Training in progress, epoch 0
Browse files- README.md +82 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +16 -0
- eval_results.json +11 -0
- preprocessor_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +1571 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- medmnist-v2
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
- precision
|
| 11 |
+
- recall
|
| 12 |
+
- f1
|
| 13 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 14 |
+
model-index:
|
| 15 |
+
- name: organc-beit-base-finetuned
|
| 16 |
+
results: []
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 20 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 21 |
+
|
| 22 |
+
# organc-beit-base-finetuned
|
| 23 |
+
|
| 24 |
+
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 medmnist-v2 dataset.
|
| 25 |
+
It achieves the following results on the evaluation set:
|
| 26 |
+
- Loss: 0.2607
|
| 27 |
+
- Accuracy: 0.9128
|
| 28 |
+
- Precision: 0.9094
|
| 29 |
+
- Recall: 0.8976
|
| 30 |
+
- F1: 0.9019
|
| 31 |
+
|
| 32 |
+
## Model description
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Intended uses & limitations
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training and evaluation data
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training procedure
|
| 45 |
+
|
| 46 |
+
### Training hyperparameters
|
| 47 |
+
|
| 48 |
+
The following hyperparameters were used during training:
|
| 49 |
+
- learning_rate: 0.005
|
| 50 |
+
- train_batch_size: 16
|
| 51 |
+
- eval_batch_size: 16
|
| 52 |
+
- seed: 42
|
| 53 |
+
- gradient_accumulation_steps: 4
|
| 54 |
+
- total_train_batch_size: 64
|
| 55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 56 |
+
- lr_scheduler_type: linear
|
| 57 |
+
- num_epochs: 10
|
| 58 |
+
- mixed_precision_training: Native AMP
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 64 |
+
| 0.7007 | 1.0 | 203 | 0.2457 | 0.9114 | 0.9019 | 0.8644 | 0.8529 |
|
| 65 |
+
| 0.6322 | 2.0 | 406 | 0.2148 | 0.9423 | 0.9424 | 0.9292 | 0.9340 |
|
| 66 |
+
| 0.6353 | 3.0 | 609 | 0.1218 | 0.9632 | 0.9546 | 0.9542 | 0.9529 |
|
| 67 |
+
| 0.6176 | 4.0 | 813 | 0.0839 | 0.9799 | 0.9775 | 0.9793 | 0.9782 |
|
| 68 |
+
| 0.4913 | 5.0 | 1016 | 0.1008 | 0.9712 | 0.9713 | 0.9717 | 0.9707 |
|
| 69 |
+
| 0.4943 | 6.0 | 1219 | 0.0805 | 0.9799 | 0.9843 | 0.9820 | 0.9828 |
|
| 70 |
+
| 0.426 | 7.0 | 1422 | 0.0671 | 0.9799 | 0.9782 | 0.9787 | 0.9781 |
|
| 71 |
+
| 0.4152 | 8.0 | 1626 | 0.0566 | 0.9870 | 0.9862 | 0.9896 | 0.9878 |
|
| 72 |
+
| 0.2927 | 9.0 | 1829 | 0.0658 | 0.9837 | 0.9850 | 0.9850 | 0.9848 |
|
| 73 |
+
| 0.3154 | 9.99 | 2030 | 0.0537 | 0.9841 | 0.9855 | 0.9854 | 0.9853 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- PEFT 0.10.0
|
| 79 |
+
- Transformers 4.38.2
|
| 80 |
+
- Pytorch 2.2.1+cu121
|
| 81 |
+
- Datasets 2.18.0
|
| 82 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "ViTForImageClassification",
|
| 5 |
+
"parent_library": "transformers.models.vit.modeling_vit"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_dropout": 0.1,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": [
|
| 21 |
+
"classifier"
|
| 22 |
+
],
|
| 23 |
+
"peft_type": "LORA",
|
| 24 |
+
"r": 16,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"value",
|
| 29 |
+
"query"
|
| 30 |
+
],
|
| 31 |
+
"task_type": null,
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7263a4d313c3148cd1e6b8fadb91f659f4d278a890ebd78dfb535b6f740cc665
|
| 3 |
+
size 2400284
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.99,
|
| 3 |
+
"eval_accuracy": 0.9127963231736816,
|
| 4 |
+
"eval_f1": 0.9018775351313549,
|
| 5 |
+
"eval_loss": 0.26074379682540894,
|
| 6 |
+
"eval_precision": 0.9094064911689247,
|
| 7 |
+
"eval_recall": 0.8975649435800629,
|
| 8 |
+
"eval_runtime": 44.5141,
|
| 9 |
+
"eval_samples_per_second": 185.739,
|
| 10 |
+
"eval_steps_per_second": 11.614,
|
| 11 |
+
"total_flos": 1.0133154899356189e+19,
|
| 12 |
+
"train_loss": 0.5219255947714369,
|
| 13 |
+
"train_runtime": 1565.9689,
|
| 14 |
+
"train_samples_per_second": 83.016,
|
| 15 |
+
"train_steps_per_second": 1.296
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.99,
|
| 3 |
+
"eval_accuracy": 0.9127963231736816,
|
| 4 |
+
"eval_f1": 0.9018775351313549,
|
| 5 |
+
"eval_loss": 0.26074379682540894,
|
| 6 |
+
"eval_precision": 0.9094064911689247,
|
| 7 |
+
"eval_recall": 0.8975649435800629,
|
| 8 |
+
"eval_runtime": 44.5141,
|
| 9 |
+
"eval_samples_per_second": 185.739,
|
| 10 |
+
"eval_steps_per_second": 11.614
|
| 11 |
+
}
|
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": 9.99,
|
| 3 |
+
"total_flos": 1.0133154899356189e+19,
|
| 4 |
+
"train_loss": 0.5219255947714369,
|
| 5 |
+
"train_runtime": 1565.9689,
|
| 6 |
+
"train_samples_per_second": 83.016,
|
| 7 |
+
"train_steps_per_second": 1.296
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1571 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9870401337792643,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-lora-medmnistv2/checkpoint-1626",
|
| 4 |
+
"epoch": 9.98769987699877,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2030,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 1.1422470808029175,
|
| 14 |
+
"learning_rate": 0.004975369458128079,
|
| 15 |
+
"loss": 1.9628,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 1.255900502204895,
|
| 21 |
+
"learning_rate": 0.004950738916256157,
|
| 22 |
+
"loss": 1.3552,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 1.5407381057739258,
|
| 28 |
+
"learning_rate": 0.00493103448275862,
|
| 29 |
+
"loss": 1.0858,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 2.6224355697631836,
|
| 35 |
+
"learning_rate": 0.0049064039408866994,
|
| 36 |
+
"loss": 1.0843,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 0.8357070088386536,
|
| 42 |
+
"learning_rate": 0.0048817733990147785,
|
| 43 |
+
"loss": 0.96,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 1.080548644065857,
|
| 49 |
+
"learning_rate": 0.004857142857142858,
|
| 50 |
+
"loss": 0.8978,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.34,
|
| 55 |
+
"grad_norm": 1.4522780179977417,
|
| 56 |
+
"learning_rate": 0.004832512315270936,
|
| 57 |
+
"loss": 0.8698,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.39,
|
| 62 |
+
"grad_norm": 0.9388962388038635,
|
| 63 |
+
"learning_rate": 0.004807881773399015,
|
| 64 |
+
"loss": 0.9796,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.44,
|
| 69 |
+
"grad_norm": 1.6392161846160889,
|
| 70 |
+
"learning_rate": 0.004783251231527094,
|
| 71 |
+
