Commit
•
f5076cb
1
Parent(s):
823dafc
initial commit
Browse files- README.md +83 -0
- all_results.json +13 -0
- config.json +36 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/May01_17-45-34_e5fd9b370bfd/events.out.tfevents.1714585535.e5fd9b370bfd.197.2 +3 -0
- runs/May01_17-50-29_e5fd9b370bfd/events.out.tfevents.1714585829.e5fd9b370bfd.8190.0 +3 -0
- runs/May01_17-50-29_e5fd9b370bfd/events.out.tfevents.1714586766.e5fd9b370bfd.8190.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +597 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-large-patch32-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- imagefolder
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: vit-large-brain-xray
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Image Classification
|
| 16 |
+
type: image-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: sartajbhuvaji/Brain-Tumor-Classification
|
| 19 |
+
type: imagefolder
|
| 20 |
+
config: default
|
| 21 |
+
split: Testing
|
| 22 |
+
args: default
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Accuracy
|
| 25 |
+
type: accuracy
|
| 26 |
+
value: 0.7081218274111675
|
| 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-large-brain-xray
|
| 33 |
+
|
| 34 |
+
This model is a fine-tuned version of [google/vit-large-patch32-224-in21k](https://huggingface.co/google/vit-large-patch32-224-in21k) on the sartajbhuvaji/Brain-Tumor-Classification dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 1.0935
|
| 37 |
+
- Accuracy: 0.7081
|
| 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 |
+
| 0.2144 | 0.5556 | 100 | 1.2679 | 0.6269 |
|
| 70 |
+
| 0.1091 | 1.1111 | 200 | 1.0935 | 0.7081 |
|
| 71 |
+
| 0.1078 | 1.6667 | 300 | 1.1237 | 0.7589 |
|
| 72 |
+
| 0.016 | 2.2222 | 400 | 1.2356 | 0.7563 |
|
| 73 |
+
| 0.0095 | 2.7778 | 500 | 1.2316 | 0.7589 |
|
| 74 |
+
| 0.0066 | 3.3333 | 600 | 1.3165 | 0.7589 |
|
| 75 |
+
| 0.0161 | 3.8889 | 700 | 1.3412 | 0.7614 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.40.1
|
| 81 |
+
- Pytorch 2.2.1+cu121
|
| 82 |
+
- Datasets 2.19.0
|
| 83 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.7081218274111675,
|
| 4 |
+
"eval_loss": 1.0935020446777344,
|
| 5 |
+
"eval_runtime": 7.0813,
|
| 6 |
+
"eval_samples_per_second": 55.64,
|
| 7 |
+
"eval_steps_per_second": 7.061,
|
| 8 |
+
"total_flos": 3.16768696086528e+18,
|
| 9 |
+
"train_loss": 0.15098576029348704,
|
| 10 |
+
"train_runtime": 924.305,
|
| 11 |
+
"train_samples_per_second": 12.42,
|
| 12 |
+
"train_steps_per_second": 0.779
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-large-patch32-224-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": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "glioma_tumor",
|
| 13 |
+
"1": "meningioma_tumor",
|
| 14 |
+
"2": "no_tumor",
|
| 15 |
+
"3": "pituitary_tumor"
|
| 16 |
+
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"glioma_tumor": "0",
|
| 22 |
+
"meningioma_tumor": "1",
|
| 23 |
+
"no_tumor": "2",
|
| 24 |
+
"pituitary_tumor": "3"
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"model_type": "vit",
|
| 28 |
+
"num_attention_heads": 16,
|
| 29 |
+
"num_channels": 3,
|
| 30 |
+
"num_hidden_layers": 24,
|
| 31 |
+
"patch_size": 32,
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"qkv_bias": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.40.1"
|
| 36 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.7081218274111675,
|
| 4 |
+
"eval_loss": 1.0935020446777344,
|
| 5 |
+
"eval_runtime": 7.0813,
|
| 6 |
+
"eval_samples_per_second": 55.64,
|
| 7 |
+
"eval_steps_per_second": 7.061
