,
|
| 1912 |
+
"learning_rate": 3.5592159559834936e-07,
|
| 1913 |
+
"loss": 0.1194,
|
| 1914 |
+
"step": 15300
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 32.77,
|
| 1918 |
+
"learning_rate": 3.535144429160935e-07,
|
| 1919 |
+
"loss": 0.1215,
|
| 1920 |
+
"step": 15400
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 32.77,
|
| 1924 |
+
"eval_accuracy": 0.9421198186846454,
|
| 1925 |
+
"eval_f1": 0.9235682615682063,
|
| 1926 |
+
"eval_loss": 0.15412107110023499,
|
| 1927 |
+
"eval_matthews_correlation": 0.8809311583014519,
|
| 1928 |
+
"eval_precision": 0.9255101036658555,
|
| 1929 |
+
"eval_recall": 0.9217672088255878,
|
| 1930 |
+
"eval_runtime": 1116.4465,
|
| 1931 |
+
"eval_samples_per_second": 54.735,
|
| 1932 |
+
"eval_steps_per_second": 1.711,
|
| 1933 |
+
"step": 15400
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 32.98,
|
| 1937 |
+
"learning_rate": 3.511072902338377e-07,
|
| 1938 |
+
"loss": 0.1168,
|
| 1939 |
+
"step": 15500
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 33.19,
|
| 1943 |
+
"learning_rate": 3.4870013755158183e-07,
|
| 1944 |
+
"loss": 0.1177,
|
| 1945 |
+
"step": 15600
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 33.19,
|
| 1949 |
+
"eval_accuracy": 0.9427252941465251,
|
| 1950 |
+
"eval_f1": 0.9240914268595931,
|
| 1951 |
+
"eval_loss": 0.15340538322925568,
|
| 1952 |
+
"eval_matthews_correlation": 0.8819306422216652,
|
| 1953 |
+
"eval_precision": 0.9276927357523115,
|
| 1954 |
+
"eval_recall": 0.9207421406121524,
|
| 1955 |
+
"eval_runtime": 1132.2669,
|
| 1956 |
+
"eval_samples_per_second": 53.97,
|
| 1957 |
+
"eval_steps_per_second": 1.687,
|
| 1958 |
+
"step": 15600
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 33.4,
|
| 1962 |
+
"learning_rate": 3.46292984869326e-07,
|
| 1963 |
+
"loss": 0.1177,
|
| 1964 |
+
"step": 15700
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 33.62,
|
| 1968 |
+
"learning_rate": 3.4388583218707015e-07,
|
| 1969 |
+
"loss": 0.1158,
|
| 1970 |
+
"step": 15800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 33.62,
|
| 1974 |
+
"eval_accuracy": 0.9428725719615768,
|
| 1975 |
+
"eval_f1": 0.9230758188747847,
|
| 1976 |
+
"eval_loss": 0.152634397149086,
|
| 1977 |
+
"eval_matthews_correlation": 0.8817097283454953,
|
| 1978 |
+
"eval_precision": 0.9314416673623378,
|
| 1979 |
+
"eval_recall": 0.9158101125474704,
|
| 1980 |
+
"eval_runtime": 1135.4508,
|
| 1981 |
+
"eval_samples_per_second": 53.819,
|
| 1982 |
+
"eval_steps_per_second": 1.682,
|
| 1983 |
+
"step": 15800
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 33.83,
|
| 1987 |
+
"learning_rate": 3.414786795048143e-07,
|
| 1988 |
+
"loss": 0.1204,
|
| 1989 |
+
"step": 15900
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 34.04,
|
| 1993 |
+
"learning_rate": 3.3907152682255847e-07,
|
| 1994 |
+
"loss": 0.1162,
|
| 1995 |
+
"step": 16000
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 34.04,
|
| 1999 |
+
"eval_accuracy": 0.9432980412050598,
|
| 2000 |
+
"eval_f1": 0.9240152122705202,
|
| 2001 |
+
"eval_loss": 0.1521940678358078,
|
| 2002 |
+
"eval_matthews_correlation": 0.8826973056971621,
|
| 2003 |
+
"eval_precision": 0.931184031044368,
|
| 2004 |
+
"eval_recall": 0.9176525879531132,
|
| 2005 |
+
"eval_runtime": 1108.668,
|
| 2006 |
+
"eval_samples_per_second": 55.119,
|
| 2007 |
+
"eval_steps_per_second": 1.723,
|
| 2008 |
+
"step": 16000
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 34.26,
|
| 2012 |
+
"learning_rate": 3.3666437414030257e-07,
|
| 2013 |
+
"loss": 0.1166,
|
| 2014 |
+
"step": 16100
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 34.47,
|
| 2018 |
+
"learning_rate": 3.3425722145804673e-07,
|
| 2019 |
+
"loss": 0.1147,
|
| 2020 |
+
"step": 16200
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 34.47,
|
| 2024 |
+
"eval_accuracy": 0.9433962264150944,
|
| 2025 |
+
"eval_f1": 0.9241868328582813,
|
| 2026 |
+
"eval_loss": 0.15216147899627686,
|
| 2027 |
+
"eval_matthews_correlation": 0.8829792231347647,
|
| 2028 |
+
"eval_precision": 0.9306640302786223,
|
| 2029 |
+
"eval_recall": 0.9184527518121871,
|
| 2030 |
+
"eval_runtime": 1132.2249,
|
| 2031 |
+
"eval_samples_per_second": 53.972,
|
| 2032 |
+
"eval_steps_per_second": 1.687,
|
| 2033 |
+
"step": 16200
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 34.68,
|
| 2037 |
+
"learning_rate": 3.3185006877579094e-07,
|
| 2038 |
+
"loss": 0.1144,
|
| 2039 |
+
"step": 16300
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 34.89,
|
| 2043 |
+
"learning_rate": 3.2944291609353505e-07,
|
| 2044 |
+
"loss": 0.1172,
|
| 2045 |
+
"step": 16400
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 34.89,
|
| 2049 |
+
"eval_accuracy": 0.943576232633491,
|
| 2050 |
+
"eval_f1": 0.9243561247442994,
|
| 2051 |
+
"eval_loss": 0.15176311135292053,
|
| 2052 |
+
"eval_matthews_correlation": 0.8833109156622424,
|
| 2053 |
+
"eval_precision": 0.9312279042987696,
|
| 2054 |
+
"eval_recall": 0.9182818529319778,
|
| 2055 |
+
"eval_runtime": 1127.5884,
|
| 2056 |
+
"eval_samples_per_second": 54.194,
|
| 2057 |
+
"eval_steps_per_second": 1.694,
|
| 2058 |
+
"step": 16400
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 35.11,
|
| 2062 |
+
"learning_rate": 3.270357634112792e-07,
|
| 2063 |
+
"loss": 0.1184,
|
| 2064 |
+
"step": 16500
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 35.32,
|
| 2068 |
+
"learning_rate": 3.2462861072902337e-07,
|
| 2069 |
+
"loss": 0.1185,
|
| 2070 |
+
"step": 16600
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 35.32,
|
| 2074 |
+
"eval_accuracy": 0.9433471338100771,
|
| 2075 |
+
"eval_f1": 0.9235180133752681,
|
| 2076 |
+
"eval_loss": 0.1514737904071808,
|
| 2077 |
+
"eval_matthews_correlation": 0.8825807929321668,
|
| 2078 |
+
"eval_precision": 0.9332458708783546,
|
| 2079 |
+
"eval_recall": 0.9151356262949316,
|
| 2080 |
+
"eval_runtime": 1129.6017,
|
| 2081 |
+
"eval_samples_per_second": 54.098,
|
| 2082 |
+
"eval_steps_per_second": 1.691,
|
| 2083 |
+
"step": 16600
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 35.53,
|
| 2087 |
+
"learning_rate": 3.222214580467675e-07,
|
| 2088 |
+
"loss": 0.1162,
|
| 2089 |
+
"step": 16700
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 35.74,
|
| 2093 |
+
"learning_rate": 3.198143053645117e-07,
|
| 2094 |
+
"loss": 0.1116,
|
| 2095 |
+
"step": 16800
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 35.74,
|
| 2099 |
+
"eval_accuracy": 0.943461683221784,
|
| 2100 |
+
"eval_f1": 0.9242074753818227,
|
| 2101 |
+
"eval_loss": 0.15152059495449066,
|
| 2102 |
+
"eval_matthews_correlation": 0.8830141159932162,
|
| 2103 |
+
"eval_precision": 0.9315726012507216,
|
| 2104 |
+
"eval_recall": 0.9176551581996923,
|
| 2105 |
+
"eval_runtime": 1106.75,
|
| 2106 |
+
"eval_samples_per_second": 55.215,
|
| 2107 |
+
"eval_steps_per_second": 1.726,
|
| 2108 |
+
"step": 16800
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 35.96,
|
| 2112 |
+
"learning_rate": 3.1740715268225584e-07,
|
| 2113 |
+
"loss": 0.113,
|
| 2114 |
+
"step": 16900
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 36.17,
|
| 2118 |
+
"learning_rate": 3.1502407152682254e-07,
|
| 2119 |
+
"loss": 0.1132,
|
| 2120 |
+
"step": 17000
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 36.17,
|
| 2124 |
+
"eval_accuracy": 0.9433307696084047,
|
| 2125 |
+
"eval_f1": 0.923392580714841,
|
| 2126 |
+
"eval_loss": 0.1517263650894165,
|
| 2127 |
+