"loss": 0.814,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.49,
|
| 76 |
+
"grad_norm": 0.7927560210227966,
|
| 77 |
+
"learning_rate": 0.004758620689655172,
|
| 78 |
+
"loss": 0.8127,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.54,
|
| 83 |
+
"grad_norm": 0.9725190997123718,
|
| 84 |
+
"learning_rate": 0.004733990147783251,
|
| 85 |
+
"loss": 0.7416,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.59,
|
| 90 |
+
"grad_norm": 1.2956442832946777,
|
| 91 |
+
"learning_rate": 0.00470935960591133,
|
| 92 |
+
"loss": 0.7281,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.64,
|
| 97 |
+
"grad_norm": 1.2394323348999023,
|
| 98 |
+
"learning_rate": 0.0046847290640394095,
|
| 99 |
+
"loss": 0.7632,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.69,
|
| 104 |
+
"grad_norm": 1.1683493852615356,
|
| 105 |
+
"learning_rate": 0.004660098522167488,
|
| 106 |
+
"loss": 0.7589,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.74,
|
| 111 |
+
"grad_norm": 0.8499715328216553,
|
| 112 |
+
"learning_rate": 0.004635467980295567,
|
| 113 |
+
"loss": 0.6864,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.79,
|
| 118 |
+
"grad_norm": 0.9673293232917786,
|
| 119 |
+
"learning_rate": 0.004610837438423646,
|
| 120 |
+
"loss": 0.6827,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.84,
|
| 125 |
+
"grad_norm": 0.7566954493522644,
|
| 126 |
+
"learning_rate": 0.0045886699507389165,
|
| 127 |
+
"loss": 0.667,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.89,
|
| 132 |
+
"grad_norm": 1.0029590129852295,
|
| 133 |
+
"learning_rate": 0.004564039408866995,
|
| 134 |
+
"loss": 0.7118,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.93,
|
| 139 |
+
"grad_norm": 0.9083508849143982,
|
| 140 |
+
"learning_rate": 0.004539408866995074,
|
| 141 |
+
"loss": 0.6388,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.98,
|
| 146 |
+
"grad_norm": 0.9889862537384033,
|
| 147 |
+
"learning_rate": 0.004514778325123153,
|
| 148 |
+
"loss": 0.7007,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.9113712374581939,
|
| 154 |
+
"eval_f1": 0.8529028766456601,
|
| 155 |
+
"eval_loss": 0.2457016110420227,
|
| 156 |
+
"eval_precision": 0.9018735870596898,
|
| 157 |
+
"eval_recall": 0.8643919959588723,
|
| 158 |
+
"eval_runtime": 12.8411,
|
| 159 |
+
"eval_samples_per_second": 186.276,
|
| 160 |
+
"eval_steps_per_second": 11.681,
|
| 161 |
+
"step": 203
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.03,
|
| 165 |
+
"grad_norm": 1.352356195449829,
|
| 166 |
+
"learning_rate": 0.004490147783251232,
|
| 167 |
+
"loss": 0.7043,
|
| 168 |
+
"step": 210
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.08,
|
| 172 |
+
"grad_norm": 0.9853256940841675,
|
| 173 |
+
"learning_rate": 0.00446551724137931,
|
| 174 |
+
"loss": 0.5867,
|
| 175 |
+
"step": 220
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.13,
|
| 179 |
+
"grad_norm": 1.2557787895202637,
|
| 180 |
+
"learning_rate": 0.004440886699507389,
|
| 181 |
+
"loss": 0.6101,
|
| 182 |
+
"step": 230
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.18,
|
| 186 |
+
"grad_norm": 0.9615167379379272,
|
| 187 |
+
"learning_rate": 0.004416256157635468,
|
| 188 |
+
"loss": 0.7143,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.23,
|
| 193 |
+
"grad_norm": 0.9772002696990967,
|
| 194 |
+
"learning_rate": 0.004391625615763547,
|
| 195 |
+
"loss": 0.6388,
|
| 196 |
+
"step": 250
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.28,
|
| 200 |
+
"grad_norm": 1.6855661869049072,
|
| 201 |
+
"learning_rate": 0.004366995073891626,
|
| 202 |
+
"loss": 0.5621,
|
| 203 |
+
"step": 260
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.33,
|
| 207 |
+
"grad_norm": 2.439969062805176,
|
| 208 |
+
"learning_rate": 0.004342364532019705,
|
| 209 |
+
"loss": 0.6839,
|
| 210 |
+
"step": 270
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.38,
|
| 214 |
+
"grad_norm": 1.0421786308288574,
|
| 215 |
+
"learning_rate": 0.004317733990147784,
|
| 216 |
+
"loss": 0.6545,
|
| 217 |
+
"step": 280
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.43,
|
| 221 |
+
"grad_norm": 1.445427417755127,
|
| 222 |
+
"learning_rate": 0.004293103448275862,
|
| 223 |
+
"loss": 0.6383,
|
| 224 |
+
"step": 290
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.48,
|
| 228 |
+
"grad_norm": 1.585347056388855,
|
| 229 |
+
"learning_rate": 0.00426847290640394,
|
| 230 |
+
"loss": 0.6446,
|
| 231 |
+
"step": 300
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.53,
|
| 235 |
+
"grad_norm": 1.3732099533081055,
|
| 236 |
+
"learning_rate": 0.004243842364532019,
|
| 237 |
+
"loss": 0.5853,
|
| 238 |
+
"step": 310
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.57,
|
| 242 |
+
"grad_norm": 1.9869935512542725,
|
| 243 |
+
"learning_rate": 0.0042192118226600985,
|
| 244 |
+
"loss": 0.6442,
|
| 245 |
+
"step": 320
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.62,
|
| 249 |
+
"grad_norm": 2.5270144939422607,
|
| 250 |
+
"learning_rate": 0.004194581280788178,
|
| 251 |
+
"loss": 0.6744,
|
| 252 |
+
"step": 330
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.67,
|
| 256 |
+
"grad_norm": 1.2350406646728516,
|
| 257 |
+
"learning_rate": 0.004169950738916256,
|
| 258 |
+
"loss": 0.711,
|
| 259 |
+
"step": 340
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.72,
|
| 263 |
+
"grad_norm": 2.2132787704467773,
|
| 264 |
+
"learning_rate": 0.004145320197044335,
|
| 265 |
+
"loss": 0.7377,
|
| 266 |
+
"step": 350
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.77,
|
| 270 |
+
"grad_norm": 1.414409875869751,
|
| 271 |
+
"learning_rate": 0.004120689655172414,
|
| 272 |
+
"loss": 0.6735,
|
| 273 |
+
"step": 360
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.82,
|
| 277 |
+
"grad_norm": 1.505163311958313,
|
| 278 |
+
"learning_rate": 0.004096059113300492,
|
| 279 |
+
"loss": 0.6941,
|
| 280 |
+
"step": 370
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.87,
|
| 284 |
+
"grad_norm": 1.286877155303955,
|
| 285 |
+
"learning_rate": 0.004071428571428571,
|
| 286 |
+
"loss": 0.5817,
|
| 287 |
+
"step": 380
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.92,
|
| 291 |
+
"grad_norm": 2.4780466556549072,
|
| 292 |
+
"learning_rate": 0.00404679802955665,
|
| 293 |
+
"loss": 0.6474,
|
| 294 |
+
"step": 390
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.97,
|
| 298 |
+
"grad_norm": 1.735863208770752,
|
| 299 |
+
"learning_rate": 0.0040221674876847295,
|
| 300 |
+
"loss": 0.6322,
|
| 301 |
+
"step": 400
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.0,
|
