Commit
•
938ce8c
1
Parent(s):
1ba08b3
DazMashaly/iee_class
Browse files- README.md +83 -0
- all_results.json +8 -0
- config.json +58 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- train_results.json +8 -0
- trainer_state.json +1663 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: vit-base-beans-demo-v5
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# vit-base-beans-demo-v5
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the bact dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0498
|
| 22 |
+
- Accuracy: 0.9882
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0002
|
| 42 |
+
- train_batch_size: 16
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 4
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 53 |
+
| 0.1764 | 0.17 | 100 | 0.2424 | 0.9345 |
|
| 54 |
+
| 0.2401 | 0.34 | 200 | 0.2909 | 0.9160 |
|
| 55 |
+
| 0.1986 | 0.5 | 300 | 0.2258 | 0.9358 |
|
| 56 |
+
| 0.1579 | 0.67 | 400 | 0.2699 | 0.9240 |
|
| 57 |
+
| 0.21 | 0.84 | 500 | 0.1416 | 0.9635 |
|
| 58 |
+
| 0.0873 | 1.01 | 600 | 0.1724 | 0.9467 |
|
| 59 |
+
| 0.1594 | 1.17 | 700 | 0.2439 | 0.9320 |
|
| 60 |
+
| 0.0824 | 1.34 | 800 | 0.1039 | 0.9702 |
|
| 61 |
+
| 0.0888 | 1.51 | 900 | 0.1496 | 0.9547 |
|
| 62 |
+
| 0.1058 | 1.68 | 1000 | 0.1100 | 0.9748 |
|
| 63 |
+
| 0.077 | 1.85 | 1100 | 0.0784 | 0.9757 |
|
| 64 |
+
| 0.0486 | 2.01 | 1200 | 0.0997 | 0.9710 |
|
| 65 |
+
| 0.0087 | 2.18 | 1300 | 0.0704 | 0.9811 |
|
| 66 |
+
| 0.0382 | 2.35 | 1400 | 0.0910 | 0.9761 |
|
| 67 |
+
| 0.046 | 2.52 | 1500 | 0.0588 | 0.9840 |
|
| 68 |
+
| 0.0163 | 2.68 | 1600 | 0.0609 | 0.9836 |
|
| 69 |
+
| 0.0876 | 2.85 | 1700 | 0.0689 | 0.9811 |
|
| 70 |
+
| 0.0072 | 3.02 | 1800 | 0.0632 | 0.9861 |
|
| 71 |
+
| 0.0022 | 3.19 | 1900 | 0.0670 | 0.9845 |
|
| 72 |
+
| 0.0018 | 3.36 | 2000 | 0.0705 | 0.9845 |
|
| 73 |
+
| 0.0023 | 3.52 | 2100 | 0.0588 | 0.9861 |
|
| 74 |
+
| 0.0017 | 3.69 | 2200 | 0.0490 | 0.9882 |
|
| 75 |
+
| 0.0248 | 3.86 | 2300 | 0.0498 | 0.9882 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.33.1
|
| 81 |
+
- Pytorch 2.0.1+cu118
|
| 82 |
+
- Datasets 2.14.5
|
| 83 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 2.953718820314874e+18,
|
| 4 |
+
"train_loss": 0.09724263496534437,
|
| 5 |
+
"train_runtime": 2056.7864,
|
| 6 |
+
"train_samples_per_second": 18.53,
|
| 7 |
+
"train_steps_per_second": 1.159
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Ascariasis",
|
| 13 |
+
"1": "Babesia",
|
| 14 |
+
"10": "Opisthorchis viverrine",
|
| 15 |
+
"11": "Paragonimus spp",
|
| 16 |
+
"12": "T. rubrum",
|
| 17 |
+
"13": "Taenia spp",
|
| 18 |
+
"14": "Trichuris trichiura",
|
| 19 |
+
"2": "Capillaria p",
|
| 20 |
+
"3": "Enterobius v",
|
| 21 |
+
"4": "Epidermophyton floccosum",
|
| 22 |
+
"5": "Fasciolopsis buski",
|
| 23 |
+
"6": "Hookworm egg",
|
| 24 |
+
"7": "Hymenolepis diminuta",
|
| 25 |
+
"8": "Hymenolepis nana",
|
| 26 |
+
"9": "Leishmania"
|
| 27 |
+
},
|
| 28 |
+
"image_size": 224,
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"Ascariasis": "0",
|
| 33 |
+
"Babesia": "1",
|
| 34 |
+
"Capillaria p": "2",
|
| 35 |
+
"Enterobius v": "3",
|
| 36 |
+
"Epidermophyton floccosum": "4",
|
| 37 |
+
"Fasciolopsis buski": "5",
|
| 38 |
+
"Hookworm egg": "6",
|
| 39 |
+
"Hymenolepis diminuta": "7",
|
| 40 |
+
"Hymenolepis nana": "8",
|
| 41 |
+
"Leishmania": "9",
|
| 42 |
+
"Opisthorchis viverrine": "10",
|
| 43 |
+
"Paragonimus spp": "11",
|
| 44 |
+
"T. rubrum": "12",
|
| 45 |
+
"Taenia spp": "13",
|
| 46 |
+
"Trichuris trichiura": "14"
|
| 47 |
+
},
|
| 48 |
+
"layer_norm_eps": 1e-12,
|
| 49 |
+
"model_type": "vit",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_channels": 3,
|
| 52 |
+
"num_hidden_layers": 12,
|
| 53 |
+
"patch_size": 16,
|
| 54 |
+
"problem_type": "single_label_classification",
|
| 55 |
+
"qkv_bias": true,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.33.1"
|
| 58 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ecfa0a9ee9553d4aa9cb4b643e8bcceff74c292293ab4054a7351d4547328a7
|
| 3 |
+
size 343308717
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 2.953718820314874e+18,
|
| 4 |
+
"train_loss": 0.09724263496534437,
|
| 5 |
+
"train_runtime": 2056.7864,
|
| 6 |
+
"train_samples_per_second": 18.53,
|
| 7 |
+
"train_steps_per_second": 1.159
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1663 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.04898680001497269,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-2200",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2384,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 0.00019916107382550338,
|
| 14 |
+
"loss": 0.5752,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 0.00019832214765100673,
|
| 20 |
+
"loss": 0.3639,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.05,
|
| 25 |
+
"learning_rate": 0.00019748322147651007,
|
| 26 |
+
"loss": 0.414,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.07,
|
| 31 |
+
"learning_rate": 0.00019664429530201342,
|
| 32 |
+
"loss": 0.4994,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.08,
|
| 37 |
+
"learning_rate": 0.0001958053691275168,
|
| 38 |
+
"loss": 0.3953,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.1,
|
| 43 |
+
"learning_rate": 0.00019496644295302013,
|
| 44 |
+
"loss": 0.1514,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12,
|
| 49 |
+
"learning_rate": 0.0001941275167785235,
|
| 50 |
+
"loss": 0.4222,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13,
|
| 55 |
+
"learning_rate": 0.00019328859060402688,
|
| 56 |
+
"loss": 0.4522,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.15,
|
| 61 |
+
"learning_rate": 0.00019244966442953022,
|
| 62 |
+
"loss": 0.39,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.17,
|
| 67 |
+
"learning_rate": 0.00019161073825503357,
|
| 68 |
+
"loss": 0.1764,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.17,
|
| 73 |
+
"eval_accuracy": 0.9345088161209067,
|
| 74 |
+
"eval_loss": 0.24242226779460907,
|
| 75 |
+
"eval_runtime": 37.0601,
|
| 76 |
+
"eval_samples_per_second": 64.274,
|
| 77 |
+
"eval_steps_per_second": 8.041,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.18,
|
| 82 |
+
"learning_rate": 0.0001907718120805369,
|
| 83 |
+
"loss": 0.199,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.2,
|
| 88 |
+
"learning_rate": 0.00018993288590604028,
|