"eval_matthews_correlation": 0.8825102281931411,
|
| 2128 |
+
"eval_precision": 0.933593905999869,
|
| 2129 |
+
"eval_recall": 0.9146349342370028,
|
| 2130 |
+
"eval_runtime": 1132.4177,
|
| 2131 |
+
"eval_samples_per_second": 53.963,
|
| 2132 |
+
"eval_steps_per_second": 1.687,
|
| 2133 |
+
"step": 17000
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 36.38,
|
| 2137 |
+
"learning_rate": 3.126169188445667e-07,
|
| 2138 |
+
"loss": 0.1127,
|
| 2139 |
+
"step": 17100
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 36.6,
|
| 2143 |
+
"learning_rate": 3.1020976616231086e-07,
|
| 2144 |
+
"loss": 0.1155,
|
| 2145 |
+
"step": 17200
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 36.6,
|
| 2149 |
+
"eval_accuracy": 0.9438707882635946,
|
| 2150 |
+
"eval_f1": 0.9249328530871743,
|
| 2151 |
+
"eval_loss": 0.15113794803619385,
|
| 2152 |
+
"eval_matthews_correlation": 0.8839614616032178,
|
| 2153 |
+
"eval_precision": 0.9313619229067885,
|
| 2154 |
+
"eval_recall": 0.9191784464817534,
|
| 2155 |
+
"eval_runtime": 1121.0877,
|
| 2156 |
+
"eval_samples_per_second": 54.509,
|
| 2157 |
+
"eval_steps_per_second": 1.704,
|
| 2158 |
+
"step": 17200
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 36.81,
|
| 2162 |
+
"learning_rate": 3.07802613480055e-07,
|
| 2163 |
+
"loss": 0.1144,
|
| 2164 |
+
"step": 17300
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 37.02,
|
| 2168 |
+
"learning_rate": 3.053954607977992e-07,
|
| 2169 |
+
"loss": 0.1105,
|
| 2170 |
+
"step": 17400
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 37.02,
|
| 2174 |
+
"eval_accuracy": 0.9439689734736291,
|
| 2175 |
+
"eval_f1": 0.9247302421488585,
|
| 2176 |
+
"eval_loss": 0.15101274847984314,
|
| 2177 |
+
"eval_matthews_correlation": 0.8840791715082791,
|
| 2178 |
+
"eval_precision": 0.9321543176187953,
|
| 2179 |
+
"eval_recall": 0.9182413488263638,
|
| 2180 |
+
"eval_runtime": 1117.9497,
|
| 2181 |
+
"eval_samples_per_second": 54.662,
|
| 2182 |
+
"eval_steps_per_second": 1.708,
|
| 2183 |
+
"step": 17400
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 37.23,
|
| 2187 |
+
"learning_rate": 3.0298830811554333e-07,
|
| 2188 |
+
"loss": 0.1121,
|
| 2189 |
+
"step": 17500
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 37.45,
|
| 2193 |
+
"learning_rate": 3.0058115543328744e-07,
|
| 2194 |
+
"loss": 0.1103,
|
| 2195 |
+
"step": 17600
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 37.45,
|
| 2199 |
+
"eval_accuracy": 0.9438544240619221,
|
| 2200 |
+
"eval_f1": 0.9248424621748557,
|
| 2201 |
+
"eval_loss": 0.15083517134189606,
|
| 2202 |
+
"eval_matthews_correlation": 0.8839318423708653,
|
| 2203 |
+
"eval_precision": 0.9312687941809888,
|
| 2204 |
+
"eval_recall": 0.9191185521215243,
|
| 2205 |
+
"eval_runtime": 1136.279,
|
| 2206 |
+
"eval_samples_per_second": 53.78,
|
| 2207 |
+
"eval_steps_per_second": 1.681,
|
| 2208 |
+
"step": 17600
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 37.66,
|
| 2212 |
+
"learning_rate": 2.981740027510316e-07,
|
| 2213 |
+
"loss": 0.1168,
|
| 2214 |
+
"step": 17700
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 37.87,
|
| 2218 |
+
"learning_rate": 2.9576685006877576e-07,
|
| 2219 |
+
"loss": 0.1104,
|
| 2220 |
+
"step": 17800
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 37.87,
|
| 2224 |
+
"eval_accuracy": 0.944001701876974,
|
| 2225 |
+
"eval_f1": 0.9255109565953598,
|
| 2226 |
+
"eval_loss": 0.15076182782649994,
|
| 2227 |
+
"eval_matthews_correlation": 0.8844550049466842,
|
| 2228 |
+
"eval_precision": 0.9300012352177646,
|
| 2229 |
+
"eval_recall": 0.9214207921543845,
|
| 2230 |
+
"eval_runtime": 1114.2003,
|
| 2231 |
+
"eval_samples_per_second": 54.846,
|
| 2232 |
+
"eval_steps_per_second": 1.714,
|
| 2233 |
+
"step": 17800
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 38.09,
|
| 2237 |
+
"learning_rate": 2.9335969738651997e-07,
|
| 2238 |
+
"loss": 0.1111,
|
| 2239 |
+
"step": 17900
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 38.3,
|
| 2243 |
+
"learning_rate": 2.9095254470426407e-07,
|
| 2244 |
+
"loss": 0.1134,
|
| 2245 |
+
"step": 18000
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 38.3,
|
| 2249 |
+
"eval_accuracy": 0.9439362450702843,
|
| 2250 |
+
"eval_f1": 0.9253671889189082,
|
| 2251 |
+
"eval_loss": 0.1507214605808258,
|
| 2252 |
+
"eval_matthews_correlation": 0.8842287570521736,
|
| 2253 |
+
"eval_precision": 0.9305811742807507,
|
| 2254 |
+
"eval_recall": 0.9206107706340921,
|
| 2255 |
+
"eval_runtime": 1111.784,
|
| 2256 |
+
"eval_samples_per_second": 54.965,
|
| 2257 |
+
"eval_steps_per_second": 1.718,
|
| 2258 |
+
"step": 18000
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 38.51,
|
| 2262 |
+
"learning_rate": 2.8856946354883077e-07,
|
| 2263 |
+
"loss": 0.1089,
|
| 2264 |
+
"step": 18100
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 38.72,
|
| 2268 |
+
"learning_rate": 2.8616231086657493e-07,
|
| 2269 |
+
"loss": 0.1106,
|
| 2270 |
+
"step": 18200
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 38.72,
|
| 2274 |
+
"eval_accuracy": 0.9441162512886809,
|
| 2275 |
+
"eval_f1": 0.9251360377006875,
|
| 2276 |
+
"eval_loss": 0.15033245086669922,
|
| 2277 |
+
"eval_matthews_correlation": 0.8843929494825783,
|
| 2278 |
+
"eval_precision": 0.9323618927884416,
|
| 2279 |
+
"eval_recall": 0.9187285395157545,
|
| 2280 |
+
"eval_runtime": 1121.674,
|
| 2281 |
+
"eval_samples_per_second": 54.48,
|
| 2282 |
+
"eval_steps_per_second": 1.703,
|
| 2283 |
+
"step": 18200
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 38.94,
|
| 2287 |
+
"learning_rate": 2.8375515818431914e-07,
|
| 2288 |
+
"loss": 0.1114,
|
| 2289 |
+
"step": 18300
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 39.15,
|
| 2293 |
+
"learning_rate": 2.8134800550206325e-07,
|
| 2294 |
+
"loss": 0.1095,
|
| 2295 |
+
"step": 18400
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 39.15,
|
| 2299 |
+
"eval_accuracy": 0.943887152465267,
|
| 2300 |
+
"eval_f1": 0.9255818230394176,
|
| 2301 |
+
"eval_loss": 0.15064190328121185,
|
| 2302 |
+
"eval_matthews_correlation": 0.8842602118056405,
|
| 2303 |
+
"eval_precision": 0.9297138876991945,
|
| 2304 |
+
"eval_recall": 0.9217534806465043,
|
| 2305 |
+
"eval_runtime": 1127.018,
|
| 2306 |
+
"eval_samples_per_second": 54.222,
|
| 2307 |
+
"eval_steps_per_second": 1.695,
|
| 2308 |
+
"step": 18400
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 39.36,
|
| 2312 |
+
"learning_rate": 2.789408528198074e-07,
|
| 2313 |
+
"loss": 0.11,
|
| 2314 |
+
"step": 18500
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 39.57,
|
| 2318 |
+
"learning_rate": 2.7653370013755156e-07,
|
| 2319 |
+
"loss": 0.1122,
|
| 2320 |
+
"step": 18600
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 39.57,
|
| 2324 |
+
"eval_accuracy": 0.9441489796920257,
|
| 2325 |
+
"eval_f1": 0.9250135407540009,
|
| 2326 |
+
"eval_loss": 0.14996594190597534,
|
| 2327 |
+
"eval_matthews_correlation": 0.884420266208998,
|
| 2328 |
+
"eval_precision": 0.9326893583639841,
|
| 2329 |
+
"eval_recall": 0.9182519548805012,
|
| 2330 |
+
"eval_runtime": 1113.4663,
|
| 2331 |
+
"eval_samples_per_second": 54.882,
|
| 2332 |
+
"eval_steps_per_second": 1.715,
|
| 2333 |
+
"step": 18600
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 39.79,
|
| 2337 |
+
"learning_rate": 2.741265474552957e-07,
|
| 2338 |
+
"loss": 0.1083,
|
| 2339 |
+
"step": 18700
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 40.0,
