End of training
Browse files- README.md +71 -0
- all_results.json +13 -0
- config.json +36 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Nov19_17-16-46_0ef6b0767e49/events.out.tfevents.1732036608.0ef6b0767e49.36.0 +3 -0
- runs/Nov19_17-16-46_0ef6b0767e49/events.out.tfevents.1732037322.0ef6b0767e49.36.1 +3 -0
- test_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +953 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: vit-base-beans
|
| 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 |
+
# vit-base-beans
|
| 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 an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0014
|
| 21 |
+
- Accuracy: 1.0
|
| 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 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 53 |
+
| 0.0532 | 0.3448 | 100 | 0.0277 | 0.9961 |
|
| 54 |
+
| 0.0518 | 0.6897 | 200 | 0.0330 | 0.9942 |
|
| 55 |
+
| 0.006 | 1.0345 | 300 | 0.0387 | 0.9923 |
|
| 56 |
+
| 0.004 | 1.3793 | 400 | 0.0696 | 0.9845 |
|
| 57 |
+
| 0.0032 | 1.7241 | 500 | 0.1609 | 0.9691 |
|
| 58 |
+
| 0.0026 | 2.0690 | 600 | 0.0025 | 1.0 |
|
| 59 |
+
| 0.0021 | 2.4138 | 700 | 0.0020 | 1.0 |
|
| 60 |
+
| 0.0018 | 2.7586 | 800 | 0.0017 | 1.0 |
|
| 61 |
+
| 0.0016 | 3.1034 | 900 | 0.0016 | 1.0 |
|
| 62 |
+
| 0.0015 | 3.4483 | 1000 | 0.0015 | 1.0 |
|
| 63 |
+
| 0.0014 | 3.7931 | 1100 | 0.0014 | 1.0 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.44.0
|
| 69 |
+
- Pytorch 2.4.0
|
| 70 |
+
- Datasets 2.21.0
|
| 71 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.0014140307903289795,
|
| 5 |
+
"eval_runtime": 40.0081,
|
| 6 |
+
"eval_samples_per_second": 55.189,
|
| 7 |
+
"eval_steps_per_second": 6.899,
|
| 8 |
+
"total_flos": 1.436727240856535e+18,
|
| 9 |
+
"train_loss": 0.027367618223170524,
|
| 10 |
+
"train_runtime": 673.711,
|
| 11 |
+
"train_samples_per_second": 27.519,
|
| 12 |
+
"train_steps_per_second": 1.722
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Bacterial spot rot",
|
| 13 |
+
"1": "Black Rot",
|
| 14 |
+
"2": "Disease Free",
|
| 15 |
+
"3": "Downy Mildew"
|
| 16 |
+
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"Bacterial spot rot": "0",
|
| 22 |
+
"Black Rot": "1",
|
| 23 |
+
"Disease Free": "2",
|
| 24 |
+
"Downy Mildew": "3"
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"model_type": "vit",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_channels": 3,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"patch_size": 16,
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"qkv_bias": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.44.0"
|
| 36 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:637ce18ed0fa1fd1e056c89adfed40fae72dc9fa366086a11639b8bb5ce01204
|
| 3 |
+
size 343230128
|
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/Nov19_17-16-46_0ef6b0767e49/events.out.tfevents.1732036608.0ef6b0767e49.36.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba801145e5ff267c8d6c35447bc3e0031a6bf2855312ab0f4c48d8939ef4aae2
|
| 3 |
+
size 33354
|
runs/Nov19_17-16-46_0ef6b0767e49/events.out.tfevents.1732037322.0ef6b0767e49.36.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39aa342ddf53009070f6dea5fff155df6b011d1b97d50057dfd85fd483154518
|
| 3 |
+
size 411
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.0014140307903289795,
|
| 5 |
+
"eval_runtime": 40.0081,
|
| 6 |
+
"eval_samples_per_second": 55.189,
|
| 7 |
+
"eval_steps_per_second": 6.899
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.436727240856535e+18,
|
| 4 |
+
"train_loss": 0.027367618223170524,
|
| 5 |
+
"train_runtime": 673.711,
|
| 6 |
+
"train_samples_per_second": 27.519,
|
| 7 |
+
"train_steps_per_second": 1.722
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,953 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0014008664293214679,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-1100",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.034482758620689655,
