dhritic99/model99123
Browse files- README.md +70 -0
- all_results.json +13 -0
- config.json +36 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +646 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-brain-tumor-detection3
|
| 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-brain-tumor-detection3
|
| 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: 0.2613
|
| 21 |
+
- Accuracy: 0.9508
|
| 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: 3e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 1000
|
| 49 |
+
- num_epochs: 60
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 56 |
+
| 0.4758 | 7.8125 | 500 | 0.5695 | 0.7939 |
|
| 57 |
+
| 0.1137 | 15.625 | 1000 | 0.4398 | 0.8711 |
|
| 58 |
+
| 0.0466 | 23.4375 | 1500 | 0.4086 | 0.9023 |
|
| 59 |
+
| 0.0086 | 31.25 | 2000 | 0.2433 | 0.9463 |
|
| 60 |
+
| 0.0034 | 39.0625 | 2500 | 0.1636 | 0.9688 |
|
| 61 |
+
| 0.002 | 46.875 | 3000 | 0.1739 | 0.9707 |
|
| 62 |
+
| 0.0014 | 54.6875 | 3500 | 0.1818 | 0.9707 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.42.4
|
| 68 |
+
- Pytorch 2.3.1+cu121
|
| 69 |
+
- Datasets 2.20.0
|
| 70 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 60.0,
|
| 3 |
+
"eval_accuracy": 0.95078125,
|
| 4 |
+
"eval_loss": 0.26134949922561646,
|
| 5 |
+
"eval_runtime": 6.7187,
|
| 6 |
+
"eval_samples_per_second": 190.513,
|
| 7 |
+
"eval_steps_per_second": 23.814,
|
| 8 |
+
"total_flos": 1.904477274611122e+19,
|
| 9 |
+
"train_loss": 0.14902369955088943,
|
| 10 |
+
"train_runtime": 2785.8591,
|
| 11 |
+
"train_samples_per_second": 88.217,
|
| 12 |
+
"train_steps_per_second": 1.378
|
| 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": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3"
|
| 16 |
+
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1,
|
| 23 |
+
"LABEL_2": 2,
|
| 24 |
+
"LABEL_3": 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": "4.42.4"
|
| 36 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 60.0,
|
| 3 |
+
"eval_accuracy": 0.95078125,
|
| 4 |
+
"eval_loss": 0.26134949922561646,
|
| 5 |
+
"eval_runtime": 6.7187,
|
| 6 |
+
"eval_samples_per_second": 190.513,
|
| 7 |
+
"eval_steps_per_second": 23.814
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3158ce4921cc7de61a99fa5043ead77c62382fbae720ec9b3a76b25a7120d00c
|
| 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 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 60.0,
|
| 3 |
+
"total_flos": 1.904477274611122e+19,
|
| 4 |
+
"train_loss": 0.14902369955088943,
|
| 5 |
+
"train_runtime": 2785.8591,
|
| 6 |
+
"train_samples_per_second": 88.217,
|
| 7 |
+
"train_steps_per_second": 1.378
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,646 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.16363227367401123,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-brain-tumor-detection3/checkpoint-2500",
|
| 4 |
+
"epoch": 60.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3840,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.78125,
|
| 13 |
+
"grad_norm": 1.8165547847747803,
|
| 14 |
+
"learning_rate": 1.5e-06,
|
| 15 |
+
"loss": 1.3842,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.5625,
|
| 20 |
+
"grad_norm": 1.1670353412628174,
|
| 21 |
+
"learning_rate": 3e-06,
|
| 22 |
+
"loss": 1.2128,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.34375,
|
| 27 |
+
"grad_norm": 1.4207779169082642,
|
| 28 |
+
"learning_rate": 4.5e-06,
|
| 29 |
+
"loss": 1.0365,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.125,
|
| 34 |
+
"grad_norm": 3.359316825866699,
|
| 35 |
+
"learning_rate": 6e-06,
|
| 36 |
+
"loss": 0.9528,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.90625,
|
| 41 |
+
"grad_norm": 1.4744346141815186,