|
| 2343 |
+
"learning_rate": 2.717193947730399e-07,
|
| 2344 |
+
"loss": 0.1104,
|
| 2345 |
+
"step": 18800
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 40.0,
|
| 2349 |
+
"eval_accuracy": 0.9440180660786464,
|
| 2350 |
+
"eval_f1": 0.9253930021308615,
|
| 2351 |
+
"eval_loss": 0.15009328722953796,
|
| 2352 |
+
"eval_matthews_correlation": 0.8844160433170132,
|
| 2353 |
+
"eval_precision": 0.9304927678821387,
|
| 2354 |
+
"eval_recall": 0.920780596053561,
|
| 2355 |
+
"eval_runtime": 1131.9242,
|
| 2356 |
+
"eval_samples_per_second": 53.987,
|
| 2357 |
+
"eval_steps_per_second": 1.687,
|
| 2358 |
+
"step": 18800
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 40.21,
|
| 2362 |
+
"learning_rate": 2.6931224209078404e-07,
|
| 2363 |
+
"loss": 0.1095,
|
| 2364 |
+
"step": 18900
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 40.43,
|
| 2368 |
+
"learning_rate": 2.669050894085282e-07,
|
| 2369 |
+
"loss": 0.1099,
|
| 2370 |
+
"step": 19000
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 40.43,
|
| 2374 |
+
"eval_accuracy": 0.9441817080953706,
|
| 2375 |
+
"eval_f1": 0.9259059644722075,
|
| 2376 |
+
"eval_loss": 0.15028244256973267,
|
| 2377 |
+
"eval_matthews_correlation": 0.8848699358673907,
|
| 2378 |
+
"eval_precision": 0.9300530378191784,
|
| 2379 |
+
"eval_recall": 0.9221055593932391,
|
| 2380 |
+
"eval_runtime": 1133.4466,
|
| 2381 |
+
"eval_samples_per_second": 53.914,
|
| 2382 |
+
"eval_steps_per_second": 1.685,
|
| 2383 |
+
"step": 19000
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 40.64,
|
| 2387 |
+
"learning_rate": 2.6449793672627236e-07,
|
| 2388 |
+
"loss": 0.105,
|
| 2389 |
+
"step": 19100
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 40.85,
|
| 2393 |
+
"learning_rate": 2.6209078404401646e-07,
|
| 2394 |
+
"loss": 0.1098,
|
| 2395 |
+
"step": 19200
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 40.85,
|
| 2399 |
+
"eval_accuracy": 0.944198072297043,
|
| 2400 |
+
"eval_f1": 0.9254187143519279,
|
| 2401 |
+
"eval_loss": 0.14963504672050476,
|
| 2402 |
+
"eval_matthews_correlation": 0.8846911439559728,
|
| 2403 |
+
"eval_precision": 0.9313966189199636,
|
| 2404 |
+
"eval_recall": 0.9200651823703107,
|
| 2405 |
+
"eval_runtime": 1146.6556,
|
| 2406 |
+
"eval_samples_per_second": 53.293,
|
| 2407 |
+
"eval_steps_per_second": 1.666,
|
| 2408 |
+
"step": 19200
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 41.06,
|
| 2412 |
+
"learning_rate": 2.596836313617606e-07,
|
| 2413 |
+
"loss": 0.1087,
|
| 2414 |
+
"step": 19300
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 41.28,
|
| 2418 |
+
"learning_rate": 2.5727647867950483e-07,
|
| 2419 |
+
"loss": 0.1105,
|
| 2420 |
+
"step": 19400
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 41.28,
|
| 2424 |
+
"eval_accuracy": 0.9444435353221293,
|
| 2425 |
+
"eval_f1": 0.9256968337682165,
|
| 2426 |
+
"eval_loss": 0.14939628541469574,
|
| 2427 |
+
"eval_matthews_correlation": 0.8851581931672046,
|
| 2428 |
+
"eval_precision": 0.9320685204142367,
|
| 2429 |
+
"eval_recall": 0.920004214549341,
|
| 2430 |
+
"eval_runtime": 1134.2905,
|
| 2431 |
+
"eval_samples_per_second": 53.874,
|
| 2432 |
+
"eval_steps_per_second": 1.684,
|
| 2433 |
+
"step": 19400
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 41.49,
|
| 2437 |
+
"learning_rate": 2.5486932599724894e-07,
|
| 2438 |
+
"loss": 0.1053,
|
| 2439 |
+
"step": 19500
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 41.7,
|
| 2443 |
+
"learning_rate": 2.524621733149931e-07,
|
| 2444 |
+
"loss": 0.1085,
|
| 2445 |
+
"step": 19600
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 41.7,
|
| 2449 |
+
"eval_accuracy": 0.9446726341455433,
|
| 2450 |
+
"eval_f1": 0.925738034839588,
|
| 2451 |
+
"eval_loss": 0.14932939410209656,
|
| 2452 |
+
"eval_matthews_correlation": 0.8854889075253487,
|
| 2453 |
+
"eval_precision": 0.9336149730127167,
|
| 2454 |
+
"eval_recall": 0.9187943227620606,
|
| 2455 |
+
"eval_runtime": 1117.9194,
|
| 2456 |
+
"eval_samples_per_second": 54.663,
|
| 2457 |
+
"eval_steps_per_second": 1.709,
|
| 2458 |
+
"step": 19600
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 41.91,
|
| 2462 |
+
"learning_rate": 2.5005502063273726e-07,
|
| 2463 |
+
"loss": 0.1062,
|
| 2464 |
+
"step": 19700
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 42.13,
|
| 2468 |
+
"learning_rate": 2.476478679504814e-07,
|
| 2469 |
+
"loss": 0.108,
|
| 2470 |
+
"step": 19800
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 42.13,
|
| 2474 |
+
"eval_accuracy": 0.9447217267505604,
|
| 2475 |
+
"eval_f1": 0.9262048825799548,
|
| 2476 |
+
"eval_loss": 0.1495121866464615,
|
| 2477 |
+
"eval_matthews_correlation": 0.8858026294978001,
|
| 2478 |
+
"eval_precision": 0.9319552420338207,
|
| 2479 |
+
"eval_recall": 0.9210483479495699,
|
| 2480 |
+
"eval_runtime": 1115.2527,
|
| 2481 |
+
"eval_samples_per_second": 54.794,
|
| 2482 |
+
"eval_steps_per_second": 1.713,
|
| 2483 |
+
"step": 19800
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 42.34,
|
| 2487 |
+
"learning_rate": 2.4524071526822557e-07,
|
| 2488 |
+
"loss": 0.1076,
|
| 2489 |
+
"step": 19900
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 42.55,
|
| 2493 |
+
"learning_rate": 2.4283356258596973e-07,
|
| 2494 |
+
"loss": 0.1044,
|
| 2495 |
+
"step": 20000
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 42.55,
|
| 2499 |
+
"eval_accuracy": 0.944508992128819,
|
| 2500 |
+
"eval_f1": 0.9261252498145538,
|
| 2501 |
+
"eval_loss": 0.14950193464756012,
|
| 2502 |
+
"eval_matthews_correlation": 0.8854199049552949,
|
| 2503 |
+
"eval_precision": 0.9313193606961945,
|
| 2504 |
+
"eval_recall": 0.9214106094253447,
|
| 2505 |
+
"eval_runtime": 1130.1649,
|
| 2506 |
+
"eval_samples_per_second": 54.071,
|
| 2507 |
+
"eval_steps_per_second": 1.69,
|
| 2508 |
+
"step": 20000
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 42.77,
|
| 2512 |
+
"learning_rate": 2.404264099037139e-07,
|
| 2513 |
+
"loss": 0.106,
|
| 2514 |
+
"step": 20100
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 42.98,
|
| 2518 |
+
"learning_rate": 2.3801925722145802e-07,
|
| 2519 |
+
"loss": 0.1076,
|
| 2520 |
+
"step": 20200
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 42.98,
|
| 2524 |
+
"eval_accuracy": 0.9446562699438708,
|
| 2525 |
+
"eval_f1": 0.9261296033746204,
|
| 2526 |
+
"eval_loss": 0.14920221269130707,
|
| 2527 |
+
"eval_matthews_correlation": 0.8855912047264707,
|
| 2528 |
+
"eval_precision": 0.9324907409462333,
|
| 2529 |
+
"eval_recall": 0.9203679728109541,
|
| 2530 |
+
"eval_runtime": 1137.936,
|
| 2531 |
+
"eval_samples_per_second": 53.702,
|
| 2532 |
+
"eval_steps_per_second": 1.678,
|
| 2533 |
+
"step": 20200
|
| 2534 |
+
},
|
| 2535 |
+
{
|
| 2536 |
+
"epoch": 43.19,
|
| 2537 |
+
"learning_rate": 2.3561210453920218e-07,
|
| 2538 |
+
"loss": 0.107,
|
| 2539 |
+
"step": 20300
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 43.4,
|
| 2543 |
+
"learning_rate": 2.3320495185694637e-07,
|
| 2544 |
+
"loss": 0.1044,
|
| 2545 |
+
"step": 20400
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 43.4,
|
| 2549 |
+
"eval_accuracy": 0.9445417205321638,
|
| 2550 |
+
"eval_f1": 0.9266300766293115,
|
| 2551 |
+
"eval_loss": 0.1497085839509964,
|
| 2552 |
+
"eval_matthews_correlation": 0.8857559939442303,
|
| 2553 |
+
"eval_precision": 0.9296997536026302,
|
| 2554 |
+
"eval_recall": 0.9237603159106365,
|
| 2555 |
+
"eval_runtime": 1136.0812,
|