|
| 13 |
+
"grad_norm": 1.4541093111038208,
|
| 14 |
+
"learning_rate": 0.00019827586206896554,
|
| 15 |
+
"loss": 0.9417,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06896551724137931,
|
| 20 |
+
"grad_norm": 0.6665103435516357,
|
| 21 |
+
"learning_rate": 0.00019655172413793104,
|
| 22 |
+
"loss": 0.3226,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10344827586206896,
|
| 27 |
+
"grad_norm": 0.33402901887893677,
|
| 28 |
+
"learning_rate": 0.00019482758620689657,
|
| 29 |
+
"loss": 0.1528,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13793103448275862,
|
| 34 |
+
"grad_norm": 0.21010038256645203,
|
| 35 |
+
"learning_rate": 0.0001931034482758621,
|
| 36 |
+
"loss": 0.1077,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1724137931034483,
|
| 41 |
+
"grad_norm": 0.2470974624156952,
|
| 42 |
+
"learning_rate": 0.0001913793103448276,
|
| 43 |
+
"loss": 0.0676,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.20689655172413793,
|
| 48 |
+
"grad_norm": 0.16962118446826935,
|
| 49 |
+
"learning_rate": 0.00018965517241379312,
|
| 50 |
+
"loss": 0.0449,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2413793103448276,
|
| 55 |
+
"grad_norm": 0.1308588832616806,
|
| 56 |
+
"learning_rate": 0.00018793103448275865,
|
| 57 |
+
"loss": 0.0346,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.27586206896551724,
|
| 62 |
+
"grad_norm": 0.11898835003376007,
|
| 63 |
+
"learning_rate": 0.00018620689655172415,
|
| 64 |
+
"loss": 0.0318,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3103448275862069,
|
| 69 |
+
"grad_norm": 0.10036325454711914,
|
| 70 |
+
"learning_rate": 0.00018448275862068968,
|
| 71 |
+
"loss": 0.0425,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3448275862068966,
|
| 76 |
+
"grad_norm": 0.10104402154684067,
|
| 77 |
+
"learning_rate": 0.00018275862068965518,
|
| 78 |
+
"loss": 0.0532,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3448275862068966,
|
| 83 |
+
"eval_accuracy": 0.9961315280464217,
|
| 84 |
+
"eval_loss": 0.027677614241838455,
|
| 85 |
+
"eval_runtime": 9.322,
|
| 86 |
+
"eval_samples_per_second": 55.46,
|
| 87 |
+
"eval_steps_per_second": 6.973,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.3793103448275862,
|
| 92 |
+
"grad_norm": 1.163355827331543,
|
| 93 |
+
"learning_rate": 0.0001810344827586207,
|
| 94 |
+
"loss": 0.1062,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.41379310344827586,
|
| 99 |
+
"grad_norm": 0.08375360816717148,
|
| 100 |
+
"learning_rate": 0.0001793103448275862,
|
| 101 |
+
"loss": 0.0258,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.4482758620689655,
|
| 106 |
+
"grad_norm": 0.09952229261398315,
|
| 107 |
+
"learning_rate": 0.00017758620689655173,
|
| 108 |
+
"loss": 0.0175,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.4827586206896552,
|
| 113 |
+
"grad_norm": 0.6083604097366333,
|
| 114 |
+
"learning_rate": 0.00017586206896551723,
|
| 115 |
+
"loss": 0.0683,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.5172413793103449,
|
| 120 |
+
"grad_norm": 0.09937556833028793,
|
| 121 |
+
"learning_rate": 0.00017413793103448276,
|
| 122 |
+
"loss": 0.0947,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.5517241379310345,
|
| 127 |
+
"grad_norm": 0.08655019849538803,
|
| 128 |
+
"learning_rate": 0.00017241379310344826,
|
| 129 |
+
"loss": 0.0201,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.5862068965517241,
|
| 134 |
+
"grad_norm": 0.059486184269189835,
|
| 135 |
+
"learning_rate": 0.0001706896551724138,
|
| 136 |
+
"loss": 0.0631,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.6206896551724138,
|
| 141 |
+
"grad_norm": 0.07637613266706467,
|
| 142 |
+
"learning_rate": 0.00016896551724137932,
|
| 143 |
+
"loss": 0.032,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.6551724137931034,
|
| 148 |
+
"grad_norm": 10.693470001220703,
|
| 149 |
+
"learning_rate": 0.00016724137931034482,
|
| 150 |
