initial commit
Browse files- README.md +83 -0
- all_results.json +13 -0
- config.json +34 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Sep02_12-45-31_e95381c6f99a/events.out.tfevents.1725281176.e95381c6f99a.604.0 +3 -0
- runs/Sep02_12-45-31_e95381c6f99a/events.out.tfevents.1725282166.e95381c6f99a.604.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +651 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- imagefolder
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: vit-brain-tumour-v2
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Image Classification
|
| 16 |
+
type: image-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: essam24/brain-tumour-v2
|
| 19 |
+
type: imagefolder
|
| 20 |
+
config: default
|
| 21 |
+
split: test
|
| 22 |
+
args: default
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Accuracy
|
| 25 |
+
type: accuracy
|
| 26 |
+
value: 0.8703703703703703
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
+
|
| 32 |
+
# vit-brain-tumour-v2
|
| 33 |
+
|
| 34 |
+
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 essam24/brain-tumour-v2 dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.5359
|
| 37 |
+
- Accuracy: 0.8704
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 0.0002
|
| 57 |
+
- train_batch_size: 16
|
| 58 |
+
- eval_batch_size: 8
|
| 59 |
+
- seed: 42
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- num_epochs: 4
|
| 63 |
+
- mixed_precision_training: Native AMP
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 69 |
+
| 0.1236 | 0.5128 | 100 | 0.5990 | 0.8481 |
|
| 70 |
+
| 0.1695 | 1.0256 | 200 | 0.5359 | 0.8704 |
|
| 71 |
+
| 0.0186 | 1.5385 | 300 | 0.5705 | 0.8975 |
|
| 72 |
+
| 0.0368 | 2.0513 | 400 | 0.6136 | 0.8975 |
|
| 73 |
+
| 0.0036 | 2.5641 | 500 | 0.6122 | 0.9012 |
|
| 74 |
+
| 0.0029 | 3.0769 | 600 | 0.6067 | 0.9025 |
|
| 75 |
+
| 0.0027 | 3.5897 | 700 | 0.6449 | 0.9025 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.42.4
|
| 81 |
+
- Pytorch 2.4.0+cu121
|
| 82 |
+
- Datasets 2.21.0
|
| 83 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.8703703703703703,
|
| 4 |
+
"eval_loss": 0.5358908772468567,
|
| 5 |
+
"eval_runtime": 17.0949,
|
| 6 |
+
"eval_samples_per_second": 47.383,
|
| 7 |
+
"eval_steps_per_second": 5.967,
|
| 8 |
+
"total_flos": 9.636990200991498e+17,
|
| 9 |
+
"train_loss": 0.06401206638472967,
|
| 10 |
+
"train_runtime": 946.5564,
|
| 11 |
+
"train_samples_per_second": 13.138,
|
| 12 |
+
"train_steps_per_second": 0.824
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "glioblastoma",
|
| 13 |
+
"1": "glioma_tumor",
|
| 14 |
+
"2": "normal"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"glioblastoma": "0",
|
| 21 |
+
"glioma_tumor": "1",
|
| 22 |
+
"normal": "2"
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"model_type": "vit",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_channels": 3,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.42.4"
|
| 34 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.8703703703703703,
|
| 4 |
+
"eval_loss": 0.5358908772468567,
|
| 5 |
+
"eval_runtime": 17.0949,
|
| 6 |
+
"eval_samples_per_second": 47.383,
|
| 7 |
+
"eval_steps_per_second": 5.967
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:333503015ef74d970e8aa1c8f506772da7746e207f2dee8b2ab7f4a225b80099
|
| 3 |
+
size 343227052
|
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/Sep02_12-45-31_e95381c6f99a/events.out.tfevents.1725281176.e95381c6f99a.604.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd6ec91b9e895792bf37e092093f73f680c3e80224072e96b049d520cfeb85e
|
| 3 |
+
size 23921
|
runs/Sep02_12-45-31_e95381c6f99a/events.out.tfevents.1725282166.e95381c6f99a.604.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84164ef0e79ccbb2caae48b150f7ad30f628c93185d6928b826caf18c2455e95