|
| 42 |
+
"learning_rate": 7.5e-06,
|
| 43 |
+
"loss": 0.8693,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.6875,
|
| 48 |
+
"grad_norm": 2.3251893520355225,
|
| 49 |
+
"learning_rate": 9e-06,
|
| 50 |
+
"loss": 0.8014,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 5.46875,
|
| 55 |
+
"grad_norm": 3.080569267272949,
|
| 56 |
+
"learning_rate": 1.05e-05,
|
| 57 |
+
"loss": 0.7156,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 6.25,
|
| 62 |
+
"grad_norm": 2.417529582977295,
|
| 63 |
+
"learning_rate": 1.2e-05,
|
| 64 |
+
"loss": 0.6215,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 7.03125,
|
| 69 |
+
"grad_norm": 2.6332898139953613,
|
| 70 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 71 |
+
"loss": 0.5781,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.8125,
|
| 76 |
+
"grad_norm": 4.613404750823975,
|
| 77 |
+
"learning_rate": 1.5e-05,
|
| 78 |
+
"loss": 0.4758,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 7.8125,
|
| 83 |
+
"eval_accuracy": 0.7939453125,
|
| 84 |
+
"eval_loss": 0.5694867372512817,
|
| 85 |
+
"eval_runtime": 6.0709,
|
| 86 |
+
"eval_samples_per_second": 168.674,
|
| 87 |
+
"eval_steps_per_second": 21.084,
|
| 88 |
+
"step": 500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 8.59375,
|
| 92 |
+
"grad_norm": 3.2593910694122314,
|
| 93 |
+
"learning_rate": 1.65e-05,
|
| 94 |
+
"loss": 0.3951,
|
| 95 |
+
"step": 550
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 9.375,
|
| 99 |
+
"grad_norm": 4.835229396820068,
|
| 100 |
+
"learning_rate": 1.8e-05,
|
| 101 |
+
"loss": 0.278,
|
| 102 |
+
"step": 600
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 10.15625,
|
| 106 |
+
"grad_norm": 2.339912176132202,
|
| 107 |
+
"learning_rate": 1.95e-05,
|
| 108 |
+
"loss": 0.2564,
|
| 109 |
+
"step": 650
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 10.9375,
|
| 113 |
+
"grad_norm": 1.6154627799987793,
|
| 114 |
+
"learning_rate": 2.1e-05,
|
| 115 |
+
"loss": 0.2094,
|
| 116 |
+
"step": 700
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 11.71875,
|
| 120 |
+
"grad_norm": 3.8827977180480957,
|
| 121 |
+
"learning_rate": 2.25e-05,
|
| 122 |
+
"loss": 0.1495,
|
| 123 |
+
"step": 750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 12.5,
|
| 127 |
+
"grad_norm": 6.941565036773682,
|
| 128 |
+
"learning_rate": 2.4e-05,
|
| 129 |
+
"loss": 0.1284,
|
| 130 |
+
"step": 800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 13.28125,
|
| 134 |
+
"grad_norm": 2.415818691253662,
|
| 135 |
+
"learning_rate": 2.55e-05,
|
| 136 |
+
"loss": 0.1136,
|
| 137 |
+
"step": 850
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 14.0625,
|
| 141 |
+
"grad_norm": 1.2879343032836914,
|
| 142 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 143 |
+
"loss": 0.0863,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 14.84375,
|
| 148 |
+
"grad_norm": 14.791470527648926,
|
| 149 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 150 |
+
"loss": 0.1258,
|
| 151 |
+
"step": 950
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 15.625,
|
| 155 |
+
"grad_norm": 13.995768547058105,
|
| 156 |
+
"learning_rate": 3e-05,
|
| 157 |
+
"loss": 0.1137,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 15.625,
|
| 162 |
+
"eval_accuracy": 0.87109375,
|
| 163 |
+
"eval_loss": 0.43984174728393555,
|
| 164 |
+
"eval_runtime": 5.4017,
|
| 165 |
+
"eval_samples_per_second": 189.569,
|
| 166 |
+
"eval_steps_per_second": 23.696,
|
| 167 |
+
"step": 1000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 16.40625,
|
| 171 |
+
"grad_norm": 24.01154327392578,
|
| 172 |
+
"learning_rate": 2.989554317548747e-05,
|
| 173 |
+
"loss": 0.0756,
|
| 174 |
+