| 305 |
+
"eval_accuracy": 0.9423076923076923,
|
| 306 |
+
"eval_f1": 0.9340154565022668,
|
| 307 |
+
"eval_loss": 0.21482966840267181,
|
| 308 |
+
"eval_precision": 0.9423994421185976,
|
| 309 |
+
"eval_recall": 0.9291886861477701,
|
| 310 |
+
"eval_runtime": 12.9083,
|
| 311 |
+
"eval_samples_per_second": 185.306,
|
| 312 |
+
"eval_steps_per_second": 11.62,
|
| 313 |
+
"step": 406
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.02,
|
| 317 |
+
"grad_norm": 1.8992809057235718,
|
| 318 |
+
"learning_rate": 0.003997536945812808,
|
| 319 |
+
"loss": 0.7819,
|
| 320 |
+
"step": 410
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.07,
|
| 324 |
+
"grad_norm": 3.8816006183624268,
|
| 325 |
+
"learning_rate": 0.003972906403940887,
|
| 326 |
+
"loss": 0.7579,
|
| 327 |
+
"step": 420
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.12,
|
| 331 |
+
"grad_norm": 2.3438549041748047,
|
| 332 |
+
"learning_rate": 0.003948275862068966,
|
| 333 |
+
"loss": 0.6899,
|
| 334 |
+
"step": 430
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.16,
|
| 338 |
+
"grad_norm": 2.111189126968384,
|
| 339 |
+
"learning_rate": 0.003923645320197044,
|
| 340 |
+
"loss": 0.6711,
|
| 341 |
+
"step": 440
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.21,
|
| 345 |
+
"grad_norm": 2.7600784301757812,
|
| 346 |
+
"learning_rate": 0.0038990147783251232,
|
| 347 |
+
"loss": 0.6031,
|
| 348 |
+
"step": 450
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.26,
|
| 352 |
+
"grad_norm": 1.7545028924942017,
|
| 353 |
+
"learning_rate": 0.0038743842364532023,
|
| 354 |
+
"loss": 0.6801,
|
| 355 |
+
"step": 460
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.31,
|
| 359 |
+
"grad_norm": 3.5373642444610596,
|
| 360 |
+
"learning_rate": 0.003849753694581281,
|
| 361 |
+
"loss": 0.6683,
|
| 362 |
+
"step": 470
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.36,
|
| 366 |
+
"grad_norm": 2.0872020721435547,
|
| 367 |
+
"learning_rate": 0.00382512315270936,
|
| 368 |
+
"loss": 0.5974,
|
| 369 |
+
"step": 480
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.41,
|
| 373 |
+
"grad_norm": 2.178804636001587,
|
| 374 |
+
"learning_rate": 0.0038004926108374383,
|
| 375 |
+
"loss": 0.5688,
|
| 376 |
+
"step": 490
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.46,
|
| 380 |
+
"grad_norm": 2.1402218341827393,
|
| 381 |
+
"learning_rate": 0.003775862068965517,
|
| 382 |
+
"loss": 0.6617,
|
| 383 |
+
"step": 500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.51,
|
| 387 |
+
"grad_norm": 3.2831871509552,
|
| 388 |
+
"learning_rate": 0.003751231527093596,
|
| 389 |
+
"loss": 0.6706,
|
| 390 |
+
"step": 510
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.56,
|
| 394 |
+
"grad_norm": 1.9515079259872437,
|
| 395 |
+
"learning_rate": 0.0037266009852216747,
|
| 396 |
+
"loss": 0.6616,
|
| 397 |
+
"step": 520
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.61,
|
| 401 |
+
"grad_norm": 1.7052913904190063,
|
| 402 |
+
"learning_rate": 0.003701970443349754,
|
| 403 |
+
"loss": 0.6816,
|
| 404 |
+
"step": 530
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.66,
|
| 408 |
+
"grad_norm": 1.4746874570846558,
|
| 409 |
+
"learning_rate": 0.0036773399014778324,
|
| 410 |
+
"loss": 0.613,
|
| 411 |
+
"step": 540
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.71,
|
| 415 |
+
"grad_norm": 1.1124660968780518,
|
| 416 |
+
"learning_rate": 0.0036527093596059115,
|
| 417 |
+
"loss": 0.6295,
|
| 418 |
+
"step": 550
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.76,
|
| 422 |
+
"grad_norm": 1.4814788103103638,
|
| 423 |
+
"learning_rate": 0.00362807881773399,
|
| 424 |
+
"loss": 0.618,
|
| 425 |
+
"step": 560
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.8,
|
| 429 |
+
"grad_norm": 1.1870466470718384,
|
| 430 |
+
"learning_rate": 0.003603448275862069,
|
| 431 |
+
"loss": 0.6529,
|
| 432 |
+
"step": 570
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.85,
|
| 436 |
+
"grad_norm": 1.1089264154434204,
|
| 437 |
+
"learning_rate": 0.003578817733990148,
|
| 438 |
+
"loss": 0.5042,
|
| 439 |
+
"step": 580
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.9,
|
| 443 |
+
"grad_norm": 2.6037137508392334,
|
| 444 |
+
"learning_rate": 0.0035541871921182266,
|
| 445 |
+
"loss": 0.7198,
|
| 446 |
+
"step": 590
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.95,
|
| 450 |
+
"grad_norm": 1.4666210412979126,
|
| 451 |
+
"learning_rate": 0.0035295566502463057,
|
| 452 |
+
"loss": 0.6353,
|
| 453 |
+
"step": 600
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.0,
|
| 457 |
+
"eval_accuracy": 0.9632107023411371,
|
| 458 |
+
"eval_f1": 0.9529335555710525,
|
| 459 |
+
"eval_loss": 0.121844083070755,
|
| 460 |
+
"eval_precision": 0.9546285621864314,
|
| 461 |
+
"eval_recall": 0.9542450303236223,
|
| 462 |
+
"eval_runtime": 12.9205,
|
| 463 |
+
"eval_samples_per_second": 185.132,
|
| 464 |
+
"eval_steps_per_second": 11.609,
|
| 465 |
+
"step": 609
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.0,
|
| 469 |
+
"grad_norm": 1.863990068435669,
|
| 470 |
+
"learning_rate": 0.0035049261083743843,
|
| 471 |
+
"loss": 0.6389,
|
| 472 |
+
"step": 610
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 3.05,
|
| 476 |
+
"grad_norm": 1.3299729824066162,
|
| 477 |
+
"learning_rate": 0.0034802955665024634,
|
| 478 |
+
"loss": 0.6781,
|
| 479 |
+
"step": 620
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.1,
|
| 483 |
+
"grad_norm": 2.5126378536224365,
|
| 484 |
+
"learning_rate": 0.003455665024630542,
|
| 485 |
+
"loss": 0.6492,
|
| 486 |
+
"step": 630
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 3.15,
|
| 490 |
+
"grad_norm": 1.380492925643921,
|
| 491 |
+
"learning_rate": 0.0034310344827586207,
|
| 492 |
+
"loss": 0.631,
|
| 493 |
+
"step": 640
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 3.2,
|
| 497 |
+
"grad_norm": 2.03764009475708,
|
| 498 |
+
"learning_rate": 0.0034064039408867,
|
| 499 |
+
"loss": 0.6221,
|
| 500 |
+
"step": 650
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.25,
|
| 504 |
+
"grad_norm": 1.1895209550857544,
|
| 505 |
+
"learning_rate": 0.0033817733990147785,
|
| 506 |
+
"loss": 0.5881,
|
| 507 |
+
"step": 660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.3,
|
| 511 |
+
"grad_norm": 1.354785442352295,
|
| 512 |
+
"learning_rate": 0.003357142857142857,
|
| 513 |
+
"loss": 0.584,
|
| 514 |
+
"step": 670
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 3.35,
|
| 518 |
+
"grad_norm": 1.9887776374816895,
|
| 519 |
+