| 2556 |
+
"eval_samples_per_second": 53.789,
|
| 2557 |
+
"eval_steps_per_second": 1.681,
|
| 2558 |
+
"step": 20400
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 43.62,
|
| 2562 |
+
"learning_rate": 2.307977991746905e-07,
|
| 2563 |
+
"loss": 0.105,
|
| 2564 |
+
"step": 20500
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 43.83,
|
| 2568 |
+
"learning_rate": 2.2839064649243466e-07,
|
| 2569 |
+
"loss": 0.1055,
|
| 2570 |
+
"step": 20600
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 43.83,
|
| 2574 |
+
"eval_accuracy": 0.9446889983472156,
|
| 2575 |
+
"eval_f1": 0.9266109603225074,
|
| 2576 |
+
"eval_loss": 0.14924582839012146,
|
| 2577 |
+
"eval_matthews_correlation": 0.8859684030602588,
|
| 2578 |
+
"eval_precision": 0.9303740597513821,
|
| 2579 |
+
"eval_recall": 0.9231584769939456,
|
| 2580 |
+
"eval_runtime": 1125.8192,
|
| 2581 |
+
"eval_samples_per_second": 54.28,
|
| 2582 |
+
"eval_steps_per_second": 1.697,
|
| 2583 |
+
"step": 20600
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 44.04,
|
| 2587 |
+
"learning_rate": 2.2598349381017882e-07,
|
| 2588 |
+
"loss": 0.1065,
|
| 2589 |
+
"step": 20700
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 44.26,
|
| 2593 |
+
"learning_rate": 2.2357634112792295e-07,
|
| 2594 |
+
"loss": 0.1043,
|
| 2595 |
+
"step": 20800
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 44.26,
|
| 2599 |
+
"eval_accuracy": 0.9446071773388536,
|
| 2600 |
+
"eval_f1": 0.9263262351610323,
|
| 2601 |
+
"eval_loss": 0.14892685413360596,
|
| 2602 |
+
"eval_matthews_correlation": 0.8856938722284602,
|
| 2603 |
+
"eval_precision": 0.9309299279423926,
|
| 2604 |
+
"eval_recall": 0.9221329854554128,
|
| 2605 |
+
"eval_runtime": 1129.4248,
|
| 2606 |
+
"eval_samples_per_second": 54.106,
|
| 2607 |
+
"eval_steps_per_second": 1.691,
|
| 2608 |
+
"step": 20800
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 44.47,
|
| 2612 |
+
"learning_rate": 2.211691884456671e-07,
|
| 2613 |
+
"loss": 0.1029,
|
| 2614 |
+
"step": 20900
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 44.68,
|
| 2618 |
+
"learning_rate": 2.187620357634113e-07,
|
| 2619 |
+
"loss": 0.1042,
|
| 2620 |
+
"step": 21000
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 44.68,
|
| 2624 |
+
"eval_accuracy": 0.944705362548888,
|
| 2625 |
+
"eval_f1": 0.9260999899887844,
|
| 2626 |
+
"eval_loss": 0.1488848179578781,
|
| 2627 |
+
"eval_matthews_correlation": 0.8857253503507664,
|
| 2628 |
+
"eval_precision": 0.9322554110387342,
|
| 2629 |
+
"eval_recall": 0.9205995144443117,
|
| 2630 |
+
"eval_runtime": 1114.3176,
|
| 2631 |
+
"eval_samples_per_second": 54.84,
|
| 2632 |
+
"eval_steps_per_second": 1.714,
|
| 2633 |
+
"step": 21000
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 44.89,
|
| 2637 |
+
"learning_rate": 2.1635488308115542e-07,
|
| 2638 |
+
"loss": 0.1076,
|
| 2639 |
+
"step": 21100
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 45.11,
|
| 2643 |
+
"learning_rate": 2.1394773039889958e-07,
|
| 2644 |
+
"loss": 0.1024,
|
| 2645 |
+
"step": 21200
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"epoch": 45.11,
|
| 2649 |
+
"eval_accuracy": 0.9449508255739744,
|
| 2650 |
+
"eval_f1": 0.9260476048473397,
|
| 2651 |
+
"eval_loss": 0.1487448662519455,
|
| 2652 |
+
"eval_matthews_correlation": 0.8860574300049961,
|
| 2653 |
+
"eval_precision": 0.9340386476068,
|
| 2654 |
+
"eval_recall": 0.9190087193195606,
|
| 2655 |
+
"eval_runtime": 1127.35,
|
| 2656 |
+
"eval_samples_per_second": 54.206,
|
| 2657 |
+
"eval_steps_per_second": 1.694,
|
| 2658 |
+
"step": 21200
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 45.32,
|
| 2662 |
+
"learning_rate": 2.1154057771664372e-07,
|
| 2663 |
+
"loss": 0.1038,
|
| 2664 |
+
"step": 21300
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 45.53,
|
| 2668 |
+
"learning_rate": 2.0913342503438787e-07,
|
| 2669 |
+
"loss": 0.1053,
|
| 2670 |
+
"step": 21400
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 45.53,
|
| 2674 |
+
"eval_accuracy": 0.9449671897756468,
|
| 2675 |
+
"eval_f1": 0.9266078787740653,
|
| 2676 |
+
"eval_loss": 0.14872543513774872,
|
| 2677 |
+
"eval_matthews_correlation": 0.8863451628405484,
|
| 2678 |
+
"eval_precision": 0.9320275040537918,
|
| 2679 |
+
"eval_recall": 0.9217133998659879,
|
| 2680 |
+
"eval_runtime": 1121.4402,
|
| 2681 |
+
"eval_samples_per_second": 54.492,
|
| 2682 |
+
"eval_steps_per_second": 1.703,
|
| 2683 |
+
"step": 21400
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 45.74,
|
| 2687 |
+
"learning_rate": 2.0672627235213206e-07,
|
| 2688 |
+
"loss": 0.1037,
|
| 2689 |
+
"step": 21500
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 45.96,
|
| 2693 |
+
"learning_rate": 2.0431911966987622e-07,
|
| 2694 |
+
"loss": 0.1023,
|
| 2695 |
+
"step": 21600
|
| 2696 |
+
},
|
| 2697 |
+
{
|
| 2698 |
+
"epoch": 45.96,
|
| 2699 |
+
"eval_accuracy": 0.9447871835572501,
|
| 2700 |
+
"eval_f1": 0.9262474411932805,
|
| 2701 |
+
"eval_loss": 0.1485784500837326,
|
| 2702 |
+
"eval_matthews_correlation": 0.8859042819526408,
|
| 2703 |
+
"eval_precision": 0.9322667829591439,
|
| 2704 |
+
"eval_recall": 0.9208211984164509,
|
| 2705 |
+
"eval_runtime": 1107.2279,
|
| 2706 |
+
"eval_samples_per_second": 55.191,
|
| 2707 |
+
"eval_steps_per_second": 1.725,
|
| 2708 |
+
"step": 21600
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 46.17,
|
| 2712 |
+
"learning_rate": 2.0191196698762035e-07,
|
| 2713 |
+
"loss": 0.1039,
|
| 2714 |
+
"step": 21700
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 46.38,
|
| 2718 |
+
"learning_rate": 1.995048143053645e-07,
|
| 2719 |
+
"loss": 0.1037,
|
| 2720 |
+
"step": 21800
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 46.38,
|
| 2724 |
+
"eval_accuracy": 0.9448362761622674,
|
| 2725 |
+
"eval_f1": 0.926612727616941,
|
| 2726 |
+
"eval_loss": 0.14873600006103516,
|
| 2727 |
+
"eval_matthews_correlation": 0.8861794892897553,
|
| 2728 |
+
"eval_precision": 0.9311237661981897,
|
| 2729 |
+
"eval_recall": 0.9225047795245841,
|
| 2730 |
+
"eval_runtime": 1134.6231,
|
| 2731 |
+
"eval_samples_per_second": 53.858,
|
| 2732 |
+
"eval_steps_per_second": 1.683,
|
| 2733 |
+
"step": 21800
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 46.6,
|
| 2737 |
+
"learning_rate": 1.9709766162310864e-07,
|
| 2738 |
+
"loss": 0.1029,
|
| 2739 |
+
"step": 21900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 46.81,
|
| 2743 |
+
"learning_rate": 1.946905089408528e-07,
|
| 2744 |
+
"loss": 0.1046,
|
| 2745 |
+
"step": 22000
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 46.81,
|
| 2749 |
+
"eval_accuracy": 0.944819911960595,
|
| 2750 |
+
"eval_f1": 0.9266815604872392,
|
| 2751 |
+
"eval_loss": 0.14862757921218872,
|
| 2752 |
+
"eval_matthews_correlation": 0.8861793421063061,
|
| 2753 |
+
"eval_precision": 0.9309033406756093,
|
| 2754 |
+
"eval_recall": 0.922807895033049,
|
| 2755 |
+
"eval_runtime": 1129.167,
|
| 2756 |
+
"eval_samples_per_second": 54.119,
|
| 2757 |
+
"eval_steps_per_second": 1.692,
|
| 2758 |
+
"step": 22000
|
| 2759 |
+
},
|
| 2760 |
+
{
|
| 2761 |
+
"epoch": 47.02,
|
| 2762 |
+
"learning_rate": 1.9230742778541952e-07,
|
| 2763 |
+
"loss": 0.1012,
|
| 2764 |
+
"step": 22100
|
| 2765 |
+
},
|
| 2766 |
+
{
|
| 2767 |
+
"epoch": 47.23,
|
| 2768 |
+
"learning_rate": 1.8990027510316368e-07,
|
| 2769 |
+
"loss": 0.1027,
|
| 2770 |
+
"step": 22200
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 47.23,