"step": 1050
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 17.1875,
|
| 178 |
+
"grad_norm": 0.24175554513931274,
|
| 179 |
+
"learning_rate": 2.979108635097493e-05,
|
| 180 |
+
"loss": 0.0933,
|
| 181 |
+
"step": 1100
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 17.96875,
|
| 185 |
+
"grad_norm": 0.25062623620033264,
|
| 186 |
+
"learning_rate": 2.96866295264624e-05,
|
| 187 |
+
"loss": 0.0676,
|
| 188 |
+
"step": 1150
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 18.75,
|
| 192 |
+
"grad_norm": 0.775455892086029,
|
| 193 |
+
"learning_rate": 2.958217270194986e-05,
|
| 194 |
+
"loss": 0.081,
|
| 195 |
+
"step": 1200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 19.53125,
|
| 199 |
+
"grad_norm": 0.12767118215560913,
|
| 200 |
+
"learning_rate": 2.947771587743733e-05,
|
| 201 |
+
"loss": 0.0756,
|
| 202 |
+
"step": 1250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 20.3125,
|
| 206 |
+
"grad_norm": 0.17824232578277588,
|
| 207 |
+
"learning_rate": 2.937325905292479e-05,
|
| 208 |
+
"loss": 0.0571,
|
| 209 |
+
"step": 1300
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 21.09375,
|
| 213 |
+
"grad_norm": 0.1250143200159073,
|
| 214 |
+
"learning_rate": 2.926880222841226e-05,
|
| 215 |
+
"loss": 0.0462,
|
| 216 |
+
"step": 1350
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 21.875,
|
| 220 |
+
"grad_norm": 1.6465438604354858,
|
| 221 |
+
"learning_rate": 2.916434540389972e-05,
|
| 222 |
+
"loss": 0.0346,
|
| 223 |
+
"step": 1400
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 22.65625,
|
| 227 |
+
"grad_norm": 9.335956573486328,
|
| 228 |
+
"learning_rate": 2.905988857938719e-05,
|
| 229 |
+
"loss": 0.046,
|
| 230 |
+
"step": 1450
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 23.4375,
|
| 234 |
+
"grad_norm": 0.20395609736442566,
|
| 235 |
+
"learning_rate": 2.895543175487465e-05,
|
| 236 |
+
"loss": 0.0466,
|
| 237 |
+
"step": 1500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 23.4375,
|
| 241 |
+
"eval_accuracy": 0.90234375,
|
| 242 |
+
"eval_loss": 0.4086352288722992,
|
| 243 |
+
"eval_runtime": 5.3678,
|
| 244 |
+
"eval_samples_per_second": 190.768,
|
| 245 |
+
"eval_steps_per_second": 23.846,
|
| 246 |
+
"step": 1500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 24.21875,
|
| 250 |
+
"grad_norm": 0.06884710490703583,
|
| 251 |
+
"learning_rate": 2.885097493036212e-05,
|
| 252 |
+
"loss": 0.044,
|
| 253 |
+
"step": 1550
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 25.0,
|
| 257 |
+
"grad_norm": 0.2089349329471588,
|
| 258 |
+
"learning_rate": 2.8746518105849583e-05,
|
| 259 |
+
"loss": 0.0382,
|
| 260 |
+
"step": 1600
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 25.78125,
|
| 264 |
+
"grad_norm": 0.09039656072854996,
|
| 265 |
+
"learning_rate": 2.8642061281337048e-05,
|
| 266 |
+
"loss": 0.0279,
|
| 267 |
+
"step": 1650
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 26.5625,
|
| 271 |
+
"grad_norm": 0.05787573382258415,
|
| 272 |
+
"learning_rate": 2.8537604456824513e-05,
|
| 273 |
+
"loss": 0.0257,
|
| 274 |
+
"step": 1700
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 27.34375,
|
| 278 |
+
"grad_norm": 0.04917814955115318,
|
| 279 |
+
"learning_rate": 2.8433147632311978e-05,
|
| 280 |
+
"loss": 0.0229,
|
| 281 |
+
"step": 1750
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 28.125,
|
| 285 |
+
"grad_norm": 0.06560017913579941,
|
| 286 |
+
"learning_rate": 2.8328690807799443e-05,
|
| 287 |
+
"loss": 0.0191,
|
| 288 |
+
"step": 1800
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 28.90625,
|
| 292 |
+
"grad_norm": 0.03920649737119675,
|
| 293 |
+
"learning_rate": 2.8224233983286908e-05,
|
| 294 |
