laiagdla/cancer-Vit-classification
Browse files- README.md +97 -0
- all_results.json +13 -0
- config.json +32 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Dec01_11-05-37_0960a716d84b/events.out.tfevents.1701428741.0960a716d84b.48.0 +3 -0
- runs/Dec01_11-12-43_0960a716d84b/events.out.tfevents.1701429165.0960a716d84b.48.1 +3 -0
- runs/Dec01_11-12-43_0960a716d84b/events.out.tfevents.1701435207.0960a716d84b.48.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +2680 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: model
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# model
|
| 17 |
+
|
| 18 |
+
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 None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1898
|
| 21 |
+
- Accuracy: 0.9243
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 4
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 0.2732 | 0.1 | 100 | 0.3969 | 0.8461 |
|
| 53 |
+
| 0.2784 | 0.21 | 200 | 0.3714 | 0.8579 |
|
| 54 |
+
| 0.301 | 0.31 | 300 | 0.3504 | 0.8376 |
|
| 55 |
+
| 0.2372 | 0.42 | 400 | 0.3391 | 0.8812 |
|
| 56 |
+
| 0.3136 | 0.52 | 500 | 0.2559 | 0.8967 |
|
| 57 |
+
| 0.3517 | 0.62 | 600 | 0.4141 | 0.8397 |
|
| 58 |
+
| 0.3312 | 0.73 | 700 | 0.3043 | 0.8841 |
|
| 59 |
+
| 0.2515 | 0.83 | 800 | 0.2541 | 0.9062 |
|
| 60 |
+
| 0.2854 | 0.93 | 900 | 0.2561 | 0.9006 |
|
| 61 |
+
| 0.2594 | 1.04 | 1000 | 0.2681 | 0.9020 |
|
| 62 |
+
| 0.177 | 1.14 | 1100 | 0.3406 | 0.8773 |
|
| 63 |
+
| 0.2717 | 1.25 | 1200 | 0.2266 | 0.9171 |
|
| 64 |
+
| 0.2197 | 1.35 | 1300 | 0.2080 | 0.9236 |
|
| 65 |
+
| 0.155 | 1.45 | 1400 | 0.2048 | 0.9236 |
|
| 66 |
+
| 0.2657 | 1.56 | 1500 | 0.2037 | 0.9256 |
|
| 67 |
+
| 0.118 | 1.66 | 1600 | 0.2616 | 0.9096 |
|
| 68 |
+
| 0.1823 | 1.77 | 1700 | 0.2158 | 0.9241 |
|
| 69 |
+
| 0.2175 | 1.87 | 1800 | 0.2159 | 0.9182 |
|
| 70 |
+
| 0.143 | 1.97 | 1900 | 0.1898 | 0.9243 |
|
| 71 |
+
| 0.1051 | 2.08 | 2000 | 0.2308 | 0.9226 |
|
| 72 |
+
| 0.1963 | 2.18 | 2100 | 0.2354 | 0.9205 |
|
| 73 |
+
| 0.0524 | 2.28 | 2200 | 0.2298 | 0.9282 |
|
| 74 |
+
| 0.097 | 2.39 | 2300 | 0.2495 | 0.9241 |
|
| 75 |
+
| 0.0744 | 2.49 | 2400 | 0.2493 | 0.9194 |
|
| 76 |
+
| 0.0744 | 2.6 | 2500 | 0.2429 | 0.9323 |
|
| 77 |
+
| 0.0345 | 2.7 | 2600 | 0.2587 | 0.9252 |
|
| 78 |
+
| 0.0097 | 2.8 | 2700 | 0.2284 | 0.9265 |
|
| 79 |
+
| 0.0775 | 2.91 | 2800 | 0.2242 | 0.9321 |
|
| 80 |
+
| 0.0634 | 3.01 | 2900 | 0.2314 | 0.9286 |
|
| 81 |
+
| 0.0109 | 3.12 | 3000 | 0.2203 | 0.9338 |
|
| 82 |
+
| 0.0039 | 3.22 | 3100 | 0.2575 | 0.9358 |
|
| 83 |
+
| 0.0139 | 3.32 | 3200 | 0.2570 | 0.9356 |
|
| 84 |
+
| 0.0358 | 3.43 | 3300 | 0.2630 | 0.9335 |
|
| 85 |
+
| 0.0347 | 3.53 | 3400 | 0.2633 | 0.9358 |
|
| 86 |
+
| 0.0408 | 3.63 | 3500 | 0.2591 | 0.9335 |
|
| 87 |
+
| 0.041 | 3.74 | 3600 | 0.2613 | 0.9367 |
|
| 88 |
+
| 0.004 | 3.84 | 3700 | 0.2587 | 0.9370 |
|
| 89 |
+
| 0.0389 | 3.95 | 3800 | 0.2535 | 0.9373 |
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
### Framework versions
|
| 93 |
+
|
| 94 |
+
- Transformers 4.35.0
|
| 95 |
+
- Pytorch 2.0.0
|
| 96 |
+
- Datasets 2.1.0
|
| 97 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9242539009241024,
|
| 4 |
+
"eval_loss": 0.18984103202819824,
|
| 5 |
+
"eval_runtime": 112.4112,
|
| 6 |
+
"eval_samples_per_second": 58.722,
|
| 7 |
+
"eval_steps_per_second": 7.348,
|
| 8 |
+
"total_flos": 4.774126496175784e+18,
|
| 9 |
+
"train_loss": 0.1544622457234444,
|
| 10 |
+
"train_runtime": 5879.4453,
|
| 11 |
+
"train_samples_per_second": 10.479,
|
| 12 |
+
"train_steps_per_second": 0.655
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "0",
|
| 13 |
+
"1": "1"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"0": "0",
|
| 20 |
+
"1": "1"
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.35.0"
|
| 32 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9242539009241024,
|
| 4 |
+
"eval_loss": 0.18984103202819824,
|
| 5 |
+
"eval_runtime": 112.4112,
|
| 6 |
+
"eval_samples_per_second": 58.722,
|
| 7 |
+
"eval_steps_per_second": 7.348
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d80664ad400f0fd9eee216d396f9dc0c609929645ed1ab817fe0b5b0faa0d787
|
| 3 |
+
size 343223968
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
runs/Dec01_11-05-37_0960a716d84b/events.out.tfevents.1701428741.0960a716d84b.48.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4abb944ba56f219961db0953d6582eee9c28520e498dc7a02def46905e9d9ff0
|
| 3 |
+
size 6990
|
runs/Dec01_11-12-43_0960a716d84b/events.out.tfevents.1701429165.0960a716d84b.48.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:929114cb0b9a1c1321c6eec5d0698b01c71a0a8afdc610336b01e85e22cb44cf
|
| 3 |
+
size 77228
|
runs/Dec01_11-12-43_0960a716d84b/events.out.tfevents.1701435207.0960a716d84b.48.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7a14a9023a9bab421c3e0f713d42d1f04df5743fe0e400067eb80fd0ab02817
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 4.774126496175784e+18,
|
| 4 |
+
"train_loss": 0.1544622457234444,
|
| 5 |
+
"train_runtime": 5879.4453,
|
| 6 |
+
"train_samples_per_second": 10.479,
|
| 7 |
+
"train_steps_per_second": 0.655
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2680 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.18984103202819824,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/working/model/checkpoint-1900",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 3852,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 0.00019948078920041537,
|
| 14 |
+
"loss": 0.6119,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 0.00019896157840083075,
|
| 20 |
+
"loss": 0.556,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 0.00019844236760124614,
|
| 26 |
+
"loss": 0.4675,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.04,
|
| 31 |
+
"learning_rate": 0.0001979231568016615,
|
| 32 |
+
"loss": 0.4472,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.05,
|
| 37 |
+
"learning_rate": 0.00019740394600207685,
|
| 38 |
+
"loss": 0.3713,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.06,
|
| 43 |
+
"learning_rate": 0.0001968847352024922,
|
| 44 |
+
"loss": 0.339,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07,
|
| 49 |
+
"learning_rate": 0.0001963655244029076,
|
| 50 |
+
"loss": 0.4431,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"learning_rate": 0.00019584631360332295,
|
| 56 |
+
"loss": 0.4784,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.09,
|
| 61 |
+
"learning_rate": 0.00019532710280373834,
|
| 62 |
+
"loss": 0.4167,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.1,
|
| 67 |
+
"learning_rate": 0.0001948078920041537,
|
| 68 |
+
"loss": 0.2732,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.1,
|
| 73 |
+
"eval_accuracy": 0.8460839266777761,
|
| 74 |
+
"eval_loss": 0.39686205983161926,
|
| 75 |
+
"eval_runtime": 106.8457,
|
| 76 |
+
"eval_samples_per_second": 61.781,
|
| 77 |
+
"eval_steps_per_second": 7.731,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.11,
|
| 82 |
+
"learning_rate": 0.00019428868120456908,
|
| 83 |
+
"loss": 0.5051,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.12,
|
| 88 |
+
"learning_rate": 0.00019376947040498444,
|
| 89 |
+
"loss": 0.306,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.13,
|
| 94 |
+
"learning_rate": 0.0001932502596053998,
|
| 95 |
+
"loss": 0.3317,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.15,
|
| 100 |
+
"learning_rate": 0.00019273104880581515,
|
| 101 |
+
"loss": 0.4264,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.16,
|
| 106 |
+
"learning_rate": 0.00019221183800623054,
|
| 107 |
+
"loss": 0.4038,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.17,
|
| 112 |
+
"learning_rate": 0.00019169262720664592,
|
| 113 |
+
"loss": 0.4715,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.18,
|
| 118 |
+
"learning_rate": 0.00019117341640706128,
|
| 119 |
+
"loss": 0.3561,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.19,
|
| 124 |
+
"learning_rate": 0.00019065420560747664,
|
| 125 |
+
"loss": 0.3471,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.2,
|
| 130 |
+
"learning_rate": 0.00019013499480789202,
|
| 131 |
+
"loss": 0.3163,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.21,
|
| 136 |
+
"learning_rate": 0.00018961578400830738,
|
| 137 |
+
"loss": 0.2784,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.21,
|
| 142 |
+
"eval_accuracy": 0.8579003181336161,
|
| 143 |
+
"eval_loss": 0.37141430377960205,
|
| 144 |
+
"eval_runtime": 106.5876,
|
| 145 |
+
"eval_samples_per_second": 61.93,
|
| 146 |
+
"eval_steps_per_second": 7.749,
|
| 147 |
+
"step": 200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.22,
|
| 151 |
+
"learning_rate": 0.00018909657320872276,
|
| 152 |
+
"loss": 0.4061,
|
| 153 |
+
"step": 210
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.23,
|
| 157 |
+
"learning_rate": 0.00018857736240913812,
|
| 158 |
+
"loss": 0.2339,
|
| 159 |
+
"step": 220
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.24,
|
| 163 |
+
"learning_rate": 0.00018805815160955348,
|
| 164 |
+
"loss": 0.3515,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.25,
|
| 169 |
+
"learning_rate": 0.00018753894080996886,
|
| 170 |
+
"loss": 0.2553,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.26,
|
| 175 |
+
"learning_rate": 0.00018701973001038422,
|
| 176 |
+
"loss": 0.4057,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.27,
|
| 181 |
+
"learning_rate": 0.00018650051921079958,
|
| 182 |
+
"loss": 0.2917,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.28,
|
| 187 |
+
"learning_rate": 0.00018598130841121496,
|
| 188 |
+
"loss": 0.384,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.29,
|
| 193 |
+
"learning_rate": 0.00018546209761163035,
|
| 194 |
+
"loss": 0.3622,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.3,
|
| 199 |
+
"learning_rate": 0.0001849428868120457,
|
| 200 |
+
"loss": 0.3697,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.31,
|
| 205 |
+
"learning_rate": 0.00018442367601246106,
|
| 206 |
+
"loss": 0.301,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.31,
|
| 211 |
+
"eval_accuracy": 0.8376003635812755,
|
| 212 |