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 9.636990200991498e+17,
|
| 4 |
+
"train_loss": 0.06401206638472967,
|
| 5 |
+
"train_runtime": 946.5564,
|
| 6 |
+
"train_samples_per_second": 13.138,
|
| 7 |
+
"train_steps_per_second": 0.824
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,651 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5358908772468567,
|
| 3 |
+
"best_model_checkpoint": "./vit-brain-tumour-v2/checkpoint-200",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 780,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05128205128205128,
|
| 13 |
+
"grad_norm": 1.8319804668426514,
|
| 14 |
+
"learning_rate": 0.00019743589743589744,
|
| 15 |
+
"loss": 0.8818,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10256410256410256,
|
| 20 |
+
"grad_norm": 0.8907442092895508,
|
| 21 |
+
"learning_rate": 0.00019487179487179487,
|
| 22 |
+
"loss": 0.3732,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15384615384615385,
|
| 27 |
+
"grad_norm": 0.5684014558792114,
|
| 28 |
+
"learning_rate": 0.00019230769230769233,
|
| 29 |
+
"loss": 0.2491,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.20512820512820512,
|
| 34 |
+
"grad_norm": 0.4306720495223999,
|
| 35 |
+
"learning_rate": 0.00018974358974358974,
|
| 36 |
+
"loss": 0.1864,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2564102564102564,
|
| 41 |
+
"grad_norm": 5.443202018737793,
|
| 42 |
+
"learning_rate": 0.0001871794871794872,
|
| 43 |
+
"loss": 0.2069,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3076923076923077,
|
| 48 |
+
"grad_norm": 0.45025336742401123,
|
| 49 |
+
"learning_rate": 0.00018461538461538463,
|
| 50 |
+
"loss": 0.2037,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.358974358974359,
|
| 55 |
+
"grad_norm": 0.8258907198905945,
|
| 56 |
+
"learning_rate": 0.00018205128205128207,
|
| 57 |
+
"loss": 0.1452,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.41025641025641024,
|
| 62 |
+
"grad_norm": 0.5631661415100098,
|
| 63 |
+
"learning_rate": 0.0001794871794871795,
|
| 64 |
+
"loss": 0.2959,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.46153846153846156,
|
| 69 |
+
"grad_norm": 0.5860559940338135,
|
| 70 |
+
"learning_rate": 0.00017692307692307693,
|
| 71 |
+
"loss": 0.0992,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5128205128205128,
|
| 76 |
+
"grad_norm": 3.4091548919677734,
|
| 77 |
+
"learning_rate": 0.00017435897435897436,
|
| 78 |
+
"loss": 0.1236,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5128205128205128,
|
| 83 |
+
"eval_accuracy": 0.8481481481481481,
|
| 84 |
+
"eval_loss": 0.5989510416984558,
|
| 85 |
+
"eval_runtime": 15.9913,
|
| 86 |
+
"eval_samples_per_second": 50.652,
|
| 87 |
+
"eval_steps_per_second": 6.378,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.5641025641025641,
|
| 92 |
+
"grad_norm": 1.3914088010787964,
|
| 93 |
+
"learning_rate": 0.0001717948717948718,
|
| 94 |
+
"loss": 0.1454,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.6153846153846154,
|
| 99 |
+
"grad_norm": 2.7670581340789795,
|
| 100 |
+
"learning_rate": 0.00016923076923076923,
|
| 101 |
+
"loss": 0.1344,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.6666666666666666,
|
| 106 |
+
"grad_norm": 0.14079055190086365,
|
| 107 |
+
"learning_rate": 0.0001666666666666667,
|
| 108 |
+
"loss": 0.2146,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.717948717948718,
|
| 113 |
+
"grad_norm": 0.2149924784898758,
|
| 114 |
+
"learning_rate": 0.0001641025641025641,
|
| 115 |
+
"loss": 0.1724,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.7692307692307693,
|
| 120 |
+
"grad_norm": 4.1687703132629395,
|
| 121 |
+
"learning_rate": 0.00016153846153846155,
|
| 122 |
+
"loss": 0.1342,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.8205128205128205,
|
| 127 |
+