| 89 |
+
"loss": 0.2534,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.22,
|
| 94 |
+
"learning_rate": 0.00018909395973154363,
|
| 95 |
+
"loss": 0.2201,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.23,
|
| 100 |
+
"learning_rate": 0.000188255033557047,
|
| 101 |
+
"loss": 0.1656,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.25,
|
| 106 |
+
"learning_rate": 0.00018741610738255034,
|
| 107 |
+
"loss": 0.3582,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27,
|
| 112 |
+
"learning_rate": 0.0001865771812080537,
|
| 113 |
+
"loss": 0.3158,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.29,
|
| 118 |
+
"learning_rate": 0.00018573825503355706,
|
| 119 |
+
"loss": 0.2936,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.3,
|
| 124 |
+
"learning_rate": 0.0001848993288590604,
|
| 125 |
+
"loss": 0.3009,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.32,
|
| 130 |
+
"learning_rate": 0.00018406040268456378,
|
| 131 |
+
"loss": 0.3815,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.34,
|
| 136 |
+
"learning_rate": 0.00018322147651006712,
|
| 137 |
+
"loss": 0.2401,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.34,
|
| 142 |
+
"eval_accuracy": 0.9160369437447523,
|
| 143 |
+
"eval_loss": 0.29085931181907654,
|
| 144 |
+
"eval_runtime": 37.2208,
|
| 145 |
+
"eval_samples_per_second": 63.996,
|
| 146 |
+
"eval_steps_per_second": 8.006,
|
| 147 |
+
"step": 200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.35,
|
| 151 |
+
"learning_rate": 0.00018238255033557047,
|
| 152 |
+
"loss": 0.3746,
|
| 153 |
+
"step": 210
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.37,
|
| 157 |
+
"learning_rate": 0.00018154362416107384,
|
| 158 |
+
"loss": 0.3423,
|
| 159 |
+
"step": 220
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.39,
|
| 163 |
+
"learning_rate": 0.00018070469798657718,
|
| 164 |
+
"loss": 0.1224,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.4,
|
| 169 |
+
"learning_rate": 0.00017986577181208056,
|
| 170 |
+
"loss": 0.2699,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.42,
|
| 175 |
+
"learning_rate": 0.0001790268456375839,
|
| 176 |
+
"loss": 0.2199,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.44,
|
| 181 |
+
"learning_rate": 0.00017818791946308727,
|
| 182 |
+
"loss": 0.4065,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.45,
|
| 187 |
+
"learning_rate": 0.00017734899328859062,
|
| 188 |
+
"loss": 0.4393,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.47,
|
| 193 |
+
"learning_rate": 0.00017651006711409396,
|
| 194 |
+
"loss": 0.3829,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.49,
|
| 199 |
+
"learning_rate": 0.00017567114093959733,
|
| 200 |
+
"loss": 0.2467,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.5,
|
| 205 |
+
"learning_rate": 0.00017483221476510068,
|
| 206 |
+
"loss": 0.1986,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5,
|
| 211 |
+
"eval_accuracy": 0.9357682619647355,
|
| 212 |
+
"eval_loss": 0.22584371268749237,
|
| 213 |
+
"eval_runtime": 37.6779,
|
| 214 |
+
"eval_samples_per_second": 63.22,
|
| 215 |
+
"eval_steps_per_second": 7.909,
|
| 216 |
+
"step": 300
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.52,
|
| 220 |
+
"learning_rate": 0.00017399328859060405,
|
| 221 |
+
"loss": 0.3105,
|
| 222 |
+
"step": 310
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.54,
|
| 226 |
+
"learning_rate": 0.0001731543624161074,
|
| 227 |
+
"loss": 0.1708,
|
| 228 |
+
"step": 320
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.55,
|
| 232 |
+
"learning_rate": 0.00017231543624161074,
|
| 233 |
+
"loss": 0.2205,
|
| 234 |
+
"step": 330
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.57,
|
| 238 |
+
"learning_rate": 0.00017147651006711408,
|
| 239 |
+
"loss": 0.1301,
|
| 240 |
+
"step": 340
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.59,
|
| 244 |
+
"learning_rate": 0.00017063758389261746,
|
| 245 |
+
"loss": 0.2069,
|
| 246 |
+
"step": 350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.6,
|
| 250 |
+
"learning_rate": 0.00016979865771812083,
|
| 251 |
+
"loss": 0.098,
|
| 252 |
+
"step": 360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.62,
|
| 256 |
+
"learning_rate": 0.00016895973154362417,
|
| 257 |
+
"loss": 0.2552,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.64,
|
| 262 |
+
"learning_rate": 0.00016812080536912754,
|
| 263 |
+
"loss": 0.2953,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.65,
|
| 268 |
+
"learning_rate": 0.00016728187919463086,
|
| 269 |
+
"loss": 0.2195,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.67,
|
| 274 |
+
"learning_rate": 0.00016644295302013423,
|
| 275 |
+
"loss": 0.1579,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.67,
|
| 280 |
+
"eval_accuracy": 0.9240134340890008,
|
| 281 |
+
"eval_loss": 0.2699319124221802,
|
| 282 |
+
"eval_runtime": 37.7055,
|
| 283 |
+
"eval_samples_per_second": 63.174,
|
| 284 |
+
"eval_steps_per_second": 7.903,
|
| 285 |
+
"step": 400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.69,
|
| 289 |
+
"learning_rate": 0.00016560402684563758,
|
| 290 |
+
"loss": 0.3875,
|
| 291 |
+
"step": 410
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.7,
|
| 295 |
+
"learning_rate": 0.00016476510067114095,
|
| 296 |
+
"loss": 0.254,
|
| 297 |
+
"step": 420
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.72,
|
| 301 |
+
"learning_rate": 0.00016401006711409396,
|
| 302 |
+
"loss": 0.2794,
|
| 303 |
+
"step": 430
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.74,
|
| 307 |
+
"learning_rate": 0.00016317114093959733,
|
| 308 |
+
"loss": 0.1986,
|
| 309 |
+
"step": 440
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.76,
|
| 313 |
+
"learning_rate": 0.00016233221476510067,
|
| 314 |
+
"loss": 0.1392,
|
| 315 |
+
"step": 450
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.77,
|
| 319 |
+
"learning_rate": 0.00016149328859060404,
|
| 320 |
+
"loss": 0.1405,
|
| 321 |
+
"step": 460
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.79,
|
| 325 |
+
"learning_rate": 0.0001606543624161074,
|
| 326 |
+
"loss": 0.0757,
|
| 327 |
+
"step": 470
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.81,
|
| 331 |
+
"learning_rate": 0.00015981543624161076,
|
| 332 |
+
"loss": 0.1505,
|
| 333 |
+
"step": 480
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.82,