|
| 2774 |
+
"eval_accuracy": 0.9451144675906986,
|
| 2775 |
+
"eval_f1": 0.9268280716567586,
|
| 2776 |
+
"eval_loss": 0.1484626680612564,
|
| 2777 |
+
"eval_matthews_correlation": 0.8866650411840761,
|
| 2778 |
+
"eval_precision": 0.9320985784552063,
|
| 2779 |
+
"eval_recall": 0.922045014897367,
|
| 2780 |
+
"eval_runtime": 1111.3061,
|
| 2781 |
+
"eval_samples_per_second": 54.988,
|
| 2782 |
+
"eval_steps_per_second": 1.719,
|
| 2783 |
+
"step": 22200
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 47.45,
|
| 2787 |
+
"learning_rate": 1.8749312242090781e-07,
|
| 2788 |
+
"loss": 0.1015,
|
| 2789 |
+
"step": 22300
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 47.66,
|
| 2793 |
+
"learning_rate": 1.8508596973865197e-07,
|
| 2794 |
+
"loss": 0.1013,
|
| 2795 |
+
"step": 22400
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 47.66,
|
| 2799 |
+
"eval_accuracy": 0.9451144675906986,
|
| 2800 |
+
"eval_f1": 0.9269906309252122,
|
| 2801 |
+
"eval_loss": 0.14851711690425873,
|
| 2802 |
+
"eval_matthews_correlation": 0.8867653549869635,
|
| 2803 |
+
"eval_precision": 0.9314070719703338,
|
| 2804 |
+
"eval_recall": 0.9229525395691017,
|
| 2805 |
+
"eval_runtime": 1067.1147,
|
| 2806 |
+
"eval_samples_per_second": 57.266,
|
| 2807 |
+
"eval_steps_per_second": 1.79,
|
| 2808 |
+
"step": 22400
|
| 2809 |
+
},
|
| 2810 |
+
{
|
| 2811 |
+
"epoch": 47.87,
|
| 2812 |
+
"learning_rate": 1.8267881705639616e-07,
|
| 2813 |
+
"loss": 0.1035,
|
| 2814 |
+
"step": 22500
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 48.09,
|
| 2818 |
+
"learning_rate": 1.8027166437414032e-07,
|
| 2819 |
+
"loss": 0.1024,
|
| 2820 |
+
"step": 22600
|
| 2821 |
+
},
|
| 2822 |
+
{
|
| 2823 |
+
"epoch": 48.09,
|
| 2824 |
+
"eval_accuracy": 0.9452944738090953,
|
| 2825 |
+
"eval_f1": 0.9269075563677092,
|
| 2826 |
+
"eval_loss": 0.14834338426589966,
|
| 2827 |
+
"eval_matthews_correlation": 0.8869764186987058,
|
| 2828 |
+
"eval_precision": 0.9327962247988729,
|
| 2829 |
+
"eval_recall": 0.92164075253014,
|
| 2830 |
+
"eval_runtime": 1041.7879,
|
| 2831 |
+
"eval_samples_per_second": 58.658,
|
| 2832 |
+
"eval_steps_per_second": 1.833,
|
| 2833 |
+
"step": 22600
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 48.3,
|
| 2837 |
+
"learning_rate": 1.7786451169188445e-07,
|
| 2838 |
+
"loss": 0.1019,
|
| 2839 |
+
"step": 22700
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 48.51,
|
| 2843 |
+
"learning_rate": 1.754573590096286e-07,
|
| 2844 |
+
"loss": 0.1017,
|
| 2845 |
+
"step": 22800
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 48.51,
|
| 2849 |
+
"eval_accuracy": 0.945016282380664,
|
| 2850 |
+
"eval_f1": 0.9267798368823591,
|
| 2851 |
+
"eval_loss": 0.1482786238193512,
|
| 2852 |
+
"eval_matthews_correlation": 0.8864825429378855,
|
| 2853 |
+
"eval_precision": 0.9318586242689054,
|
| 2854 |
+
"eval_recall": 0.9221523757100277,
|
| 2855 |
+
"eval_runtime": 1047.8174,
|
| 2856 |
+
"eval_samples_per_second": 58.32,
|
| 2857 |
+
"eval_steps_per_second": 1.823,
|
| 2858 |
+
"step": 22800
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 48.72,
|
| 2862 |
+
"learning_rate": 1.7305020632737277e-07,
|
| 2863 |
+
"loss": 0.1023,
|
| 2864 |
+
"step": 22900
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 48.94,
|
| 2868 |
+
"learning_rate": 1.7066712517193946e-07,
|
| 2869 |
+
"loss": 0.1003,
|
| 2870 |
+
"step": 23000
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 48.94,
|
| 2874 |
+
"eval_accuracy": 0.9450490107840089,
|
| 2875 |
+
"eval_f1": 0.927166667024839,
|
| 2876 |
+
"eval_loss": 0.1484668105840683,
|
| 2877 |
+
"eval_matthews_correlation": 0.8866843486297423,
|
| 2878 |
+
"eval_precision": 0.9311237652714297,
|
| 2879 |
+
"eval_recall": 0.9234908404182439,
|
| 2880 |
+
"eval_runtime": 1048.467,
|
| 2881 |
+
"eval_samples_per_second": 58.284,
|
| 2882 |
+
"eval_steps_per_second": 1.822,
|
| 2883 |
+
"step": 23000
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 49.15,
|
| 2887 |
+
"learning_rate": 1.6825997248968362e-07,
|
| 2888 |
+
"loss": 0.1007,
|
| 2889 |
+
"step": 23100
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 49.36,
|
| 2893 |
+
"learning_rate": 1.6585281980742778e-07,
|
| 2894 |
+
"loss": 0.1019,
|
| 2895 |
+
"step": 23200
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 49.36,
|
| 2899 |
+
"eval_accuracy": 0.9454908442291643,
|
| 2900 |
+
"eval_f1": 0.9270481922188618,
|
| 2901 |
+
"eval_loss": 0.14815160632133484,
|
| 2902 |
+
"eval_matthews_correlation": 0.887288083753074,
|
| 2903 |
+
"eval_precision": 0.9338332607657969,
|
| 2904 |
+
"eval_recall": 0.9209852332071188,
|
| 2905 |
+
"eval_runtime": 1043.8215,
|
| 2906 |
+
"eval_samples_per_second": 58.544,
|
| 2907 |
+
"eval_steps_per_second": 1.83,
|
| 2908 |
+
"step": 23200
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 49.57,
|
| 2912 |
+
"learning_rate": 1.6344566712517194e-07,
|
| 2913 |
+
"loss": 0.1008,
|
| 2914 |
+
"step": 23300
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 49.79,
|
| 2918 |
+
"learning_rate": 1.610385144429161e-07,
|
| 2919 |
+
"loss": 0.0984,
|
| 2920 |
+
"step": 23400
|
| 2921 |
+
},
|
| 2922 |
+
{
|
| 2923 |
+
"epoch": 49.79,
|
| 2924 |
+
"eval_accuracy": 0.9450490107840089,
|
| 2925 |
+
"eval_f1": 0.9272141389942649,
|
| 2926 |
+
"eval_loss": 0.1484888792037964,
|
| 2927 |
+
"eval_matthews_correlation": 0.8867470893089248,
|
| 2928 |
+
"eval_precision": 0.930697822539048,
|
| 2929 |
+
"eval_recall": 0.9239834966686141,
|
| 2930 |
+
"eval_runtime": 1046.2775,
|
| 2931 |
+
"eval_samples_per_second": 58.406,
|
| 2932 |
+
"eval_steps_per_second": 1.826,
|
| 2933 |
+
"step": 23400
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 50.0,
|
| 2937 |
+
"learning_rate": 1.5863136176066023e-07,
|
| 2938 |
+
"loss": 0.1005,
|
| 2939 |
+
"step": 23500
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 50.21,
|
| 2943 |
+
"learning_rate": 1.5622420907840441e-07,
|
| 2944 |
+
"loss": 0.1007,
|
| 2945 |
+
"step": 23600
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 50.21,
|
| 2949 |
+
"eval_accuracy": 0.9451799243973883,
|
| 2950 |
+
"eval_f1": 0.9271281688970315,
|
| 2951 |
+
"eval_loss": 0.14829137921333313,
|
| 2952 |
+
"eval_matthews_correlation": 0.8868975027838668,
|
| 2953 |
+
"eval_precision": 0.9315634975546264,
|
| 2954 |
+
"eval_recall": 0.9230624706283415,
|
| 2955 |
+
"eval_runtime": 1042.8498,
|
| 2956 |
+
"eval_samples_per_second": 58.598,
|
| 2957 |
+
"eval_steps_per_second": 1.832,
|
| 2958 |
+
"step": 23600
|
| 2959 |
+
},
|
| 2960 |
+
{
|
| 2961 |
+
"epoch": 50.43,
|
| 2962 |
+
"learning_rate": 1.5381705639614855e-07,
|
| 2963 |
+
"loss": 0.1001,
|
| 2964 |
+
"step": 23700
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 50.64,
|
| 2968 |
+
"learning_rate": 1.514099037138927e-07,
|
| 2969 |
+
"loss": 0.0968,
|
| 2970 |
+
"step": 23800
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 50.64,
|
| 2974 |
+
"eval_accuracy": 0.9454090232208022,
|
| 2975 |
+
"eval_f1": 0.9272991700931191,
|
| 2976 |
+
"eval_loss": 0.14818619191646576,
|
| 2977 |
+
"eval_matthews_correlation": 0.8872938388879654,
|
| 2978 |
+
"eval_precision": 0.9323994024344309,
|
| 2979 |
+
"eval_recall": 0.9226563864074547,
|
| 2980 |
+
"eval_runtime": 1044.5886,
|
| 2981 |
+
"eval_samples_per_second": 58.501,
|
| 2982 |
+
"eval_steps_per_second": 1.828,
|
| 2983 |
+
"step": 23800
|
| 2984 |
+
},
|
| 2985 |
+
{
|
| 2986 |
+
"epoch": 50.85,