+
"eval_loss": 0.35040077567100525,
|
| 213 |
+
"eval_runtime": 106.1282,
|
| 214 |
+
"eval_samples_per_second": 62.198,
|
| 215 |
+
"eval_steps_per_second": 7.783,
|
| 216 |
+
"step": 300
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.32,
|
| 220 |
+
"learning_rate": 0.00018390446521287642,
|
| 221 |
+
"loss": 0.3128,
|
| 222 |
+
"step": 310
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.33,
|
| 226 |
+
"learning_rate": 0.0001833852544132918,
|
| 227 |
+
"loss": 0.2876,
|
| 228 |
+
"step": 320
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.34,
|
| 232 |
+
"learning_rate": 0.0001828660436137072,
|
| 233 |
+
"loss": 0.2879,
|
| 234 |
+
"step": 330
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.35,
|
| 238 |
+
"learning_rate": 0.00018234683281412255,
|
| 239 |
+
"loss": 0.2336,
|
| 240 |
+
"step": 340
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.36,
|
| 244 |
+
"learning_rate": 0.0001818276220145379,
|
| 245 |
+
"loss": 0.3879,
|
| 246 |
+
"step": 350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.37,
|
| 250 |
+
"learning_rate": 0.0001813084112149533,
|
| 251 |
+
"loss": 0.333,
|
| 252 |
+
"step": 360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.38,
|
| 256 |
+
"learning_rate": 0.00018078920041536865,
|
| 257 |
+
"loss": 0.3831,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.39,
|
| 262 |
+
"learning_rate": 0.000180269989615784,
|
| 263 |
+
"loss": 0.2895,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.4,
|
| 268 |
+
"learning_rate": 0.0001797507788161994,
|
| 269 |
+
"loss": 0.3258,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.42,
|
| 274 |
+
"learning_rate": 0.00017923156801661475,
|
| 275 |
+
"loss": 0.2372,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.42,
|
| 280 |
+
"eval_accuracy": 0.8812301166489925,
|
| 281 |
+
"eval_loss": 0.3391087055206299,
|
| 282 |
+
"eval_runtime": 106.4818,
|
| 283 |
+
"eval_samples_per_second": 61.992,
|
| 284 |
+
"eval_steps_per_second": 7.757,
|
| 285 |
+
"step": 400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.43,
|
| 289 |
+
"learning_rate": 0.00017871235721703013,
|
| 290 |
+
"loss": 0.4028,
|
| 291 |
+
"step": 410
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.44,
|
| 295 |
+
"learning_rate": 0.0001781931464174455,
|
| 296 |
+
"loss": 0.244,
|
| 297 |
+
"step": 420
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.45,
|
| 301 |
+
"learning_rate": 0.00017767393561786085,
|
| 302 |
+
"loss": 0.2848,
|
| 303 |
+
"step": 430
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.46,
|
| 307 |
+
"learning_rate": 0.00017715472481827623,
|
| 308 |
+
"loss": 0.3357,
|
| 309 |
+
"step": 440
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.47,
|
| 313 |
+
"learning_rate": 0.00017663551401869162,
|
| 314 |
+
"loss": 0.3361,
|
| 315 |
+
"step": 450
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.48,
|
| 319 |
+
"learning_rate": 0.00017611630321910697,
|
| 320 |
+
"loss": 0.3148,
|
| 321 |
+
"step": 460
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.49,
|
| 325 |
+
"learning_rate": 0.00017559709241952233,
|
| 326 |
+
"loss": 0.3378,
|
| 327 |
+
"step": 470
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.5,
|
| 331 |
+
"learning_rate": 0.0001750778816199377,
|
| 332 |
+
"loss": 0.3758,
|
| 333 |
+
"step": 480
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.51,
|
| 337 |
+
"learning_rate": 0.00017455867082035307,
|
| 338 |
+
"loss": 0.2882,
|
| 339 |
+
"step": 490
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.52,
|
| 343 |
+
"learning_rate": 0.00017403946002076843,
|
| 344 |
+
"loss": 0.3136,
|
| 345 |
+
"step": 500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.52,
|
| 349 |
+
"eval_accuracy": 0.8966823208604757,
|
| 350 |
+
"eval_loss": 0.2559354901313782,
|
| 351 |
+
"eval_runtime": 106.8533,
|
| 352 |
+
"eval_samples_per_second": 61.776,
|
| 353 |
+
"eval_steps_per_second": 7.73,
|
| 354 |
+
"step": 500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.53,
|
| 358 |
+
"learning_rate": 0.00017352024922118382,
|
| 359 |
+
"loss": 0.2467,
|
| 360 |
+
"step": 510
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.54,
|
| 364 |
+
"learning_rate": 0.00017300103842159917,
|
| 365 |
+
"loss": 0.2569,
|
| 366 |
+
"step": 520
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.55,
|
| 370 |
+
"learning_rate": 0.00017248182762201456,
|
| 371 |
+
"loss": 0.2846,
|
| 372 |
+
"step": 530
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.56,
|
| 376 |
+
"learning_rate": 0.00017196261682242992,
|
| 377 |
+
"loss": 0.3017,
|
| 378 |
+
"step": 540
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.57,
|
| 382 |
+
"learning_rate": 0.00017144340602284527,
|
| 383 |
+
"loss": 0.2795,
|
| 384 |
+
"step": 550
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.58,
|
| 388 |
+
"learning_rate": 0.00017092419522326063,
|
| 389 |
+
"loss": 0.3047,
|
| 390 |
+
"step": 560
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.59,
|
| 394 |
+
"learning_rate": 0.00017040498442367602,
|
| 395 |
+
"loss": 0.3351,
|
| 396 |
+
"step": 570
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.6,
|
| 400 |
+
"learning_rate": 0.0001698857736240914,
|
| 401 |
+
"loss": 0.2825,
|
| 402 |
+
"step": 580
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.61,
|
| 406 |
+
"learning_rate": 0.00016936656282450676,
|
| 407 |
+
"loss": 0.2019,
|
| 408 |
+
"step": 590
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.62,
|
| 412 |
+
"learning_rate": 0.00016884735202492212,
|
| 413 |
+
"loss": 0.3517,
|
| 414 |
+
"step": 600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.62,
|
| 418 |
+
"eval_accuracy": 0.8397212543554007,
|
| 419 |
+
"eval_loss": 0.41408056020736694,
|
| 420 |
+
"eval_runtime": 104.998,
|
| 421 |
+
"eval_samples_per_second": 62.868,
|
| 422 |
+
"eval_steps_per_second": 7.867,
|
| 423 |
+
"step": 600
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.63,
|
| 427 |
+
"learning_rate": 0.0001683281412253375,
|
| 428 |
+
"loss": 0.3487,
|
| 429 |
+
"step": 610
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.64,
|
| 433 |
+
"learning_rate": 0.00016780893042575286,
|
| 434 |
+
"loss": 0.2473,
|
| 435 |
+
"step": 620
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.65,
|
| 439 |
+
"learning_rate": 0.00016728971962616824,
|
| 440 |
+
"loss": 0.2432,
|
| 441 |
+
"step": 630
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.66,
|
| 445 |
+
"learning_rate": 0.0001667705088265836,
|
| 446 |
+
"loss": 0.3265,
|
| 447 |
+
"step": 640
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.67,
|
| 451 |
+
"learning_rate": 0.00016625129802699896,
|
| 452 |
+
"loss": 0.2954,
|
| 453 |
+
"step": 650
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.69,
|
| 457 |
+
"learning_rate": 0.00016573208722741434,
|
| 458 |
+
"loss": 0.2389,
|
| 459 |
+
"step": 660
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.7,
|
| 463 |
+
"learning_rate": 0.0001652128764278297,
|
| 464 |
+
"loss": 0.2444,
|
| 465 |
+
"step": 670
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.71,
|
| 469 |
+
"learning_rate": 0.00016469366562824509,
|
| 470 |
+
"loss": 0.2776,
|
| 471 |
+
"step": 680
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.72,
|
| 475 |
+
"learning_rate": 0.00016417445482866044,
|
| 476 |
+
"loss": 0.3284,
|
| 477 |
+
"step": 690
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.73,
|
| 481 |
+
"learning_rate": 0.00016365524402907583,
|
| 482 |
+
"loss": 0.3312,
|
| 483 |
+
"step": 700
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.73,
|
| 487 |
+
"eval_accuracy": 0.8841084684138767,
|
| 488 |
+
"eval_loss": 0.3043135702610016,
|
| 489 |
+
"eval_runtime": 108.7426,
|
| 490 |
+
"eval_samples_per_second": 60.703,
|
| 491 |
+
"eval_steps_per_second": 7.596,
|
| 492 |
+
"step": 700
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.74,
|
| 496 |
+
"learning_rate": 0.00016313603322949118,
|
| 497 |
+
"loss": 0.1868,
|
| 498 |
+
"step": 710
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.75,
|
| 502 |
+
"learning_rate": 0.00016261682242990654,
|
| 503 |
+
"loss": 0.3254,
|
| 504 |
+
"step": 720
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.76,
|
| 508 |
+
"learning_rate": 0.0001620976116303219,
|
| 509 |
+
"loss": 0.3054,
|
| 510 |
+
"step": 730
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.77,
|
| 514 |
+
"learning_rate": 0.00016157840083073728,
|
| 515 |
+
"loss": 0.1782,
|
| 516 |
+
"step": 740
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.78,
|
| 520 |
+
"learning_rate": 0.00016105919003115267,
|
| 521 |
+
"loss": 0.2538,
|
| 522 |
+
"step": 750
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.79,
|
| 526 |
+
"learning_rate": 0.00016053997923156803,
|
| 527 |
+
"loss": 0.2088,
|
| 528 |
+
"step": 760
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8,
|
| 532 |
+
"learning_rate": 0.00016002076843198338,
|
| 533 |
+
"loss": 0.3186,
|
| 534 |
+
"step": 770
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.81,
|
| 538 |
+
"learning_rate": 0.00015950155763239877,
|
| 539 |
+
"loss": 0.3071,
|
| 540 |
+
"step": 780
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.82,
|
| 544 |
+
"learning_rate": 0.00015898234683281413,
|
| 545 |
+
"loss": 0.2838,
|
| 546 |
+
"step": 790
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.83,
|
| 550 |
+
"learning_rate": 0.0001584631360332295,
|
| 551 |
+
"loss": 0.2515,
|
| 552 |
+
"step": 800
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.83,
|
| 556 |
+
"eval_accuracy": 0.9062263293440388,
|
| 557 |
+
"eval_loss": 0.2541460394859314,
|
| 558 |
+
"eval_runtime": 106.4027,
|
| 559 |
+
"eval_samples_per_second": 62.038,
|
| 560 |
+
"eval_steps_per_second": 7.763,
|
| 561 |
+
"step": 800
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.84,
|
| 565 |
+
"learning_rate": 0.00015794392523364487,
|
| 566 |
+
"loss": 0.3887,
|
| 567 |
+
"step": 810
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.85,
|
| 571 |
+
"learning_rate": 0.00015742471443406023,
|
| 572 |
+
"loss": 0.2235,
|
| 573 |
+
"step": 820