+
"loss": 0.0542,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.6896551724137931,
|
| 155 |
+
"grad_norm": 0.09118778258562088,
|
| 156 |
+
"learning_rate": 0.00016551724137931035,
|
| 157 |
+
"loss": 0.0518,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.6896551724137931,
|
| 162 |
+
"eval_accuracy": 0.9941972920696325,
|
| 163 |
+
"eval_loss": 0.03303845226764679,
|
| 164 |
+
"eval_runtime": 9.2358,
|
| 165 |
+
"eval_samples_per_second": 55.978,
|
| 166 |
+
"eval_steps_per_second": 7.038,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.7241379310344828,
|
| 171 |
+
"grad_norm": 0.04961516335606575,
|
| 172 |
+
"learning_rate": 0.00016379310344827587,
|
| 173 |
+
"loss": 0.0708,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.7586206896551724,
|
| 178 |
+
"grad_norm": 0.058188311755657196,
|
| 179 |
+
"learning_rate": 0.00016206896551724137,
|
| 180 |
+
"loss": 0.0392,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.7931034482758621,
|
| 185 |
+
"grad_norm": 0.041994284838438034,
|
| 186 |
+
"learning_rate": 0.0001603448275862069,
|
| 187 |
+
"loss": 0.0116,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.8275862068965517,
|
| 192 |
+
"grad_norm": 0.05082221329212189,
|
| 193 |
+
"learning_rate": 0.00015862068965517243,
|
| 194 |
+
"loss": 0.0376,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.8620689655172413,
|
| 199 |
+
"grad_norm": 0.07286480814218521,
|
| 200 |
+
"learning_rate": 0.00015689655172413793,
|
| 201 |
+
"loss": 0.0382,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.896551724137931,
|
| 206 |
+
"grad_norm": 0.03850896656513214,
|
| 207 |
+
"learning_rate": 0.00015517241379310346,
|
| 208 |
+
"loss": 0.0178,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.9310344827586207,
|
| 213 |
+
"grad_norm": 0.031015470623970032,
|
| 214 |
+
"learning_rate": 0.00015344827586206899,
|
| 215 |
+
"loss": 0.0328,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.9655172413793104,
|
| 220 |
+
"grad_norm": 0.03393784165382385,
|
| 221 |
+
"learning_rate": 0.00015172413793103449,
|
| 222 |
+
"loss": 0.0072,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.0,
|
| 227 |
+
"grad_norm": 0.09719406068325043,
|
| 228 |
+
"learning_rate": 0.00015000000000000001,
|
| 229 |
+
"loss": 0.0071,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.0344827586206897,
|
| 234 |
+
"grad_norm": 0.02531067281961441,
|
| 235 |
+
"learning_rate": 0.00014827586206896554,
|
| 236 |
+
"loss": 0.006,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.0344827586206897,
|
| 241 |
+
"eval_accuracy": 0.9922630560928434,
|
| 242 |
+
"eval_loss": 0.038734398782253265,
|
| 243 |
+
"eval_runtime": 9.1377,
|
| 244 |
+
"eval_samples_per_second": 56.579,
|
| 245 |
+
"eval_steps_per_second": 7.113,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.0689655172413792,
|
| 250 |
+
"grad_norm": 0.02636132761836052,
|
| 251 |
+
"learning_rate": 0.00014655172413793104,
|
| 252 |
+
"loss": 0.0057,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.103448275862069,
|
| 257 |
+
"grad_norm": 0.023396922275424004,
|
| 258 |
+
"learning_rate": 0.00014482758620689657,
|
| 259 |
+
"loss": 0.0053,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.1379310344827587,
|
| 264 |
+
"grad_norm": 0.022781934589147568,
|
| 265 |
+
"learning_rate": 0.0001431034482758621,
|
| 266 |
+
"loss": 0.005,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.1724137931034484,
|
| 271 |
+
"grad_norm": 0.020923634991049767,
|
| 272 |
+
"learning_rate": 0.0001413793103448276,
|
| 273 |
+
"loss": 0.0048,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.206896551724138,
|
| 278 |
+
"grad_norm": 0.020241938531398773,
|
| 279 |
+
"learning_rate": 0.0001396551724137931,
|
| 280 |
+
"loss": 0.0046,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.2413793103448276,
|
| 285 |
+
"grad_norm": 0.0188324972987175,
|
| 286 |
+
"learning_rate": 0.00013793103448275863,