+
"loss": 0.0114,
|
| 295 |
+
"step": 1850
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 29.6875,
|
| 299 |
+
"grad_norm": 0.9064533114433289,
|
| 300 |
+
"learning_rate": 2.8119777158774373e-05,
|
| 301 |
+
"loss": 0.0165,
|
| 302 |
+
"step": 1900
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 30.46875,
|
| 306 |
+
"grad_norm": 0.03491423651576042,
|
| 307 |
+
"learning_rate": 2.8015320334261838e-05,
|
| 308 |
+
"loss": 0.0078,
|
| 309 |
+
"step": 1950
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 31.25,
|
| 313 |
+
"grad_norm": 0.029768764972686768,
|
| 314 |
+
"learning_rate": 2.7910863509749306e-05,
|
| 315 |
+
"loss": 0.0086,
|
| 316 |
+
"step": 2000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 31.25,
|
| 320 |
+
"eval_accuracy": 0.9462890625,
|
| 321 |
+
"eval_loss": 0.2432650774717331,
|
| 322 |
+
"eval_runtime": 5.6297,
|
| 323 |
+
"eval_samples_per_second": 181.891,
|
| 324 |
+
"eval_steps_per_second": 22.736,
|
| 325 |
+
"step": 2000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 32.03125,
|
| 329 |
+
"grad_norm": 0.02953988127410412,
|
| 330 |
+
"learning_rate": 2.780640668523677e-05,
|
| 331 |
+
"loss": 0.0062,
|
| 332 |
+
"step": 2050
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 32.8125,
|
| 336 |
+
"grad_norm": 0.025788016617298126,
|
| 337 |
+
"learning_rate": 2.7701949860724236e-05,
|
| 338 |
+
"loss": 0.0057,
|
| 339 |
+
"step": 2100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 33.59375,
|
| 343 |
+
"grad_norm": 0.03053743578493595,
|
| 344 |
+
"learning_rate": 2.75974930362117e-05,
|
| 345 |
+
"loss": 0.0053,
|
| 346 |
+
"step": 2150
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 34.375,
|
| 350 |
+
"grad_norm": 0.021916454657912254,
|
| 351 |
+
"learning_rate": 2.7493036211699166e-05,
|
| 352 |
+
"loss": 0.0049,
|
| 353 |
+
"step": 2200
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 35.15625,
|
| 357 |
+
"grad_norm": 0.021212272346019745,
|
| 358 |
+
"learning_rate": 2.738857938718663e-05,
|
| 359 |
+
"loss": 0.0045,
|
| 360 |
+
"step": 2250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 35.9375,
|
| 364 |
+
"grad_norm": 0.020344305783510208,
|
| 365 |
+
"learning_rate": 2.7284122562674096e-05,
|
| 366 |
+
"loss": 0.0043,
|
| 367 |
+
"step": 2300
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 36.71875,
|
| 371 |
+
"grad_norm": 0.018891936168074608,
|
| 372 |
+
"learning_rate": 2.717966573816156e-05,
|
| 373 |
+
"loss": 0.004,
|
| 374 |
+
"step": 2350
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 37.5,
|
| 378 |
+
"grad_norm": 0.017234979197382927,
|
| 379 |
+
"learning_rate": 2.7075208913649025e-05,
|
| 380 |
+
"loss": 0.0038,
|
| 381 |
+
"step": 2400
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 38.28125,
|
| 385 |
+
"grad_norm": 0.016466792672872543,
|
| 386 |
+
"learning_rate": 2.697075208913649e-05,
|
| 387 |
+
"loss": 0.0035,
|
| 388 |
+
"step": 2450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 39.0625,
|
| 392 |
+
"grad_norm": 0.017314311116933823,
|
| 393 |
+
"learning_rate": 2.6866295264623955e-05,
|
| 394 |
+
"loss": 0.0034,
|
| 395 |
+
"step": 2500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 39.0625,
|
| 399 |
+
"eval_accuracy": 0.96875,
|
| 400 |
+
"eval_loss": 0.16363227367401123,
|
| 401 |
+
"eval_runtime": 6.1162,
|
| 402 |
+
"eval_samples_per_second": 167.424,
|
| 403 |
+
"eval_steps_per_second": 20.928,
|
| 404 |
+
"step": 2500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 39.84375,
|
| 408 |
+
"grad_norm": 0.01642526686191559,
|
| 409 |
+
"learning_rate": 2.676183844011142e-05,
|
| 410 |
+
"loss": 0.0032,
|
| 411 |
+
"step": 2550
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 40.625,
