🍻 cheers
Browse files- README.md +80 -0
- all_results.json +13 -0
- config.json +42 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Apr28_09-24-43_8de383cac982/events.out.tfevents.1714296294.8de383cac982.2041.0 +3 -0
- runs/Apr28_09-24-43_8de383cac982/events.out.tfevents.1714296828.8de383cac982.2041.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1559 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: finetuned-clothes
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# finetuned-clothes
|
| 18 |
+
|
| 19 |
+
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 clothes_simplifiedv2 dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2225
|
| 22 |
+
- Accuracy: 0.9417
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 5e-05
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 4
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 0.7725 | 0.2058 | 100 | 0.7008 | 0.8178 |
|
| 55 |
+
| 0.5535 | 0.4115 | 200 | 0.4494 | 0.8994 |
|
| 56 |
+
| 0.4334 | 0.6173 | 300 | 0.3649 | 0.9169 |
|
| 57 |
+
| 0.3921 | 0.8230 | 400 | 0.3085 | 0.9184 |
|
| 58 |
+
| 0.3695 | 1.0288 | 500 | 0.3091 | 0.9184 |
|
| 59 |
+
| 0.2634 | 1.2346 | 600 | 0.3339 | 0.9082 |
|
| 60 |
+
| 0.4788 | 1.4403 | 700 | 0.2827 | 0.9257 |
|
| 61 |
+
| 0.3337 | 1.6461 | 800 | 0.2499 | 0.9344 |
|
| 62 |
+
| 0.34 | 1.8519 | 900 | 0.2586 | 0.9315 |
|
| 63 |
+
| 0.2424 | 2.0576 | 1000 | 0.2248 | 0.9402 |
|
| 64 |
+
| 0.1559 | 2.2634 | 1100 | 0.2333 | 0.9344 |
|
| 65 |
+
| 0.351 | 2.4691 | 1200 | 0.2495 | 0.9359 |
|
| 66 |
+
| 0.2206 | 2.6749 | 1300 | 0.2622 | 0.9242 |
|
| 67 |
+
| 0.3814 | 2.8807 | 1400 | 0.3138 | 0.9155 |
|
| 68 |
+
| 0.2141 | 3.0864 | 1500 | 0.2613 | 0.9315 |
|
| 69 |
+
| 0.112 | 3.2922 | 1600 | 0.2266 | 0.9402 |
|
| 70 |
+
| 0.0631 | 3.4979 | 1700 | 0.2255 | 0.9402 |
|
| 71 |
+
| 0.1986 | 3.7037 | 1800 | 0.2225 | 0.9417 |
|
| 72 |
+
| 0.2345 | 3.9095 | 1900 | 0.2235 | 0.9373 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.40.1
|
| 78 |
+
- Pytorch 2.2.1+cu121
|
| 79 |
+
- Datasets 2.19.0
|
| 80 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9416909620991254,
|
| 4 |
+
"eval_loss": 0.22252099215984344,
|
| 5 |
+
"eval_runtime": 7.4442,
|
| 6 |
+
"eval_samples_per_second": 92.153,
|
| 7 |
+
"eval_steps_per_second": 11.553,
|
| 8 |
+
"total_flos": 1.2048994477712425e+18,
|
| 9 |
+
"train_loss": 0.3544519797212793,
|
| 10 |
+
"train_runtime": 505.606,
|
| 11 |
+
"train_samples_per_second": 30.751,
|
| 12 |
+
"train_steps_per_second": 3.845
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Hat",
|
| 13 |
+
"1": "Longsleeve",
|
| 14 |
+
"2": "Outwear",
|
| 15 |
+
"3": "Pants",
|
| 16 |
+
"4": "Shoes",
|
| 17 |
+
"5": "Shorts",
|
| 18 |
+
"6": "Shortsleeve"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"Hat": "0",
|
| 25 |
+
"Longsleeve": "1",
|
| 26 |
+
"Outwear": "2",
|
| 27 |
+
"Pants": "3",
|
| 28 |
+
"Shoes": "4",
|
| 29 |
+
"Shorts": "5",
|
| 30 |
+
"Shortsleeve": "6"
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "vit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"qkv_bias": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.40.1"
|
| 42 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9416909620991254,
|
| 4 |
+
"eval_loss": 0.22252099215984344,
|
| 5 |
+
"eval_runtime": 7.4442,
|
| 6 |
+
"eval_samples_per_second": 92.153,
|
| 7 |
+
"eval_steps_per_second": 11.553
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a63787376b3045c7867b265ce5ccec7f5bb76974b4a3ba8c554830f137febe9
|
| 3 |
+
size 343239356
|
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/Apr28_09-24-43_8de383cac982/events.out.tfevents.1714296294.8de383cac982.2041.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23cdb2859db0046112b6540028c4a9b2474bff43db913245c05f2a707637ffe0
|
| 3 |
+
size 52226
|