"learning_rate": 0.003332512315270936,
|
| 520 |
+
"loss": 0.5914,
|
| 521 |
+
"step": 680
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 3.39,
|
| 525 |
+
"grad_norm": 1.7261571884155273,
|
| 526 |
+
"learning_rate": 0.0033078817733990145,
|
| 527 |
+
"loss": 0.5608,
|
| 528 |
+
"step": 690
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 3.44,
|
| 532 |
+
"grad_norm": 1.3888462781906128,
|
| 533 |
+
"learning_rate": 0.0032832512315270936,
|
| 534 |
+
"loss": 0.5832,
|
| 535 |
+
"step": 700
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 3.49,
|
| 539 |
+
"grad_norm": 1.6422044038772583,
|
| 540 |
+
"learning_rate": 0.003258620689655172,
|
| 541 |
+
"loss": 0.5759,
|
| 542 |
+
"step": 710
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.54,
|
| 546 |
+
"grad_norm": 1.2814769744873047,
|
| 547 |
+
"learning_rate": 0.0032339901477832513,
|
| 548 |
+
"loss": 0.5845,
|
| 549 |
+
"step": 720
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.59,
|
| 553 |
+
"grad_norm": 1.835681676864624,
|
| 554 |
+
"learning_rate": 0.00320935960591133,
|
| 555 |
+
"loss": 0.5756,
|
| 556 |
+
"step": 730
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 3.64,
|
| 560 |
+
"grad_norm": 1.3922501802444458,
|
| 561 |
+
"learning_rate": 0.003184729064039409,
|
| 562 |
+
"loss": 0.5878,
|
| 563 |
+
"step": 740
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 3.69,
|
| 567 |
+
"grad_norm": 1.3808457851409912,
|
| 568 |
+
"learning_rate": 0.0031600985221674877,
|
| 569 |
+
"loss": 0.5593,
|
| 570 |
+
"step": 750
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 3.74,
|
| 574 |
+
"grad_norm": 1.3295152187347412,
|
| 575 |
+
"learning_rate": 0.0031379310344827587,
|
| 576 |
+
"loss": 0.5563,
|
| 577 |
+
"step": 760
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 3.79,
|
| 581 |
+
"grad_norm": 2.4613001346588135,
|
| 582 |
+
"learning_rate": 0.003113300492610838,
|
| 583 |
+
"loss": 0.5341,
|
| 584 |
+
"step": 770
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.84,
|
| 588 |
+
"grad_norm": 1.1632391214370728,
|
| 589 |
+
"learning_rate": 0.0030886699507389165,
|
| 590 |
+
"loss": 0.6108,
|
| 591 |
+
"step": 780
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 3.89,
|
| 595 |
+
"grad_norm": 1.0384527444839478,
|
| 596 |
+
"learning_rate": 0.0030640394088669956,
|
| 597 |
+
"loss": 0.5597,
|
| 598 |
+
"step": 790
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 3.94,
|
| 602 |
+
"grad_norm": 1.5166749954223633,
|
| 603 |
+
"learning_rate": 0.0030394088669950738,
|
| 604 |
+
"loss": 0.5153,
|
| 605 |
+
"step": 800
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 3.99,
|
| 609 |
+
"grad_norm": 1.5253658294677734,
|
| 610 |
+
"learning_rate": 0.0030147783251231524,
|
| 611 |
+
"loss": 0.6176,
|
| 612 |
+
"step": 810
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 4.0,
|
| 616 |
+
"eval_accuracy": 0.979933110367893,
|
| 617 |
+
"eval_f1": 0.9781756712736359,
|
| 618 |
+
"eval_loss": 0.08385530859231949,
|
| 619 |
+
"eval_precision": 0.9775461189264221,
|
| 620 |
+
"eval_recall": 0.979303313253159,
|
| 621 |
+
"eval_runtime": 12.9634,
|
| 622 |
+
"eval_samples_per_second": 184.519,
|
| 623 |
+
"eval_steps_per_second": 11.571,
|
| 624 |
+
"step": 813
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.03,
|
| 628 |
+
"grad_norm": 1.8829090595245361,
|
| 629 |
+
"learning_rate": 0.0029901477832512315,
|
| 630 |
+
"loss": 0.5208,
|
| 631 |
+
"step": 820
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 4.08,
|
| 635 |
+
"grad_norm": 1.4730515480041504,
|
| 636 |
+
"learning_rate": 0.00296551724137931,
|
| 637 |
+
"loss": 0.5205,
|
| 638 |
+
"step": 830
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.13,
|
| 642 |
+
"grad_norm": 0.6617820858955383,
|
| 643 |
+
"learning_rate": 0.0029408866995073893,
|
| 644 |
+
"loss": 0.5029,
|
| 645 |
+
"step": 840
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 4.18,
|
| 649 |
+
"grad_norm": 0.9558489918708801,
|
| 650 |
+
"learning_rate": 0.002916256157635468,
|
| 651 |
+
"loss": 0.533,
|
| 652 |
+
"step": 850
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 4.23,
|
| 656 |
+
"grad_norm": 2.0359411239624023,
|
| 657 |
+
"learning_rate": 0.0028916256157635466,
|
| 658 |
+
"loss": 0.4633,
|
| 659 |
+
"step": 860
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 4.28,
|
| 663 |
+
"grad_norm": 2.325270414352417,
|
| 664 |
+
"learning_rate": 0.0028669950738916257,
|
| 665 |
+
"loss": 0.5877,
|
| 666 |
+
"step": 870
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 4.33,
|
| 670 |
+
"grad_norm": 1.3358855247497559,
|
| 671 |
+
"learning_rate": 0.0028423645320197043,
|
| 672 |
+
"loss": 0.4447,
|
| 673 |
+
"step": 880
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 4.38,
|
| 677 |
+
"grad_norm": 1.4927520751953125,
|
| 678 |
+
"learning_rate": 0.0028177339901477834,
|
| 679 |
+
"loss": 0.5783,
|
| 680 |
+
"step": 890
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.43,
|
| 684 |
+
"grad_norm": 1.231078028678894,
|
| 685 |
+
"learning_rate": 0.002793103448275862,
|
| 686 |
+
"loss": 0.5606,
|
| 687 |
+
"step": 900
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 4.48,
|
| 691 |
+
"grad_norm": 1.4861023426055908,
|
| 692 |
+
"learning_rate": 0.002768472906403941,
|
| 693 |
+
"loss": 0.5006,
|
| 694 |
+
"step": 910
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 4.53,
|
| 698 |
+
"grad_norm": 1.0326859951019287,
|
| 699 |
+
"learning_rate": 0.00274384236453202,
|
| 700 |
+
"loss": 0.4989,
|
| 701 |
+
"step": 920
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 4.58,
|
| 705 |
+
"grad_norm": 1.290980577468872,
|
| 706 |
+
"learning_rate": 0.0027192118226600985,
|
| 707 |
+
"loss": 0.514,
|
| 708 |
+
"step": 930
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 4.62,
|
| 712 |
+
"grad_norm": 1.3768541812896729,
|
| 713 |
+
"learning_rate": 0.0026945812807881776,
|
| 714 |
+
"loss": 0.5221,
|
| 715 |
+
"step": 940
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 4.67,
|
| 719 |
+
"grad_norm": 4.485782623291016,
|
| 720 |
+
"learning_rate": 0.0026699507389162562,
|
| 721 |
+
"loss": 0.4992,
|
| 722 |
+
"step": 950
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 4.72,
|
| 726 |
+
"grad_norm": 1.4199550151824951,
|
| 727 |
+
"learning_rate": 0.0026453201970443353,
|
| 728 |
+
"loss": 0.5256,
|
| 729 |
+
"step": 960
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 4.77,
|
| 733 |
+
"grad_norm": 1.4900827407836914,
|
| 734 |
+
"learning_rate": 0.002620689655172414,
|
| 735 |
+
"loss": 0.5111,