|
| 2987 |
+
"learning_rate": 1.4900275103163686e-07,
|
| 2988 |
+
"loss": 0.102,
|
| 2989 |
+
"step": 23900
|
| 2990 |
+
},
|
| 2991 |
+
{
|
| 2992 |
+
"epoch": 51.06,
|
| 2993 |
+
"learning_rate": 1.46595598349381e-07,
|
| 2994 |
+
"loss": 0.102,
|
| 2995 |
+
"step": 24000
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 51.06,
|
| 2999 |
+
"eval_accuracy": 0.9451635601957159,
|
| 3000 |
+
"eval_f1": 0.9269136270508408,
|
| 3001 |
+
"eval_loss": 0.14807577431201935,
|
| 3002 |
+
"eval_matthews_correlation": 0.8867722689003014,
|
| 3003 |
+
"eval_precision": 0.9321366838249306,
|
| 3004 |
+
"eval_recall": 0.9221728394253835,
|
| 3005 |
+
"eval_runtime": 1040.229,
|
| 3006 |
+
"eval_samples_per_second": 58.746,
|
| 3007 |
+
"eval_steps_per_second": 1.836,
|
| 3008 |
+
"step": 24000
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 51.28,
|
| 3012 |
+
"learning_rate": 1.4418844566712518e-07,
|
| 3013 |
+
"loss": 0.0996,
|
| 3014 |
+
"step": 24100
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 51.49,
|
| 3018 |
+
"learning_rate": 1.417812929848693e-07,
|
| 3019 |
+
"loss": 0.0974,
|
| 3020 |
+
"step": 24200
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 51.49,
|
| 3024 |
+
"eval_accuracy": 0.9452290170024056,
|
| 3025 |
+
"eval_f1": 0.9270979729816141,
|
| 3026 |
+
"eval_loss": 0.1479618400335312,
|
| 3027 |
+
"eval_matthews_correlation": 0.8869160040122801,
|
| 3028 |
+
"eval_precision": 0.9322256627524821,
|
| 3029 |
+
"eval_recall": 0.9224124168662996,
|
| 3030 |
+
"eval_runtime": 1046.5218,
|
| 3031 |
+
"eval_samples_per_second": 58.392,
|
| 3032 |
+
"eval_steps_per_second": 1.825,
|
| 3033 |
+
"step": 24200
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 51.7,
|
| 3037 |
+
"learning_rate": 1.3937414030261347e-07,
|
| 3038 |
+
"loss": 0.1015,
|
| 3039 |
+
"step": 24300
|
| 3040 |
+
},
|
| 3041 |
+
{
|
| 3042 |
+
"epoch": 51.91,
|
| 3043 |
+
"learning_rate": 1.3696698762035763e-07,
|
| 3044 |
+
"loss": 0.0997,
|
| 3045 |
+
"step": 24400
|
| 3046 |
+
},
|
| 3047 |
+
{
|
| 3048 |
+
"epoch": 51.91,
|
| 3049 |
+
"eval_accuracy": 0.945441751624147,
|
| 3050 |
+
"eval_f1": 0.927200876203088,
|
| 3051 |
+
"eval_loss": 0.14792127907276154,
|
| 3052 |
+
"eval_matthews_correlation": 0.8872321998942353,
|
| 3053 |
+
"eval_precision": 0.9334694817739616,
|
| 3054 |
+
"eval_recall": 0.9215315698638195,
|
| 3055 |
+
"eval_runtime": 1046.7981,
|
| 3056 |
+
"eval_samples_per_second": 58.377,
|
| 3057 |
+
"eval_steps_per_second": 1.825,
|
| 3058 |
+
"step": 24400
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 52.13,
|
| 3062 |
+
"learning_rate": 1.345598349381018e-07,
|
| 3063 |
+
"loss": 0.0969,
|
| 3064 |
+
"step": 24500
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 52.34,
|
| 3068 |
+
"learning_rate": 1.3215268225584592e-07,
|
| 3069 |
+
"loss": 0.0991,
|
| 3070 |
+
"step": 24600
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 52.34,
|
| 3074 |
+
"eval_accuracy": 0.9454090232208022,
|
| 3075 |
+
"eval_f1": 0.9275124073961015,
|
| 3076 |
+
"eval_loss": 0.148192897439003,
|
| 3077 |
+
"eval_matthews_correlation": 0.8874202841376583,
|
| 3078 |
+
"eval_precision": 0.9315495664101637,
|
| 3079 |
+
"eval_recall": 0.9237972745662067,
|
| 3080 |
+
"eval_runtime": 1056.3168,
|
| 3081 |
+
"eval_samples_per_second": 57.851,
|
| 3082 |
+
"eval_steps_per_second": 1.808,
|
| 3083 |
+
"step": 24600
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 52.55,
|
| 3087 |
+
"learning_rate": 1.297455295735901e-07,
|
| 3088 |
+
"loss": 0.0999,
|
| 3089 |
+
"step": 24700
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 52.77,
|
| 3093 |
+
"learning_rate": 1.2733837689133424e-07,
|
| 3094 |
+
"loss": 0.0961,
|
| 3095 |
+
"step": 24800
|
| 3096 |
+
},
|
| 3097 |
+
{
|
| 3098 |
+
"epoch": 52.77,
|
| 3099 |
+
"eval_accuracy": 0.9454090232208022,
|
| 3100 |
+
"eval_f1": 0.9276125960433504,
|
| 3101 |
+
"eval_loss": 0.14825843274593353,
|
| 3102 |
+
"eval_matthews_correlation": 0.8874404098766001,
|
| 3103 |
+
"eval_precision": 0.931482950472307,
|
| 3104 |
+
"eval_recall": 0.9240306380532243,
|
| 3105 |
+
"eval_runtime": 1049.1068,
|
| 3106 |
+
"eval_samples_per_second": 58.249,
|
| 3107 |
+
"eval_steps_per_second": 1.821,
|
| 3108 |
+
"step": 24800
|
| 3109 |
+
},
|
| 3110 |
+
{
|
| 3111 |
+
"epoch": 52.98,
|
| 3112 |
+
"learning_rate": 1.249312242090784e-07,
|
| 3113 |
+
"loss": 0.1015,
|
| 3114 |
+
"step": 24900
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 53.19,
|
| 3118 |
+
"learning_rate": 1.2252407152682256e-07,
|
| 3119 |
+
"loss": 0.1003,
|
| 3120 |
+
"step": 25000
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 53.19,
|
| 3124 |
+
"eval_accuracy": 0.9454908442291643,
|
| 3125 |
+
"eval_f1": 0.9269883425691566,
|
| 3126 |
+
"eval_loss": 0.14782409369945526,
|
| 3127 |
+
"eval_matthews_correlation": 0.8872681574002631,
|
| 3128 |
+
"eval_precision": 0.9339854248197991,
|
| 3129 |
+
"eval_recall": 0.9207518697201013,
|
| 3130 |
+
"eval_runtime": 1048.4394,
|
| 3131 |
+
"eval_samples_per_second": 58.286,
|
| 3132 |
+
"eval_steps_per_second": 1.822,
|
| 3133 |
+
"step": 25000
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 53.4,
|
| 3137 |
+
"learning_rate": 1.2011691884456671e-07,
|
| 3138 |
+
"loss": 0.0969,
|
| 3139 |
+
"step": 25100
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 53.62,
|
| 3143 |
+
"learning_rate": 1.1770976616231087e-07,
|
| 3144 |
+
"loss": 0.0988,
|
| 3145 |
+
"step": 25200
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 53.62,
|
| 3149 |
+
"eval_accuracy": 0.9456053936408713,
|
| 3150 |
+
"eval_f1": 0.9274062041867052,
|
| 3151 |
+
"eval_loss": 0.1478436291217804,
|
| 3152 |
+
"eval_matthews_correlation": 0.8876168167324782,
|
| 3153 |
+
"eval_precision": 0.9332789328012385,
|
| 3154 |
+
"eval_recall": 0.9221045841897744,
|
| 3155 |
+
"eval_runtime": 1048.83,
|
| 3156 |
+
"eval_samples_per_second": 58.264,
|
| 3157 |
+
"eval_steps_per_second": 1.821,
|
| 3158 |
+
"step": 25200
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 53.83,
|
| 3162 |
+
"learning_rate": 1.1530261348005502e-07,
|
| 3163 |
+
"loss": 0.098,
|
| 3164 |
+
"step": 25300
|
| 3165 |
+
},
|
| 3166 |
+
{
|
| 3167 |
+
"epoch": 54.04,
|
| 3168 |
+
"learning_rate": 1.1289546079779916e-07,
|
| 3169 |
+
"loss": 0.0986,
|
| 3170 |
+
"step": 25400
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 54.04,
|
| 3174 |
+
"eval_accuracy": 0.9456708504475609,
|
| 3175 |
+
"eval_f1": 0.9274017208924298,
|
| 3176 |
+
"eval_loss": 0.1477716565132141,
|
| 3177 |
+
"eval_matthews_correlation": 0.8877505832830167,
|
| 3178 |
+
"eval_precision": 0.9333189939052119,
|
| 3179 |
+
"eval_recall": 0.9220848688673379,
|
| 3180 |
+
"eval_runtime": 1045.0852,
|
| 3181 |
+
"eval_samples_per_second": 58.473,
|
| 3182 |
+
"eval_steps_per_second": 1.828,
|
| 3183 |
+
"step": 25400
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 54.26,
|
| 3187 |
+
"learning_rate": 1.1048830811554334e-07,
|
| 3188 |
+
"loss": 0.0963,
|
| 3189 |
+
"step": 25500
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 54.47,
|
| 3193 |
+
"learning_rate": 1.0808115543328748e-07,
|
| 3194 |
+
"loss": 0.1003,
|
| 3195 |
+
"step": 25600
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 54.47,
|
| 3199 |
+
"eval_accuracy": 0.945441751624147,
|
| 3200 |
+
"eval_f1": 0.9272576298526598,
|
| 3201 |
+
"eval_loss": 0.1478091925382614,
|
| 3202 |
+