|
| 337 |
+
"learning_rate": 0.0001589765100671141,
|
| 338 |
+
"loss": 0.3554,
|
| 339 |
+
"step": 490
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.84,
|
| 343 |
+
"learning_rate": 0.00015813758389261745,
|
| 344 |
+
"loss": 0.21,
|
| 345 |
+
"step": 500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.84,
|
| 349 |
+
"eval_accuracy": 0.9634760705289672,
|
| 350 |
+
"eval_loss": 0.1416286677122116,
|
| 351 |
+
"eval_runtime": 37.8399,
|
| 352 |
+
"eval_samples_per_second": 62.949,
|
| 353 |
+
"eval_steps_per_second": 7.875,
|
| 354 |
+
"step": 500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.86,
|
| 358 |
+
"learning_rate": 0.00015729865771812082,
|
| 359 |
+
"loss": 0.24,
|
| 360 |
+
"step": 510
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.87,
|
| 364 |
+
"learning_rate": 0.00015645973154362417,
|
| 365 |
+
"loss": 0.161,
|
| 366 |
+
"step": 520
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.89,
|
| 370 |
+
"learning_rate": 0.00015562080536912754,
|
| 371 |
+
"loss": 0.1271,
|
| 372 |
+
"step": 530
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.91,
|
| 376 |
+
"learning_rate": 0.00015478187919463088,
|
| 377 |
+
"loss": 0.2553,
|
| 378 |
+
"step": 540
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.92,
|
| 382 |
+
"learning_rate": 0.00015394295302013423,
|
| 383 |
+
"loss": 0.223,
|
| 384 |
+
"step": 550
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.94,
|
| 388 |
+
"learning_rate": 0.00015310402684563757,
|
| 389 |
+
"loss": 0.1555,
|
| 390 |
+
"step": 560
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.96,
|
| 394 |
+
"learning_rate": 0.00015226510067114095,
|
| 395 |
+
"loss": 0.2612,
|
| 396 |
+
"step": 570
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.97,
|
| 400 |
+
"learning_rate": 0.00015142617449664432,
|
| 401 |
+
"loss": 0.1819,
|
| 402 |
+
"step": 580
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.99,
|
| 406 |
+
"learning_rate": 0.00015058724832214766,
|
| 407 |
+
"loss": 0.2398,
|
| 408 |
+
"step": 590
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.01,
|
| 412 |
+
"learning_rate": 0.00014974832214765103,
|
| 413 |
+
"loss": 0.0873,
|
| 414 |
+
"step": 600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.01,
|
| 418 |
+
"eval_accuracy": 0.9466834592779177,
|
| 419 |
+
"eval_loss": 0.1723610907793045,
|
| 420 |
+
"eval_runtime": 36.2673,
|
| 421 |
+
"eval_samples_per_second": 65.679,
|
| 422 |
+
"eval_steps_per_second": 8.217,
|
| 423 |
+
"step": 600
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.02,
|
| 427 |
+
"learning_rate": 0.00014890939597315435,
|
| 428 |
+
"loss": 0.1876,
|
| 429 |
+
"step": 610
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.04,
|
| 433 |
+
"learning_rate": 0.00014807046979865772,
|
| 434 |
+
"loss": 0.0848,
|
| 435 |
+
"step": 620
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.06,
|
| 439 |
+
"learning_rate": 0.00014723154362416107,
|
| 440 |
+
"loss": 0.0784,
|
| 441 |
+
"step": 630
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.07,
|
| 445 |
+
"learning_rate": 0.00014639261744966444,
|
| 446 |
+
"loss": 0.0697,
|
| 447 |
+
"step": 640
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.09,
|
| 451 |
+
"learning_rate": 0.0001455536912751678,
|
| 452 |
+
"loss": 0.1411,
|
| 453 |
+
"step": 650
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.11,
|
| 457 |
+
"learning_rate": 0.00014471476510067116,
|
| 458 |
+
"loss": 0.0589,
|
| 459 |
+
"step": 660
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.12,
|
| 463 |
+
"learning_rate": 0.0001438758389261745,
|
| 464 |
+
"loss": 0.0867,
|
| 465 |
+
"step": 670
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.14,
|
| 469 |
+
"learning_rate": 0.00014303691275167785,
|
| 470 |
+
"loss": 0.0671,
|
| 471 |
+
"step": 680
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.16,
|
| 475 |
+
"learning_rate": 0.00014219798657718122,
|
| 476 |
+
"loss": 0.0821,
|
| 477 |
+
"step": 690
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.17,
|
| 481 |
+
"learning_rate": 0.00014135906040268456,
|
| 482 |
+
"loss": 0.1594,
|
| 483 |
+
"step": 700
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.17,
|
| 487 |
+
"eval_accuracy": 0.9319899244332494,
|
| 488 |
+
"eval_loss": 0.24392056465148926,
|
| 489 |
+
"eval_runtime": 37.3417,
|
| 490 |
+
"eval_samples_per_second": 63.789,
|
| 491 |
+
"eval_steps_per_second": 7.98,
|
| 492 |
+
"step": 700
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.19,
|
| 496 |
+
"learning_rate": 0.00014052013422818793,
|
| 497 |
+
"loss": 0.1412,
|
| 498 |
+
"step": 710
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.21,
|
| 502 |
+
"learning_rate": 0.00013968120805369128,
|
| 503 |
+
"loss": 0.1345,
|
| 504 |
+
"step": 720
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.22,
|
| 508 |
+
"learning_rate": 0.00013884228187919462,
|
| 509 |
+
"loss": 0.0804,
|
| 510 |
+
"step": 730
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.24,
|
| 514 |
+
"learning_rate": 0.000138003355704698,
|
| 515 |
+
"loss": 0.0858,
|
| 516 |
+
"step": 740
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.26,
|
| 520 |
+
"learning_rate": 0.00013716442953020134,
|
| 521 |
+
"loss": 0.1313,
|
| 522 |
+
"step": 750
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.28,
|
| 526 |
+
"learning_rate": 0.0001363255033557047,
|
| 527 |
+
"loss": 0.0775,
|
| 528 |
+
"step": 760
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.29,
|
| 532 |
+
"learning_rate": 0.00013548657718120806,
|
| 533 |
+
"loss": 0.119,
|
| 534 |
+
"step": 770
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.31,
|
| 538 |
+
"learning_rate": 0.00013464765100671143,
|
| 539 |
+
"loss": 0.0896,
|
| 540 |
+
"step": 780
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.33,
|
| 544 |
+
"learning_rate": 0.00013380872483221477,
|
| 545 |
+
"loss": 0.0962,
|
| 546 |
+
"step": 790
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.34,
|
| 550 |
+
"learning_rate": 0.00013296979865771812,
|
| 551 |
+
"loss": 0.0824,
|
| 552 |
+
"step": 800
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.34,
|
| 556 |
+
"eval_accuracy": 0.9701931150293871,
|
| 557 |
+
"eval_loss": 0.10386788845062256,
|
| 558 |
+
"eval_runtime": 37.9403,
|
| 559 |
+
"eval_samples_per_second": 62.783,
|
| 560 |