|
| 736 |
+
"step": 970
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 4.82,
|
| 740 |
+
"grad_norm": 1.874714970588684,
|
| 741 |
+
"learning_rate": 0.002596059113300493,
|
| 742 |
+
"loss": 0.4774,
|
| 743 |
+
"step": 980
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 4.87,
|
| 747 |
+
"grad_norm": 1.254228115081787,
|
| 748 |
+
"learning_rate": 0.0025714285714285713,
|
| 749 |
+
"loss": 0.4789,
|
| 750 |
+
"step": 990
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 4.92,
|
| 754 |
+
"grad_norm": 2.317281723022461,
|
| 755 |
+
"learning_rate": 0.00254679802955665,
|
| 756 |
+
"loss": 0.5338,
|
| 757 |
+
"step": 1000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 4.97,
|
| 761 |
+
"grad_norm": 1.482914686203003,
|
| 762 |
+
"learning_rate": 0.002522167487684729,
|
| 763 |
+
"loss": 0.4913,
|
| 764 |
+
"step": 1010
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 5.0,
|
| 768 |
+
"eval_accuracy": 0.9711538461538461,
|
| 769 |
+
"eval_f1": 0.9707062805947578,
|
| 770 |
+
"eval_loss": 0.10083355009555817,
|
| 771 |
+
"eval_precision": 0.9712614809682641,
|
| 772 |
+
"eval_recall": 0.9717429310005482,
|
| 773 |
+
"eval_runtime": 12.9897,
|
| 774 |
+
"eval_samples_per_second": 184.146,
|
| 775 |
+
"eval_steps_per_second": 11.548,
|
| 776 |
+
"step": 1016
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 5.02,
|
| 780 |
+
"grad_norm": 1.070559024810791,
|
| 781 |
+
"learning_rate": 0.002497536945812808,
|
| 782 |
+
"loss": 0.4719,
|
| 783 |
+
"step": 1020
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 5.07,
|
| 787 |
+
"grad_norm": 1.206444263458252,
|
| 788 |
+
"learning_rate": 0.002472906403940887,
|
| 789 |
+
"loss": 0.4973,
|
| 790 |
+
"step": 1030
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 5.12,
|
| 794 |
+
"grad_norm": 1.2651773691177368,
|
| 795 |
+
"learning_rate": 0.0024482758620689654,
|
| 796 |
+
"loss": 0.5203,
|
| 797 |
+
"step": 1040
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 5.17,
|
| 801 |
+
"grad_norm": 1.162040114402771,
|
| 802 |
+
"learning_rate": 0.002423645320197044,
|
| 803 |
+
"loss": 0.4781,
|
| 804 |
+
"step": 1050
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 5.22,
|
| 808 |
+
"grad_norm": 1.2628921270370483,
|
| 809 |
+
"learning_rate": 0.002399014778325123,
|
| 810 |
+
"loss": 0.558,
|
| 811 |
+
"step": 1060
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 5.26,
|
| 815 |
+
"grad_norm": 0.6029661297798157,
|
| 816 |
+
"learning_rate": 0.002374384236453202,
|
| 817 |
+
"loss": 0.4991,
|
| 818 |
+
"step": 1070
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 5.31,
|
| 822 |
+
"grad_norm": 1.7291909456253052,
|
| 823 |
+
"learning_rate": 0.002349753694581281,
|
| 824 |
+
"loss": 0.5331,
|
| 825 |
+
"step": 1080
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 5.36,
|
| 829 |
+
"grad_norm": 0.8556851148605347,
|
| 830 |
+
"learning_rate": 0.0023251231527093596,
|
| 831 |
+
"loss": 0.4594,
|
| 832 |
+
"step": 1090
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 5.41,
|
| 836 |
+
"grad_norm": 0.9938213229179382,
|
| 837 |
+
"learning_rate": 0.0023004926108374387,
|
| 838 |
+
"loss": 0.4841,
|
| 839 |
+
"step": 1100
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 5.46,
|
| 843 |
+
"grad_norm": 2.558023452758789,
|
| 844 |
+
"learning_rate": 0.0022758620689655173,
|
| 845 |
+
"loss": 0.5241,
|
| 846 |
+
"step": 1110
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 5.51,
|
| 850 |
+
"grad_norm": 1.3117694854736328,
|
| 851 |
+
"learning_rate": 0.0022512315270935964,
|
| 852 |
+
"loss": 0.4821,
|
| 853 |
+
"step": 1120
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 5.56,
|
| 857 |
+
"grad_norm": 1.2305413484573364,
|
| 858 |
+
"learning_rate": 0.0022266009852216747,
|
| 859 |
+
"loss": 0.4234,
|
| 860 |
+
"step": 1130
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 5.61,
|
| 864 |
+
"grad_norm": 1.0140172243118286,
|
| 865 |
+
"learning_rate": 0.0022019704433497538,
|
| 866 |
+
"loss": 0.4008,
|
| 867 |
+
"step": 1140
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 5.66,
|
| 871 |
+
"grad_norm": 1.2372822761535645,
|
| 872 |
+
"learning_rate": 0.0021773399014778324,
|
| 873 |
+
"loss": 0.4507,
|
| 874 |
+
"step": 1150
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 5.71,
|
| 878 |
+
"grad_norm": 0.8806868195533752,
|
| 879 |
+
"learning_rate": 0.0021527093596059115,
|
| 880 |
+
"loss": 0.5398,
|
| 881 |
+
"step": 1160
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 5.76,
|
| 885 |
+
"grad_norm": 0.9182419180870056,
|
| 886 |
+
"learning_rate": 0.00212807881773399,
|
| 887 |
+
"loss": 0.4085,
|
| 888 |
+
"step": 1170
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 5.81,
|
| 892 |
+
"grad_norm": 1.4466331005096436,
|
| 893 |
+
"learning_rate": 0.0021034482758620692,
|
| 894 |
+
"loss": 0.4966,
|
| 895 |
+
"step": 1180
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 5.85,
|
| 899 |
+
"grad_norm": 1.1195909976959229,
|
| 900 |
+
"learning_rate": 0.002078817733990148,
|
| 901 |
+
"loss": 0.4349,
|
| 902 |
+
"step": 1190
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 5.9,
|
| 906 |
+
"grad_norm": 1.7363073825836182,
|
| 907 |
+
"learning_rate": 0.0020541871921182266,
|
| 908 |
+
"loss": 0.4528,
|
| 909 |
+
"step": 1200
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 5.95,
|
| 913 |
+
"grad_norm": 1.3727185726165771,
|
| 914 |
+
"learning_rate": 0.0020295566502463057,
|
| 915 |
+
"loss": 0.4943,
|
| 916 |
+
"step": 1210
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 6.0,
|
| 920 |
+
"eval_accuracy": 0.979933110367893,
|
| 921 |
+
"eval_f1": 0.9828335162681155,
|
| 922 |
+
"eval_loss": 0.08049997687339783,
|
| 923 |
+
"eval_precision": 0.9843107832686134,
|
| 924 |
+
"eval_recall": 0.9819606365532088,
|
| 925 |
+
"eval_runtime": 12.9302,
|
| 926 |
+
"eval_samples_per_second": 184.993,
|
| 927 |
+
"eval_steps_per_second": 11.601,
|
| 928 |
+
"step": 1219
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 6.0,
|
| 932 |
+
"grad_norm": 0.9201492667198181,
|
| 933 |
+
"learning_rate": 0.0020049261083743843,
|
| 934 |
+
"loss": 0.4137,
|
| 935 |
+
"step": 1220
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 6.05,
|
| 939 |
+
"grad_norm": 1.0448100566864014,
|
| 940 |
+
"learning_rate": 0.001980295566502463,
|
| 941 |
+
"loss": 0.4731,
|
| 942 |
+
"step": 1230
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 6.1,
|
| 946 |
+
"grad_norm": 7.53134298324585,
|
| 947 |
+
"learning_rate": 0.001955665024630542,
|
| 948 |