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f20682313c689880b290f25df7f7285c02008199174ac41de0f2eff2748cc23
|
| 3 |
+
size 1222104568
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
runs/May01_17-45-34_e5fd9b370bfd/events.out.tfevents.1714585535.e5fd9b370bfd.197.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5a4e952f2917e518dd263b2415fbd78c403c364ad47702e1b85b4bc6bf93fbe
|
| 3 |
+
size 4810
|
runs/May01_17-50-29_e5fd9b370bfd/events.out.tfevents.1714585829.e5fd9b370bfd.8190.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9266936398f2c28a2ad7f63277a0450c2464f6264046231c59a5fa3aec13f069
|
| 3 |
+
size 22564
|
runs/May01_17-50-29_e5fd9b370bfd/events.out.tfevents.1714586766.e5fd9b370bfd.8190.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c7512d4495f6bc1ff1079eb70f2117c4df0901f627dc8383df97806ff7beb8b
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 3.16768696086528e+18,
|
| 4 |
+
"train_loss": 0.15098576029348704,
|
| 5 |
+
"train_runtime": 924.305,
|
| 6 |
+
"train_samples_per_second": 12.42,
|
| 7 |
+
"train_steps_per_second": 0.779
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,597 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0935020446777344,
|
| 3 |
+
"best_model_checkpoint": "./vit-large-brain-xray/checkpoint-200",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 720,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05555555555555555,
|
| 13 |
+
"grad_norm": 1.083911657333374,
|
| 14 |
+
"learning_rate": 0.00019722222222222225,
|
| 15 |
+
"loss": 1.3206,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1111111111111111,
|
| 20 |
+
"grad_norm": 1.5310566425323486,
|
| 21 |
+
"learning_rate": 0.00019444444444444446,
|
| 22 |
+
"loss": 0.9361,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16666666666666666,
|
| 27 |
+
"grad_norm": 3.7486021518707275,
|
| 28 |
+
"learning_rate": 0.00019166666666666667,
|
| 29 |
+
"loss": 0.5999,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2222222222222222,
|
| 34 |
+
"grad_norm": 3.448930025100708,
|
| 35 |
+
"learning_rate": 0.00018888888888888888,
|
| 36 |
+
"loss": 0.5138,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2777777777777778,
|
| 41 |
+
"grad_norm": 1.6228857040405273,
|
| 42 |
+
"learning_rate": 0.00018611111111111112,
|
| 43 |
+
"loss": 0.4566,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3333333333333333,
|
| 48 |
+
"grad_norm": 2.215758800506592,
|
| 49 |
+
"learning_rate": 0.00018333333333333334,
|
| 50 |
+
"loss": 0.4068,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3888888888888889,
|
| 55 |
+
"grad_norm": 1.5400978326797485,
|
| 56 |
+
"learning_rate": 0.00018055555555555557,
|
| 57 |
+
"loss": 0.3305,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4444444444444444,
|
| 62 |
+
"grad_norm": 1.4063529968261719,
|
| 63 |
+
"learning_rate": 0.00017777777777777779,
|
| 64 |
+
"loss": 0.4062,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5,
|
| 69 |
+
"grad_norm": 0.7729310393333435,
|
| 70 |
+
"learning_rate": 0.00017527777777777778,
|
| 71 |
+
"loss": 0.2615,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5555555555555556,
|
| 76 |
+
"grad_norm": 6.676679611206055,
|
| 77 |
+
"learning_rate": 0.00017250000000000002,
|
| 78 |
+
"loss": 0.2144,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5555555555555556,
|
| 83 |
+
"eval_accuracy": 0.6269035532994924,
|
| 84 |
+
"eval_loss": 1.2678815126419067,
|
| 85 |
+
"eval_runtime": 7.3748,
|
| 86 |
+
"eval_samples_per_second": 53.425,
|
| 87 |
+
"eval_steps_per_second": 6.78,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.6111111111111112,
|
| 92 |
+
"grad_norm": 1.6695863008499146,
|