runs/Apr28_09-24-43_8de383cac982/events.out.tfevents.1714296828.8de383cac982.2041.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9c357624e0844ac8993ddbfe88e442164e40e923ef5061ae3084c0f658d2422
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.2048994477712425e+18,
|
| 4 |
+
"train_loss": 0.3544519797212793,
|
| 5 |
+
"train_runtime": 505.606,
|
| 6 |
+
"train_samples_per_second": 30.751,
|
| 7 |
+
"train_steps_per_second": 3.845
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1559 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.22252099215984344,
|
| 3 |
+
"best_model_checkpoint": "finetuned-clothes/checkpoint-1800",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1944,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0205761316872428,
|
| 13 |
+
"grad_norm": 2.173704147338867,
|
| 14 |
+
"learning_rate": 4.974279835390947e-05,
|
| 15 |
+
"loss": 1.8548,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0411522633744856,
|
| 20 |
+
"grad_norm": 4.239943981170654,
|
| 21 |
+
"learning_rate": 4.948559670781893e-05,
|
| 22 |
+
"loss": 1.6474,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06172839506172839,
|
| 27 |
+
"grad_norm": 3.0864417552948,
|
| 28 |
+
"learning_rate": 4.92283950617284e-05,
|
| 29 |
+
"loss": 1.4579,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0823045267489712,
|
| 34 |
+
"grad_norm": 2.301297187805176,
|
| 35 |
+
"learning_rate": 4.8971193415637865e-05,
|
| 36 |
+
"loss": 1.3241,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.102880658436214,
|
| 41 |
+
"grad_norm": 2.933986186981201,
|
| 42 |
+
"learning_rate": 4.871399176954733e-05,
|
| 43 |
+
"loss": 1.1818,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12345679012345678,
|
| 48 |
+
"grad_norm": 2.552161931991577,
|
| 49 |
+
"learning_rate": 4.845679012345679e-05,
|
| 50 |
+
"loss": 1.0563,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1440329218106996,
|
| 55 |
+
"grad_norm": 2.6376731395721436,
|
| 56 |
+
"learning_rate": 4.819958847736626e-05,
|
| 57 |
+
"loss": 1.0264,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1646090534979424,
|
| 62 |
+
"grad_norm": 3.713806390762329,
|
| 63 |
+
"learning_rate": 4.794238683127572e-05,
|
| 64 |
+
"loss": 0.9449,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18518518518518517,
|
| 69 |
+
"grad_norm": 4.88785982131958,
|
| 70 |
+
"learning_rate": 4.768518518518519e-05,
|
| 71 |
+
"loss": 0.7746,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.205761316872428,
|
| 76 |
+
"grad_norm": 2.0521767139434814,
|
| 77 |
+
"learning_rate": 4.742798353909465e-05,
|
| 78 |
+
"loss": 0.7725,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.205761316872428,
|
| 83 |
+
"eval_accuracy": 0.8177842565597667,
|
| 84 |
+
"eval_loss": 0.7007715106010437,
|
| 85 |
+
"eval_runtime": 5.2424,
|
| 86 |
+
"eval_samples_per_second": 130.856,
|
| 87 |
+
"eval_steps_per_second": 16.405,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.22633744855967078,
|
| 92 |
+
"grad_norm": 1.4839606285095215,
|
| 93 |
+
"learning_rate": 4.7170781893004116e-05,
|
| 94 |
+
"loss": 0.6586,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.24691358024691357,
|
| 99 |
+
"grad_norm": 5.147204875946045,
|
| 100 |
+
"learning_rate": 4.691358024691358e-05,
|
| 101 |
+
"loss": 0.7189,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.2674897119341564,
|
| 106 |
+
"grad_norm": 7.209930896759033,
|
| 107 |
+
"learning_rate": 4.665637860082305e-05,
|
| 108 |
+
"loss": 0.7384,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2880658436213992,
|
| 113 |
+
"grad_norm": 5.127917766571045,
|
| 114 |
+
"learning_rate": 4.639917695473252e-05,
|
| 115 |
+
"loss": 0.7484,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.30864197530864196,
|
| 120 |
+
"grad_norm": 3.2841947078704834,
|
| 121 |
+
"learning_rate": 4.614197530864198e-05,
|
| 122 |
+
"loss": 0.6732,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.3292181069958848,