+
"eval_steps_per_second": 7.854,
|
| 561 |
+
"step": 800
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.36,
|
| 565 |
+
"learning_rate": 0.0001321308724832215,
|
| 566 |
+
"loss": 0.0185,
|
| 567 |
+
"step": 810
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.38,
|
| 571 |
+
"learning_rate": 0.00013129194630872484,
|
| 572 |
+
"loss": 0.0723,
|
| 573 |
+
"step": 820
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.39,
|
| 577 |
+
"learning_rate": 0.0001304530201342282,
|
| 578 |
+
"loss": 0.1575,
|
| 579 |
+
"step": 830
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.41,
|
| 583 |
+
"learning_rate": 0.00012961409395973155,
|
| 584 |
+
"loss": 0.1435,
|
| 585 |
+
"step": 840
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.43,
|
| 589 |
+
"learning_rate": 0.0001287751677852349,
|
| 590 |
+
"loss": 0.0303,
|
| 591 |
+
"step": 850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.44,
|
| 595 |
+
"learning_rate": 0.00012793624161073827,
|
| 596 |
+
"loss": 0.1279,
|
| 597 |
+
"step": 860
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.46,
|
| 601 |
+
"learning_rate": 0.00012709731543624161,
|
| 602 |
+
"loss": 0.1075,
|
| 603 |
+
"step": 870
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.48,
|
| 607 |
+
"learning_rate": 0.00012625838926174499,
|
| 608 |
+
"loss": 0.0728,
|
| 609 |
+
"step": 880
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.49,
|
| 613 |
+
"learning_rate": 0.00012541946308724833,
|
| 614 |
+
"loss": 0.1591,
|
| 615 |
+
"step": 890
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.51,
|
| 619 |
+
"learning_rate": 0.0001245805369127517,
|
| 620 |
+
"loss": 0.0888,
|
| 621 |
+
"step": 900
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.51,
|
| 625 |
+
"eval_accuracy": 0.9546599496221663,
|
| 626 |
+
"eval_loss": 0.14956098794937134,
|
| 627 |
+
"eval_runtime": 37.2049,
|
| 628 |
+
"eval_samples_per_second": 64.024,
|
| 629 |
+
"eval_steps_per_second": 8.01,
|
| 630 |
+
"step": 900
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.53,
|
| 634 |
+
"learning_rate": 0.00012374161073825502,
|
| 635 |
+
"loss": 0.0903,
|
| 636 |
+
"step": 910
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.54,
|
| 640 |
+
"learning_rate": 0.0001229026845637584,
|
| 641 |
+
"loss": 0.0751,
|
| 642 |
+
"step": 920
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.56,
|
| 646 |
+
"learning_rate": 0.00012206375838926174,
|
| 647 |
+
"loss": 0.1672,
|
| 648 |
+
"step": 930
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.58,
|
| 652 |
+
"learning_rate": 0.00012122483221476511,
|
| 653 |
+
"loss": 0.0507,
|
| 654 |
+
"step": 940
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.59,
|
| 658 |
+
"learning_rate": 0.00012038590604026847,
|
| 659 |
+
"loss": 0.1459,
|
| 660 |
+
"step": 950
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.61,
|
| 664 |
+
"learning_rate": 0.00011954697986577181,
|
| 665 |
+
"loss": 0.0659,
|
| 666 |
+
"step": 960
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.63,
|
| 670 |
+
"learning_rate": 0.00011870805369127518,
|
| 671 |
+
"loss": 0.0726,
|
| 672 |
+
"step": 970
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.64,
|
| 676 |
+
"learning_rate": 0.00011786912751677853,
|
| 677 |
+
"loss": 0.0898,
|
| 678 |
+
"step": 980
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.66,
|
| 682 |
+
"learning_rate": 0.00011703020134228189,
|
| 683 |
+
"loss": 0.1465,
|
| 684 |
+
"step": 990
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.68,
|
| 688 |
+
"learning_rate": 0.00011619127516778523,
|
| 689 |
+
"loss": 0.1058,
|
| 690 |
+
"step": 1000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.68,
|
| 694 |
+
"eval_accuracy": 0.9748110831234257,
|
| 695 |
+
"eval_loss": 0.1099860668182373,
|
| 696 |
+
"eval_runtime": 37.5608,
|
| 697 |
+
"eval_samples_per_second": 63.417,
|
| 698 |
+
"eval_steps_per_second": 7.934,
|
| 699 |
+
"step": 1000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.69,
|
| 703 |
+
"learning_rate": 0.00011535234899328859,
|
| 704 |
+
"loss": 0.1159,
|
| 705 |
+
"step": 1010
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.71,
|
| 709 |
+
"learning_rate": 0.00011451342281879196,
|
| 710 |
+
"loss": 0.0583,
|
| 711 |
+
"step": 1020
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.73,
|
| 715 |
+
"learning_rate": 0.0001136744966442953,
|
| 716 |
+
"loss": 0.1075,
|
| 717 |
+
"step": 1030
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.74,
|
| 721 |
+
"learning_rate": 0.00011283557046979866,
|
| 722 |
+
"loss": 0.1809,
|
| 723 |
+
"step": 1040
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.76,
|
| 727 |
+
"learning_rate": 0.00011199664429530201,
|
| 728 |
+
"loss": 0.1112,
|
| 729 |
+
"step": 1050
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.78,
|
| 733 |
+
"learning_rate": 0.00011115771812080538,
|
| 734 |
+
"loss": 0.0408,
|
| 735 |
+
"step": 1060
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.8,
|
| 739 |
+
"learning_rate": 0.00011031879194630873,
|
| 740 |
+
"loss": 0.1428,
|
| 741 |
+
"step": 1070
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.81,
|
| 745 |
+
"learning_rate": 0.00010947986577181208,
|
| 746 |
+
"loss": 0.0248,
|
| 747 |
+
"step": 1080
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.83,
|
| 751 |
+
"learning_rate": 0.00010864093959731546,
|
| 752 |
+
"loss": 0.0873,
|
| 753 |
+
"step": 1090
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.85,
|
| 757 |
+
"learning_rate": 0.00010780201342281879,
|
| 758 |
+
"loss": 0.077,
|
| 759 |
+
"step": 1100
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.85,
|
| 763 |
+
"eval_accuracy": 0.9756507136859782,
|
| 764 |
+
"eval_loss": 0.07842576503753662,
|
| 765 |
+
"eval_runtime": 36.9225,
|
| 766 |
+
"eval_samples_per_second": 64.513,
|
| 767 |
+
"eval_steps_per_second": 8.071,
|
| 768 |
+
"step": 1100
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.86,
|
| 772 |
+
"learning_rate": 0.00010696308724832216,
|
| 773 |
+
"loss": 0.1448,
|
| 774 |
+
"step": 1110
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.88,
|
| 778 |
+
"learning_rate": 0.0001061241610738255,
|
| 779 |
+
"loss": 0.1401,
|
| 780 |
+
"step": 1120
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.9,
|
| 784 |
+
"learning_rate": 0.00010528523489932886,
|
| 785 |
+