+
"loss": 0.4018,
|
| 949 |
+
"step": 1240
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 6.15,
|
| 953 |
+
"grad_norm": 1.0926949977874756,
|
| 954 |
+
"learning_rate": 0.0019310344827586207,
|
| 955 |
+
"loss": 0.4643,
|
| 956 |
+
"step": 1250
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 6.2,
|
| 960 |
+
"grad_norm": 1.1615904569625854,
|
| 961 |
+
"learning_rate": 0.0019064039408866996,
|
| 962 |
+
"loss": 0.4885,
|
| 963 |
+
"step": 1260
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 6.25,
|
| 967 |
+
"grad_norm": 1.0068614482879639,
|
| 968 |
+
"learning_rate": 0.0018817733990147785,
|
| 969 |
+
"loss": 0.4001,
|
| 970 |
+
"step": 1270
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 6.3,
|
| 974 |
+
"grad_norm": 1.080955982208252,
|
| 975 |
+
"learning_rate": 0.0018571428571428573,
|
| 976 |
+
"loss": 0.4136,
|
| 977 |
+
"step": 1280
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 6.35,
|
| 981 |
+
"grad_norm": 1.4813597202301025,
|
| 982 |
+
"learning_rate": 0.001832512315270936,
|
| 983 |
+
"loss": 0.3908,
|
| 984 |
+
"step": 1290
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 6.4,
|
| 988 |
+
"grad_norm": 0.8198271989822388,
|
| 989 |
+
"learning_rate": 0.0018078817733990149,
|
| 990 |
+
"loss": 0.4096,
|
| 991 |
+
"step": 1300
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 6.45,
|
| 995 |
+
"grad_norm": 0.9625017642974854,
|
| 996 |
+
"learning_rate": 0.0017832512315270935,
|
| 997 |
+
"loss": 0.408,
|
| 998 |
+
"step": 1310
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 6.49,
|
| 1002 |
+
"grad_norm": 0.969749391078949,
|
| 1003 |
+
"learning_rate": 0.0017586206896551724,
|
| 1004 |
+
"loss": 0.4371,
|
| 1005 |
+
"step": 1320
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 6.54,
|
| 1009 |
+
"grad_norm": 1.013454794883728,
|
| 1010 |
+
"learning_rate": 0.0017339901477832513,
|
| 1011 |
+
"loss": 0.4635,
|
| 1012 |
+
"step": 1330
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 6.59,
|
| 1016 |
+
"grad_norm": 1.1573213338851929,
|
| 1017 |
+
"learning_rate": 0.0017093596059113301,
|
| 1018 |
+
"loss": 0.3503,
|
| 1019 |
+
"step": 1340
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 6.64,
|
| 1023 |
+
"grad_norm": 0.9733229875564575,
|
| 1024 |
+
"learning_rate": 0.0016847290640394088,
|
| 1025 |
+
"loss": 0.447,
|
| 1026 |
+
"step": 1350
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 6.69,
|
| 1030 |
+
"grad_norm": 0.6445940136909485,
|
| 1031 |
+
"learning_rate": 0.0016600985221674877,
|
| 1032 |
+
"loss": 0.4405,
|
| 1033 |
+
"step": 1360
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 6.74,
|
| 1037 |
+
"grad_norm": 1.0442399978637695,
|
| 1038 |
+
"learning_rate": 0.0016354679802955666,
|
| 1039 |
+
"loss": 0.3957,
|
| 1040 |
+
"step": 1370
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 6.79,
|
| 1044 |
+
"grad_norm": 1.03929603099823,
|
| 1045 |
+
"learning_rate": 0.0016108374384236454,
|
| 1046 |
+
"loss": 0.4509,
|
| 1047 |
+
"step": 1380
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 6.84,
|
| 1051 |
+
"grad_norm": 0.7856884598731995,
|
| 1052 |
+
"learning_rate": 0.0015862068965517243,
|
| 1053 |
+
"loss": 0.3689,
|
| 1054 |
+
"step": 1390
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 6.89,
|
| 1058 |
+
"grad_norm": 0.6504011750221252,
|
| 1059 |
+
"learning_rate": 0.001561576354679803,
|
| 1060 |
+
"loss": 0.4059,
|
| 1061 |
+
"step": 1400
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 6.94,
|
| 1065 |
+
"grad_norm": 1.0724025964736938,
|
| 1066 |
+
"learning_rate": 0.0015369458128078816,
|
| 1067 |
+
"loss": 0.4188,
|
| 1068 |
+
"step": 1410
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 6.99,
|
| 1072 |
+
"grad_norm": 0.8927863836288452,
|
| 1073 |
+
"learning_rate": 0.0015123152709359605,
|
| 1074 |
+
"loss": 0.426,
|
| 1075 |
+
"step": 1420
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 7.0,
|
| 1079 |
+
"eval_accuracy": 0.979933110367893,
|
| 1080 |
+
"eval_f1": 0.9780623859702803,
|
| 1081 |
+
"eval_loss": 0.06709808856248856,
|
| 1082 |
+
"eval_precision": 0.9782146710296142,
|
| 1083 |
+
"eval_recall": 0.9786844286441465,
|
| 1084 |
+
"eval_runtime": 12.9674,
|
| 1085 |
+
"eval_samples_per_second": 184.462,
|
| 1086 |
+
"eval_steps_per_second": 11.567,
|
| 1087 |
+
"step": 1422
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 7.04,
|
| 1091 |
+
"grad_norm": 0.7571507096290588,
|
| 1092 |
+
"learning_rate": 0.0014876847290640394,
|
| 1093 |
+
"loss": 0.3513,
|
| 1094 |
+
"step": 1430
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 7.08,
|
| 1098 |
+
"grad_norm": 0.9653282761573792,
|
| 1099 |
+
"learning_rate": 0.0014630541871921182,
|
| 1100 |
+
"loss": 0.3661,
|
| 1101 |
+
"step": 1440
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 7.13,
|
| 1105 |
+
"grad_norm": 1.1139851808547974,
|
| 1106 |
+
"learning_rate": 0.001438423645320197,
|
| 1107 |
+
"loss": 0.3978,
|
| 1108 |
+
"step": 1450
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 7.18,
|
| 1112 |
+
"grad_norm": 1.7360243797302246,
|
| 1113 |
+
"learning_rate": 0.001413793103448276,
|
| 1114 |
+
"loss": 0.3504,
|
| 1115 |
+
"step": 1460
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 7.23,
|
| 1119 |
+
"grad_norm": 1.009930968284607,
|
| 1120 |
+
"learning_rate": 0.0013891625615763549,
|
| 1121 |
+
"loss": 0.3718,
|
| 1122 |
+
"step": 1470
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 7.28,
|
| 1126 |
+
"grad_norm": 1.2110596895217896,
|
| 1127 |
+
"learning_rate": 0.0013645320197044337,
|
| 1128 |
+
"loss": 0.4109,
|
| 1129 |
+
"step": 1480
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 7.33,
|
| 1133 |
+
"grad_norm": 1.1028022766113281,
|
| 1134 |
+
"learning_rate": 0.0013399014778325122,
|
| 1135 |
+
"loss": 0.4052,
|
| 1136 |
+
"step": 1490
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 7.38,
|
| 1140 |
+
"grad_norm": 1.0521297454833984,
|
| 1141 |
+
"learning_rate": 0.001315270935960591,
|
| 1142 |
+
"loss": 0.4152,
|
| 1143 |
+
"step": 1500
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 7.43,
|
| 1147 |
+
"grad_norm": 0.8621806502342224,
|
| 1148 |
+
"learning_rate": 0.00129064039408867,
|
| 1149 |
+
"loss": 0.3573,
|
| 1150 |
+
"step": 1510
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 7.48,
|
| 1154 |
+
"grad_norm": 1.0334779024124146,
|
| 1155 |
+
"learning_rate": 0.0012660098522167488,
|
| 1156 |
+
"loss": 0.3673,
|
| 1157 |
+
"step": 1520
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 7.53,
|
| 1161 |
+