"eval_matthews_correlation": 0.8873054994658675,
|
| 3203 |
+
"eval_precision": 0.9328576996809682,
|
| 3204 |
+
"eval_recall": 0.9221798017722014,
|
| 3205 |
+
"eval_runtime": 1047.8846,
|
| 3206 |
+
"eval_samples_per_second": 58.317,
|
| 3207 |
+
"eval_steps_per_second": 1.823,
|
| 3208 |
+
"step": 25600
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 54.68,
|
| 3212 |
+
"learning_rate": 1.0567400275103163e-07,
|
| 3213 |
+
"loss": 0.0967,
|
| 3214 |
+
"step": 25700
|
| 3215 |
+
},
|
| 3216 |
+
{
|
| 3217 |
+
"epoch": 54.89,
|
| 3218 |
+
"learning_rate": 1.0326685006877579e-07,
|
| 3219 |
+
"loss": 0.0974,
|
| 3220 |
+
"step": 25800
|
| 3221 |
+
},
|
| 3222 |
+
{
|
| 3223 |
+
"epoch": 54.89,
|
| 3224 |
+
"eval_accuracy": 0.9454090232208022,
|
| 3225 |
+
"eval_f1": 0.9272324111514144,
|
| 3226 |
+
"eval_loss": 0.14785851538181305,
|
| 3227 |
+
"eval_matthews_correlation": 0.8872587311118877,
|
| 3228 |
+
"eval_precision": 0.9326477457141271,
|
| 3229 |
+
"eval_recall": 0.9223193058150961,
|
| 3230 |
+
"eval_runtime": 1042.5297,
|
| 3231 |
+
"eval_samples_per_second": 58.616,
|
| 3232 |
+
"eval_steps_per_second": 1.832,
|
| 3233 |
+
"step": 25800
|
| 3234 |
+
},
|
| 3235 |
+
{
|
| 3236 |
+
"epoch": 55.11,
|
| 3237 |
+
"learning_rate": 1.0085969738651993e-07,
|
| 3238 |
+
"loss": 0.0978,
|
| 3239 |
+
"step": 25900
|
| 3240 |
+
},
|
| 3241 |
+
{
|
| 3242 |
+
"epoch": 55.32,
|
| 3243 |
+
"learning_rate": 9.84525447042641e-08,
|
| 3244 |
+
"loss": 0.0985,
|
| 3245 |
+
"step": 26000
|
| 3246 |
+
},
|
| 3247 |
+
{
|
| 3248 |
+
"epoch": 55.32,
|
| 3249 |
+
"eval_accuracy": 0.9455890294391988,
|
| 3250 |
+
"eval_f1": 0.92763614192194,
|
| 3251 |
+
"eval_loss": 0.14787529408931732,
|
| 3252 |
+
"eval_matthews_correlation": 0.8877198200242857,
|
| 3253 |
+
"eval_precision": 0.9322731450973873,
|
| 3254 |
+
"eval_recall": 0.9233930121989798,
|
| 3255 |
+
"eval_runtime": 1052.7253,
|
| 3256 |
+
"eval_samples_per_second": 58.048,
|
| 3257 |
+
"eval_steps_per_second": 1.814,
|
| 3258 |
+
"step": 26000
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 55.53,
|
| 3262 |
+
"learning_rate": 9.604539202200825e-08,
|
| 3263 |
+
"loss": 0.0974,
|
| 3264 |
+
"step": 26100
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 55.74,
|
| 3268 |
+
"learning_rate": 9.36382393397524e-08,
|
| 3269 |
+
"loss": 0.0968,
|
| 3270 |
+
"step": 26200
|
| 3271 |
+
},
|
| 3272 |
+
{
|
| 3273 |
+
"epoch": 55.74,
|
| 3274 |
+
"eval_accuracy": 0.9453599306157849,
|
| 3275 |
+
"eval_f1": 0.9277711434618366,
|
| 3276 |
+
"eval_loss": 0.1481289565563202,
|
| 3277 |
+
"eval_matthews_correlation": 0.8874539900521103,
|
| 3278 |
+
"eval_precision": 0.930771508987792,
|
| 3279 |
+
"eval_recall": 0.9249659138549541,
|
| 3280 |
+
"eval_runtime": 1046.0675,
|
| 3281 |
+
"eval_samples_per_second": 58.418,
|
| 3282 |
+
"eval_steps_per_second": 1.826,
|
| 3283 |
+
"step": 26200
|
| 3284 |
+
},
|
| 3285 |
+
{
|
| 3286 |
+
"epoch": 55.96,
|
| 3287 |
+
"learning_rate": 9.123108665749657e-08,
|
| 3288 |
+
"loss": 0.0965,
|
| 3289 |
+
"step": 26300
|
| 3290 |
+
},
|
| 3291 |
+
{
|
| 3292 |
+
"epoch": 56.17,
|
| 3293 |
+
"learning_rate": 8.882393397524071e-08,
|
| 3294 |
+
"loss": 0.0994,
|
| 3295 |
+
"step": 26400
|
| 3296 |
+
},
|
| 3297 |
+
{
|
| 3298 |
+
"epoch": 56.17,
|
| 3299 |
+
"eval_accuracy": 0.9454581158258194,
|
| 3300 |
+
"eval_f1": 0.9273153737422503,
|
| 3301 |
+
"eval_loss": 0.14774879813194275,
|
| 3302 |
+
"eval_matthews_correlation": 0.8873663018017705,
|
| 3303 |
+
"eval_precision": 0.9326728846418783,
|
| 3304 |
+
"eval_recall": 0.9224471303431127,
|
| 3305 |
+
"eval_runtime": 1044.2012,
|
| 3306 |
+
"eval_samples_per_second": 58.522,
|
| 3307 |
+
"eval_steps_per_second": 1.829,
|
| 3308 |
+
"step": 26400
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 56.38,
|
| 3312 |
+
"learning_rate": 8.641678129298487e-08,
|
| 3313 |
+
"loss": 0.0986,
|
| 3314 |
+
"step": 26500
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 56.6,
|
| 3318 |
+
"learning_rate": 8.400962861072902e-08,
|
| 3319 |
+
"loss": 0.0967,
|
| 3320 |
+
"step": 26600
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 56.6,
|
| 3324 |
+
"eval_accuracy": 0.9452617454057504,
|
| 3325 |
+
"eval_f1": 0.9275893994739569,
|
| 3326 |
+
"eval_loss": 0.14803829789161682,
|
| 3327 |
+
"eval_matthews_correlation": 0.8872133913846761,
|
| 3328 |
+
"eval_precision": 0.9308688570782452,
|
| 3329 |
+
"eval_recall": 0.9245287598645741,
|
| 3330 |
+
"eval_runtime": 1045.1221,
|
| 3331 |
+
"eval_samples_per_second": 58.471,
|
| 3332 |
+
"eval_steps_per_second": 1.828,
|
| 3333 |
+
"step": 26600
|
| 3334 |
+
},
|
| 3335 |
+
{
|
| 3336 |
+
"epoch": 56.81,
|
| 3337 |
+
"learning_rate": 8.160247592847317e-08,
|
| 3338 |
+
"loss": 0.0928,
|
| 3339 |
+
"step": 26700
|
| 3340 |
+
},
|
| 3341 |
+
{
|
| 3342 |
+
"epoch": 57.02,
|
| 3343 |
+
"learning_rate": 7.919532324621733e-08,
|
| 3344 |
+
"loss": 0.0981,
|
| 3345 |
+
"step": 26800
|
| 3346 |
+
},
|
| 3347 |
+
{
|
| 3348 |
+
"epoch": 57.02,
|
| 3349 |
+
"eval_accuracy": 0.9457035788509057,
|
| 3350 |
+
"eval_f1": 0.927635695095954,
|
| 3351 |
+
"eval_loss": 0.14773297309875488,
|
| 3352 |
+
"eval_matthews_correlation": 0.8878658482696629,
|
| 3353 |
+
"eval_precision": 0.9330727346915296,
|
| 3354 |
+
"eval_recall": 0.9226973138381661,
|
| 3355 |
+
"eval_runtime": 1044.5351,
|
| 3356 |
+
"eval_samples_per_second": 58.504,
|
| 3357 |
+
"eval_steps_per_second": 1.829,
|
| 3358 |
+
"step": 26800
|
| 3359 |
+
},
|
| 3360 |
+
{
|
| 3361 |
+
"epoch": 57.23,
|
| 3362 |
+
"learning_rate": 7.678817056396149e-08,
|
| 3363 |
+
"loss": 0.0974,
|
| 3364 |
+
"step": 26900
|
| 3365 |
+
},
|
| 3366 |
+
{
|
| 3367 |
+
"epoch": 57.45,
|
| 3368 |
+
"learning_rate": 7.438101788170564e-08,
|
| 3369 |
+
"loss": 0.0971,
|
| 3370 |
+
"step": 27000
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 57.45,
|
| 3374 |
+
"eval_accuracy": 0.9454581158258194,
|
| 3375 |
+
"eval_f1": 0.9276437107725939,
|
| 3376 |
+
"eval_loss": 0.14780069887638092,
|
| 3377 |
+
"eval_matthews_correlation": 0.8875004428021673,
|
| 3378 |
+
"eval_precision": 0.931844513397709,
|
| 3379 |
+
"eval_recall": 0.9237695234362117,
|
| 3380 |
+
"eval_runtime": 1046.8891,
|
| 3381 |
+
"eval_samples_per_second": 58.372,
|
| 3382 |
+
"eval_steps_per_second": 1.824,
|
| 3383 |
+
"step": 27000
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 57.66,
|
| 3387 |
+
"learning_rate": 7.197386519944978e-08,
|
| 3388 |
+
"loss": 0.0964,
|
| 3389 |
+
"step": 27100
|
| 3390 |
+
},
|
| 3391 |
+
{
|
| 3392 |
+
"epoch": 57.87,
|
| 3393 |
+
"learning_rate": 6.956671251719394e-08,
|
| 3394 |
+
"loss": 0.096,
|
| 3395 |
+
"step": 27200
|
| 3396 |
+
},
|
| 3397 |
+
{
|
| 3398 |
+
"epoch": 57.87,
|
| 3399 |
+
"eval_accuracy": 0.9454908442291643,
|
| 3400 |
+
"eval_f1": 0.9274937428896638,
|
| 3401 |
+
"eval_loss": 0.1477871984243393,
|
| 3402 |
+
"eval_matthews_correlation": 0.8875013471949721,
|
| 3403 |
+
"eval_precision": 0.9322600481554396,
|
| 3404 |
+
"eval_recall": 0.9231373631429468,
|
| 3405 |
+
"eval_runtime": 1045.0428,
|
| 3406 |
+
"eval_samples_per_second": 58.475,
|
| 3407 |
+
"eval_steps_per_second": 1.828,
|
| 3408 |
+
"step": 27200
|
| 3409 |
+
},
|
| 3410 |
+
{
|
| 3411 |
+
"epoch": 58.09,
|
| 3412 |
+
"learning_rate": 6.71595598349381e-08,
|
| 3413 |
+
"loss": 0.0983,
|
| 3414 |
+
"step": 27300
|
| 3415 |
+
},
|
| 3416 |
+
{
|
| 3417 |
+
"epoch": 58.3,
|
| 3418 |
+