"loss": 0.0186,
|
| 786 |
+
"step": 1130
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.91,
|
| 790 |
+
"learning_rate": 0.00010444630872483221,
|
| 791 |
+
"loss": 0.0693,
|
| 792 |
+
"step": 1140
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.93,
|
| 796 |
+
"learning_rate": 0.00010360738255033558,
|
| 797 |
+
"loss": 0.0521,
|
| 798 |
+
"step": 1150
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.95,
|
| 802 |
+
"learning_rate": 0.00010276845637583894,
|
| 803 |
+
"loss": 0.0286,
|
| 804 |
+
"step": 1160
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.96,
|
| 808 |
+
"learning_rate": 0.00010192953020134228,
|
| 809 |
+
"loss": 0.0321,
|
| 810 |
+
"step": 1170
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.98,
|
| 814 |
+
"learning_rate": 0.00010109060402684565,
|
| 815 |
+
"loss": 0.1065,
|
| 816 |
+
"step": 1180
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.0,
|
| 820 |
+
"learning_rate": 0.00010025167785234899,
|
| 821 |
+
"loss": 0.071,
|
| 822 |
+
"step": 1190
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.01,
|
| 826 |
+
"learning_rate": 9.941275167785236e-05,
|
| 827 |
+
"loss": 0.0486,
|
| 828 |
+
"step": 1200
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.01,
|
| 832 |
+
"eval_accuracy": 0.9710327455919395,
|
| 833 |
+
"eval_loss": 0.09972918033599854,
|
| 834 |
+
"eval_runtime": 38.6678,
|
| 835 |
+
"eval_samples_per_second": 61.602,
|
| 836 |
+
"eval_steps_per_second": 7.707,
|
| 837 |
+
"step": 1200
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.03,
|
| 841 |
+
"learning_rate": 9.857382550335572e-05,
|
| 842 |
+
"loss": 0.04,
|
| 843 |
+
"step": 1210
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.05,
|
| 847 |
+
"learning_rate": 9.773489932885906e-05,
|
| 848 |
+
"loss": 0.0241,
|
| 849 |
+
"step": 1220
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.06,
|
| 853 |
+
"learning_rate": 9.689597315436242e-05,
|
| 854 |
+
"loss": 0.0574,
|
| 855 |
+
"step": 1230
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.08,
|
| 859 |
+
"learning_rate": 9.605704697986578e-05,
|
| 860 |
+
"loss": 0.0196,
|
| 861 |
+
"step": 1240
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.1,
|
| 865 |
+
"learning_rate": 9.521812080536914e-05,
|
| 866 |
+
"loss": 0.0344,
|
| 867 |
+
"step": 1250
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.11,
|
| 871 |
+
"learning_rate": 9.43791946308725e-05,
|
| 872 |
+
"loss": 0.0342,
|
| 873 |
+
"step": 1260
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.13,
|
| 877 |
+
"learning_rate": 9.354026845637585e-05,
|
| 878 |
+
"loss": 0.0121,
|
| 879 |
+
"step": 1270
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.15,
|
| 883 |
+
"learning_rate": 9.27013422818792e-05,
|
| 884 |
+
"loss": 0.0251,
|
| 885 |
+
"step": 1280
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.16,
|
| 889 |
+
"learning_rate": 9.186241610738255e-05,
|
| 890 |
+
"loss": 0.0503,
|
| 891 |
+
"step": 1290
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.18,
|
| 895 |
+
"learning_rate": 9.102348993288591e-05,
|
| 896 |
+
"loss": 0.0087,
|
| 897 |
+
"step": 1300
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.18,
|
| 901 |
+
"eval_accuracy": 0.9811083123425692,
|
| 902 |
+
"eval_loss": 0.07042522728443146,
|
| 903 |
+
"eval_runtime": 37.2902,
|
| 904 |
+
"eval_samples_per_second": 63.877,
|
| 905 |
+
"eval_steps_per_second": 7.991,
|
| 906 |
+
"step": 1300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.2,
|
| 910 |
+
"learning_rate": 9.018456375838926e-05,
|
| 911 |
+
"loss": 0.0676,
|
| 912 |
+
"step": 1310
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.21,
|
| 916 |
+
"learning_rate": 8.934563758389262e-05,
|
| 917 |
+
"loss": 0.0445,
|
| 918 |
+
"step": 1320
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.23,
|
| 922 |
+
"learning_rate": 8.850671140939599e-05,
|
| 923 |
+
"loss": 0.0157,
|
| 924 |
+
"step": 1330
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.25,
|
| 928 |
+
"learning_rate": 8.766778523489933e-05,
|
| 929 |
+
"loss": 0.045,
|
| 930 |
+
"step": 1340
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 2.27,
|
| 934 |
+
"learning_rate": 8.682885906040269e-05,
|
| 935 |
+
"loss": 0.0071,
|
| 936 |
+
"step": 1350
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.28,
|
| 940 |
+
"learning_rate": 8.598993288590605e-05,
|
| 941 |
+
"loss": 0.0219,
|
| 942 |
+
"step": 1360
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.3,
|
| 946 |
+
"learning_rate": 8.51510067114094e-05,
|
| 947 |
+
"loss": 0.0201,
|
| 948 |
+
"step": 1370
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.32,
|
| 952 |
+
"learning_rate": 8.431208053691275e-05,
|
| 953 |
+
"loss": 0.0097,
|
| 954 |
+
"step": 1380
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.33,
|
| 958 |
+
"learning_rate": 8.347315436241611e-05,
|
| 959 |
+
"loss": 0.0552,
|
| 960 |
+
"step": 1390
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.35,
|
| 964 |
+
"learning_rate": 8.263422818791947e-05,
|
| 965 |
+
"loss": 0.0382,
|
| 966 |
+
"step": 1400
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.35,
|
| 970 |
+
"eval_accuracy": 0.9760705289672544,
|
| 971 |
+
"eval_loss": 0.09097278863191605,
|
| 972 |
+
"eval_runtime": 38.1785,
|
| 973 |
+
"eval_samples_per_second": 62.391,
|
| 974 |
+
"eval_steps_per_second": 7.805,
|
| 975 |
+
"step": 1400
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.37,
|
| 979 |
+
"learning_rate": 8.179530201342283e-05,
|
| 980 |
+
"loss": 0.0136,
|
| 981 |
+
"step": 1410
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.38,
|
| 985 |
+
"learning_rate": 8.095637583892619e-05,
|
| 986 |
+
"loss": 0.0735,
|
| 987 |
+
"step": 1420
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 2.4,
|
| 991 |
+
"learning_rate": 8.011744966442953e-05,
|
| 992 |
+
"loss": 0.0244,
|
| 993 |
+
"step": 1430
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.42,
|
| 997 |
+
"learning_rate": 7.927852348993289e-05,
|
| 998 |
+
"loss": 0.0208,
|
| 999 |
+
"step": 1440
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.43,
|
| 1003 |
+
"learning_rate": 7.843959731543625e-05,
|
| 1004 |
+
"loss": 0.0289,
|
| 1005 |
+
"step": 1450
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.45,
|
| 1009 |
+
"learning_rate": 7.760067114093959e-05,
|
| 1010 |
+
"loss": 0.023,
|
| 1011 |