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.86,
|
| 577 |
+
"learning_rate": 0.0001569055036344756,
|
| 578 |
+
"loss": 0.2313,
|
| 579 |
+
"step": 830
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.87,
|
| 583 |
+
"learning_rate": 0.00015638629283489097,
|
| 584 |
+
"loss": 0.274,
|
| 585 |
+
"step": 840
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.88,
|
| 589 |
+
"learning_rate": 0.00015586708203530633,
|
| 590 |
+
"loss": 0.2223,
|
| 591 |
+
"step": 850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.89,
|
| 595 |
+
"learning_rate": 0.0001553478712357217,
|
| 596 |
+
"loss": 0.3155,
|
| 597 |
+
"step": 860
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9,
|
| 601 |
+
"learning_rate": 0.0001548286604361371,
|
| 602 |
+
"loss": 0.2737,
|
| 603 |
+
"step": 870
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.91,
|
| 607 |
+
"learning_rate": 0.00015430944963655245,
|
| 608 |
+
"loss": 0.2564,
|
| 609 |
+
"step": 880
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.92,
|
| 613 |
+
"learning_rate": 0.0001537902388369678,
|
| 614 |
+
"loss": 0.2587,
|
| 615 |
+
"step": 890
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.93,
|
| 619 |
+
"learning_rate": 0.00015327102803738317,
|
| 620 |
+
"loss": 0.2854,
|
| 621 |
+
"step": 900
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.93,
|
| 625 |
+
"eval_accuracy": 0.9006211180124224,
|
| 626 |
+
"eval_loss": 0.2561000883579254,
|
| 627 |
+
"eval_runtime": 107.0006,
|
| 628 |
+
"eval_samples_per_second": 61.691,
|
| 629 |
+
"eval_steps_per_second": 7.72,
|
| 630 |
+
"step": 900
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.94,
|
| 634 |
+
"learning_rate": 0.00015275181723779855,
|
| 635 |
+
"loss": 0.2348,
|
| 636 |
+
"step": 910
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.96,
|
| 640 |
+
"learning_rate": 0.00015223260643821394,
|
| 641 |
+
"loss": 0.2356,
|
| 642 |
+
"step": 920
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.97,
|
| 646 |
+
"learning_rate": 0.0001517133956386293,
|
| 647 |
+
"loss": 0.2324,
|
| 648 |
+
"step": 930
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.98,
|
| 652 |
+
"learning_rate": 0.00015119418483904465,
|
| 653 |
+
"loss": 0.265,
|
| 654 |
+
"step": 940
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.99,
|
| 658 |
+
"learning_rate": 0.00015067497403946004,
|
| 659 |
+
"loss": 0.2554,
|
| 660 |
+
"step": 950
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.0,
|
| 664 |
+
"learning_rate": 0.0001501557632398754,
|
| 665 |
+
"loss": 0.2845,
|
| 666 |
+
"step": 960
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.01,
|
| 670 |
+
"learning_rate": 0.00014963655244029075,
|
| 671 |
+
"loss": 0.3135,
|
| 672 |
+
"step": 970
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.02,
|
| 676 |
+
"learning_rate": 0.00014911734164070614,
|
| 677 |
+
"loss": 0.1335,
|
| 678 |
+
"step": 980
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.03,
|
| 682 |
+
"learning_rate": 0.0001485981308411215,
|
| 683 |
+
"loss": 0.3072,
|
| 684 |
+
"step": 990
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.04,
|
| 688 |
+
"learning_rate": 0.00014807892004153688,
|
| 689 |
+
"loss": 0.2594,
|
| 690 |
+
"step": 1000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.04,
|
| 694 |
+
"eval_accuracy": 0.9019845477957885,
|
| 695 |
+
"eval_loss": 0.26812365651130676,
|
| 696 |
+
"eval_runtime": 106.2371,
|
| 697 |
+
"eval_samples_per_second": 62.135,
|
| 698 |
+
"eval_steps_per_second": 7.775,
|
| 699 |
+
"step": 1000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.05,
|
| 703 |
+
"learning_rate": 0.00014755970924195224,
|
| 704 |
+
"loss": 0.1768,
|
| 705 |
+
"step": 1010
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.06,
|
| 709 |
+
"learning_rate": 0.0001470404984423676,
|
| 710 |
+
"loss": 0.187,
|
| 711 |
+
"step": 1020
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.07,
|
| 715 |
+
"learning_rate": 0.00014652128764278298,
|
| 716 |
+
"loss": 0.1335,
|
| 717 |
+
"step": 1030
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.08,
|
| 721 |
+
"learning_rate": 0.00014600207684319837,
|
| 722 |
+
"loss": 0.1969,
|
| 723 |
+
"step": 1040
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.09,
|
| 727 |
+
"learning_rate": 0.00014548286604361372,
|
| 728 |
+
"loss": 0.228,
|
| 729 |
+
"step": 1050
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.1,
|
| 733 |
+
"learning_rate": 0.00014496365524402908,
|
| 734 |
+
"loss": 0.1665,
|
| 735 |
+
"step": 1060
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.11,
|
| 739 |
+
"learning_rate": 0.00014444444444444444,
|
| 740 |
+
"loss": 0.1743,
|
| 741 |
+
"step": 1070
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.12,
|
| 745 |
+
"learning_rate": 0.00014392523364485982,
|
| 746 |
+
"loss": 0.228,
|
| 747 |
+
"step": 1080
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.13,
|
| 751 |
+
"learning_rate": 0.00014340602284527518,
|
| 752 |
+
"loss": 0.1356,
|
| 753 |
+
"step": 1090
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.14,
|
| 757 |
+
"learning_rate": 0.00014288681204569056,
|
| 758 |
+
"loss": 0.177,
|
| 759 |
+
"step": 1100
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.14,
|
| 763 |
+
"eval_accuracy": 0.8772913194970459,
|
| 764 |
+
"eval_loss": 0.3406391143798828,
|
| 765 |
+
"eval_runtime": 105.7842,
|
| 766 |
+
"eval_samples_per_second": 62.401,
|
| 767 |
+
"eval_steps_per_second": 7.808,
|
| 768 |
+
"step": 1100
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.15,
|
| 772 |
+
"learning_rate": 0.00014236760124610592,
|
| 773 |
+
"loss": 0.1793,
|
| 774 |
+
"step": 1110
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.16,
|
| 778 |
+
"learning_rate": 0.0001418483904465213,
|
| 779 |
+
"loss": 0.2743,
|
| 780 |
+
"step": 1120
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.17,
|
| 784 |
+
"learning_rate": 0.00014132917964693666,
|
| 785 |
+
"loss": 0.3143,
|
| 786 |
+
"step": 1130
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.18,
|
| 790 |
+
"learning_rate": 0.00014080996884735202,
|
| 791 |
+
"loss": 0.1482,
|
| 792 |
+
"step": 1140
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.19,
|
| 796 |
+
"learning_rate": 0.00014029075804776738,
|
| 797 |
+
"loss": 0.1937,
|
| 798 |
+
"step": 1150
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.2,
|
| 802 |
+
"learning_rate": 0.00013977154724818276,
|
| 803 |
+
"loss": 0.1386,
|
| 804 |
+
"step": 1160
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.21,
|
| 808 |
+
"learning_rate": 0.00013925233644859815,
|
| 809 |
+
"loss": 0.1427,
|
| 810 |
+
"step": 1170
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.23,
|
| 814 |
+
"learning_rate": 0.0001387331256490135,
|
| 815 |
+
"loss": 0.1565,
|
| 816 |
+
"step": 1180
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.24,
|
| 820 |
+
"learning_rate": 0.00013821391484942886,
|
| 821 |
+
"loss": 0.2196,
|
| 822 |
+
"step": 1190
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.25,
|
| 826 |
+
"learning_rate": 0.00013769470404984425,
|
| 827 |
+
"loss": 0.2717,
|
| 828 |
+
"step": 1200
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.25,
|
| 832 |
+
"eval_accuracy": 0.917133767610968,
|
| 833 |
+
"eval_loss": 0.22659926116466522,
|
| 834 |
+
"eval_runtime": 105.225,
|
| 835 |
+
"eval_samples_per_second": 62.732,
|
| 836 |
+
"eval_steps_per_second": 7.85,
|
| 837 |
+
"step": 1200
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.26,
|
| 841 |
+
"learning_rate": 0.0001371754932502596,
|
| 842 |
+
"loss": 0.2137,
|
| 843 |
+
"step": 1210
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.27,
|
| 847 |
+
"learning_rate": 0.000136656282450675,
|
| 848 |
+
"loss": 0.1641,
|
| 849 |
+
"step": 1220
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.28,
|
| 853 |
+
"learning_rate": 0.00013613707165109035,
|
| 854 |
+
"loss": 0.1665,
|
| 855 |
+
"step": 1230
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.29,
|
| 859 |
+
"learning_rate": 0.0001356178608515057,
|
| 860 |
+
"loss": 0.1631,
|
| 861 |
+
"step": 1240
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.3,
|
| 865 |
+
"learning_rate": 0.0001350986500519211,
|
| 866 |
+
"loss": 0.2048,
|
| 867 |
+
"step": 1250
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.31,
|
| 871 |
+
"learning_rate": 0.00013457943925233645,
|
| 872 |
+
"loss": 0.1899,
|
| 873 |
+
"step": 1260
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.32,
|
| 877 |
+
"learning_rate": 0.0001340602284527518,
|
| 878 |
+
"loss": 0.1521,
|
| 879 |
+
"step": 1270
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.33,
|
| 883 |
+
"learning_rate": 0.0001335410176531672,
|
| 884 |
+
"loss": 0.1784,
|
| 885 |
+
"step": 1280
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.34,
|
| 889 |
+
"learning_rate": 0.00013302180685358258,
|
| 890 |
+
"loss": 0.122,
|
| 891 |
+
"step": 1290
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.35,
|
| 895 |
+
"learning_rate": 0.00013250259605399793,
|
| 896 |
+
"loss": 0.2197,
|
| 897 |
+
"step": 1300
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.35,
|
| 901 |
+
"eval_accuracy": 0.9236479321314952,
|
| 902 |
+
"eval_loss": 0.20801472663879395,
|
| 903 |
+
"eval_runtime": 105.552,
|
| 904 |
+
"eval_samples_per_second": 62.538,
|
| 905 |
+
"eval_steps_per_second": 7.826,
|
| 906 |
+
"step": 1300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.36,
|
| 910 |
+
"learning_rate": 0.0001319833852544133,
|
| 911 |
+
"loss": 0.0729,
|
| 912 |
+
"step": 1310
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.37,
|
| 916 |
+
"learning_rate": 0.00013146417445482865,
|
| 917 |
+
"loss": 0.2226,
|
| 918 |
+
"step": 1320
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 1.38,
|
| 922 |
+
"learning_rate": 0.00013094496365524403,
|
| 923 |
+
"loss": 0.1275,
|
| 924 |
+
"step": 1330
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.39,
|
| 928 |
+
"learning_rate": 0.00013042575285565942,
|
| 929 |
+
"loss": 0.2397,
|
| 930 |
+
"step": 1340
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.4,
|
| 934 |
+
"learning_rate": 0.00012990654205607478,
|