|
| 287 |
+
"loss": 0.0046,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.2758620689655173,
|
| 292 |
+
"grad_norm": 0.019414547830820084,
|
| 293 |
+
"learning_rate": 0.00013620689655172413,
|
| 294 |
+
"loss": 0.0043,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.3103448275862069,
|
| 299 |
+
"grad_norm": 0.019972946494817734,
|
| 300 |
+
"learning_rate": 0.00013448275862068965,
|
| 301 |
+
"loss": 0.0075,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.3448275862068966,
|
| 306 |
+
"grad_norm": 0.02629067189991474,
|
| 307 |
+
"learning_rate": 0.00013275862068965518,
|
| 308 |
+
"loss": 0.0377,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.3793103448275863,
|
| 313 |
+
"grad_norm": 0.027980973944067955,
|
| 314 |
+
"learning_rate": 0.00013103448275862068,
|
| 315 |
+
"loss": 0.004,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.3793103448275863,
|
| 320 |
+
"eval_accuracy": 0.9845261121856866,
|
| 321 |
+
"eval_loss": 0.0695781335234642,
|
| 322 |
+
"eval_runtime": 9.2324,
|
| 323 |
+
"eval_samples_per_second": 55.998,
|
| 324 |
+
"eval_steps_per_second": 7.04,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.4137931034482758,
|
| 329 |
+
"grad_norm": 10.141643524169922,
|
| 330 |
+
"learning_rate": 0.0001293103448275862,
|
| 331 |
+
"loss": 0.0441,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4482758620689655,
|
| 336 |
+
"grad_norm": 0.017165783792734146,
|
| 337 |
+
"learning_rate": 0.00012758620689655174,
|
| 338 |
+
"loss": 0.0049,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4827586206896552,
|
| 343 |
+
"grad_norm": 0.01630399189889431,
|
| 344 |
+
"learning_rate": 0.00012586206896551724,
|
| 345 |
+
"loss": 0.0492,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.5172413793103448,
|
| 350 |
+
"grad_norm": 0.018257714807987213,
|
| 351 |
+
"learning_rate": 0.00012413793103448277,
|
| 352 |
+
"loss": 0.0526,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5517241379310345,
|
| 357 |
+
"grad_norm": 0.01886160485446453,
|
| 358 |
+
"learning_rate": 0.00012241379310344827,
|
| 359 |
+
"loss": 0.0402,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.5862068965517242,
|
| 364 |
+
"grad_norm": 0.01721111685037613,
|
| 365 |
+
"learning_rate": 0.0001206896551724138,
|
| 366 |
+
"loss": 0.0359,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.6206896551724137,
|
| 371 |
+
"grad_norm": 0.020360512658953667,
|
| 372 |
+
"learning_rate": 0.00011896551724137932,
|
| 373 |
+
"loss": 0.0051,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.6551724137931034,
|
| 378 |
+
"grad_norm": 0.01872898079454899,
|
| 379 |
+
"learning_rate": 0.00011724137931034482,
|
| 380 |
+
"loss": 0.004,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.6896551724137931,
|
| 385 |
+
"grad_norm": 0.015705358237028122,
|
| 386 |
+
"learning_rate": 0.00011551724137931035,
|
| 387 |
+
"loss": 0.0036,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.7241379310344827,
|
| 392 |
+
"grad_norm": 0.022712524980306625,
|
| 393 |
+
"learning_rate": 0.00011379310344827588,
|
| 394 |
+
"loss": 0.0032,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.7241379310344827,
|
| 399 |
+
"eval_accuracy": 0.9690522243713733,
|
| 400 |
+
"eval_loss": 0.16091904044151306,
|
| 401 |
+
"eval_runtime": 9.2258,
|
| 402 |
+
"eval_samples_per_second": 56.039,
|
| 403 |
+
"eval_steps_per_second": 7.045,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.7586206896551724,
|
| 408 |
+
"grad_norm": 0.02154046855866909,
|
| 409 |
+
"learning_rate": 0.00011206896551724138,
|
| 410 |
+
"loss": 0.0837,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.793103448275862,
|
| 415 |
+
"grad_norm": 0.01605401560664177,
|
| 416 |
+
"learning_rate": 0.0001103448275862069,
|
| 417 |
+
"loss": 0.0033,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.8275862068965516,
|
| 422 |
+
"grad_norm": 0.04890372231602669,
|
| 423 |
+