"grad_norm": 0.09244555979967117,
|
| 128 |
+
"learning_rate": 0.00015897435897435896,
|
| 129 |
+
"loss": 0.1174,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.8717948717948718,
|
| 134 |
+
"grad_norm": 3.8858108520507812,
|
| 135 |
+
"learning_rate": 0.00015641025641025642,
|
| 136 |
+
"loss": 0.1445,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.9230769230769231,
|
| 141 |
+
"grad_norm": 0.13063883781433105,
|
| 142 |
+
"learning_rate": 0.00015384615384615385,
|
| 143 |
+
"loss": 0.086,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.9743589743589743,
|
| 148 |
+
"grad_norm": 0.4698440432548523,
|
| 149 |
+
"learning_rate": 0.00015128205128205128,
|
| 150 |
+
"loss": 0.0978,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.0256410256410255,
|
| 155 |
+
"grad_norm": 0.7778797149658203,
|
| 156 |
+
"learning_rate": 0.00014871794871794872,
|
| 157 |
+
"loss": 0.1695,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.0256410256410255,
|
| 162 |
+
"eval_accuracy": 0.8703703703703703,
|
| 163 |
+
"eval_loss": 0.5358908772468567,
|
| 164 |
+
"eval_runtime": 15.8447,
|
| 165 |
+
"eval_samples_per_second": 51.121,
|
| 166 |
+
"eval_steps_per_second": 6.437,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.0769230769230769,
|
| 171 |
+
"grad_norm": 0.09852629154920578,
|
| 172 |
+
"learning_rate": 0.00014615384615384615,
|
| 173 |
+
"loss": 0.0657,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.1282051282051282,
|
| 178 |
+
"grad_norm": 3.54819655418396,
|
| 179 |
+
"learning_rate": 0.0001435897435897436,
|
| 180 |
+
"loss": 0.0461,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.1794871794871795,
|
| 185 |
+
"grad_norm": 0.0645141452550888,
|
| 186 |
+
"learning_rate": 0.00014102564102564104,
|
| 187 |
+
"loss": 0.0754,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.2307692307692308,
|
| 192 |
+
"grad_norm": 0.2788432240486145,
|
| 193 |
+
"learning_rate": 0.00013846153846153847,
|
| 194 |
+
"loss": 0.0592,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.282051282051282,
|
| 199 |
+
"grad_norm": 0.9937513470649719,
|
| 200 |
+
"learning_rate": 0.0001358974358974359,
|
| 201 |
+
"loss": 0.0509,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.3333333333333333,
|
| 206 |
+
"grad_norm": 1.003893494606018,
|
| 207 |
+
"learning_rate": 0.00013333333333333334,
|
| 208 |
+
"loss": 0.0319,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.3846153846153846,
|
| 213 |
+
"grad_norm": 0.04893897473812103,
|
| 214 |
+
"learning_rate": 0.00013076923076923077,
|
| 215 |
+
"loss": 0.0348,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.435897435897436,
|
| 220 |
+
"grad_norm": 1.5978337526321411,
|
| 221 |
+
"learning_rate": 0.00012820512820512823,
|
| 222 |
+
"loss": 0.0434,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.4871794871794872,
|
| 227 |
+
"grad_norm": 0.044942498207092285,
|
| 228 |
+
"learning_rate": 0.00012564102564102564,
|
| 229 |
+
"loss": 0.0787,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.5384615384615383,
|
| 234 |
+
"grad_norm": 0.04497215896844864,
|
| 235 |
+
"learning_rate": 0.0001230769230769231,
|
| 236 |
+
"loss": 0.0186,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.5384615384615383,
|
| 241 |
+
"eval_accuracy": 0.8975308641975308,
|
| 242 |
+
"eval_loss": 0.570486843585968,
|
| 243 |
+
"eval_runtime": 16.7695,
|
| 244 |
+
"eval_samples_per_second": 48.302,
|
| 245 |
+
"eval_steps_per_second": 6.082,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.5897435897435899,
|
| 250 |
+
"grad_norm": 0.03568781167268753,
|
| 251 |
+
"learning_rate": 0.00012051282051282052,
|
| 252 |
+
"loss": 0.0339,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.641025641025641,
|
| 257 |
+
"grad_norm": 0.034062109887599945,
|
| 258 |
+