| 93 |
+
"learning_rate": 0.00016972222222222223,
|
| 94 |
+
"loss": 0.3772,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.6666666666666666,
|
| 99 |
+
"grad_norm": 0.457354336977005,
|
| 100 |
+
"learning_rate": 0.00016694444444444447,
|
| 101 |
+
"loss": 0.261,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.7222222222222222,
|
| 106 |
+
"grad_norm": 6.663379192352295,
|
| 107 |
+
"learning_rate": 0.00016416666666666668,
|
| 108 |
+
"loss": 0.2832,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.7777777777777778,
|
| 113 |
+
"grad_norm": 0.6463492512702942,
|
| 114 |
+
"learning_rate": 0.0001613888888888889,
|
| 115 |
+
"loss": 0.1613,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.8333333333333334,
|
| 120 |
+
"grad_norm": 5.534128189086914,
|
| 121 |
+
"learning_rate": 0.0001586111111111111,
|
| 122 |
+
"loss": 0.452,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.8888888888888888,
|
| 127 |
+
"grad_norm": 1.487303614616394,
|
| 128 |
+
"learning_rate": 0.00015583333333333334,
|
| 129 |
+
"loss": 0.3549,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.9444444444444444,
|
| 134 |
+
"grad_norm": 8.732577323913574,
|
| 135 |
+
"learning_rate": 0.00015305555555555556,
|
| 136 |
+
"loss": 0.26,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.0,
|
| 141 |
+
"grad_norm": 0.3070247173309326,
|
| 142 |
+
"learning_rate": 0.0001502777777777778,
|
| 143 |
+
"loss": 0.1787,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.0555555555555556,
|
| 148 |
+
"grad_norm": 0.15718808770179749,
|
| 149 |
+
"learning_rate": 0.0001475,
|
| 150 |
+
"loss": 0.156,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.1111111111111112,
|
| 155 |
+
"grad_norm": 1.4413491487503052,
|
| 156 |
+
"learning_rate": 0.00014472222222222222,
|
| 157 |
+
"loss": 0.1091,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.1111111111111112,
|
| 162 |
+
"eval_accuracy": 0.7081218274111675,
|
| 163 |
+
"eval_loss": 1.0935020446777344,
|
| 164 |
+
"eval_runtime": 6.8075,
|
| 165 |
+
"eval_samples_per_second": 57.877,
|
| 166 |
+
"eval_steps_per_second": 7.345,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.1666666666666667,
|
| 171 |
+
"grad_norm": 1.1086454391479492,
|
| 172 |
+
"learning_rate": 0.00014194444444444446,
|
| 173 |
+
"loss": 0.1243,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.2222222222222223,
|
| 178 |
+
"grad_norm": 0.09483372420072556,
|
| 179 |
+
"learning_rate": 0.00013916666666666667,
|
| 180 |
+
"loss": 0.1712,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.2777777777777777,
|
| 185 |
+
"grad_norm": 2.7763671875,
|
| 186 |
+
"learning_rate": 0.0001363888888888889,
|
| 187 |
+
"loss": 0.2156,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.3333333333333333,
|
| 192 |
+
"grad_norm": 1.6603256464004517,
|
| 193 |
+
"learning_rate": 0.00013361111111111112,
|
| 194 |
+
"loss": 0.1186,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.3888888888888888,
|
| 199 |
+
"grad_norm": 5.325634479522705,
|
| 200 |
+
"learning_rate": 0.00013083333333333333,
|
| 201 |
+
"loss": 0.1065,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.4444444444444444,
|
| 206 |
+
"grad_norm": 0.07357333600521088,
|
| 207 |
+
"learning_rate": 0.00012805555555555555,
|
| 208 |
+
"loss": 0.1192,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.5,
|
| 213 |
+
"grad_norm": 3.8914055824279785,
|
| 214 |
+
"learning_rate": 0.00012527777777777778,
|
| 215 |
+
"loss": 0.0622,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.5555555555555556,
|
| 220 |
+
"grad_norm": 0.37973469495773315,
|
| 221 |
+
"learning_rate": 0.00012250000000000002,