"learning_rate": 0.00010862068965517242,
|
| 424 |
+
"loss": 0.0431,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.8620689655172413,
|
| 429 |
+
"grad_norm": 0.017495185136795044,
|
| 430 |
+
"learning_rate": 0.00010689655172413792,
|
| 431 |
+
"loss": 0.0038,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.896551724137931,
|
| 436 |
+
"grad_norm": 0.017458785325288773,
|
| 437 |
+
"learning_rate": 0.00010517241379310345,
|
| 438 |
+
"loss": 0.0036,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.9310344827586206,
|
| 443 |
+
"grad_norm": 0.01829078048467636,
|
| 444 |
+
"learning_rate": 0.00010344827586206898,
|
| 445 |
+
"loss": 0.003,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.9655172413793105,
|
| 450 |
+
"grad_norm": 0.015696866437792778,
|
| 451 |
+
"learning_rate": 0.00010172413793103448,
|
| 452 |
+
"loss": 0.0029,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.0,
|
| 457 |
+
"grad_norm": 0.015601696446537971,
|
| 458 |
+
"learning_rate": 0.0001,
|
| 459 |
+
"loss": 0.0027,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.0344827586206895,
|
| 464 |
+
"grad_norm": 0.014859354123473167,
|
| 465 |
+
"learning_rate": 9.827586206896552e-05,
|
| 466 |
+
"loss": 0.0027,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.0689655172413794,
|
| 471 |
+
"grad_norm": 0.013295358046889305,
|
| 472 |
+
"learning_rate": 9.655172413793105e-05,
|
| 473 |
+
"loss": 0.0026,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.0689655172413794,
|
| 478 |
+
"eval_accuracy": 1.0,
|
| 479 |
+
"eval_loss": 0.0025033194106072187,
|
| 480 |
+
"eval_runtime": 9.5465,
|
| 481 |
+
"eval_samples_per_second": 54.156,
|
| 482 |
+
"eval_steps_per_second": 6.809,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.103448275862069,
|
| 487 |
+
"grad_norm": 0.015505661256611347,
|
| 488 |
+
"learning_rate": 9.482758620689656e-05,
|
| 489 |
+
"loss": 0.0025,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.1379310344827585,
|
| 494 |
+
"grad_norm": 0.010766665451228619,
|
| 495 |
+
"learning_rate": 9.310344827586207e-05,
|
| 496 |
+
"loss": 0.0024,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.1724137931034484,
|
| 501 |
+
"grad_norm": 0.010864505544304848,
|
| 502 |
+
"learning_rate": 9.137931034482759e-05,
|
| 503 |
+
"loss": 0.0023,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.206896551724138,
|
| 508 |
+
"grad_norm": 0.009982941672205925,
|
| 509 |
+
"learning_rate": 8.96551724137931e-05,
|
| 510 |
+
"loss": 0.0023,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.2413793103448274,
|
| 515 |
+
"grad_norm": 0.009656297974288464,
|
| 516 |
+
"learning_rate": 8.793103448275862e-05,
|
| 517 |
+
"loss": 0.0022,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.2758620689655173,
|
| 522 |
+
"grad_norm": 0.009799299761652946,
|
| 523 |
+
"learning_rate": 8.620689655172413e-05,
|
| 524 |
+
"loss": 0.0022,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.310344827586207,
|
| 529 |
+
"grad_norm": 0.01052001304924488,
|
| 530 |
+
"learning_rate": 8.448275862068966e-05,
|
| 531 |
+
"loss": 0.0022,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.344827586206897,
|
| 536 |
+
"grad_norm": 0.009396790526807308,
|
| 537 |
+
"learning_rate": 8.275862068965517e-05,
|
| 538 |
+
"loss": 0.0021,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.3793103448275863,
|
| 543 |
+
"grad_norm": 0.00975924450904131,
|
| 544 |
+
"learning_rate": 8.103448275862069e-05,
|
| 545 |
+
"loss": 0.0021,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.413793103448276,
|
| 550 |
+
"grad_norm": 0.009396582841873169,
|
| 551 |
+
"learning_rate": 7.931034482758621e-05,
|
| 552 |
+
"loss": 0.0021,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.413793103448276,
|
| 557 |
+
"eval_accuracy": 1.0,
|
| 558 |
+
"eval_loss": 0.002028640592470765,
|
| 559 |
+
"eval_runtime": 9.6653,
|
| 560 |
+
"eval_samples_per_second": 53.49,
|
| 561 |
+