"learning_rate": 0.00011794871794871796,
|
| 259 |
+
"loss": 0.0072,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.6923076923076923,
|
| 264 |
+
"grad_norm": 0.03320033475756645,
|
| 265 |
+
"learning_rate": 0.00011538461538461538,
|
| 266 |
+
"loss": 0.0062,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.7435897435897436,
|
| 271 |
+
"grad_norm": 0.03138517960906029,
|
| 272 |
+
"learning_rate": 0.00011282051282051283,
|
| 273 |
+
"loss": 0.0063,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.7948717948717947,
|
| 278 |
+
"grad_norm": 0.04579005390405655,
|
| 279 |
+
"learning_rate": 0.00011025641025641027,
|
| 280 |
+
"loss": 0.0064,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.8461538461538463,
|
| 285 |
+
"grad_norm": 0.02792205847799778,
|
| 286 |
+
"learning_rate": 0.0001076923076923077,
|
| 287 |
+
"loss": 0.0076,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.8974358974358974,
|
| 292 |
+
"grad_norm": 0.03118390031158924,
|
| 293 |
+
"learning_rate": 0.00010512820512820514,
|
| 294 |
+
"loss": 0.0068,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.9487179487179487,
|
| 299 |
+
"grad_norm": 0.02970140054821968,
|
| 300 |
+
"learning_rate": 0.00010256410256410256,
|
| 301 |
+
"loss": 0.006,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"grad_norm": 0.09769738465547562,
|
| 307 |
+
"learning_rate": 0.0001,
|
| 308 |
+
"loss": 0.0374,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.051282051282051,
|
| 313 |
+
"grad_norm": 0.09561528265476227,
|
| 314 |
+
"learning_rate": 9.743589743589744e-05,
|
| 315 |
+
"loss": 0.0368,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.051282051282051,
|
| 320 |
+
"eval_accuracy": 0.8975308641975308,
|
| 321 |
+
"eval_loss": 0.6135894656181335,
|
| 322 |
+
"eval_runtime": 16.0452,
|
| 323 |
+
"eval_samples_per_second": 50.482,
|
| 324 |
+
"eval_steps_per_second": 6.357,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.1025641025641026,
|
| 329 |
+
"grad_norm": 0.02449757605791092,
|
| 330 |
+
"learning_rate": 9.487179487179487e-05,
|
| 331 |
+
"loss": 0.0051,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.1538461538461537,
|
| 336 |
+
"grad_norm": 0.02481868490576744,
|
| 337 |
+
"learning_rate": 9.230769230769232e-05,
|
| 338 |
+
"loss": 0.0044,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.2051282051282053,
|
| 343 |
+
"grad_norm": 0.02576032653450966,
|
| 344 |
+
"learning_rate": 8.974358974358975e-05,
|
| 345 |
+
"loss": 0.0044,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.2564102564102564,
|
| 350 |
+
"grad_norm": 0.026232751086354256,
|
| 351 |
+
"learning_rate": 8.717948717948718e-05,
|
| 352 |
+
"loss": 0.0043,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.3076923076923075,
|
| 357 |
+
"grad_norm": 0.02455274388194084,
|
| 358 |
+
"learning_rate": 8.461538461538461e-05,
|
| 359 |
+
"loss": 0.0039,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.358974358974359,
|
| 364 |
+
"grad_norm": 0.02121666818857193,
|
| 365 |
+
"learning_rate": 8.205128205128205e-05,
|
| 366 |
+
"loss": 0.007,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.41025641025641,
|
| 371 |
+
"grad_norm": 0.022693779319524765,
|
| 372 |
+
"learning_rate": 7.948717948717948e-05,
|
| 373 |
+
"loss": 0.0045,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.4615384615384617,
|
| 378 |
+
"grad_norm": 0.8521128296852112,
|
| 379 |
+
"learning_rate": 7.692307692307693e-05,
|
| 380 |
+
"loss": 0.0044,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.5128205128205128,
|
| 385 |
+
"grad_norm": 0.01888178288936615,
|
| 386 |
+
"learning_rate": 7.435897435897436e-05,
|
| 387 |
+
"loss": 0.0117,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.564102564102564,
|
| 392 |
+
"grad_norm": 0.026412444189190865,
|
| 393 |
+