| 935 |
+
"loss": 0.153,
|
| 936 |
+
"step": 1350
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 1.41,
|
| 940 |
+
"learning_rate": 0.00012938733125649013,
|
| 941 |
+
"loss": 0.178,
|
| 942 |
+
"step": 1360
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 1.42,
|
| 946 |
+
"learning_rate": 0.00012886812045690552,
|
| 947 |
+
"loss": 0.2325,
|
| 948 |
+
"step": 1370
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.43,
|
| 952 |
+
"learning_rate": 0.00012834890965732088,
|
| 953 |
+
"loss": 0.2731,
|
| 954 |
+
"step": 1380
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.44,
|
| 958 |
+
"learning_rate": 0.00012782969885773626,
|
| 959 |
+
"loss": 0.1804,
|
| 960 |
+
"step": 1390
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.45,
|
| 964 |
+
"learning_rate": 0.00012731048805815162,
|
| 965 |
+
"loss": 0.155,
|
| 966 |
+
"step": 1400
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 1.45,
|
| 970 |
+
"eval_accuracy": 0.9236479321314952,
|
| 971 |
+
"eval_loss": 0.20478595793247223,
|
| 972 |
+
"eval_runtime": 104.1144,
|
| 973 |
+
"eval_samples_per_second": 63.401,
|
| 974 |
+
"eval_steps_per_second": 7.934,
|
| 975 |
+
"step": 1400
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.46,
|
| 979 |
+
"learning_rate": 0.00012679127725856698,
|
| 980 |
+
"loss": 0.1645,
|
| 981 |
+
"step": 1410
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.47,
|
| 985 |
+
"learning_rate": 0.00012627206645898236,
|
| 986 |
+
"loss": 0.2205,
|
| 987 |
+
"step": 1420
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.48,
|
| 991 |
+
"learning_rate": 0.00012575285565939772,
|
| 992 |
+
"loss": 0.1507,
|
| 993 |
+
"step": 1430
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.5,
|
| 997 |
+
"learning_rate": 0.00012523364485981308,
|
| 998 |
+
"loss": 0.4007,
|
| 999 |
+
"step": 1440
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.51,
|
| 1003 |
+
"learning_rate": 0.00012471443406022846,
|
| 1004 |
+
"loss": 0.1829,
|
| 1005 |
+
"step": 1450
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.52,
|
| 1009 |
+
"learning_rate": 0.00012419522326064384,
|
| 1010 |
+
"loss": 0.1755,
|
| 1011 |
+
"step": 1460
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.53,
|
| 1015 |
+
"learning_rate": 0.0001236760124610592,
|
| 1016 |
+
"loss": 0.0943,
|
| 1017 |
+
"step": 1470
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.54,
|
| 1021 |
+
"learning_rate": 0.00012315680166147456,
|
| 1022 |
+
"loss": 0.1359,
|
| 1023 |
+
"step": 1480
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.55,
|
| 1027 |
+
"learning_rate": 0.00012263759086188992,
|
| 1028 |
+
"loss": 0.2615,
|
| 1029 |
+
"step": 1490
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.56,
|
| 1033 |
+
"learning_rate": 0.0001221183800623053,
|
| 1034 |
+
"loss": 0.2657,
|
| 1035 |
+
"step": 1500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.56,
|
| 1039 |
+
"eval_accuracy": 0.9256173307074685,
|
| 1040 |
+
"eval_loss": 0.2036730796098709,
|
| 1041 |
+
"eval_runtime": 104.5196,
|
| 1042 |
+
"eval_samples_per_second": 63.156,
|
| 1043 |
+
"eval_steps_per_second": 7.903,
|
| 1044 |
+
"step": 1500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.57,
|
| 1048 |
+
"learning_rate": 0.00012159916926272067,
|
| 1049 |
+
"loss": 0.1653,
|
| 1050 |
+
"step": 1510
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.58,
|
| 1054 |
+
"learning_rate": 0.00012107995846313604,
|
| 1055 |
+
"loss": 0.2066,
|
| 1056 |
+
"step": 1520
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.59,
|
| 1060 |
+
"learning_rate": 0.00012056074766355142,
|
| 1061 |
+
"loss": 0.1706,
|
| 1062 |
+
"step": 1530
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.6,
|
| 1066 |
+
"learning_rate": 0.00012004153686396677,
|
| 1067 |
+
"loss": 0.2103,
|
| 1068 |
+
"step": 1540
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 1.61,
|
| 1072 |
+
"learning_rate": 0.00011952232606438214,
|
| 1073 |
+
"loss": 0.2336,
|
| 1074 |
+
"step": 1550
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.62,
|
| 1078 |
+
"learning_rate": 0.0001190031152647975,
|
| 1079 |
+
"loss": 0.1792,
|
| 1080 |
+
"step": 1560
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.63,
|
| 1084 |
+
"learning_rate": 0.00011848390446521289,
|
| 1085 |
+
"loss": 0.0966,
|
| 1086 |
+
"step": 1570
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.64,
|
| 1090 |
+
"learning_rate": 0.00011796469366562826,
|
| 1091 |
+
"loss": 0.1713,
|
| 1092 |
+
"step": 1580
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 1.65,
|
| 1096 |
+
"learning_rate": 0.00011744548286604362,
|
| 1097 |
+
"loss": 0.1289,
|
| 1098 |
+
"step": 1590
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.66,
|
| 1102 |
+
"learning_rate": 0.00011692627206645899,
|
| 1103 |
+
"loss": 0.118,
|
| 1104 |
+
"step": 1600
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.66,
|
| 1108 |
+
"eval_accuracy": 0.9095591577033783,
|
| 1109 |
+
"eval_loss": 0.26160144805908203,
|
| 1110 |
+
"eval_runtime": 104.9104,
|
| 1111 |
+
"eval_samples_per_second": 62.92,
|
| 1112 |
+
"eval_steps_per_second": 7.873,
|
| 1113 |
+
"step": 1600
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.67,
|
| 1117 |
+
"learning_rate": 0.00011640706126687434,
|
| 1118 |
+
"loss": 0.1872,
|
| 1119 |
+
"step": 1610
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.68,
|
| 1123 |
+
"learning_rate": 0.00011588785046728972,
|
| 1124 |
+
"loss": 0.152,
|
| 1125 |
+
"step": 1620
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.69,
|
| 1129 |
+
"learning_rate": 0.0001153686396677051,
|
| 1130 |
+
"loss": 0.1337,
|
| 1131 |
+
"step": 1630
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.7,
|
| 1135 |
+
"learning_rate": 0.00011484942886812047,
|
| 1136 |
+
"loss": 0.1553,
|
| 1137 |
+
"step": 1640
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.71,
|
| 1141 |
+
"learning_rate": 0.00011433021806853583,
|
| 1142 |
+
"loss": 0.1428,
|
| 1143 |
+
"step": 1650
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.72,
|
| 1147 |
+
"learning_rate": 0.0001138110072689512,
|
| 1148 |
+
"loss": 0.1911,
|
| 1149 |
+
"step": 1660
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.73,
|
| 1153 |
+
"learning_rate": 0.00011329179646936656,
|
| 1154 |
+
"loss": 0.1263,
|
| 1155 |
+
"step": 1670
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.74,
|
| 1159 |
+
"learning_rate": 0.00011277258566978193,
|
| 1160 |
+
"loss": 0.1414,
|
| 1161 |
+
"step": 1680
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.75,
|
| 1165 |
+
"learning_rate": 0.00011225337487019731,
|
| 1166 |
+
"loss": 0.2111,
|
| 1167 |
+
"step": 1690
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 1.77,
|
| 1171 |
+
"learning_rate": 0.00011173416407061268,
|
| 1172 |
+
"loss": 0.1823,
|
| 1173 |
+
"step": 1700
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 1.77,
|
| 1177 |
+
"eval_accuracy": 0.9241024087259506,
|
| 1178 |
+
"eval_loss": 0.21581591665744781,
|
| 1179 |
+
"eval_runtime": 104.5278,
|
| 1180 |
+
"eval_samples_per_second": 63.151,
|
| 1181 |
+
"eval_steps_per_second": 7.902,
|
| 1182 |
+
"step": 1700
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.78,
|
| 1186 |
+
"learning_rate": 0.00011121495327102804,
|
| 1187 |
+
"loss": 0.1266,
|
| 1188 |
+
"step": 1710
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 1.79,
|
| 1192 |
+
"learning_rate": 0.00011069574247144341,
|
| 1193 |
+
"loss": 0.1765,
|
| 1194 |
+
"step": 1720
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.8,
|
| 1198 |
+
"learning_rate": 0.00011017653167185877,
|
| 1199 |
+
"loss": 0.1983,
|
| 1200 |
+
"step": 1730
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.81,
|
| 1204 |
+
"learning_rate": 0.00010965732087227414,
|
| 1205 |
+
"loss": 0.253,
|
| 1206 |
+
"step": 1740
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.82,
|
| 1210 |
+
"learning_rate": 0.00010913811007268953,
|
| 1211 |
+
"loss": 0.1542,
|
| 1212 |
+
"step": 1750
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 1.83,
|
| 1216 |
+
"learning_rate": 0.00010861889927310488,
|
| 1217 |
+
"loss": 0.1171,
|
| 1218 |
+
"step": 1760
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.84,
|
| 1222 |
+
"learning_rate": 0.00010809968847352026,
|
| 1223 |
+
"loss": 0.1701,
|
| 1224 |
+
"step": 1770
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.85,
|
| 1228 |
+
"learning_rate": 0.00010758047767393563,
|
| 1229 |
+
"loss": 0.1689,
|
| 1230 |
+
"step": 1780
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.86,
|
| 1234 |
+
"learning_rate": 0.00010706126687435098,
|
| 1235 |
+
"loss": 0.1405,
|
| 1236 |
+
"step": 1790
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.87,
|
| 1240 |
+
"learning_rate": 0.00010654205607476636,
|
| 1241 |
+
"loss": 0.2175,
|
| 1242 |
+
"step": 1800
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.87,
|
| 1246 |
+
"eval_accuracy": 0.9181942129980306,
|
| 1247 |
+
"eval_loss": 0.21594561636447906,
|
| 1248 |
+
"eval_runtime": 103.9435,
|
| 1249 |
+
"eval_samples_per_second": 63.506,
|
| 1250 |
+
"eval_steps_per_second": 7.947,
|
| 1251 |
+
"step": 1800
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 1.88,
|
| 1255 |
+
"learning_rate": 0.00010602284527518174,
|
| 1256 |
+
"loss": 0.1923,
|
| 1257 |
+
"step": 1810
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.89,
|
| 1261 |
+
"learning_rate": 0.0001055036344755971,
|
| 1262 |
+
"loss": 0.2476,
|
| 1263 |
+
"step": 1820
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.9,
|
| 1267 |
+
"learning_rate": 0.00010498442367601247,
|
| 1268 |
+
"loss": 0.2243,
|
| 1269 |
+
"step": 1830
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.91,
|
| 1273 |
+
"learning_rate": 0.00010446521287642783,
|
| 1274 |
+
"loss": 0.2611,
|
| 1275 |
+
"step": 1840
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.92,
|
| 1279 |
+
"learning_rate": 0.0001039460020768432,
|
| 1280 |
+
"loss": 0.2186,
|
| 1281 |
+
"step": 1850
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.93,
|
| 1285 |
+
"learning_rate": 0.00010342679127725856,
|
| 1286 |
+
"loss": 0.141,
|
| 1287 |
+