"eval_steps_per_second": 6.725,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.4482758620689653,
|
| 566 |
+
"grad_norm": 0.008813206106424332,
|
| 567 |
+
"learning_rate": 7.758620689655173e-05,
|
| 568 |
+
"loss": 0.002,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.4827586206896552,
|
| 573 |
+
"grad_norm": 0.008702595718204975,
|
| 574 |
+
"learning_rate": 7.586206896551724e-05,
|
| 575 |
+
"loss": 0.002,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.5172413793103448,
|
| 580 |
+
"grad_norm": 0.010061556473374367,
|
| 581 |
+
"learning_rate": 7.413793103448277e-05,
|
| 582 |
+
"loss": 0.002,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.5517241379310347,
|
| 587 |
+
"grad_norm": 0.010726147331297398,
|
| 588 |
+
"learning_rate": 7.241379310344828e-05,
|
| 589 |
+
"loss": 0.0019,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.586206896551724,
|
| 594 |
+
"grad_norm": 0.009536409750580788,
|
| 595 |
+
"learning_rate": 7.06896551724138e-05,
|
| 596 |
+
"loss": 0.0019,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.6206896551724137,
|
| 601 |
+
"grad_norm": 0.008245566859841347,
|
| 602 |
+
"learning_rate": 6.896551724137931e-05,
|
| 603 |
+
"loss": 0.0019,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.655172413793103,
|
| 608 |
+
"grad_norm": 0.010203349404036999,
|
| 609 |
+
"learning_rate": 6.724137931034483e-05,
|
| 610 |
+
"loss": 0.0019,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.689655172413793,
|
| 615 |
+
"grad_norm": 0.008181954734027386,
|
| 616 |
+
"learning_rate": 6.551724137931034e-05,
|
| 617 |
+
"loss": 0.0018,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.7241379310344827,
|
| 622 |
+
"grad_norm": 0.008396759629249573,
|
| 623 |
+
"learning_rate": 6.379310344827587e-05,
|
| 624 |
+
"loss": 0.0018,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.7586206896551726,
|
| 629 |
+
"grad_norm": 0.008574232459068298,
|
| 630 |
+
"learning_rate": 6.206896551724138e-05,
|
| 631 |
+
"loss": 0.0018,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.7586206896551726,
|
| 636 |
+
"eval_accuracy": 1.0,
|
| 637 |
+
"eval_loss": 0.0017438590293750167,
|
| 638 |
+
"eval_runtime": 9.2473,
|
| 639 |
+
"eval_samples_per_second": 55.908,
|
| 640 |
+
"eval_steps_per_second": 7.029,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.793103448275862,
|
| 645 |
+
"grad_norm": 0.008582869544625282,
|
| 646 |
+
"learning_rate": 6.03448275862069e-05,
|
| 647 |
+
"loss": 0.0017,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.8275862068965516,
|
| 652 |
+
"grad_norm": 0.00796087272465229,
|
| 653 |
+
"learning_rate": 5.862068965517241e-05,
|
| 654 |
+
"loss": 0.0017,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.862068965517241,
|
| 659 |
+
"grad_norm": 0.00767522631213069,
|
| 660 |
+
"learning_rate": 5.689655172413794e-05,
|
| 661 |
+
"loss": 0.0017,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.896551724137931,
|
| 666 |
+
"grad_norm": 0.007729759905487299,
|
| 667 |
+
"learning_rate": 5.517241379310345e-05,
|
| 668 |
+
"loss": 0.0017,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.9310344827586206,
|
| 673 |
+
"grad_norm": 0.007915050722658634,
|
| 674 |
+
"learning_rate": 5.344827586206896e-05,
|
| 675 |
+
"loss": 0.0016,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.9655172413793105,
|
| 680 |
+
"grad_norm": 0.008189872838556767,
|
| 681 |
+
"learning_rate": 5.172413793103449e-05,
|
| 682 |
+
"loss": 0.0016,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.0,
|
| 687 |
+
"grad_norm": 0.007728048134595156,
|
| 688 |
+
"learning_rate": 5e-05,
|
| 689 |
+
"loss": 0.0016,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 3.0344827586206895,
|
| 694 |
+
"grad_norm": 0.007373048458248377,
|
| 695 |
+
"learning_rate": 4.827586206896552e-05,
|
| 696 |
+
"loss": 0.0016,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 3.0689655172413794,
|
| 701 |
+
"grad_norm": 0.00832042470574379,