"grad_norm": 0.7882916331291199,
|
| 1162 |
+
"learning_rate": 0.0012413793103448277,
|
| 1163 |
+
"loss": 0.3391,
|
| 1164 |
+
"step": 1530
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 7.58,
|
| 1168 |
+
"grad_norm": 1.2786757946014404,
|
| 1169 |
+
"learning_rate": 0.0012167487684729065,
|
| 1170 |
+
"loss": 0.3939,
|
| 1171 |
+
"step": 1540
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 7.63,
|
| 1175 |
+
"grad_norm": 1.4354298114776611,
|
| 1176 |
+
"learning_rate": 0.0011921182266009852,
|
| 1177 |
+
"loss": 0.4541,
|
| 1178 |
+
"step": 1550
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 7.68,
|
| 1182 |
+
"grad_norm": 1.0900424718856812,
|
| 1183 |
+
"learning_rate": 0.001167487684729064,
|
| 1184 |
+
"loss": 0.3183,
|
| 1185 |
+
"step": 1560
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 7.72,
|
| 1189 |
+
"grad_norm": 0.8424840569496155,
|
| 1190 |
+
"learning_rate": 0.001142857142857143,
|
| 1191 |
+
"loss": 0.3408,
|
| 1192 |
+
"step": 1570
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 7.77,
|
| 1196 |
+
"grad_norm": 0.6967119574546814,
|
| 1197 |
+
"learning_rate": 0.0011182266009852216,
|
| 1198 |
+
"loss": 0.4029,
|
| 1199 |
+
"step": 1580
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 7.82,
|
| 1203 |
+
"grad_norm": 0.7286412119865417,
|
| 1204 |
+
"learning_rate": 0.0010935960591133005,
|
| 1205 |
+
"loss": 0.3717,
|
| 1206 |
+
"step": 1590
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 7.87,
|
| 1210 |
+
"grad_norm": 0.9532930254936218,
|
| 1211 |
+
"learning_rate": 0.0010689655172413793,
|
| 1212 |
+
"loss": 0.3215,
|
| 1213 |
+
"step": 1600
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 7.92,
|
| 1217 |
+
"grad_norm": 1.0920195579528809,
|
| 1218 |
+
"learning_rate": 0.001044334975369458,
|
| 1219 |
+
"loss": 0.3885,
|
| 1220 |
+
"step": 1610
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 7.97,
|
| 1224 |
+
"grad_norm": 0.8902508020401001,
|
| 1225 |
+
"learning_rate": 0.0010197044334975369,
|
| 1226 |
+
"loss": 0.4152,
|
| 1227 |
+
"step": 1620
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 8.0,
|
| 1231 |
+
"eval_accuracy": 0.9870401337792643,
|
| 1232 |
+
"eval_f1": 0.9877879659430536,
|
| 1233 |
+
"eval_loss": 0.056644052267074585,
|
| 1234 |
+
"eval_precision": 0.9862146260055851,
|
| 1235 |
+
"eval_recall": 0.9896401486739793,
|
| 1236 |
+
"eval_runtime": 12.9254,
|
| 1237 |
+
"eval_samples_per_second": 185.062,
|
| 1238 |
+
"eval_steps_per_second": 11.605,
|
| 1239 |
+
"step": 1626
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 8.02,
|
| 1243 |
+
"grad_norm": 0.998824954032898,
|
| 1244 |
+
"learning_rate": 0.0009950738916256158,
|
| 1245 |
+
"loss": 0.289,
|
| 1246 |
+
"step": 1630
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 8.07,
|
| 1250 |
+
"grad_norm": 0.6882240772247314,
|
| 1251 |
+
"learning_rate": 0.0009704433497536946,
|
| 1252 |
+
"loss": 0.3786,
|
| 1253 |
+
"step": 1640
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 8.12,
|
| 1257 |
+
"grad_norm": 0.8674384951591492,
|
| 1258 |
+
"learning_rate": 0.0009458128078817735,
|
| 1259 |
+
"loss": 0.4118,
|
| 1260 |
+
"step": 1650
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 8.17,
|
| 1264 |
+
"grad_norm": 1.109112024307251,
|
| 1265 |
+
"learning_rate": 0.0009211822660098522,
|
| 1266 |
+
"loss": 0.3298,
|
| 1267 |
+
"step": 1660
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 8.22,
|
| 1271 |
+
"grad_norm": 0.8515803217887878,
|
| 1272 |
+
"learning_rate": 0.000896551724137931,
|
| 1273 |
+
"loss": 0.2702,
|
| 1274 |
+
"step": 1670
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 8.27,
|
| 1278 |
+
"grad_norm": 1.003696322441101,
|
| 1279 |
+
"learning_rate": 0.0008719211822660099,
|
| 1280 |
+
"loss": 0.3509,
|
| 1281 |
+
"step": 1680
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 8.31,
|
| 1285 |
+
"grad_norm": 0.8540720343589783,
|
| 1286 |
+
"learning_rate": 0.0008472906403940888,
|
| 1287 |
+
"loss": 0.31,
|
| 1288 |
+
"step": 1690
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 8.36,
|
| 1292 |
+
"grad_norm": 1.6798268556594849,
|
| 1293 |
+
"learning_rate": 0.0008226600985221674,
|
| 1294 |
+
"loss": 0.3727,
|
| 1295 |
+
"step": 1700
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 8.41,
|
| 1299 |
+
"grad_norm": 0.8054636120796204,
|
| 1300 |
+
"learning_rate": 0.0007980295566502463,
|
| 1301 |
+
"loss": 0.3159,
|
| 1302 |
+
"step": 1710
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 8.46,
|
| 1306 |
+
"grad_norm": 1.4890103340148926,
|
| 1307 |
+
"learning_rate": 0.0007733990147783252,
|
| 1308 |
+
"loss": 0.3387,
|
| 1309 |
+
"step": 1720
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 8.51,
|
| 1313 |
+
"grad_norm": 0.7350850105285645,
|
| 1314 |
+
"learning_rate": 0.000748768472906404,
|
| 1315 |
+
"loss": 0.3237,
|
| 1316 |
+
"step": 1730
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 8.56,
|
| 1320 |
+
"grad_norm": 1.4844990968704224,
|
| 1321 |
+
"learning_rate": 0.0007241379310344828,
|
| 1322 |
+
"loss": 0.3395,
|
| 1323 |
+
"step": 1740
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 8.61,
|
| 1327 |
+
"grad_norm": 0.887062132358551,
|
| 1328 |
+
"learning_rate": 0.0006995073891625616,
|
| 1329 |
+
"loss": 0.3418,
|
| 1330 |
+
"step": 1750
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 8.66,
|
| 1334 |
+
"grad_norm": 0.7276543378829956,
|
| 1335 |
+
"learning_rate": 0.0006748768472906404,
|
| 1336 |
+
"loss": 0.3433,
|
| 1337 |
+
"step": 1760
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 8.71,
|
| 1341 |
+
"grad_norm": 0.6962388753890991,
|
| 1342 |
+
"learning_rate": 0.0006502463054187192,
|
| 1343 |
+
"loss": 0.3588,
|
| 1344 |
+
"step": 1770
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 8.76,
|
| 1348 |
+
"grad_norm": 1.764138102531433,
|
| 1349 |
+
"learning_rate": 0.0006256157635467981,
|
| 1350 |
+
"loss": 0.3565,
|
| 1351 |
+
"step": 1780
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 8.81,
|
| 1355 |
+
"grad_norm": 0.7240989208221436,
|
| 1356 |
+
"learning_rate": 0.0006009852216748769,
|
| 1357 |
+
"loss": 0.3361,
|
| 1358 |
+
"step": 1790
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 8.86,
|
| 1362 |
+
"grad_norm": 0.9319175481796265,
|
| 1363 |
+
"learning_rate": 0.0005763546798029557,
|
| 1364 |
+
"loss": 0.3313,
|
| 1365 |
+
"step": 1800
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 8.91,
|
| 1369 |
+
"grad_norm": 0.8015260100364685,
|
| 1370 |
+
"learning_rate": 0.0005517241379310345,