"step": 1860
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.94,
|
| 1291 |
+
"learning_rate": 0.00010290758047767395,
|
| 1292 |
+
"loss": 0.1086,
|
| 1293 |
+
"step": 1870
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 1.95,
|
| 1297 |
+
"learning_rate": 0.00010238836967808931,
|
| 1298 |
+
"loss": 0.1948,
|
| 1299 |
+
"step": 1880
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.96,
|
| 1303 |
+
"learning_rate": 0.00010186915887850468,
|
| 1304 |
+
"loss": 0.166,
|
| 1305 |
+
"step": 1890
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.97,
|
| 1309 |
+
"learning_rate": 0.00010134994807892004,
|
| 1310 |
+
"loss": 0.143,
|
| 1311 |
+
"step": 1900
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.97,
|
| 1315 |
+
"eval_accuracy": 0.9242539009241024,
|
| 1316 |
+
"eval_loss": 0.18984103202819824,
|
| 1317 |
+
"eval_runtime": 107.0187,
|
| 1318 |
+
"eval_samples_per_second": 61.681,
|
| 1319 |
+
"eval_steps_per_second": 7.718,
|
| 1320 |
+
"step": 1900
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.98,
|
| 1324 |
+
"learning_rate": 0.00010083073727933541,
|
| 1325 |
+
"loss": 0.1538,
|
| 1326 |
+
"step": 1910
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.99,
|
| 1330 |
+
"learning_rate": 0.00010031152647975077,
|
| 1331 |
+
"loss": 0.1682,
|
| 1332 |
+
"step": 1920
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.0,
|
| 1336 |
+
"learning_rate": 9.979231568016615e-05,
|
| 1337 |
+
"loss": 0.09,
|
| 1338 |
+
"step": 1930
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.01,
|
| 1342 |
+
"learning_rate": 9.927310488058152e-05,
|
| 1343 |
+
"loss": 0.0338,
|
| 1344 |
+
"step": 1940
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.02,
|
| 1348 |
+
"learning_rate": 9.87538940809969e-05,
|
| 1349 |
+
"loss": 0.1026,
|
| 1350 |
+
"step": 1950
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.04,
|
| 1354 |
+
"learning_rate": 9.823468328141225e-05,
|
| 1355 |
+
"loss": 0.1165,
|
| 1356 |
+
"step": 1960
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.05,
|
| 1360 |
+
"learning_rate": 9.771547248182762e-05,
|
| 1361 |
+
"loss": 0.0652,
|
| 1362 |
+
"step": 1970
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.06,
|
| 1366 |
+
"learning_rate": 9.7196261682243e-05,
|
| 1367 |
+
"loss": 0.1643,
|
| 1368 |
+
"step": 1980
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.07,
|
| 1372 |
+
"learning_rate": 9.667705088265837e-05,
|
| 1373 |
+
"loss": 0.0903,
|
| 1374 |
+
"step": 1990
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.08,
|
| 1378 |
+
"learning_rate": 9.615784008307374e-05,
|
| 1379 |
+
"loss": 0.1051,
|
| 1380 |
+
"step": 2000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 2.08,
|
| 1384 |
+
"eval_accuracy": 0.9225874867444327,
|
| 1385 |
+
"eval_loss": 0.23080797493457794,
|
| 1386 |
+
"eval_runtime": 105.3241,
|
| 1387 |
+
"eval_samples_per_second": 62.673,
|
| 1388 |
+
"eval_steps_per_second": 7.842,
|
| 1389 |
+
"step": 2000
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.09,
|
| 1393 |
+
"learning_rate": 9.56386292834891e-05,
|
| 1394 |
+
"loss": 0.1135,
|
| 1395 |
+
"step": 2010
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.1,
|
| 1399 |
+
"learning_rate": 9.511941848390447e-05,
|
| 1400 |
+
"loss": 0.0586,
|
| 1401 |
+
"step": 2020
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 2.11,
|
| 1405 |
+
"learning_rate": 9.460020768431984e-05,
|
| 1406 |
+
"loss": 0.1016,
|
| 1407 |
+
"step": 2030
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 2.12,
|
| 1411 |
+
"learning_rate": 9.408099688473521e-05,
|
| 1412 |
+
"loss": 0.0808,
|
| 1413 |
+
"step": 2040
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.13,
|
| 1417 |
+
"learning_rate": 9.356178608515057e-05,
|
| 1418 |
+
"loss": 0.0502,
|
| 1419 |
+
"step": 2050
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 2.14,
|
| 1423 |
+
"learning_rate": 9.304257528556595e-05,
|
| 1424 |
+
"loss": 0.0712,
|
| 1425 |
+
"step": 2060
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.15,
|
| 1429 |
+
"learning_rate": 9.252336448598131e-05,
|
| 1430 |
+
"loss": 0.0938,
|
| 1431 |
+
"step": 2070
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.16,
|
| 1435 |
+
"learning_rate": 9.200415368639668e-05,
|
| 1436 |
+
"loss": 0.0539,
|
| 1437 |
+
"step": 2080
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.17,
|
| 1441 |
+
"learning_rate": 9.148494288681205e-05,
|
| 1442 |
+
"loss": 0.1137,
|
| 1443 |
+
"step": 2090
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 2.18,
|
| 1447 |
+
"learning_rate": 9.096573208722742e-05,
|
| 1448 |
+
"loss": 0.1963,
|
| 1449 |
+
"step": 2100
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.18,
|
| 1453 |
+
"eval_accuracy": 0.9204665959703076,
|
| 1454 |
+
"eval_loss": 0.23536920547485352,
|
| 1455 |
+
"eval_runtime": 106.2404,
|
| 1456 |
+
"eval_samples_per_second": 62.133,
|
| 1457 |
+
"eval_steps_per_second": 7.775,
|
| 1458 |
+
"step": 2100
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.19,
|
| 1462 |
+
"learning_rate": 9.044652128764278e-05,
|
| 1463 |
+
"loss": 0.1132,
|
| 1464 |
+
"step": 2110
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 2.2,
|
| 1468 |
+
"learning_rate": 8.992731048805816e-05,
|
| 1469 |
+
"loss": 0.0318,
|
| 1470 |
+
"step": 2120
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 2.21,
|
| 1474 |
+
"learning_rate": 8.940809968847352e-05,
|
| 1475 |
+
"loss": 0.0562,
|
| 1476 |
+
"step": 2130
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 2.22,
|
| 1480 |
+
"learning_rate": 8.888888888888889e-05,
|
| 1481 |
+
"loss": 0.0991,
|
| 1482 |
+
"step": 2140
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 2.23,
|
| 1486 |
+
"learning_rate": 8.836967808930426e-05,
|
| 1487 |
+
"loss": 0.1263,
|
| 1488 |
+
"step": 2150
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.24,
|
| 1492 |
+
"learning_rate": 8.785046728971964e-05,
|
| 1493 |
+
"loss": 0.093,
|
| 1494 |
+
"step": 2160
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.25,
|
| 1498 |
+
"learning_rate": 8.733125649013499e-05,
|
| 1499 |
+
"loss": 0.0992,
|
| 1500 |
+
"step": 2170
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.26,
|
| 1504 |
+
"learning_rate": 8.681204569055036e-05,
|
| 1505 |
+
"loss": 0.0787,
|
| 1506 |
+
"step": 2180
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.27,
|
| 1510 |
+
"learning_rate": 8.629283489096574e-05,
|
| 1511 |
+
"loss": 0.1306,
|
| 1512 |
+
"step": 2190
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 2.28,
|
| 1516 |
+
"learning_rate": 8.577362409138109e-05,
|
| 1517 |
+
"loss": 0.0524,
|
| 1518 |
+
"step": 2200
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 2.28,
|
| 1522 |
+
"eval_accuracy": 0.9281926980760491,
|
| 1523 |
+
"eval_loss": 0.22982539236545563,
|
| 1524 |
+
"eval_runtime": 105.4663,
|
| 1525 |
+
"eval_samples_per_second": 62.589,
|
| 1526 |
+
"eval_steps_per_second": 7.832,
|
| 1527 |
+
"step": 2200
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 2.29,
|
| 1531 |
+
"learning_rate": 8.525441329179648e-05,
|
| 1532 |
+
"loss": 0.1902,
|
| 1533 |
+
"step": 2210
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 2.31,
|
| 1537 |
+
"learning_rate": 8.473520249221184e-05,
|
| 1538 |
+
"loss": 0.0755,
|
| 1539 |
+
"step": 2220
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 2.32,
|
| 1543 |
+
"learning_rate": 8.42159916926272e-05,
|
| 1544 |
+
"loss": 0.0826,
|
| 1545 |
+
"step": 2230
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 2.33,
|
| 1549 |
+
"learning_rate": 8.369678089304258e-05,
|
| 1550 |
+
"loss": 0.1252,
|
| 1551 |
+
"step": 2240
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.34,
|
| 1555 |
+
"learning_rate": 8.317757009345795e-05,
|
| 1556 |
+
"loss": 0.0848,
|
| 1557 |
+
"step": 2250
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.35,
|
| 1561 |
+
"learning_rate": 8.265835929387332e-05,
|
| 1562 |
+
"loss": 0.0134,
|
| 1563 |
+
"step": 2260
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.36,
|
| 1567 |
+
"learning_rate": 8.213914849428869e-05,
|
| 1568 |
+
"loss": 0.1297,
|
| 1569 |
+
"step": 2270
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 2.37,
|
| 1573 |
+
"learning_rate": 8.161993769470405e-05,
|
| 1574 |
+
"loss": 0.0633,
|
| 1575 |
+
"step": 2280
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 2.38,
|
| 1579 |
+
"learning_rate": 8.110072689511943e-05,
|
| 1580 |
+
"loss": 0.0625,
|
| 1581 |
+
"step": 2290
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 2.39,
|
| 1585 |
+
"learning_rate": 8.058151609553479e-05,
|
| 1586 |
+
"loss": 0.097,
|
| 1587 |
+
"step": 2300
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 2.39,
|
| 1591 |
+
"eval_accuracy": 0.9241024087259506,
|
| 1592 |
+
"eval_loss": 0.24952168762683868,
|
| 1593 |
+
"eval_runtime": 105.3776,
|
| 1594 |
+
"eval_samples_per_second": 62.641,
|
| 1595 |
+
"eval_steps_per_second": 7.838,
|
| 1596 |
+
"step": 2300
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 2.4,
|
| 1600 |
+
"learning_rate": 8.006230529595016e-05,
|
| 1601 |
+
"loss": 0.0439,
|
| 1602 |
+
"step": 2310
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 2.41,
|
| 1606 |
+
"learning_rate": 7.954309449636553e-05,
|
| 1607 |
+
"loss": 0.0743,
|
| 1608 |
+
"step": 2320
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.42,
|
| 1612 |
+
"learning_rate": 7.90238836967809e-05,
|
| 1613 |
+
"loss": 0.1643,
|
| 1614 |
+
"step": 2330
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.43,
|
| 1618 |
+
"learning_rate": 7.850467289719626e-05,
|
| 1619 |
+
"loss": 0.1348,
|
| 1620 |
+
"step": 2340
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.44,
|
| 1624 |
+
"learning_rate": 7.798546209761163e-05,
|
| 1625 |
+
"loss": 0.1049,
|
| 1626 |
+
"step": 2350
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.45,
|
| 1630 |
+
"learning_rate": 7.7466251298027e-05,
|
| 1631 |
+
"loss": 0.1646,
|
| 1632 |
+
"step": 2360
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 2.46,
|
| 1636 |
+
"learning_rate": 7.694704049844238e-05,
|
| 1637 |
+
"loss": 0.123,
|
| 1638 |
+
"step": 2370