|
| 222 |
+
"loss": 0.2217,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.6111111111111112,
|
| 227 |
+
"grad_norm": 0.08939097821712494,
|
| 228 |
+
"learning_rate": 0.00011972222222222222,
|
| 229 |
+
"loss": 0.1868,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.6666666666666665,
|
| 234 |
+
"grad_norm": 0.29244643449783325,
|
| 235 |
+
"learning_rate": 0.00011694444444444446,
|
| 236 |
+
"loss": 0.1078,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.6666666666666665,
|
| 241 |
+
"eval_accuracy": 0.7588832487309645,
|
| 242 |
+
"eval_loss": 1.1237390041351318,
|
| 243 |
+
"eval_runtime": 6.6691,
|
| 244 |
+
"eval_samples_per_second": 59.078,
|
| 245 |
+
"eval_steps_per_second": 7.497,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.7222222222222223,
|
| 250 |
+
"grad_norm": 2.0514800548553467,
|
| 251 |
+
"learning_rate": 0.00011416666666666667,
|
| 252 |
+
"loss": 0.0995,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.7777777777777777,
|
| 257 |
+
"grad_norm": 0.3739979863166809,
|
| 258 |
+
"learning_rate": 0.0001113888888888889,
|
| 259 |
+
"loss": 0.0752,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.8333333333333335,
|
| 264 |
+
"grad_norm": 0.07262101769447327,
|
| 265 |
+
"learning_rate": 0.00010861111111111111,
|
| 266 |
+
"loss": 0.1004,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.8888888888888888,
|
| 271 |
+
"grad_norm": 1.6550071239471436,
|
| 272 |
+
"learning_rate": 0.00010583333333333334,
|
| 273 |
+
"loss": 0.0593,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.9444444444444444,
|
| 278 |
+
"grad_norm": 1.8396694660186768,
|
| 279 |
+
"learning_rate": 0.00010305555555555555,
|
| 280 |
+
"loss": 0.1425,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.0,
|
| 285 |
+
"grad_norm": 0.061273444443941116,
|
| 286 |
+
"learning_rate": 0.00010027777777777779,
|
| 287 |
+
"loss": 0.0944,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.0555555555555554,
|
| 292 |
+
"grad_norm": 1.0921915769577026,
|
| 293 |
+
"learning_rate": 9.75e-05,
|
| 294 |
+
"loss": 0.118,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.111111111111111,
|
| 299 |
+
"grad_norm": 0.16066594421863556,
|
| 300 |
+
"learning_rate": 9.472222222222222e-05,
|
| 301 |
+
"loss": 0.0479,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.1666666666666665,
|
| 306 |
+
"grad_norm": 0.06149543076753616,
|
| 307 |
+
"learning_rate": 9.194444444444445e-05,
|
| 308 |
+
"loss": 0.0161,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.2222222222222223,
|
| 313 |
+
"grad_norm": 0.10219839215278625,
|
| 314 |
+
"learning_rate": 8.916666666666667e-05,
|
| 315 |
+
"loss": 0.016,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.2222222222222223,
|
| 320 |
+
"eval_accuracy": 0.7563451776649747,
|
| 321 |
+
"eval_loss": 1.235643982887268,
|
| 322 |
+
"eval_runtime": 6.0001,
|
| 323 |
+
"eval_samples_per_second": 65.666,
|
| 324 |
+
"eval_steps_per_second": 8.333,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.2777777777777777,
|
| 329 |
+
"grad_norm": 0.36931440234184265,
|
| 330 |
+
"learning_rate": 8.63888888888889e-05,
|
| 331 |
+
"loss": 0.0674,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.3333333333333335,
|
| 336 |
+
"grad_norm": 0.05050282925367355,
|
| 337 |
+
"learning_rate": 8.361111111111111e-05,
|
| 338 |
+
"loss": 0.0404,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.388888888888889,
|
| 343 |
+
"grad_norm": 0.0446784570813179,
|
| 344 |
+
"learning_rate": 8.083333333333334e-05,
|
| 345 |
+
"loss": 0.0205,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.4444444444444446,