"learning_rate": 7.17948717948718e-05,
|
| 394 |
+
"loss": 0.0036,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.564102564102564,
|
| 399 |
+
"eval_accuracy": 0.9012345679012346,
|
| 400 |
+
"eval_loss": 0.6121538877487183,
|
| 401 |
+
"eval_runtime": 16.7144,
|
| 402 |
+
"eval_samples_per_second": 48.461,
|
| 403 |
+
"eval_steps_per_second": 6.103,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.6153846153846154,
|
| 408 |
+
"grad_norm": 0.0200443584471941,
|
| 409 |
+
"learning_rate": 6.923076923076924e-05,
|
| 410 |
+
"loss": 0.0037,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.6666666666666665,
|
| 415 |
+
"grad_norm": 0.021741095930337906,
|
| 416 |
+
"learning_rate": 6.666666666666667e-05,
|
| 417 |
+
"loss": 0.0162,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.717948717948718,
|
| 422 |
+
"grad_norm": 1.7510725259780884,
|
| 423 |
+
"learning_rate": 6.410256410256412e-05,
|
| 424 |
+
"loss": 0.0044,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.769230769230769,
|
| 429 |
+
"grad_norm": 0.018649321049451828,
|
| 430 |
+
"learning_rate": 6.153846153846155e-05,
|
| 431 |
+
"loss": 0.0034,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.8205128205128203,
|
| 436 |
+
"grad_norm": 0.018490077927708626,
|
| 437 |
+
"learning_rate": 5.897435897435898e-05,
|
| 438 |
+
"loss": 0.0032,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.871794871794872,
|
| 443 |
+
"grad_norm": 0.018017606809735298,
|
| 444 |
+
"learning_rate": 5.6410256410256414e-05,
|
| 445 |
+
"loss": 0.003,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.9230769230769234,
|
| 450 |
+
"grad_norm": 0.01674257032573223,
|
| 451 |
+
"learning_rate": 5.384615384615385e-05,
|
| 452 |
+
"loss": 0.0031,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.9743589743589745,
|
| 457 |
+
"grad_norm": 0.017541637644171715,
|
| 458 |
+
"learning_rate": 5.128205128205128e-05,
|
| 459 |
+
"loss": 0.0031,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.0256410256410255,
|
| 464 |
+
"grad_norm": 0.016599087044596672,
|
| 465 |
+
"learning_rate": 4.871794871794872e-05,
|
| 466 |
+
"loss": 0.0029,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.076923076923077,
|
| 471 |
+
"grad_norm": 0.017430290579795837,
|
| 472 |
+
"learning_rate": 4.615384615384616e-05,
|
| 473 |
+
"loss": 0.0029,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.076923076923077,
|
| 478 |
+
"eval_accuracy": 0.9024691358024691,
|
| 479 |
+
"eval_loss": 0.6067318320274353,
|
| 480 |
+
"eval_runtime": 16.2775,
|
| 481 |
+
"eval_samples_per_second": 49.762,
|
| 482 |
+
"eval_steps_per_second": 6.266,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.128205128205128,
|
| 487 |
+
"grad_norm": 0.016984164714813232,
|
| 488 |
+
"learning_rate": 4.358974358974359e-05,
|
| 489 |
+
"loss": 0.003,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 3.1794871794871793,
|
| 494 |
+
"grad_norm": 0.01852291077375412,
|
| 495 |
+
"learning_rate": 4.1025641025641023e-05,
|
| 496 |
+
"loss": 0.0028,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 3.230769230769231,
|
| 501 |
+
"grad_norm": 0.016155986115336418,
|
| 502 |
+
"learning_rate": 3.846153846153846e-05,
|
| 503 |
+
"loss": 0.0066,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.282051282051282,
|
| 508 |
+
"grad_norm": 0.015048054046928883,
|
| 509 |
+
"learning_rate": 3.58974358974359e-05,
|
| 510 |
+
"loss": 0.0027,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 3.3333333333333335,
|
| 515 |
+
"grad_norm": 0.014590720646083355,
|
| 516 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 517 |
+
"loss": 0.0028,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.3846153846153846,
|
| 522 |
+
"grad_norm": 0.015942472964525223,
|
| 523 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 524 |
+