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 2.47,
|
| 1642 |
+
"learning_rate": 7.642782969885775e-05,
|
| 1643 |
+
"loss": 0.0567,
|
| 1644 |
+
"step": 2380
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 2.48,
|
| 1648 |
+
"learning_rate": 7.59086188992731e-05,
|
| 1649 |
+
"loss": 0.1242,
|
| 1650 |
+
"step": 2390
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.49,
|
| 1654 |
+
"learning_rate": 7.538940809968848e-05,
|
| 1655 |
+
"loss": 0.0744,
|
| 1656 |
+
"step": 2400
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 2.49,
|
| 1660 |
+
"eval_accuracy": 0.9194061505832449,
|
| 1661 |
+
"eval_loss": 0.24930374324321747,
|
| 1662 |
+
"eval_runtime": 104.785,
|
| 1663 |
+
"eval_samples_per_second": 62.996,
|
| 1664 |
+
"eval_steps_per_second": 7.883,
|
| 1665 |
+
"step": 2400
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 2.5,
|
| 1669 |
+
"learning_rate": 7.487019730010385e-05,
|
| 1670 |
+
"loss": 0.0935,
|
| 1671 |
+
"step": 2410
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.51,
|
| 1675 |
+
"learning_rate": 7.435098650051922e-05,
|
| 1676 |
+
"loss": 0.0632,
|
| 1677 |
+
"step": 2420
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 2.52,
|
| 1681 |
+
"learning_rate": 7.383177570093458e-05,
|
| 1682 |
+
"loss": 0.0975,
|
| 1683 |
+
"step": 2430
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.53,
|
| 1687 |
+
"learning_rate": 7.331256490134996e-05,
|
| 1688 |
+
"loss": 0.0355,
|
| 1689 |
+
"step": 2440
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.54,
|
| 1693 |
+
"learning_rate": 7.279335410176532e-05,
|
| 1694 |
+
"loss": 0.0485,
|
| 1695 |
+
"step": 2450
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 2.55,
|
| 1699 |
+
"learning_rate": 7.227414330218069e-05,
|
| 1700 |
+
"loss": 0.0503,
|
| 1701 |
+
"step": 2460
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 2.56,
|
| 1705 |
+
"learning_rate": 7.175493250259606e-05,
|
| 1706 |
+
"loss": 0.0745,
|
| 1707 |
+
"step": 2470
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 2.58,
|
| 1711 |
+
"learning_rate": 7.123572170301143e-05,
|
| 1712 |
+
"loss": 0.1093,
|
| 1713 |
+
"step": 2480
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 2.59,
|
| 1717 |
+
"learning_rate": 7.071651090342679e-05,
|
| 1718 |
+
"loss": 0.0554,
|
| 1719 |
+
"step": 2490
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 2.6,
|
| 1723 |
+
"learning_rate": 7.019730010384217e-05,
|
| 1724 |
+
"loss": 0.0744,
|
| 1725 |
+
"step": 2500
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.6,
|
| 1729 |
+
"eval_accuracy": 0.9322829874261476,
|
| 1730 |
+
"eval_loss": 0.2428741455078125,
|
| 1731 |
+
"eval_runtime": 104.9683,
|
| 1732 |
+
"eval_samples_per_second": 62.886,
|
| 1733 |
+
"eval_steps_per_second": 7.869,
|
| 1734 |
+
"step": 2500
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 2.61,
|
| 1738 |
+
"learning_rate": 6.967808930425753e-05,
|
| 1739 |
+
"loss": 0.0998,
|
| 1740 |
+
"step": 2510
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 2.62,
|
| 1744 |
+
"learning_rate": 6.91588785046729e-05,
|
| 1745 |
+
"loss": 0.0561,
|
| 1746 |
+
"step": 2520
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.63,
|
| 1750 |
+
"learning_rate": 6.863966770508827e-05,
|
| 1751 |
+
"loss": 0.0452,
|
| 1752 |
+
"step": 2530
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.64,
|
| 1756 |
+
"learning_rate": 6.812045690550364e-05,
|
| 1757 |
+
"loss": 0.1821,
|
| 1758 |
+
"step": 2540
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 2.65,
|
| 1762 |
+
"learning_rate": 6.7601246105919e-05,
|
| 1763 |
+
"loss": 0.0598,
|
| 1764 |
+
"step": 2550
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 2.66,
|
| 1768 |
+
"learning_rate": 6.708203530633437e-05,
|
| 1769 |
+
"loss": 0.0722,
|
| 1770 |
+
"step": 2560
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 2.67,
|
| 1774 |
+
"learning_rate": 6.656282450674974e-05,
|
| 1775 |
+
"loss": 0.0532,
|
| 1776 |
+
"step": 2570
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 2.68,
|
| 1780 |
+
"learning_rate": 6.60436137071651e-05,
|
| 1781 |
+
"loss": 0.0644,
|
| 1782 |
+
"step": 2580
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 2.69,
|
| 1786 |
+
"learning_rate": 6.552440290758049e-05,
|
| 1787 |
+
"loss": 0.1235,
|
| 1788 |
+
"step": 2590
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.7,
|
| 1792 |
+
"learning_rate": 6.500519210799584e-05,
|
| 1793 |
+
"loss": 0.0345,
|
| 1794 |
+
"step": 2600
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.7,
|
| 1798 |
+
"eval_accuracy": 0.9251628541130131,
|
| 1799 |
+
"eval_loss": 0.2586543560028076,
|
| 1800 |
+
"eval_runtime": 104.6212,
|
| 1801 |
+
"eval_samples_per_second": 63.094,
|
| 1802 |
+
"eval_steps_per_second": 7.895,
|
| 1803 |
+
"step": 2600
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.71,
|
| 1807 |
+
"learning_rate": 6.448598130841122e-05,
|
| 1808 |
+
"loss": 0.1686,
|
| 1809 |
+
"step": 2610
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.72,
|
| 1813 |
+
"learning_rate": 6.396677050882659e-05,
|
| 1814 |
+
"loss": 0.0775,
|
| 1815 |
+
"step": 2620
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.73,
|
| 1819 |
+
"learning_rate": 6.344755970924196e-05,
|
| 1820 |
+
"loss": 0.0956,
|
| 1821 |
+
"step": 2630
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 2.74,
|
| 1825 |
+
"learning_rate": 6.292834890965732e-05,
|
| 1826 |
+
"loss": 0.135,
|
| 1827 |
+
"step": 2640
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 2.75,
|
| 1831 |
+
"learning_rate": 6.24091381100727e-05,
|
| 1832 |
+
"loss": 0.1582,
|
| 1833 |
+
"step": 2650
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 2.76,
|
| 1837 |
+
"learning_rate": 6.188992731048806e-05,
|
| 1838 |
+
"loss": 0.0668,
|
| 1839 |
+
"step": 2660
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 2.77,
|
| 1843 |
+
"learning_rate": 6.137071651090343e-05,
|
| 1844 |
+
"loss": 0.1317,
|
| 1845 |
+
"step": 2670
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 2.78,
|
| 1849 |
+
"learning_rate": 6.08515057113188e-05,
|
| 1850 |
+
"loss": 0.0756,
|
| 1851 |
+
"step": 2680
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.79,
|
| 1855 |
+
"learning_rate": 6.0332294911734164e-05,
|
| 1856 |
+
"loss": 0.0565,
|
| 1857 |
+
"step": 2690
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.8,
|
| 1861 |
+
"learning_rate": 5.981308411214953e-05,
|
| 1862 |
+
"loss": 0.0097,
|
| 1863 |
+
"step": 2700
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 2.8,
|
| 1867 |
+
"eval_accuracy": 0.9265262838963794,
|
| 1868 |
+
"eval_loss": 0.22841490805149078,
|
| 1869 |
+
"eval_runtime": 104.4263,
|
| 1870 |
+
"eval_samples_per_second": 63.212,
|
| 1871 |
+
"eval_steps_per_second": 7.91,
|
| 1872 |
+
"step": 2700
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.81,
|
| 1876 |
+
"learning_rate": 5.9293873312564906e-05,
|
| 1877 |
+
"loss": 0.0621,
|
| 1878 |
+
"step": 2710
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.82,
|
| 1882 |
+
"learning_rate": 5.877466251298027e-05,
|
| 1883 |
+
"loss": 0.0684,
|
| 1884 |
+
"step": 2720
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 2.83,
|
| 1888 |
+
"learning_rate": 5.8255451713395635e-05,
|
| 1889 |
+
"loss": 0.0408,
|
| 1890 |
+
"step": 2730
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 2.85,
|
| 1894 |
+
"learning_rate": 5.773624091381101e-05,
|
| 1895 |
+
"loss": 0.1156,
|
| 1896 |
+
"step": 2740
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 2.86,
|
| 1900 |
+
"learning_rate": 5.721703011422638e-05,
|
| 1901 |
+
"loss": 0.0228,
|
| 1902 |
+
"step": 2750
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 2.87,
|
| 1906 |
+
"learning_rate": 5.669781931464174e-05,
|
| 1907 |
+
"loss": 0.1417,
|
| 1908 |
+
"step": 2760
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 2.88,
|
| 1912 |
+
"learning_rate": 5.617860851505712e-05,
|
| 1913 |
+
"loss": 0.0443,
|
| 1914 |
+
"step": 2770
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.89,
|
| 1918 |
+
"learning_rate": 5.5659397715472484e-05,
|
| 1919 |
+
"loss": 0.0903,
|
| 1920 |
+
"step": 2780
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.9,
|
| 1924 |
+
"learning_rate": 5.514018691588785e-05,
|
| 1925 |
+
"loss": 0.0395,
|
| 1926 |
+
"step": 2790
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 2.91,
|
| 1930 |
+
"learning_rate": 5.4620976116303226e-05,
|
| 1931 |
+
"loss": 0.0775,
|
| 1932 |
+
"step": 2800
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 2.91,
|
| 1936 |
+
"eval_accuracy": 0.9321314952279958,
|
| 1937 |
+
"eval_loss": 0.22424499690532684,
|
| 1938 |
+
"eval_runtime": 104.7535,
|
| 1939 |
+
"eval_samples_per_second": 63.015,
|
| 1940 |
+
"eval_steps_per_second": 7.885,
|
| 1941 |
+
"step": 2800
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.92,
|
| 1945 |
+
"learning_rate": 5.410176531671859e-05,
|
| 1946 |
+
"loss": 0.0281,
|
| 1947 |
+
"step": 2810
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 2.93,
|
| 1951 |
+
"learning_rate": 5.3582554517133955e-05,
|
| 1952 |
+
"loss": 0.0756,
|
| 1953 |
+
"step": 2820
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 2.94,
|
| 1957 |
+
"learning_rate": 5.306334371754933e-05,
|
| 1958 |
+
"loss": 0.083,
|
| 1959 |
+
"step": 2830
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 2.95,
|
| 1963 |
+
"learning_rate": 5.25441329179647e-05,
|
| 1964 |
+
"loss": 0.0804,
|
| 1965 |
+
"step": 2840
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 2.96,
|
| 1969 |
+
"learning_rate": 5.202492211838006e-05,
|
| 1970 |
+
"loss": 0.068,
|
| 1971 |
+
"step": 2850
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 2.97,
|
| 1975 |
+
"learning_rate": 5.150571131879543e-05,
|
| 1976 |
+
"loss": 0.0549,
|
| 1977 |
+
"step": 2860
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.98,
|
| 1981 |
+
"learning_rate": 5.09865005192108e-05,
|
| 1982 |
+
"loss": 0.1113,
|
| 1983 |
+
"step": 2870
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 2.99,
|
| 1987 |
+
"learning_rate": 5.046728971962617e-05,
|
| 1988 |
+
"loss": 0.1297,
|
| 1989 |
+
"step": 2880