|
| 415 |
+
"grad_norm": 0.013880325481295586,
|
| 416 |
+
"learning_rate": 2.665738161559889e-05,
|
| 417 |
+
"loss": 0.003,
|
| 418 |
+
"step": 2600
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 41.40625,
|
| 422 |
+
"grad_norm": 0.01303493045270443,
|
| 423 |
+
"learning_rate": 2.655292479108635e-05,
|
| 424 |
+
"loss": 0.0028,
|
| 425 |
+
"step": 2650
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 42.1875,
|
| 429 |
+
"grad_norm": 0.013205628842115402,
|
| 430 |
+
"learning_rate": 2.644846796657382e-05,
|
| 431 |
+
"loss": 0.0027,
|
| 432 |
+
"step": 2700
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 42.96875,
|
| 436 |
+
"grad_norm": 0.011895690113306046,
|
| 437 |
+
"learning_rate": 2.634401114206128e-05,
|
| 438 |
+
"loss": 0.0026,
|
| 439 |
+
"step": 2750
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 43.75,
|
| 443 |
+
"grad_norm": 0.011271192692220211,
|
| 444 |
+
"learning_rate": 2.6239554317548748e-05,
|
| 445 |
+
"loss": 0.0024,
|
| 446 |
+
"step": 2800
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 44.53125,
|
| 450 |
+
"grad_norm": 0.011179978027939796,
|
| 451 |
+
"learning_rate": 2.613509749303621e-05,
|
| 452 |
+
"loss": 0.0024,
|
| 453 |
+
"step": 2850
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 45.3125,
|
| 457 |
+
"grad_norm": 0.010614069178700447,
|
| 458 |
+
"learning_rate": 2.6030640668523678e-05,
|
| 459 |
+
"loss": 0.0022,
|
| 460 |
+
"step": 2900
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 46.09375,
|
| 464 |
+
"grad_norm": 0.009998313151299953,
|
| 465 |
+
"learning_rate": 2.5926183844011143e-05,
|
| 466 |
+
"loss": 0.0021,
|
| 467 |
+
"step": 2950
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 46.875,
|
| 471 |
+
"grad_norm": 0.009446458891034126,
|
| 472 |
+
"learning_rate": 2.5821727019498608e-05,
|
| 473 |
+
"loss": 0.002,
|
| 474 |
+
"step": 3000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 46.875,
|
| 478 |
+
"eval_accuracy": 0.970703125,
|
| 479 |
+
"eval_loss": 0.17385585606098175,
|
| 480 |
+
"eval_runtime": 5.8806,
|
| 481 |
+
"eval_samples_per_second": 174.131,
|
| 482 |
+
"eval_steps_per_second": 21.766,
|
| 483 |
+
"step": 3000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 47.65625,
|
| 487 |
+
"grad_norm": 0.009701834060251713,
|
| 488 |
+
"learning_rate": 2.5717270194986073e-05,
|
| 489 |
+
"loss": 0.002,
|
| 490 |
+
"step": 3050
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 48.4375,
|
| 494 |
+
"grad_norm": 0.009180723689496517,
|
| 495 |
+
"learning_rate": 2.5612813370473538e-05,
|
| 496 |
+
"loss": 0.0019,
|
| 497 |
+
"step": 3100
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 49.21875,
|
| 501 |
+
"grad_norm": 0.008364294655621052,
|
| 502 |
+
"learning_rate": 2.5508356545961006e-05,
|
| 503 |
+
"loss": 0.0018,
|
| 504 |
+
"step": 3150
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 50.0,
|
| 508 |
+
"grad_norm": 0.008195644244551659,
|
| 509 |
+
"learning_rate": 2.5403899721448468e-05,
|
| 510 |
+
"loss": 0.0017,
|
| 511 |
+
"step": 3200
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 50.78125,
|
| 515 |
+
"grad_norm": 0.008112799376249313,
|
| 516 |
+
"learning_rate": 2.5299442896935936e-05,
|
| 517 |
+
"loss": 0.0016,
|
| 518 |
+
"step": 3250
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 51.5625,
|
| 522 |
+
"grad_norm": 0.007568549830466509,
|
| 523 |
+
"learning_rate": 2.5194986072423398e-05,
|
| 524 |
+
"loss": 0.0016,
|
| 525 |
+
"step": 3300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 52.34375,
|
| 529 |
+
"grad_norm": 0.007013232912868261,
|
| 530 |
+
"learning_rate": 2.5090529247910866e-05,
|
| 531 |
+
"loss": 0.0015,
|
| 532 |