"loss": 0.0027,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.435897435897436,
|
| 529 |
+
"grad_norm": 0.015167794190347195,
|
| 530 |
+
"learning_rate": 2.8205128205128207e-05,
|
| 531 |
+
"loss": 0.0031,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.4871794871794872,
|
| 536 |
+
"grad_norm": 0.015961118042469025,
|
| 537 |
+
"learning_rate": 2.564102564102564e-05,
|
| 538 |
+
"loss": 0.0027,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.5384615384615383,
|
| 543 |
+
"grad_norm": 0.01679452508687973,
|
| 544 |
+
"learning_rate": 2.307692307692308e-05,
|
| 545 |
+
"loss": 0.0029,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.58974358974359,
|
| 550 |
+
"grad_norm": 0.014717783778905869,
|
| 551 |
+
"learning_rate": 2.0512820512820512e-05,
|
| 552 |
+
"loss": 0.0027,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.58974358974359,
|
| 557 |
+
"eval_accuracy": 0.9024691358024691,
|
| 558 |
+
"eval_loss": 0.644864022731781,
|
| 559 |
+
"eval_runtime": 16.2975,
|
| 560 |
+
"eval_samples_per_second": 49.701,
|
| 561 |
+
"eval_steps_per_second": 6.259,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.641025641025641,
|
| 566 |
+
"grad_norm": 0.01574333943426609,
|
| 567 |
+
"learning_rate": 1.794871794871795e-05,
|
| 568 |
+
"loss": 0.0028,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.6923076923076925,
|
| 573 |
+
"grad_norm": 0.014611059799790382,
|
| 574 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 575 |
+
"loss": 0.0029,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.7435897435897436,
|
| 580 |
+
"grad_norm": 0.014431651681661606,
|
| 581 |
+
"learning_rate": 1.282051282051282e-05,
|
| 582 |
+
"loss": 0.0026,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.7948717948717947,
|
| 587 |
+
"grad_norm": 0.015641087666153908,
|
| 588 |
+
"learning_rate": 1.0256410256410256e-05,
|
| 589 |
+
"loss": 0.0025,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.8461538461538463,
|
| 594 |
+
"grad_norm": 0.021887468174099922,
|
| 595 |
+
"learning_rate": 7.692307692307694e-06,
|
| 596 |
+
"loss": 0.0027,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.8974358974358974,
|
| 601 |
+
"grad_norm": 0.015822410583496094,
|
| 602 |
+
"learning_rate": 5.128205128205128e-06,
|
| 603 |
+
"loss": 0.0025,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.948717948717949,
|
| 608 |
+
"grad_norm": 0.015171283856034279,
|
| 609 |
+
"learning_rate": 2.564102564102564e-06,
|
| 610 |
+
"loss": 0.0026,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.0,
|
| 615 |
+
"grad_norm": 0.0153021439909935,
|
| 616 |
+
"learning_rate": 0.0,
|
| 617 |
+
"loss": 0.0028,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 4.0,
|
| 622 |
+
"step": 780,
|
| 623 |
+
"total_flos": 9.636990200991498e+17,
|
| 624 |
+
"train_loss": 0.06401206638472967,
|
| 625 |
+
"train_runtime": 946.5564,
|
| 626 |
+
"train_samples_per_second": 13.138,
|
| 627 |
+
"train_steps_per_second": 0.824
|
| 628 |
+
}
|
| 629 |
+
],
|
| 630 |
+
"logging_steps": 10,
|
| 631 |
+
"max_steps": 780,
|
| 632 |
+
"num_input_tokens_seen": 0,
|
| 633 |
+
"num_train_epochs": 4,
|
| 634 |
+
"save_steps": 100,
|
| 635 |
+
"stateful_callbacks": {
|
| 636 |
+
"TrainerControl": {
|
| 637 |
+
"args": {
|
| 638 |
+
"should_epoch_stop": false,
|
| 639 |
+
"should_evaluate": false,
|
| 640 |
+
"should_log": false,
|
| 641 |
+
"should_save": true,
|
| 642 |
+
"should_training_stop": true
|
| 643 |
+
},
|
| 644 |
+
"attributes": {}
|
| 645 |
+
}
|
| 646 |
+
},
|
| 647 |
+
"total_flos": 9.636990200991498e+17,
|
| 648 |
+
"train_batch_size": 16,
|
| 649 |
+
"trial_name": null,
|
| 650 |
+
"trial_params": null
|
| 651 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44d8f9c4ba7b8808c714914f424b69d95c828cf2cb269bd7b1f1d0075846807c
|
| 3 |
+
size 5112
|