|
| 350 |
+
"grad_norm": 0.04102100059390068,
|
| 351 |
+
"learning_rate": 7.805555555555556e-05,
|
| 352 |
+
"loss": 0.0207,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.5,
|
| 357 |
+
"grad_norm": 4.75399112701416,
|
| 358 |
+
"learning_rate": 7.527777777777777e-05,
|
| 359 |
+
"loss": 0.0526,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.5555555555555554,
|
| 364 |
+
"grad_norm": 0.046476561576128006,
|
| 365 |
+
"learning_rate": 7.25e-05,
|
| 366 |
+
"loss": 0.0461,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.611111111111111,
|
| 371 |
+
"grad_norm": 5.1403632164001465,
|
| 372 |
+
"learning_rate": 6.972222222222223e-05,
|
| 373 |
+
"loss": 0.0424,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.6666666666666665,
|
| 378 |
+
"grad_norm": 0.04179733246564865,
|
| 379 |
+
"learning_rate": 6.694444444444444e-05,
|
| 380 |
+
"loss": 0.0831,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.7222222222222223,
|
| 385 |
+
"grad_norm": 0.0394105389714241,
|
| 386 |
+
"learning_rate": 6.416666666666668e-05,
|
| 387 |
+
"loss": 0.0102,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.7777777777777777,
|
| 392 |
+
"grad_norm": 0.039878394454717636,
|
| 393 |
+
"learning_rate": 6.13888888888889e-05,
|
| 394 |
+
"loss": 0.0095,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.7777777777777777,
|
| 399 |
+
"eval_accuracy": 0.7588832487309645,
|
| 400 |
+
"eval_loss": 1.2315524816513062,
|
| 401 |
+
"eval_runtime": 6.6635,
|
| 402 |
+
"eval_samples_per_second": 59.128,
|
| 403 |
+
"eval_steps_per_second": 7.504,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.8333333333333335,
|
| 408 |
+
"grad_norm": 3.2955222129821777,
|
| 409 |
+
"learning_rate": 5.8611111111111114e-05,
|
| 410 |
+
"loss": 0.0223,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.888888888888889,
|
| 415 |
+
"grad_norm": 0.03517436608672142,
|
| 416 |
+
"learning_rate": 5.583333333333334e-05,
|
| 417 |
+
"loss": 0.0083,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.9444444444444446,
|
| 422 |
+
"grad_norm": 0.03378378599882126,
|
| 423 |
+
"learning_rate": 5.305555555555556e-05,
|
| 424 |
+
"loss": 0.017,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.0,
|
| 429 |
+
"grad_norm": 0.029930729418992996,
|
| 430 |
+
"learning_rate": 5.027777777777778e-05,
|
| 431 |
+
"loss": 0.0076,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.0555555555555554,
|
| 436 |
+
"grad_norm": 0.030685801059007645,
|
| 437 |
+
"learning_rate": 4.75e-05,
|
| 438 |
+
"loss": 0.0082,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.111111111111111,
|
| 443 |
+
"grad_norm": 0.029904644936323166,
|
| 444 |
+
"learning_rate": 4.472222222222223e-05,
|
| 445 |
+
"loss": 0.0073,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.1666666666666665,
|
| 450 |
+
"grad_norm": 0.02878139540553093,
|
| 451 |
+
"learning_rate": 4.194444444444445e-05,
|
| 452 |
+
"loss": 0.0069,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.2222222222222223,
|
| 457 |
+
"grad_norm": 0.028465483337640762,
|
| 458 |
+
"learning_rate": 3.9166666666666665e-05,
|
| 459 |
+
"loss": 0.0067,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.2777777777777777,
|
| 464 |
+
"grad_norm": 0.026676874607801437,
|
| 465 |
+
"learning_rate": 3.638888888888889e-05,
|
| 466 |
+
"loss": 0.0067,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.3333333333333335,
|
| 471 |
+
"grad_norm": 0.028720058500766754,
|
| 472 |
+
"learning_rate": 3.3611111111111116e-05,
|
| 473 |
+
"loss": 0.0066,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.3333333333333335,
|
| 478 |
+