|
| 702 |
+
"learning_rate": 4.655172413793104e-05,
|
| 703 |
+
"loss": 0.0016,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.103448275862069,
|
| 708 |
+
"grad_norm": 0.007547506596893072,
|
| 709 |
+
"learning_rate": 4.482758620689655e-05,
|
| 710 |
+
"loss": 0.0016,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.103448275862069,
|
| 715 |
+
"eval_accuracy": 1.0,
|
| 716 |
+
"eval_loss": 0.0015662283403798938,
|
| 717 |
+
"eval_runtime": 9.1484,
|
| 718 |
+
"eval_samples_per_second": 56.513,
|
| 719 |
+
"eval_steps_per_second": 7.105,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.1379310344827585,
|
| 724 |
+
"grad_norm": 0.007507437374442816,
|
| 725 |
+
"learning_rate": 4.3103448275862066e-05,
|
| 726 |
+
"loss": 0.0016,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 3.1724137931034484,
|
| 731 |
+
"grad_norm": 0.008085578680038452,
|
| 732 |
+
"learning_rate": 4.1379310344827587e-05,
|
| 733 |
+
"loss": 0.0015,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.206896551724138,
|
| 738 |
+
"grad_norm": 0.007526910398155451,
|
| 739 |
+
"learning_rate": 3.965517241379311e-05,
|
| 740 |
+
"loss": 0.0015,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 3.2413793103448274,
|
| 745 |
+
"grad_norm": 0.007942083291709423,
|
| 746 |
+
"learning_rate": 3.793103448275862e-05,
|
| 747 |
+
"loss": 0.0015,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 3.2758620689655173,
|
| 752 |
+
"grad_norm": 0.007609126623719931,
|
| 753 |
+
"learning_rate": 3.620689655172414e-05,
|
| 754 |
+
"loss": 0.0015,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 3.310344827586207,
|
| 759 |
+
"grad_norm": 0.007188369985669851,
|
| 760 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 761 |
+
"loss": 0.0015,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 3.344827586206897,
|
| 766 |
+
"grad_norm": 0.0077166566625237465,
|
| 767 |
+
"learning_rate": 3.275862068965517e-05,
|
| 768 |
+
"loss": 0.0015,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 3.3793103448275863,
|
| 773 |
+
"grad_norm": 0.007557329256087542,
|
| 774 |
+
"learning_rate": 3.103448275862069e-05,
|
| 775 |
+
"loss": 0.0015,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.413793103448276,
|
| 780 |
+
"grad_norm": 0.006876759696751833,
|
| 781 |
+
"learning_rate": 2.9310344827586206e-05,
|
| 782 |
+
"loss": 0.0015,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 3.4482758620689653,
|
| 787 |
+
"grad_norm": 0.007274131290614605,
|
| 788 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 789 |
+
"loss": 0.0015,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 3.4482758620689653,
|
| 794 |
+
"eval_accuracy": 1.0,
|
| 795 |
+
"eval_loss": 0.001456769765354693,
|
| 796 |
+
"eval_runtime": 9.1926,
|
| 797 |
+
"eval_samples_per_second": 56.241,
|
| 798 |
+
"eval_steps_per_second": 7.071,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 3.4827586206896552,
|
| 803 |
+
"grad_norm": 0.007954578846693039,
|
| 804 |
+
"learning_rate": 2.5862068965517244e-05,
|
| 805 |
+
"loss": 0.0015,
|
| 806 |
+
"step": 1010
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.5172413793103448,
|
| 810 |
+
"grad_norm": 0.007275938987731934,
|
| 811 |
+
"learning_rate": 2.413793103448276e-05,
|
| 812 |
+
"loss": 0.0015,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.5517241379310347,
|
| 817 |
+
"grad_norm": 0.006545715499669313,
|
| 818 |
+
"learning_rate": 2.2413793103448276e-05,
|
| 819 |
+
"loss": 0.0014,
|
| 820 |
+
"step": 1030
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 3.586206896551724,
|
| 824 |
+
"grad_norm": 0.006517117377370596,
|
| 825 |
+
"learning_rate": 2.0689655172413793e-05,
|
| 826 |
+
"loss": 0.0014,
|
| 827 |
+
"step": 1040
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.6206896551724137,
|
| 831 |
+
"grad_norm": 0.006700526457279921,
|
| 832 |
+
"learning_rate": 1.896551724137931e-05,
|
| 833 |
+
"loss": 0.0014,