|
| 1371 |
+
"loss": 0.3776,
|
| 1372 |
+
"step": 1810
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 8.95,
|
| 1376 |
+
"grad_norm": 0.6193283200263977,
|
| 1377 |
+
"learning_rate": 0.0005270935960591134,
|
| 1378 |
+
"loss": 0.2927,
|
| 1379 |
+
"step": 1820
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 9.0,
|
| 1383 |
+
"eval_accuracy": 0.9836956521739131,
|
| 1384 |
+
"eval_f1": 0.9847638806045893,
|
| 1385 |
+
"eval_loss": 0.06579139083623886,
|
| 1386 |
+
"eval_precision": 0.9850023004987147,
|
| 1387 |
+
"eval_recall": 0.9849849759564541,
|
| 1388 |
+
"eval_runtime": 12.7582,
|
| 1389 |
+
"eval_samples_per_second": 187.488,
|
| 1390 |
+
"eval_steps_per_second": 11.757,
|
| 1391 |
+
"step": 1829
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 9.0,
|
| 1395 |
+
"grad_norm": 0.6149892210960388,
|
| 1396 |
+
"learning_rate": 0.0005024630541871921,
|
| 1397 |
+
"loss": 0.3451,
|
| 1398 |
+
"step": 1830
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 9.05,
|
| 1402 |
+
"grad_norm": 0.7571848034858704,
|
| 1403 |
+
"learning_rate": 0.00047783251231527096,
|
| 1404 |
+
"loss": 0.3187,
|
| 1405 |
+
"step": 1840
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 9.1,
|
| 1409 |
+
"grad_norm": 0.8765355348587036,
|
| 1410 |
+
"learning_rate": 0.00045320197044334973,
|
| 1411 |
+
"loss": 0.3447,
|
| 1412 |
+
"step": 1850
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 9.15,
|
| 1416 |
+
"grad_norm": 0.5563300848007202,
|
| 1417 |
+
"learning_rate": 0.0004285714285714286,
|
| 1418 |
+
"loss": 0.3529,
|
| 1419 |
+
"step": 1860
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 9.2,
|
| 1423 |
+
"grad_norm": 0.7253230810165405,
|
| 1424 |
+
"learning_rate": 0.0004039408866995074,
|
| 1425 |
+
"loss": 0.2695,
|
| 1426 |
+
"step": 1870
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 9.25,
|
| 1430 |
+
"grad_norm": 0.6665922403335571,
|
| 1431 |
+
"learning_rate": 0.0003793103448275862,
|
| 1432 |
+
"loss": 0.3091,
|
| 1433 |
+
"step": 1880
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 9.3,
|
| 1437 |
+
"grad_norm": 1.43943452835083,
|
| 1438 |
+
"learning_rate": 0.00035467980295566506,
|
| 1439 |
+
"loss": 0.2942,
|
| 1440 |
+
"step": 1890
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 9.35,
|
| 1444 |
+
"grad_norm": 2.071869373321533,
|
| 1445 |
+
"learning_rate": 0.00033004926108374383,
|
| 1446 |
+
"loss": 0.3097,
|
| 1447 |
+
"step": 1900
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 9.4,
|
| 1451 |
+
"grad_norm": 0.6491404175758362,
|
| 1452 |
+
"learning_rate": 0.0003054187192118227,
|
| 1453 |
+
"loss": 0.2895,
|
| 1454 |
+
"step": 1910
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 9.45,
|
| 1458 |
+
"grad_norm": 0.9849537014961243,
|
| 1459 |
+
"learning_rate": 0.0002807881773399015,
|
| 1460 |
+
"loss": 0.3157,
|
| 1461 |
+
"step": 1920
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 9.5,
|
| 1465 |
+
"grad_norm": 8.456196784973145,
|
| 1466 |
+
"learning_rate": 0.0002561576354679803,
|
| 1467 |
+
"loss": 0.322,
|
| 1468 |
+
"step": 1930
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 9.54,
|
| 1472 |
+
"grad_norm": 0.5972003936767578,
|
| 1473 |
+
"learning_rate": 0.0002315270935960591,
|
| 1474 |
+
"loss": 0.2867,
|
| 1475 |
+
"step": 1940
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 9.59,
|
| 1479 |
+
"grad_norm": 0.42175132036209106,
|
| 1480 |
+
"learning_rate": 0.00020689655172413793,
|
| 1481 |
+
"loss": 0.2804,
|
| 1482 |
+
"step": 1950
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 9.64,
|
| 1486 |
+
"grad_norm": 1.2799464464187622,
|
| 1487 |
+
"learning_rate": 0.00018226600985221675,
|
| 1488 |
+
"loss": 0.2941,
|
| 1489 |
+
"step": 1960
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 9.69,
|
| 1493 |
+
"grad_norm": 0.8577640056610107,
|
| 1494 |
+
"learning_rate": 0.00015763546798029557,
|
| 1495 |
+
"loss": 0.3202,
|
| 1496 |
+
"step": 1970
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 9.74,
|
| 1500 |
+
"grad_norm": 0.9166315197944641,
|
| 1501 |
+
"learning_rate": 0.00013300492610837438,
|
| 1502 |
+
"loss": 0.3404,
|
| 1503 |
+
"step": 1980
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 9.79,
|
| 1507 |
+
"grad_norm": 1.3336009979248047,
|
| 1508 |
+
"learning_rate": 0.0001083743842364532,
|
| 1509 |
+
"loss": 0.3071,
|
| 1510 |
+
"step": 1990
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 9.84,
|
| 1514 |
+
"grad_norm": 0.7033586502075195,
|
| 1515 |
+
"learning_rate": 8.374384236453201e-05,
|
| 1516 |
+
"loss": 0.3037,
|
| 1517 |
+
"step": 2000
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 9.89,
|
| 1521 |
+
"grad_norm": 0.48131078481674194,
|
| 1522 |
+
"learning_rate": 5.9113300492610844e-05,
|
| 1523 |
+
"loss": 0.289,
|
| 1524 |
+
"step": 2010
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 9.94,
|
| 1528 |
+
"grad_norm": 0.8269424438476562,
|
| 1529 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 1530 |
+
"loss": 0.3021,
|
| 1531 |
+
"step": 2020
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 9.99,
|
| 1535 |
+
"grad_norm": 1.1306647062301636,
|
| 1536 |
+
"learning_rate": 9.852216748768473e-06,
|
| 1537 |
+
"loss": 0.3154,
|
| 1538 |
+
"step": 2030
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 9.99,
|
| 1542 |
+
"eval_accuracy": 0.9841137123745819,
|
| 1543 |
+
"eval_f1": 0.9852639526448546,
|
| 1544 |
+
"eval_loss": 0.0536968968808651,
|
| 1545 |
+
"eval_precision": 0.9855005493602992,
|
| 1546 |
+
"eval_recall": 0.9854135689141749,
|
| 1547 |
+
"eval_runtime": 12.8562,
|
| 1548 |
+
"eval_samples_per_second": 186.058,
|
| 1549 |
+
"eval_steps_per_second": 11.668,
|
| 1550 |
+
"step": 2030
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 9.99,
|
| 1554 |
+
"step": 2030,
|
| 1555 |
+
"total_flos": 1.0133154899356189e+19,
|
| 1556 |
+
"train_loss": 0.5219255947714369,
|
| 1557 |
+
"train_runtime": 1565.9689,
|
| 1558 |
+
"train_samples_per_second": 83.016,
|
| 1559 |
+
"train_steps_per_second": 1.296
|
| 1560 |
+
}
|
| 1561 |
+
],
|
| 1562 |
+
"logging_steps": 10,
|
| 1563 |
+
"max_steps": 2030,
|
| 1564 |
+
"num_input_tokens_seen": 0,
|
| 1565 |
+
"num_train_epochs": 10,
|
| 1566 |
+
"save_steps": 500,
|
| 1567 |
+
"total_flos": 1.0133154899356189e+19,
|
| 1568 |
+
"train_batch_size": 16,
|
| 1569 |
+
"trial_name": null,
|
| 1570 |
+
"trial_params": null
|
| 1571 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c062acd83ee2ca580a9704ecd3d8efd31c27d20ee1585c2f9b475a09eeb40b3
|
| 3 |
+
size 5112
|