"eval_accuracy": 0.7588832487309645,
|
| 479 |
+
"eval_loss": 1.3164998292922974,
|
| 480 |
+
"eval_runtime": 6.9479,
|
| 481 |
+
"eval_samples_per_second": 56.707,
|
| 482 |
+
"eval_steps_per_second": 7.196,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.388888888888889,
|
| 487 |
+
"grad_norm": 0.030909936875104904,
|
| 488 |
+
"learning_rate": 3.0833333333333335e-05,
|
| 489 |
+
"loss": 0.0066,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 3.4444444444444446,
|
| 494 |
+
"grad_norm": 0.02741164341568947,
|
| 495 |
+
"learning_rate": 2.8055555555555557e-05,
|
| 496 |
+
"loss": 0.0429,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 3.5,
|
| 501 |
+
"grad_norm": 0.028826788067817688,
|
| 502 |
+
"learning_rate": 2.527777777777778e-05,
|
| 503 |
+
"loss": 0.0079,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.5555555555555554,
|
| 508 |
+
"grad_norm": 0.02735409140586853,
|
| 509 |
+
"learning_rate": 2.25e-05,
|
| 510 |
+
"loss": 0.0066,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 3.611111111111111,
|
| 515 |
+
"grad_norm": 0.10283248126506805,
|
| 516 |
+
"learning_rate": 1.9722222222222224e-05,
|
| 517 |
+
"loss": 0.0159,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.6666666666666665,
|
| 522 |
+
"grad_norm": 0.028924111276865005,
|
| 523 |
+
"learning_rate": 1.6944444444444446e-05,
|
| 524 |
+
"loss": 0.0064,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.7222222222222223,
|
| 529 |
+
"grad_norm": 0.025118501856923103,
|
| 530 |
+
"learning_rate": 1.4166666666666668e-05,
|
| 531 |
+
"loss": 0.0062,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.7777777777777777,
|
| 536 |
+
"grad_norm": 0.05767374858260155,
|
| 537 |
+
"learning_rate": 1.138888888888889e-05,
|
| 538 |
+
"loss": 0.0065,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.8333333333333335,
|
| 543 |
+
"grad_norm": 0.0323575958609581,
|
| 544 |
+
"learning_rate": 8.611111111111112e-06,
|
| 545 |
+
"loss": 0.0064,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.888888888888889,
|
| 550 |
+
"grad_norm": 0.026371095329523087,
|
| 551 |
+
"learning_rate": 5.833333333333334e-06,
|
| 552 |
+
"loss": 0.0161,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.888888888888889,
|
| 557 |
+
"eval_accuracy": 0.7614213197969543,
|
| 558 |
+
"eval_loss": 1.341164469718933,
|
| 559 |
+
"eval_runtime": 5.8873,
|
| 560 |
+
"eval_samples_per_second": 66.924,
|
| 561 |
+
"eval_steps_per_second": 8.493,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.9444444444444446,
|
| 566 |
+
"grad_norm": 0.025476330891251564,
|
| 567 |
+
"learning_rate": 3.0555555555555556e-06,
|
| 568 |
+
"loss": 0.0062,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.0,
|
| 573 |
+
"grad_norm": 0.041727062314748764,
|
| 574 |
+
"learning_rate": 2.777777777777778e-07,
|
| 575 |
+
"loss": 0.0097,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.0,
|
| 580 |
+
"step": 720,
|
| 581 |
+
"total_flos": 3.16768696086528e+18,
|
| 582 |
+
"train_loss": 0.15098576029348704,
|
| 583 |
+
"train_runtime": 924.305,
|
| 584 |
+
"train_samples_per_second": 12.42,
|
| 585 |
+
"train_steps_per_second": 0.779
|
| 586 |
+
}
|
| 587 |
+
],
|
| 588 |
+
"logging_steps": 10,
|
| 589 |
+
"max_steps": 720,
|
| 590 |
+
"num_input_tokens_seen": 0,
|
| 591 |
+
"num_train_epochs": 4,
|
| 592 |
+
"save_steps": 100,
|
| 593 |
+
"total_flos": 3.16768696086528e+18,
|
| 594 |
+
"train_batch_size": 16,
|
| 595 |
+
"trial_name": null,
|
| 596 |
+
"trial_params": null
|
| 597 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e70ceac62f8179510d4ddd273ceca649f5752a19a00c2cbb59c7f9eabae6d13
|
| 3 |
+
size 4984
|