+
"step": 1460
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.47,
|
| 1015 |
+
"learning_rate": 7.676174496644296e-05,
|
| 1016 |
+
"loss": 0.006,
|
| 1017 |
+
"step": 1470
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.48,
|
| 1021 |
+
"learning_rate": 7.592281879194631e-05,
|
| 1022 |
+
"loss": 0.0415,
|
| 1023 |
+
"step": 1480
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.5,
|
| 1027 |
+
"learning_rate": 7.508389261744967e-05,
|
| 1028 |
+
"loss": 0.0253,
|
| 1029 |
+
"step": 1490
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.52,
|
| 1033 |
+
"learning_rate": 7.424496644295303e-05,
|
| 1034 |
+
"loss": 0.046,
|
| 1035 |
+
"step": 1500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.52,
|
| 1039 |
+
"eval_accuracy": 0.984047019311503,
|
| 1040 |
+
"eval_loss": 0.05878419801592827,
|
| 1041 |
+
"eval_runtime": 37.7397,
|
| 1042 |
+
"eval_samples_per_second": 63.116,
|
| 1043 |
+
"eval_steps_per_second": 7.896,
|
| 1044 |
+
"step": 1500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.53,
|
| 1048 |
+
"learning_rate": 7.340604026845638e-05,
|
| 1049 |
+
"loss": 0.0409,
|
| 1050 |
+
"step": 1510
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.55,
|
| 1054 |
+
"learning_rate": 7.256711409395973e-05,
|
| 1055 |
+
"loss": 0.0335,
|
| 1056 |
+
"step": 1520
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 2.57,
|
| 1060 |
+
"learning_rate": 7.172818791946309e-05,
|
| 1061 |
+
"loss": 0.0049,
|
| 1062 |
+
"step": 1530
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.58,
|
| 1066 |
+
"learning_rate": 7.088926174496645e-05,
|
| 1067 |
+
"loss": 0.0119,
|
| 1068 |
+
"step": 1540
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.6,
|
| 1072 |
+
"learning_rate": 7.00503355704698e-05,
|
| 1073 |
+
"loss": 0.0188,
|
| 1074 |
+
"step": 1550
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.62,
|
| 1078 |
+
"learning_rate": 6.921140939597316e-05,
|
| 1079 |
+
"loss": 0.0047,
|
| 1080 |
+
"step": 1560
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.63,
|
| 1084 |
+
"learning_rate": 6.83724832214765e-05,
|
| 1085 |
+
"loss": 0.0053,
|
| 1086 |
+
"step": 1570
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 2.65,
|
| 1090 |
+
"learning_rate": 6.753355704697986e-05,
|
| 1091 |
+
"loss": 0.0034,
|
| 1092 |
+
"step": 1580
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 2.67,
|
| 1096 |
+
"learning_rate": 6.669463087248322e-05,
|
| 1097 |
+
"loss": 0.0026,
|
| 1098 |
+
"step": 1590
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.68,
|
| 1102 |
+
"learning_rate": 6.585570469798658e-05,
|
| 1103 |
+
"loss": 0.0163,
|
| 1104 |
+
"step": 1600
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.68,
|
| 1108 |
+
"eval_accuracy": 0.9836272040302267,
|
| 1109 |
+
"eval_loss": 0.06088751554489136,
|
| 1110 |
+
"eval_runtime": 38.2646,
|
| 1111 |
+
"eval_samples_per_second": 62.251,
|
| 1112 |
+
"eval_steps_per_second": 7.788,
|
| 1113 |
+
"step": 1600
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.7,
|
| 1117 |
+
"learning_rate": 6.501677852348994e-05,
|
| 1118 |
+
"loss": 0.0029,
|
| 1119 |
+
"step": 1610
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.72,
|
| 1123 |
+
"learning_rate": 6.41778523489933e-05,
|
| 1124 |
+
"loss": 0.0027,
|
| 1125 |
+
"step": 1620
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 2.73,
|
| 1129 |
+
"learning_rate": 6.333892617449664e-05,
|
| 1130 |
+
"loss": 0.0394,
|
| 1131 |
+
"step": 1630
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.75,
|
| 1135 |
+
"learning_rate": 6.25e-05,
|
| 1136 |
+
"loss": 0.0235,
|
| 1137 |
+
"step": 1640
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.77,
|
| 1141 |
+
"learning_rate": 6.166107382550336e-05,
|
| 1142 |
+
"loss": 0.0199,
|
| 1143 |
+
"step": 1650
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.79,
|
| 1147 |
+
"learning_rate": 6.082214765100671e-05,
|
| 1148 |
+
"loss": 0.0037,
|
| 1149 |
+
"step": 1660
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 2.8,
|
| 1153 |
+
"learning_rate": 5.998322147651006e-05,
|
| 1154 |
+
"loss": 0.0151,
|
| 1155 |
+
"step": 1670
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.82,
|
| 1159 |
+
"learning_rate": 5.914429530201343e-05,
|
| 1160 |
+
"loss": 0.0472,
|
| 1161 |
+
"step": 1680
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.84,
|
| 1165 |
+
"learning_rate": 5.8305369127516786e-05,
|
| 1166 |
+
"loss": 0.0406,
|
| 1167 |
+
"step": 1690
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.85,
|
| 1171 |
+
"learning_rate": 5.746644295302014e-05,
|
| 1172 |
+
"loss": 0.0876,
|
| 1173 |
+
"step": 1700
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.85,
|
| 1177 |
+
"eval_accuracy": 0.9811083123425692,
|
| 1178 |
+
"eval_loss": 0.06890641152858734,
|
| 1179 |
+
"eval_runtime": 38.0085,
|
| 1180 |
+
"eval_samples_per_second": 62.67,
|
| 1181 |
+
"eval_steps_per_second": 7.84,
|
| 1182 |
+
"step": 1700
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.87,
|
| 1186 |
+
"learning_rate": 5.6627516778523496e-05,
|
| 1187 |
+
"loss": 0.0033,
|
| 1188 |
+
"step": 1710
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.89,
|
| 1192 |
+
"learning_rate": 5.578859060402685e-05,
|
| 1193 |
+
"loss": 0.003,
|
| 1194 |
+
"step": 1720
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.9,
|
| 1198 |
+
"learning_rate": 5.49496644295302e-05,
|
| 1199 |
+
"loss": 0.0024,
|
| 1200 |
+
"step": 1730
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.92,
|
| 1204 |
+
"learning_rate": 5.411073825503356e-05,
|
| 1205 |
+
"loss": 0.0122,
|
| 1206 |
+
"step": 1740
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.94,
|
| 1210 |
+
"learning_rate": 5.327181208053692e-05,
|
| 1211 |
+
"loss": 0.0072,
|
| 1212 |
+
"step": 1750
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 2.95,
|
| 1216 |
+
"learning_rate": 5.2432885906040274e-05,
|
| 1217 |
+
"loss": 0.0023,
|
| 1218 |
+
"step": 1760
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.97,
|
| 1222 |
+
"learning_rate": 5.1593959731543626e-05,
|
| 1223 |
+
"loss": 0.0098,
|
| 1224 |
+
"step": 1770
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.99,
|
| 1228 |
+
"learning_rate": 5.0755033557046984e-05,
|
| 1229 |
+
"loss": 0.035,
|
| 1230 |
+
"step": 1780
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 3.0,
|
| 1234 |
+