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 3.0,
|
| 1993 |
+
"learning_rate": 4.994807892004154e-05,
|
| 1994 |
+
"loss": 0.0397,
|
| 1995 |
+
"step": 2890
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 3.01,
|
| 1999 |
+
"learning_rate": 4.9428868120456904e-05,
|
| 2000 |
+
"loss": 0.0634,
|
| 2001 |
+
"step": 2900
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.01,
|
| 2005 |
+
"eval_accuracy": 0.9286471746705045,
|
| 2006 |
+
"eval_loss": 0.23135913908481598,
|
| 2007 |
+
"eval_runtime": 104.8164,
|
| 2008 |
+
"eval_samples_per_second": 62.977,
|
| 2009 |
+
"eval_steps_per_second": 7.88,
|
| 2010 |
+
"step": 2900
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 3.02,
|
| 2014 |
+
"learning_rate": 4.8909657320872275e-05,
|
| 2015 |
+
"loss": 0.02,
|
| 2016 |
+
"step": 2910
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 3.03,
|
| 2020 |
+
"learning_rate": 4.8390446521287646e-05,
|
| 2021 |
+
"loss": 0.0324,
|
| 2022 |
+
"step": 2920
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.04,
|
| 2026 |
+
"learning_rate": 4.787123572170301e-05,
|
| 2027 |
+
"loss": 0.0064,
|
| 2028 |
+
"step": 2930
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 3.05,
|
| 2032 |
+
"learning_rate": 4.735202492211838e-05,
|
| 2033 |
+
"loss": 0.0063,
|
| 2034 |
+
"step": 2940
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 3.06,
|
| 2038 |
+
"learning_rate": 4.683281412253375e-05,
|
| 2039 |
+
"loss": 0.0372,
|
| 2040 |
+
"step": 2950
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 3.07,
|
| 2044 |
+
"learning_rate": 4.631360332294912e-05,
|
| 2045 |
+
"loss": 0.0679,
|
| 2046 |
+
"step": 2960
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 3.08,
|
| 2050 |
+
"learning_rate": 4.579439252336449e-05,
|
| 2051 |
+
"loss": 0.0517,
|
| 2052 |
+
"step": 2970
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 3.09,
|
| 2056 |
+
"learning_rate": 4.527518172377986e-05,
|
| 2057 |
+
"loss": 0.097,
|
| 2058 |
+
"step": 2980
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.1,
|
| 2062 |
+
"learning_rate": 4.4755970924195224e-05,
|
| 2063 |
+
"loss": 0.1,
|
| 2064 |
+
"step": 2990
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 3.12,
|
| 2068 |
+
"learning_rate": 4.4236760124610595e-05,
|
| 2069 |
+
"loss": 0.0109,
|
| 2070 |
+
"step": 3000
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 3.12,
|
| 2074 |
+
"eval_accuracy": 0.9337979094076655,
|
| 2075 |
+
"eval_loss": 0.22030013799667358,
|
| 2076 |
+
"eval_runtime": 105.6713,
|
| 2077 |
+
"eval_samples_per_second": 62.467,
|
| 2078 |
+
"eval_steps_per_second": 7.817,
|
| 2079 |
+
"step": 3000
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 3.13,
|
| 2083 |
+
"learning_rate": 4.3717549325025966e-05,
|
| 2084 |
+
"loss": 0.0143,
|
| 2085 |
+
"step": 3010
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 3.14,
|
| 2089 |
+
"learning_rate": 4.319833852544133e-05,
|
| 2090 |
+
"loss": 0.0638,
|
| 2091 |
+
"step": 3020
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 3.15,
|
| 2095 |
+
"learning_rate": 4.26791277258567e-05,
|
| 2096 |
+
"loss": 0.0213,
|
| 2097 |
+
"step": 3030
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 3.16,
|
| 2101 |
+
"learning_rate": 4.2159916926272066e-05,
|
| 2102 |
+
"loss": 0.0153,
|
| 2103 |
+
"step": 3040
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 3.17,
|
| 2107 |
+
"learning_rate": 4.164070612668744e-05,
|
| 2108 |
+
"loss": 0.0052,
|
| 2109 |
+
"step": 3050
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 3.18,
|
| 2113 |
+
"learning_rate": 4.11214953271028e-05,
|
| 2114 |
+
"loss": 0.0406,
|
| 2115 |
+
"step": 3060
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 3.19,
|
| 2119 |
+
"learning_rate": 4.060228452751817e-05,
|
| 2120 |
+
"loss": 0.0109,
|
| 2121 |
+
"step": 3070
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 3.2,
|
| 2125 |
+
"learning_rate": 4.0083073727933544e-05,
|
| 2126 |
+
"loss": 0.0058,
|
| 2127 |
+
"step": 3080
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 3.21,
|
| 2131 |
+
"learning_rate": 3.956386292834891e-05,
|
| 2132 |
+
"loss": 0.005,
|
| 2133 |
+
"step": 3090
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 3.22,
|
| 2137 |
+
"learning_rate": 3.904465212876428e-05,
|
| 2138 |
+
"loss": 0.0039,
|
| 2139 |
+
"step": 3100
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 3.22,
|
| 2143 |
+
"eval_accuracy": 0.9357673079836388,
|
| 2144 |
+
"eval_loss": 0.2575285732746124,
|
| 2145 |
+
"eval_runtime": 105.4895,
|
| 2146 |
+
"eval_samples_per_second": 62.575,
|
| 2147 |
+
"eval_steps_per_second": 7.83,
|
| 2148 |
+
"step": 3100
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 3.23,
|
| 2152 |
+
"learning_rate": 3.852544132917965e-05,
|
| 2153 |
+
"loss": 0.0284,
|
| 2154 |
+
"step": 3110
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 3.24,
|
| 2158 |
+
"learning_rate": 3.8006230529595015e-05,
|
| 2159 |
+
"loss": 0.0042,
|
| 2160 |
+
"step": 3120
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 3.25,
|
| 2164 |
+
"learning_rate": 3.7487019730010386e-05,
|
| 2165 |
+
"loss": 0.0407,
|
| 2166 |
+
"step": 3130
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.26,
|
| 2170 |
+
"learning_rate": 3.696780893042576e-05,
|
| 2171 |
+
"loss": 0.009,
|
| 2172 |
+
"step": 3140
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 3.27,
|
| 2176 |
+
"learning_rate": 3.644859813084112e-05,
|
| 2177 |
+
"loss": 0.0342,
|
| 2178 |
+
"step": 3150
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 3.28,
|
| 2182 |
+
"learning_rate": 3.592938733125649e-05,
|
| 2183 |
+
"loss": 0.056,
|
| 2184 |
+
"step": 3160
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 3.29,
|
| 2188 |
+
"learning_rate": 3.5410176531671864e-05,
|
| 2189 |
+
"loss": 0.0384,
|
| 2190 |
+
"step": 3170
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 3.3,
|
| 2194 |
+
"learning_rate": 3.489096573208723e-05,
|
| 2195 |
+
"loss": 0.0319,
|
| 2196 |
+
"step": 3180
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 3.31,
|
| 2200 |
+
"learning_rate": 3.43717549325026e-05,
|
| 2201 |
+
"loss": 0.0619,
|
| 2202 |
+
"step": 3190
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 3.32,
|
| 2206 |
+
"learning_rate": 3.385254413291797e-05,
|
| 2207 |
+
"loss": 0.0139,
|
| 2208 |
+
"step": 3200
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 3.32,
|
| 2212 |
+
"eval_accuracy": 0.935615815785487,
|
| 2213 |
+
"eval_loss": 0.25701212882995605,
|
| 2214 |
+
"eval_runtime": 105.4027,
|
| 2215 |
+
"eval_samples_per_second": 62.626,
|
| 2216 |
+
"eval_steps_per_second": 7.837,
|
| 2217 |
+
"step": 3200
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 3.33,
|
| 2221 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 2222 |
+
"loss": 0.0035,
|
| 2223 |
+
"step": 3210
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 3.34,
|
| 2227 |
+
"learning_rate": 3.2814122533748706e-05,
|
| 2228 |
+
"loss": 0.0232,
|
| 2229 |
+
"step": 3220
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 3.35,
|
| 2233 |
+
"learning_rate": 3.229491173416408e-05,
|
| 2234 |
+
"loss": 0.0078,
|
| 2235 |
+
"step": 3230
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 3.36,
|
| 2239 |
+
"learning_rate": 3.177570093457944e-05,
|
| 2240 |
+
"loss": 0.041,
|
| 2241 |
+
"step": 3240
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 3.37,
|
| 2245 |
+
"learning_rate": 3.1256490134994806e-05,
|
| 2246 |
+
"loss": 0.0408,
|
| 2247 |
+
"step": 3250
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 3.39,
|
| 2251 |
+
"learning_rate": 3.073727933541018e-05,
|
| 2252 |
+
"loss": 0.0372,
|
| 2253 |
+
"step": 3260
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 3.4,
|
| 2257 |
+
"learning_rate": 3.0218068535825545e-05,
|
| 2258 |
+
"loss": 0.0639,
|
| 2259 |
+
"step": 3270
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 3.41,
|
| 2263 |
+
"learning_rate": 2.9698857736240916e-05,
|
| 2264 |
+
"loss": 0.0205,
|
| 2265 |
+
"step": 3280
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 3.42,
|
| 2269 |
+
"learning_rate": 2.9179646936656284e-05,
|
| 2270 |
+
"loss": 0.0579,
|
| 2271 |
+
"step": 3290
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 3.43,
|
| 2275 |
+
"learning_rate": 2.866043613707165e-05,
|
| 2276 |
+
"loss": 0.0358,
|
| 2277 |
+
"step": 3300
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 3.43,
|
| 2281 |
+
"eval_accuracy": 0.9334949250113619,
|
| 2282 |
+
"eval_loss": 0.2629750072956085,
|
| 2283 |
+
"eval_runtime": 105.1034,
|
| 2284 |
+
"eval_samples_per_second": 62.805,
|
| 2285 |
+
"eval_steps_per_second": 7.859,
|
| 2286 |
+
"step": 3300
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 3.44,
|
| 2290 |
+
"learning_rate": 2.814122533748702e-05,
|
| 2291 |
+
"loss": 0.0598,
|
| 2292 |
+
"step": 3310
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 3.45,
|
| 2296 |
+
"learning_rate": 2.762201453790239e-05,
|
| 2297 |
+
"loss": 0.0089,
|
| 2298 |
+
"step": 3320
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 3.46,
|
| 2302 |
+
"learning_rate": 2.7102803738317755e-05,
|
| 2303 |
+
"loss": 0.0032,
|
| 2304 |
+
"step": 3330
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 3.47,
|
| 2308 |
+
"learning_rate": 2.6583592938733126e-05,
|
| 2309 |
+
"loss": 0.0039,
|
| 2310 |
+
"step": 3340
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 3.48,
|
| 2314 |
+
"learning_rate": 2.6064382139148497e-05,
|
| 2315 |
+
"loss": 0.0053,
|
| 2316 |
+
"step": 3350
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 3.49,
|
| 2320 |
+
"learning_rate": 2.554517133956386e-05,
|
| 2321 |
+
"loss": 0.0093,
|
| 2322 |
+
"step": 3360
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 3.5,
|
| 2326 |
+
"learning_rate": 2.5025960539979233e-05,
|
| 2327 |
+
"loss": 0.0657,
|
| 2328 |
+
"step": 3370
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 3.51,
|
| 2332 |
+
"learning_rate": 2.4506749740394604e-05,
|
| 2333 |
+
"loss": 0.0027,
|
| 2334 |
+
"step": 3380
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 3.52,
|
| 2338 |
+
"learning_rate": 2.398753894080997e-05,
|
| 2339 |
+
"loss": 0.0775,