+
"step": 3350
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 53.125,
|
| 536 |
+
"grad_norm": 0.006883300840854645,
|
| 537 |
+
"learning_rate": 2.4986072423398327e-05,
|
| 538 |
+
"loss": 0.0014,
|
| 539 |
+
"step": 3400
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 53.90625,
|
| 543 |
+
"grad_norm": 0.006791520398110151,
|
| 544 |
+
"learning_rate": 2.4881615598885796e-05,
|
| 545 |
+
"loss": 0.0014,
|
| 546 |
+
"step": 3450
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 54.6875,
|
| 550 |
+
"grad_norm": 0.008187716826796532,
|
| 551 |
+
"learning_rate": 2.4777158774373257e-05,
|
| 552 |
+
"loss": 0.0014,
|
| 553 |
+
"step": 3500
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 54.6875,
|
| 557 |
+
"eval_accuracy": 0.970703125,
|
| 558 |
+
"eval_loss": 0.1817573606967926,
|
| 559 |
+
"eval_runtime": 5.8237,
|
| 560 |
+
"eval_samples_per_second": 175.833,
|
| 561 |
+
"eval_steps_per_second": 21.979,
|
| 562 |
+
"step": 3500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 55.46875,
|
| 566 |
+
"grad_norm": 0.0065140994265675545,
|
| 567 |
+
"learning_rate": 2.4672701949860726e-05,
|
| 568 |
+
"loss": 0.0013,
|
| 569 |
+
"step": 3550
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 56.25,
|
| 573 |
+
"grad_norm": 0.007060408126562834,
|
| 574 |
+
"learning_rate": 2.456824512534819e-05,
|
| 575 |
+
"loss": 0.0012,
|
| 576 |
+
"step": 3600
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 57.03125,
|
| 580 |
+
"grad_norm": 0.0056546530686318874,
|
| 581 |
+
"learning_rate": 2.4463788300835655e-05,
|
| 582 |
+
"loss": 0.0012,
|
| 583 |
+
"step": 3650
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 57.8125,
|
| 587 |
+
"grad_norm": 0.006707963068038225,
|
| 588 |
+
"learning_rate": 2.435933147632312e-05,
|
| 589 |
+
"loss": 0.0012,
|
| 590 |
+
"step": 3700
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 58.59375,
|
| 594 |
+
"grad_norm": 0.006301193963736296,
|
| 595 |
+
"learning_rate": 2.4254874651810585e-05,
|
| 596 |
+
"loss": 0.0011,
|
| 597 |
+
"step": 3750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 59.375,
|
| 601 |
+
"grad_norm": 0.005066621117293835,
|
| 602 |
+
"learning_rate": 2.415041782729805e-05,
|
| 603 |
+
"loss": 0.0011,
|
| 604 |
+
"step": 3800
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 60.0,
|
| 608 |
+
"step": 3840,
|
| 609 |
+
"total_flos": 1.904477274611122e+19,
|
| 610 |
+
"train_loss": 0.14902369955088943,
|
| 611 |
+
"train_runtime": 2785.8591,
|
| 612 |
+
"train_samples_per_second": 88.217,
|
| 613 |
+
"train_steps_per_second": 1.378
|
| 614 |
+
}
|
| 615 |
+
],
|
| 616 |
+
"logging_steps": 50,
|
| 617 |
+
"max_steps": 3840,
|
| 618 |
+
"num_input_tokens_seen": 0,
|
| 619 |
+
"num_train_epochs": 60,
|
| 620 |
+
"save_steps": 500,
|
| 621 |
+
"stateful_callbacks": {
|
| 622 |
+
"EarlyStoppingCallback": {
|
| 623 |
+
"args": {
|
| 624 |
+
"early_stopping_patience": 5,
|
| 625 |
+
"early_stopping_threshold": 0.0
|
| 626 |
+
},
|
| 627 |
+
"attributes": {
|
| 628 |
+
"early_stopping_patience_counter": 0
|
| 629 |
+
}
|
| 630 |
+
},
|
| 631 |
+
"TrainerControl": {
|
| 632 |
+
"args": {
|
| 633 |
+
"should_epoch_stop": false,
|
| 634 |
+
"should_evaluate": false,
|
| 635 |
+
"should_log": false,
|
| 636 |
+
"should_save": true,
|
| 637 |
+
"should_training_stop": true
|
| 638 |
+
},
|
| 639 |
+
"attributes": {}
|
| 640 |
+
}
|
| 641 |
+
},
|
| 642 |
+
"total_flos": 1.904477274611122e+19,
|
| 643 |
+
"train_batch_size": 16,
|
| 644 |
+
"trial_name": null,
|
| 645 |
+
"trial_params": null
|
| 646 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84173542b25ab0ff865d0db2a4e5d9b4838d6312ff6d86d248cd2347a190daf4
|
| 3 |
+
size 5112
|