"learning_rate": 6.475240715268225e-08,
|
| 3419 |
+
"loss": 0.0971,
|
| 3420 |
+
"step": 27400
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 58.3,
|
| 3424 |
+
"eval_accuracy": 0.9455235726325091,
|
| 3425 |
+
"eval_f1": 0.927552029801575,
|
| 3426 |
+
"eval_loss": 0.14768995344638824,
|
| 3427 |
+
"eval_matthews_correlation": 0.8875535000143042,
|
| 3428 |
+
"eval_precision": 0.9324442829035213,
|
| 3429 |
+
"eval_recall": 0.9230756469290579,
|
| 3430 |
+
"eval_runtime": 1046.0553,
|
| 3431 |
+
"eval_samples_per_second": 58.419,
|
| 3432 |
+
"eval_steps_per_second": 1.826,
|
| 3433 |
+
"step": 27400
|
| 3434 |
+
},
|
| 3435 |
+
{
|
| 3436 |
+
"epoch": 58.51,
|
| 3437 |
+
"learning_rate": 6.23452544704264e-08,
|
| 3438 |
+
"loss": 0.0952,
|
| 3439 |
+
"step": 27500
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 58.72,
|
| 3443 |
+
"learning_rate": 5.993810178817056e-08,
|
| 3444 |
+
"loss": 0.0961,
|
| 3445 |
+
"step": 27600
|
| 3446 |
+
},
|
| 3447 |
+
{
|
| 3448 |
+
"epoch": 58.72,
|
| 3449 |
+
"eval_accuracy": 0.945638122044216,
|
| 3450 |
+
"eval_f1": 0.9279565448439383,
|
| 3451 |
+
"eval_loss": 0.14801862835884094,
|
| 3452 |
+
"eval_matthews_correlation": 0.8879656940505886,
|
| 3453 |
+
"eval_precision": 0.9314274864696435,
|
| 3454 |
+
"eval_recall": 0.9247395127147543,
|
| 3455 |
+
"eval_runtime": 1043.4327,
|
| 3456 |
+
"eval_samples_per_second": 58.565,
|
| 3457 |
+
"eval_steps_per_second": 1.83,
|
| 3458 |
+
"step": 27600
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"epoch": 58.94,
|
| 3462 |
+
"learning_rate": 5.753094910591472e-08,
|
| 3463 |
+
"loss": 0.0959,
|
| 3464 |
+
"step": 27700
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 59.15,
|
| 3468 |
+
"learning_rate": 5.512379642365887e-08,
|
| 3469 |
+
"loss": 0.0966,
|
| 3470 |
+
"step": 27800
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 59.15,
|
| 3474 |
+
"eval_accuracy": 0.945638122044216,
|
| 3475 |
+
"eval_f1": 0.9278932427247907,
|
| 3476 |
+
"eval_loss": 0.14785251021385193,
|
| 3477 |
+
"eval_matthews_correlation": 0.8879297115031657,
|
| 3478 |
+
"eval_precision": 0.9316436960957745,
|
| 3479 |
+
"eval_recall": 0.9244283613987311,
|
| 3480 |
+
"eval_runtime": 1042.6,
|
| 3481 |
+
"eval_samples_per_second": 58.612,
|
| 3482 |
+
"eval_steps_per_second": 1.832,
|
| 3483 |
+
"step": 27800
|
| 3484 |
+
},
|
| 3485 |
+
{
|
| 3486 |
+
"epoch": 59.36,
|
| 3487 |
+
"learning_rate": 5.2716643741403025e-08,
|
| 3488 |
+
"loss": 0.0964,
|
| 3489 |
+
"step": 27900
|
| 3490 |
+
},
|
| 3491 |
+
{
|
| 3492 |
+
"epoch": 59.57,
|
| 3493 |
+
"learning_rate": 5.030949105914718e-08,
|
| 3494 |
+
"loss": 0.0951,
|
| 3495 |
+
"step": 28000
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 59.57,
|
| 3499 |
+
"eval_accuracy": 0.9457035788509057,
|
| 3500 |
+
"eval_f1": 0.9276842027293449,
|
| 3501 |
+
"eval_loss": 0.14763057231903076,
|
| 3502 |
+
"eval_matthews_correlation": 0.8879028981021795,
|
| 3503 |
+
"eval_precision": 0.932791895372278,
|
| 3504 |
+
"eval_recall": 0.9230343944305247,
|
| 3505 |
+
"eval_runtime": 1042.025,
|
| 3506 |
+
"eval_samples_per_second": 58.644,
|
| 3507 |
+
"eval_steps_per_second": 1.833,
|
| 3508 |
+
"step": 28000
|
| 3509 |
+
}
|
| 3510 |
+
],
|
| 3511 |
+
"max_steps": 30080,
|
| 3512 |
+
"num_train_epochs": 64,
|
| 3513 |
+
"total_flos": 3.277848535588889e+21,
|
| 3514 |
+
"trial_name": null,
|
| 3515 |
+
"trial_params": null
|
| 3516 |
+
}
|
checkpoint-28000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57baa79002412724df84c2245162da376aadf840a069713b1da995d4d81fba74
|
| 3 |
+
size 3311
|
checkpoint-30000/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-384",
|
| 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": "Front",
|
| 13 |
+
"1": "Middle",
|
| 14 |
+
"2": "Back"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 384,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Back": "2",
|
| 21 |
+
"Front": "0",
|
| 22 |
+
"Middle": "1"
|
| 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": "4.20.0"
|
| 34 |
+
}
|
checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f1e69aa37cc1e49234f6e96d5c4e46d8d3b20a2eb5c45cc47abb6f2337c63d7
|
| 3 |
+
size 688858465
|
checkpoint-30000/preprocessor_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_std": [
|
| 11 |
+
0.5,
|
| 12 |
+
0.5,
|
| 13 |
+
0.5
|
| 14 |
+
],
|
| 15 |
+
"resample": 2,
|
| 16 |
+
"size": 384
|
| 17 |
+
}
|
checkpoint-30000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adfad27bae3bf040a7aad83c624d32b8f31090364d2999e14a37e4f58d2592a5
|
| 3 |
+
size 344437425
|
checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d014eefe837880243c764eb322650e1c8847dd50f3b2085c84680feb5cfd0e2a
|
| 3 |
+
size 14503
|
checkpoint-30000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c63aaeae1fc9a56c321f3b1530994d52feddba4e1d9af2e871f56cd917ad345
|
| 3 |
+
size 559
|
checkpoint-30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d5e64a3317dae6ac6b918e32a6ed7ffe8a2f8ea5a0e32ed3a021e91fb9c2251
|
| 3 |
+
size 623
|
checkpoint-30000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57baa79002412724df84c2245162da376aadf840a069713b1da995d4d81fba74
|
| 3 |
+
size 3311
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-384",
|
| 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": "Front",
|
| 13 |
+
"1": "Middle",
|
| 14 |
+
"2": "Back"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 384,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Back": "2",
|
| 21 |
+
"Front": "0",
|
| 22 |
+
"Middle": "1"
|
| 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": "4.20.0"
|
| 34 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 64.0,
|
| 3 |
+
"eval_accuracy": 0.9457035788509057,
|
| 4 |
+
"eval_f1": 0.9276842027293449,
|
| 5 |
+
"eval_loss": 0.14763057231903076,
|
| 6 |
+
"eval_matthews_correlation": 0.8879028981021795,
|
| 7 |
+
"eval_precision": 0.932791895372278,
|
| 8 |
+
"eval_recall": 0.9230343944305247,
|
| 9 |
+
"eval_runtime": 1043.6137,
|
| 10 |
+
"eval_samples_per_second": 58.555,
|
| 11 |
+
"eval_steps_per_second": 1.83
|
| 12 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_std": [
|
| 11 |
+
0.5,
|
| 12 |
+
0.5,
|
| 13 |
+
0.5
|
| 14 |
+
],
|
| 15 |
+
"resample": 2,
|
| 16 |
+
"size": 384
|
| 17 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7aeae6401eee261a920c4636609b82fc52762b4b566ab785089a4bb27c1d0cb
|
| 3 |
+
size 344437425
|
runs/Jun29_00-57-15_ficino/1656457039.4100714/events.out.tfevents.1656457039.ficino.3045589.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d310e8ad33d183473343c5c2b89944b35045b3370fef4e53d73c8f30d9634e93
|
| 3 |
+
size 5372
|
runs/Jun29_00-57-15_ficino/events.out.tfevents.1656457039.ficino.3045589.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa3577efc50404a59b241804b1bff7130a02113cc8385937ba8ad370aac6aa78
|
| 3 |
+
size 132647
|
runs/Jun29_00-57-15_ficino/events.out.tfevents.1657055182.ficino.3045589.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41d7f6643ab946ac2aedf7a50e2d774f1ad7f3898489ad9bcd444d356b21831c
|
| 3 |
+
size 586
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 64.0,
|
| 3 |
+
"train_loss": 0.1566047928276214,
|
| 4 |
+
"train_runtime": 597098.8722,
|
| 5 |
+
"train_samples_per_second": 25.809,
|
| 6 |
+
"train_steps_per_second": 0.05
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57baa79002412724df84c2245162da376aadf840a069713b1da995d4d81fba74
|
| 3 |
+
size 3311
|