"learning_rate": 4.9916107382550336e-05,
|
| 1235 |
+
"loss": 0.0349,
|
| 1236 |
+
"step": 1790
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 3.02,
|
| 1240 |
+
"learning_rate": 4.9077181208053694e-05,
|
| 1241 |
+
"loss": 0.0072,
|
| 1242 |
+
"step": 1800
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 3.02,
|
| 1246 |
+
"eval_accuracy": 0.9861460957178841,
|
| 1247 |
+
"eval_loss": 0.06315400451421738,
|
| 1248 |
+
"eval_runtime": 38.6086,
|
| 1249 |
+
"eval_samples_per_second": 61.696,
|
| 1250 |
+
"eval_steps_per_second": 7.718,
|
| 1251 |
+
"step": 1800
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.04,
|
| 1255 |
+
"learning_rate": 4.823825503355705e-05,
|
| 1256 |
+
"loss": 0.0022,
|
| 1257 |
+
"step": 1810
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 3.05,
|
| 1261 |
+
"learning_rate": 4.7399328859060404e-05,
|
| 1262 |
+
"loss": 0.0131,
|
| 1263 |
+
"step": 1820
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.07,
|
| 1267 |
+
"learning_rate": 4.6560402684563755e-05,
|
| 1268 |
+
"loss": 0.0031,
|
| 1269 |
+
"step": 1830
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.09,
|
| 1273 |
+
"learning_rate": 4.572147651006712e-05,
|
| 1274 |
+
"loss": 0.0024,
|
| 1275 |
+
"step": 1840
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 3.1,
|
| 1279 |
+
"learning_rate": 4.488255033557047e-05,
|
| 1280 |
+
"loss": 0.0022,
|
| 1281 |
+
"step": 1850
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 3.12,
|
| 1285 |
+
"learning_rate": 4.4043624161073823e-05,
|
| 1286 |
+
"loss": 0.0029,
|
| 1287 |
+
"step": 1860
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 3.14,
|
| 1291 |
+
"learning_rate": 4.320469798657718e-05,
|
| 1292 |
+
"loss": 0.0018,
|
| 1293 |
+
"step": 1870
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.15,
|
| 1297 |
+
"learning_rate": 4.236577181208054e-05,
|
| 1298 |
+
"loss": 0.0019,
|
| 1299 |
+
"step": 1880
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 3.17,
|
| 1303 |
+
"learning_rate": 4.152684563758389e-05,
|
| 1304 |
+
"loss": 0.0046,
|
| 1305 |
+
"step": 1890
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.19,
|
| 1309 |
+
"learning_rate": 4.068791946308725e-05,
|
| 1310 |
+
"loss": 0.0022,
|
| 1311 |
+
"step": 1900
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.19,
|
| 1315 |
+
"eval_accuracy": 0.9844668345927792,
|
| 1316 |
+
"eval_loss": 0.0669856071472168,
|
| 1317 |
+
"eval_runtime": 38.9734,
|
| 1318 |
+
"eval_samples_per_second": 61.119,
|
| 1319 |
+
"eval_steps_per_second": 7.646,
|
| 1320 |
+
"step": 1900
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 3.2,
|
| 1324 |
+
"learning_rate": 3.984899328859061e-05,
|
| 1325 |
+
"loss": 0.0031,
|
| 1326 |
+
"step": 1910
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 3.22,
|
| 1330 |
+
"learning_rate": 3.901006711409396e-05,
|
| 1331 |
+
"loss": 0.0033,
|
| 1332 |
+
"step": 1920
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 3.24,
|
| 1336 |
+
"learning_rate": 3.817114093959732e-05,
|
| 1337 |
+
"loss": 0.0171,
|
| 1338 |
+
"step": 1930
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 3.26,
|
| 1342 |
+
"learning_rate": 3.733221476510067e-05,
|
| 1343 |
+
"loss": 0.0022,
|
| 1344 |
+
"step": 1940
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 3.27,
|
| 1348 |
+
"learning_rate": 3.649328859060403e-05,
|
| 1349 |
+
"loss": 0.0023,
|
| 1350 |
+
"step": 1950
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 3.29,
|
| 1354 |
+
"learning_rate": 3.5654362416107386e-05,
|
| 1355 |
+
"loss": 0.0036,
|
| 1356 |
+
"step": 1960
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 3.31,
|
| 1360 |
+
"learning_rate": 3.481543624161074e-05,
|
| 1361 |
+
"loss": 0.0038,
|
| 1362 |
+
"step": 1970
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 3.32,
|
| 1366 |
+
"learning_rate": 3.3976510067114096e-05,
|
| 1367 |
+
"loss": 0.0016,
|
| 1368 |
+
"step": 1980
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 3.34,
|
| 1372 |
+
"learning_rate": 3.3137583892617455e-05,
|
| 1373 |
+
"loss": 0.0022,
|
| 1374 |
+
"step": 1990
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.36,
|
| 1378 |
+
"learning_rate": 3.2298657718120806e-05,
|
| 1379 |
+
"loss": 0.0018,
|
| 1380 |
+
"step": 2000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 3.36,
|
| 1384 |
+
"eval_accuracy": 0.9844668345927792,
|
| 1385 |
+
"eval_loss": 0.0704568475484848,
|
| 1386 |
+
"eval_runtime": 36.8214,
|
| 1387 |
+
"eval_samples_per_second": 64.691,
|
| 1388 |
+
"eval_steps_per_second": 8.093,
|
| 1389 |
+
"step": 2000
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.37,
|
| 1393 |
+
"learning_rate": 3.145973154362416e-05,
|
| 1394 |
+
"loss": 0.0036,
|
| 1395 |
+
"step": 2010
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.39,
|
| 1399 |
+
"learning_rate": 3.062080536912752e-05,
|
| 1400 |
+
"loss": 0.0018,
|
| 1401 |
+
"step": 2020
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 3.41,
|
| 1405 |
+
"learning_rate": 2.9781879194630874e-05,
|
| 1406 |
+
"loss": 0.0015,
|
| 1407 |
+
"step": 2030
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 3.42,
|
| 1411 |
+
"learning_rate": 2.894295302013423e-05,
|
| 1412 |
+
"loss": 0.0018,
|
| 1413 |
+
"step": 2040
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 3.44,
|
| 1417 |
+
"learning_rate": 2.8104026845637588e-05,
|
| 1418 |
+
"loss": 0.0021,
|
| 1419 |
+
"step": 2050
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 3.46,
|
| 1423 |
+
"learning_rate": 2.7265100671140943e-05,
|
| 1424 |
+
"loss": 0.0016,
|
| 1425 |
+
"step": 2060
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 3.47,
|
| 1429 |
+
"learning_rate": 2.6426174496644297e-05,
|
| 1430 |
+
"loss": 0.0019,
|
| 1431 |
+
"step": 2070
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.49,
|
| 1435 |
+
"learning_rate": 2.558724832214765e-05,
|
| 1436 |
+
"loss": 0.0025,
|
| 1437 |
+
"step": 2080
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 3.51,
|
| 1441 |
+
"learning_rate": 2.4748322147651007e-05,
|
| 1442 |
+
"loss": 0.0071,
|
| 1443 |
+
"step": 2090
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 3.52,
|
| 1447 |
+
"learning_rate": 2.3909395973154362e-05,
|
| 1448 |
+
"loss": 0.0023,
|
| 1449 |
+
"step": 2100
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 3.52,
|
| 1453 |
+