|
| 834 |
+
"step": 1050
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.655172413793103,
|
| 838 |
+
"grad_norm": 0.006489131134003401,
|
| 839 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 840 |
+
"loss": 0.0014,
|
| 841 |
+
"step": 1060
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.689655172413793,
|
| 845 |
+
"grad_norm": 0.006455055437982082,
|
| 846 |
+
"learning_rate": 1.5517241379310346e-05,
|
| 847 |
+
"loss": 0.0014,
|
| 848 |
+
"step": 1070
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.7241379310344827,
|
| 852 |
+
"grad_norm": 0.006427043117582798,
|
| 853 |
+
"learning_rate": 1.3793103448275863e-05,
|
| 854 |
+
"loss": 0.0014,
|
| 855 |
+
"step": 1080
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 3.7586206896551726,
|
| 859 |
+
"grad_norm": 0.006561470218002796,
|
| 860 |
+
"learning_rate": 1.206896551724138e-05,
|
| 861 |
+
"loss": 0.0014,
|
| 862 |
+
"step": 1090
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 3.793103448275862,
|
| 866 |
+
"grad_norm": 0.007191502954810858,
|
| 867 |
+
"learning_rate": 1.0344827586206897e-05,
|
| 868 |
+
"loss": 0.0014,
|
| 869 |
+
"step": 1100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.793103448275862,
|
| 873 |
+
"eval_accuracy": 1.0,
|
| 874 |
+
"eval_loss": 0.0014008664293214679,
|
| 875 |
+
"eval_runtime": 9.2274,
|
| 876 |
+
"eval_samples_per_second": 56.029,
|
| 877 |
+
"eval_steps_per_second": 7.044,
|
| 878 |
+
"step": 1100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.8275862068965516,
|
| 882 |
+
"grad_norm": 0.006780336145311594,
|
| 883 |
+
"learning_rate": 8.620689655172414e-06,
|
| 884 |
+
"loss": 0.0014,
|
| 885 |
+
"step": 1110
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.862068965517241,
|
| 889 |
+
"grad_norm": 0.006570115685462952,
|
| 890 |
+
"learning_rate": 6.896551724137932e-06,
|
| 891 |
+
"loss": 0.0014,
|
| 892 |
+
"step": 1120
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.896551724137931,
|
| 896 |
+
"grad_norm": 0.00782351940870285,
|
| 897 |
+
"learning_rate": 5.172413793103448e-06,
|
| 898 |
+
"loss": 0.0014,
|
| 899 |
+
"step": 1130
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.9310344827586206,
|
| 903 |
+
"grad_norm": 0.006399817299097776,
|
| 904 |
+
"learning_rate": 3.448275862068966e-06,
|
| 905 |
+
"loss": 0.0014,
|
| 906 |
+
"step": 1140
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 3.9655172413793105,
|
| 910 |
+
"grad_norm": 0.00720432261005044,
|
| 911 |
+
"learning_rate": 1.724137931034483e-06,
|
| 912 |
+
"loss": 0.0014,
|
| 913 |
+
"step": 1150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 4.0,
|
| 917 |
+
"grad_norm": 0.006754900328814983,
|
| 918 |
+
"learning_rate": 0.0,
|
| 919 |
+
"loss": 0.0014,
|
| 920 |
+
"step": 1160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.0,
|
| 924 |
+
"step": 1160,
|
| 925 |
+
"total_flos": 1.436727240856535e+18,
|
| 926 |
+
"train_loss": 0.027367618223170524,
|
| 927 |
+
"train_runtime": 673.711,
|
| 928 |
+
"train_samples_per_second": 27.519,
|
| 929 |
+
"train_steps_per_second": 1.722
|
| 930 |
+
}
|
| 931 |
+
],
|
| 932 |
+
"logging_steps": 10,
|
| 933 |
+
"max_steps": 1160,
|
| 934 |
+
"num_input_tokens_seen": 0,
|
| 935 |
+
"num_train_epochs": 4,
|
| 936 |
+
"save_steps": 100,
|
| 937 |
+
"stateful_callbacks": {
|
| 938 |
+
"TrainerControl": {
|
| 939 |
+
"args": {
|
| 940 |
+
"should_epoch_stop": false,
|
| 941 |
+
"should_evaluate": false,
|
| 942 |
+
"should_log": false,
|
| 943 |
+
"should_save": true,
|
| 944 |
+
"should_training_stop": true
|
| 945 |
+
},
|
| 946 |
+
"attributes": {}
|
| 947 |
+
}
|
| 948 |
+
},
|
| 949 |
+
"total_flos": 1.436727240856535e+18,
|
| 950 |
+
"train_batch_size": 16,
|
| 951 |
+
"trial_name": null,
|
| 952 |
+
"trial_params": null
|
| 953 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7193ac5a61802fa2893efd6451518db670f51f08a2106a05a2bf4227a76453f3
|
| 3 |
+
size 5176
|