|
| 2340 |
+
"step": 3390
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 3.53,
|
| 2344 |
+
"learning_rate": 2.3468328141225336e-05,
|
| 2345 |
+
"loss": 0.0347,
|
| 2346 |
+
"step": 3400
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 3.53,
|
| 2350 |
+
"eval_accuracy": 0.9357673079836388,
|
| 2351 |
+
"eval_loss": 0.2633425295352936,
|
| 2352 |
+
"eval_runtime": 105.2554,
|
| 2353 |
+
"eval_samples_per_second": 62.714,
|
| 2354 |
+
"eval_steps_per_second": 7.848,
|
| 2355 |
+
"step": 3400
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 3.54,
|
| 2359 |
+
"learning_rate": 2.2949117341640707e-05,
|
| 2360 |
+
"loss": 0.0288,
|
| 2361 |
+
"step": 3410
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 3.55,
|
| 2365 |
+
"learning_rate": 2.2429906542056075e-05,
|
| 2366 |
+
"loss": 0.039,
|
| 2367 |
+
"step": 3420
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 3.56,
|
| 2371 |
+
"learning_rate": 2.1910695742471443e-05,
|
| 2372 |
+
"loss": 0.0565,
|
| 2373 |
+
"step": 3430
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 3.57,
|
| 2377 |
+
"learning_rate": 2.1391484942886814e-05,
|
| 2378 |
+
"loss": 0.0412,
|
| 2379 |
+
"step": 3440
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 3.58,
|
| 2383 |
+
"learning_rate": 2.087227414330218e-05,
|
| 2384 |
+
"loss": 0.0391,
|
| 2385 |
+
"step": 3450
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 3.59,
|
| 2389 |
+
"learning_rate": 2.0353063343717553e-05,
|
| 2390 |
+
"loss": 0.0036,
|
| 2391 |
+
"step": 3460
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 3.6,
|
| 2395 |
+
"learning_rate": 1.983385254413292e-05,
|
| 2396 |
+
"loss": 0.0045,
|
| 2397 |
+
"step": 3470
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 3.61,
|
| 2401 |
+
"learning_rate": 1.9314641744548288e-05,
|
| 2402 |
+
"loss": 0.0679,
|
| 2403 |
+
"step": 3480
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 3.62,
|
| 2407 |
+
"learning_rate": 1.8795430944963656e-05,
|
| 2408 |
+
"loss": 0.0169,
|
| 2409 |
+
"step": 3490
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 3.63,
|
| 2413 |
+
"learning_rate": 1.8276220145379024e-05,
|
| 2414 |
+
"loss": 0.0408,
|
| 2415 |
+
"step": 3500
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 3.63,
|
| 2419 |
+
"eval_accuracy": 0.9334949250113619,
|
| 2420 |
+
"eval_loss": 0.2590745985507965,
|
| 2421 |
+
"eval_runtime": 105.6016,
|
| 2422 |
+
"eval_samples_per_second": 62.509,
|
| 2423 |
+
"eval_steps_per_second": 7.822,
|
| 2424 |
+
"step": 3500
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 3.64,
|
| 2428 |
+
"learning_rate": 1.775700934579439e-05,
|
| 2429 |
+
"loss": 0.0217,
|
| 2430 |
+
"step": 3510
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 3.66,
|
| 2434 |
+
"learning_rate": 1.7237798546209763e-05,
|
| 2435 |
+
"loss": 0.0186,
|
| 2436 |
+
"step": 3520
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 3.67,
|
| 2440 |
+
"learning_rate": 1.671858774662513e-05,
|
| 2441 |
+
"loss": 0.006,
|
| 2442 |
+
"step": 3530
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 3.68,
|
| 2446 |
+
"learning_rate": 1.6199376947040498e-05,
|
| 2447 |
+
"loss": 0.0216,
|
| 2448 |
+
"step": 3540
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 3.69,
|
| 2452 |
+
"learning_rate": 1.568016614745587e-05,
|
| 2453 |
+
"loss": 0.0108,
|
| 2454 |
+
"step": 3550
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 3.7,
|
| 2458 |
+
"learning_rate": 1.5160955347871237e-05,
|
| 2459 |
+
"loss": 0.0033,
|
| 2460 |
+
"step": 3560
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 3.71,
|
| 2464 |
+
"learning_rate": 1.4641744548286603e-05,
|
| 2465 |
+
"loss": 0.0038,
|
| 2466 |
+
"step": 3570
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 3.72,
|
| 2470 |
+
"learning_rate": 1.4122533748701974e-05,
|
| 2471 |
+
"loss": 0.0039,
|
| 2472 |
+
"step": 3580
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 3.73,
|
| 2476 |
+
"learning_rate": 1.3603322949117342e-05,
|
| 2477 |
+
"loss": 0.0311,
|
| 2478 |
+
"step": 3590
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 3.74,
|
| 2482 |
+
"learning_rate": 1.308411214953271e-05,
|
| 2483 |
+
"loss": 0.041,
|
| 2484 |
+
"step": 3600
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 3.74,
|
| 2488 |
+
"eval_accuracy": 0.9366762611725497,
|
| 2489 |
+
"eval_loss": 0.2612759470939636,
|
| 2490 |
+
"eval_runtime": 105.1174,
|
| 2491 |
+
"eval_samples_per_second": 62.796,
|
| 2492 |
+
"eval_steps_per_second": 7.858,
|
| 2493 |
+
"step": 3600
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 3.75,
|
| 2497 |
+
"learning_rate": 1.256490134994808e-05,
|
| 2498 |
+
"loss": 0.0035,
|
| 2499 |
+
"step": 3610
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 3.76,
|
| 2503 |
+
"learning_rate": 1.2045690550363447e-05,
|
| 2504 |
+
"loss": 0.0501,
|
| 2505 |
+
"step": 3620
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 3.77,
|
| 2509 |
+
"learning_rate": 1.1526479750778816e-05,
|
| 2510 |
+
"loss": 0.0398,
|
| 2511 |
+
"step": 3630
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 3.78,
|
| 2515 |
+
"learning_rate": 1.1007268951194186e-05,
|
| 2516 |
+
"loss": 0.0042,
|
| 2517 |
+
"step": 3640
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 3.79,
|
| 2521 |
+
"learning_rate": 1.0488058151609554e-05,
|
| 2522 |
+
"loss": 0.0044,
|
| 2523 |
+
"step": 3650
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 3.8,
|
| 2527 |
+
"learning_rate": 9.968847352024923e-06,
|
| 2528 |
+
"loss": 0.087,
|
| 2529 |
+
"step": 3660
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 3.81,
|
| 2533 |
+
"learning_rate": 9.44963655244029e-06,
|
| 2534 |
+
"loss": 0.005,
|
| 2535 |
+
"step": 3670
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 3.82,
|
| 2539 |
+
"learning_rate": 8.93042575285566e-06,
|
| 2540 |
+
"loss": 0.0404,
|
| 2541 |
+
"step": 3680
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 3.83,
|
| 2545 |
+
"learning_rate": 8.411214953271028e-06,
|
| 2546 |
+
"loss": 0.0401,
|
| 2547 |
+
"step": 3690
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 3.84,
|
| 2551 |
+
"learning_rate": 7.892004153686398e-06,
|
| 2552 |
+
"loss": 0.004,
|
| 2553 |
+
"step": 3700
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 3.84,
|
| 2557 |
+
"eval_accuracy": 0.9369792455688533,
|
| 2558 |
+
"eval_loss": 0.25872641801834106,
|
| 2559 |
+
"eval_runtime": 106.8562,
|
| 2560 |
+
"eval_samples_per_second": 61.775,
|
| 2561 |
+
"eval_steps_per_second": 7.73,
|
| 2562 |
+
"step": 3700
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 3.85,
|
| 2566 |
+
"learning_rate": 7.372793354101766e-06,
|
| 2567 |
+
"loss": 0.0411,
|
| 2568 |
+
"step": 3710
|
| 2569 |
+
},
|
| 2570 |
+
{
|
| 2571 |
+
"epoch": 3.86,
|
| 2572 |
+
"learning_rate": 6.853582554517134e-06,
|
| 2573 |
+
"loss": 0.0689,
|
| 2574 |
+
"step": 3720
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 3.87,
|
| 2578 |
+
"learning_rate": 6.3343717549325025e-06,
|
| 2579 |
+
"loss": 0.0428,
|
| 2580 |
+
"step": 3730
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"epoch": 3.88,
|
| 2584 |
+
"learning_rate": 5.815160955347872e-06,
|
| 2585 |
+
"loss": 0.0464,
|
| 2586 |
+
"step": 3740
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 3.89,
|
| 2590 |
+
"learning_rate": 5.29595015576324e-06,
|
| 2591 |
+
"loss": 0.024,
|
| 2592 |
+
"step": 3750
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 3.9,
|
| 2596 |
+
"learning_rate": 4.776739356178609e-06,
|
| 2597 |
+
"loss": 0.0732,
|
| 2598 |
+
"step": 3760
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 3.91,
|
| 2602 |
+
"learning_rate": 4.257528556593978e-06,
|
| 2603 |
+
"loss": 0.0386,
|
| 2604 |
+
"step": 3770
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 3.93,
|
| 2608 |
+
"learning_rate": 3.7383177570093455e-06,
|
| 2609 |
+
"loss": 0.0532,
|
| 2610 |
+
"step": 3780
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 3.94,
|
| 2614 |
+
"learning_rate": 3.2191069574247146e-06,
|
| 2615 |
+
"loss": 0.0413,
|
| 2616 |
+
"step": 3790
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 3.95,
|
| 2620 |
+
"learning_rate": 2.699896157840083e-06,
|
| 2621 |
+
"loss": 0.0389,
|
| 2622 |
+
"step": 3800
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 3.95,
|
| 2626 |
+
"eval_accuracy": 0.9372822299651568,
|
| 2627 |
+
"eval_loss": 0.25349465012550354,
|
| 2628 |
+
"eval_runtime": 110.0172,
|
| 2629 |
+
"eval_samples_per_second": 60.0,
|
| 2630 |
+
"eval_steps_per_second": 7.508,
|
| 2631 |
+
"step": 3800
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 3.96,
|
| 2635 |
+
"learning_rate": 2.1806853582554518e-06,
|
| 2636 |
+
"loss": 0.0383,
|
| 2637 |
+
"step": 3810
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 3.97,
|
| 2641 |
+
"learning_rate": 1.6614745586708204e-06,
|
| 2642 |
+
"loss": 0.0169,
|
| 2643 |
+
"step": 3820
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 3.98,
|
| 2647 |
+
"learning_rate": 1.142263759086189e-06,
|
| 2648 |
+
"loss": 0.0072,
|
| 2649 |
+
"step": 3830
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 3.99,
|
| 2653 |
+
"learning_rate": 6.230529595015577e-07,
|
| 2654 |
+
"loss": 0.0054,
|
| 2655 |
+
"step": 3840
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 4.0,
|
| 2659 |
+
"learning_rate": 1.0384215991692627e-07,
|
| 2660 |
+
"loss": 0.0044,
|
| 2661 |
+
"step": 3850
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 4.0,
|
| 2665 |
+
"step": 3852,
|
| 2666 |
+
"total_flos": 4.774126496175784e+18,
|
| 2667 |
+
"train_loss": 0.1544622457234444,
|
| 2668 |
+
"train_runtime": 5879.4453,
|
| 2669 |
+
"train_samples_per_second": 10.479,
|
| 2670 |
+
"train_steps_per_second": 0.655
|
| 2671 |
+
}
|
| 2672 |
+
],
|
| 2673 |
+
"logging_steps": 10,
|
| 2674 |
+
"max_steps": 3852,
|
| 2675 |
+
"num_train_epochs": 4,
|
| 2676 |
+
"save_steps": 100,
|
| 2677 |
+
"total_flos": 4.774126496175784e+18,
|
| 2678 |
+
"trial_name": null,
|
| 2679 |
+
"trial_params": null
|
| 2680 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f329bca8bd9b9817272ace58e44f39ea1488db84d107d97767f33a7942bd97f
|
| 3 |
+
size 4155
|