"eval_accuracy": 0.9861460957178841,
|
| 1454 |
+
"eval_loss": 0.0588483065366745,
|
| 1455 |
+
"eval_runtime": 36.7062,
|
| 1456 |
+
"eval_samples_per_second": 64.894,
|
| 1457 |
+
"eval_steps_per_second": 8.119,
|
| 1458 |
+
"step": 2100
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 3.54,
|
| 1462 |
+
"learning_rate": 2.3070469798657717e-05,
|
| 1463 |
+
"loss": 0.0111,
|
| 1464 |
+
"step": 2110
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 3.56,
|
| 1468 |
+
"learning_rate": 2.2231543624161076e-05,
|
| 1469 |
+
"loss": 0.0019,
|
| 1470 |
+
"step": 2120
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 3.57,
|
| 1474 |
+
"learning_rate": 2.139261744966443e-05,
|
| 1475 |
+
"loss": 0.007,
|
| 1476 |
+
"step": 2130
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 3.59,
|
| 1480 |
+
"learning_rate": 2.0553691275167785e-05,
|
| 1481 |
+
"loss": 0.0022,
|
| 1482 |
+
"step": 2140
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 3.61,
|
| 1486 |
+
"learning_rate": 1.9714765100671144e-05,
|
| 1487 |
+
"loss": 0.0019,
|
| 1488 |
+
"step": 2150
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 3.62,
|
| 1492 |
+
"learning_rate": 1.8875838926174495e-05,
|
| 1493 |
+
"loss": 0.0017,
|
| 1494 |
+
"step": 2160
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 3.64,
|
| 1498 |
+
"learning_rate": 1.8036912751677854e-05,
|
| 1499 |
+
"loss": 0.0017,
|
| 1500 |
+
"step": 2170
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 3.66,
|
| 1504 |
+
"learning_rate": 1.719798657718121e-05,
|
| 1505 |
+
"loss": 0.0134,
|
| 1506 |
+
"step": 2180
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 3.67,
|
| 1510 |
+
"learning_rate": 1.6359060402684563e-05,
|
| 1511 |
+
"loss": 0.0017,
|
| 1512 |
+
"step": 2190
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 3.69,
|
| 1516 |
+
"learning_rate": 1.5520134228187922e-05,
|
| 1517 |
+
"loss": 0.0017,
|
| 1518 |
+
"step": 2200
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 3.69,
|
| 1522 |
+
"eval_accuracy": 0.9882451721242653,
|
| 1523 |
+
"eval_loss": 0.04898680001497269,
|
| 1524 |
+
"eval_runtime": 36.2766,
|
| 1525 |
+
"eval_samples_per_second": 65.662,
|
| 1526 |
+
"eval_steps_per_second": 8.215,
|
| 1527 |
+
"step": 2200
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 3.71,
|
| 1531 |
+
"learning_rate": 1.4681208053691275e-05,
|
| 1532 |
+
"loss": 0.002,
|
| 1533 |
+
"step": 2210
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 3.72,
|
| 1537 |
+
"learning_rate": 1.3842281879194632e-05,
|
| 1538 |
+
"loss": 0.0019,
|
| 1539 |
+
"step": 2220
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 3.74,
|
| 1543 |
+
"learning_rate": 1.3003355704697987e-05,
|
| 1544 |
+
"loss": 0.0017,
|
| 1545 |
+
"step": 2230
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 3.76,
|
| 1549 |
+
"learning_rate": 1.2164429530201343e-05,
|
| 1550 |
+
"loss": 0.0021,
|
| 1551 |
+
"step": 2240
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 3.78,
|
| 1555 |
+
"learning_rate": 1.1325503355704698e-05,
|
| 1556 |
+
"loss": 0.0027,
|
| 1557 |
+
"step": 2250
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 3.79,
|
| 1561 |
+
"learning_rate": 1.0486577181208055e-05,
|
| 1562 |
+
"loss": 0.0027,
|
| 1563 |
+
"step": 2260
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 3.81,
|
| 1567 |
+
"learning_rate": 9.64765100671141e-06,
|
| 1568 |
+
"loss": 0.0021,
|
| 1569 |
+
"step": 2270
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 3.83,
|
| 1573 |
+
"learning_rate": 8.808724832214765e-06,
|
| 1574 |
+
"loss": 0.0017,
|
| 1575 |
+
"step": 2280
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 3.84,
|
| 1579 |
+
"learning_rate": 7.969798657718121e-06,
|
| 1580 |
+
"loss": 0.0018,
|
| 1581 |
+
"step": 2290
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 3.86,
|
| 1585 |
+
"learning_rate": 7.130872483221476e-06,
|
| 1586 |
+
"loss": 0.0248,
|
| 1587 |
+
"step": 2300
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 3.86,
|
| 1591 |
+
"eval_accuracy": 0.9882451721242653,
|
| 1592 |
+
"eval_loss": 0.04982466623187065,
|
| 1593 |
+
"eval_runtime": 37.2392,
|
| 1594 |
+
"eval_samples_per_second": 63.965,
|
| 1595 |
+
"eval_steps_per_second": 8.002,
|
| 1596 |
+
"step": 2300
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 3.88,
|
| 1600 |
+
"learning_rate": 6.291946308724833e-06,
|
| 1601 |
+
"loss": 0.0024,
|
| 1602 |
+
"step": 2310
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 3.89,
|
| 1606 |
+
"learning_rate": 5.453020134228188e-06,
|
| 1607 |
+
"loss": 0.0017,
|
| 1608 |
+
"step": 2320
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 3.91,
|
| 1612 |
+
"learning_rate": 4.6140939597315445e-06,
|
| 1613 |
+
"loss": 0.0315,
|
| 1614 |
+
"step": 2330
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 3.93,
|
| 1618 |
+
"learning_rate": 3.7751677852349e-06,
|
| 1619 |
+
"loss": 0.0018,
|
| 1620 |
+
"step": 2340
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 3.94,
|
| 1624 |
+
"learning_rate": 2.936241610738255e-06,
|
| 1625 |
+
"loss": 0.0018,
|
| 1626 |
+
"step": 2350
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 3.96,
|
| 1630 |
+
"learning_rate": 2.097315436241611e-06,
|
| 1631 |
+
"loss": 0.0016,
|
| 1632 |
+
"step": 2360
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 3.98,
|
| 1636 |
+
"learning_rate": 1.2583892617449663e-06,
|
| 1637 |
+
"loss": 0.0027,
|
| 1638 |
+
"step": 2370
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 3.99,
|
| 1642 |
+
"learning_rate": 4.1946308724832216e-07,
|
| 1643 |
+
"loss": 0.0133,
|
| 1644 |
+
"step": 2380
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 4.0,
|
| 1648 |
+
"step": 2384,
|
| 1649 |
+
"total_flos": 2.953718820314874e+18,
|
| 1650 |
+
"train_loss": 0.09724263496534437,
|
| 1651 |
+
"train_runtime": 2056.7864,
|
| 1652 |
+
"train_samples_per_second": 18.53,
|
| 1653 |
+
"train_steps_per_second": 1.159
|
| 1654 |
+
}
|
| 1655 |
+
],
|
| 1656 |
+
"logging_steps": 10,
|
| 1657 |
+
"max_steps": 2384,
|
| 1658 |
+
"num_train_epochs": 4,
|
| 1659 |
+
"save_steps": 100,
|
| 1660 |
+
"total_flos": 2.953718820314874e+18,
|
| 1661 |
+
"trial_name": null,
|
| 1662 |
+
"trial_params": null
|
| 1663 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0881837600d9608fa30ddd4c0831e2247c08f5962997b3a559610238a2c5850
|
| 3 |
+
size 4027
|