|
| 127 |
+
"grad_norm": 5.1268110275268555,
|
| 128 |
+
"learning_rate": 4.5884773662551446e-05,
|
| 129 |
+
"loss": 0.6015,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.3497942386831276,
|
| 134 |
+
"grad_norm": 5.863048553466797,
|
| 135 |
+
"learning_rate": 4.5627572016460906e-05,
|
| 136 |
+
"loss": 0.594,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.37037037037037035,
|
| 141 |
+
"grad_norm": 2.000070095062256,
|
| 142 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 143 |
+
"loss": 0.5165,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.39094650205761317,
|
| 148 |
+
"grad_norm": 4.510650157928467,
|
| 149 |
+
"learning_rate": 4.5113168724279834e-05,
|
| 150 |
+
"loss": 0.621,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.411522633744856,
|
| 155 |
+
"grad_norm": 2.4744088649749756,
|
| 156 |
+
"learning_rate": 4.48559670781893e-05,
|
| 157 |
+
"loss": 0.5535,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.411522633744856,
|
| 162 |
+
"eval_accuracy": 0.8994169096209913,
|
| 163 |
+
"eval_loss": 0.44938138127326965,
|
| 164 |
+
"eval_runtime": 5.2054,
|
| 165 |
+
"eval_samples_per_second": 131.787,
|
| 166 |
+
"eval_steps_per_second": 16.521,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.43209876543209874,
|
| 171 |
+
"grad_norm": 7.232150077819824,
|
| 172 |
+
"learning_rate": 4.459876543209877e-05,
|
| 173 |
+
"loss": 0.7554,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.45267489711934156,
|
| 178 |
+
"grad_norm": 2.480642318725586,
|
| 179 |
+
"learning_rate": 4.4341563786008236e-05,
|
| 180 |
+
"loss": 0.6475,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.4732510288065844,
|
| 185 |
+
"grad_norm": 6.75883150100708,
|
| 186 |
+
"learning_rate": 4.40843621399177e-05,
|
| 187 |
+
"loss": 0.4951,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.49382716049382713,
|
| 192 |
+
"grad_norm": 2.3725767135620117,
|
| 193 |
+
"learning_rate": 4.3827160493827164e-05,
|
| 194 |
+
"loss": 0.5711,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.51440329218107,
|
| 199 |
+
"grad_norm": 4.138972282409668,
|
| 200 |
+
"learning_rate": 4.3569958847736625e-05,
|
| 201 |
+
"loss": 0.5318,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.5349794238683128,
|
| 206 |
+
"grad_norm": 11.300224304199219,
|
| 207 |
+
"learning_rate": 4.331275720164609e-05,
|
| 208 |
+
"loss": 0.5041,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.5555555555555556,
|
| 213 |
+
"grad_norm": 6.57551383972168,
|
| 214 |
+
"learning_rate": 4.305555555555556e-05,
|
| 215 |
+
"loss": 0.5828,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.5761316872427984,
|
| 220 |
+
"grad_norm": 4.986762523651123,
|
| 221 |
+
"learning_rate": 4.279835390946502e-05,
|
| 222 |
+
"loss": 0.491,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.5967078189300411,
|
| 227 |
+
"grad_norm": 3.5556581020355225,
|
| 228 |
+
"learning_rate": 4.254115226337449e-05,
|
| 229 |
+
"loss": 0.4911,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.6172839506172839,
|
| 234 |
+
"grad_norm": 0.6545975804328918,
|
| 235 |
+
"learning_rate": 4.230967078189301e-05,
|
| 236 |
+
"loss": 0.4334,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.6172839506172839,
|
| 241 |
+
"eval_accuracy": 0.9169096209912536,
|
| 242 |
+
"eval_loss": 0.3648872971534729,
|
| 243 |
+
"eval_runtime": 5.389,
|
| 244 |
+
"eval_samples_per_second": 127.297,
|
| 245 |
+
"eval_steps_per_second": 15.959,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.6378600823045267,
|
| 250 |
+
"grad_norm": 6.065480709075928,
|
| 251 |
+
"learning_rate": 4.205246913580247e-05,
|
| 252 |
+
"loss": 0.4079,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.6584362139917695,
|
| 257 |
+
"grad_norm": 7.807397842407227,
|
| 258 |
+
"learning_rate": 4.1795267489711935e-05,
|
| 259 |
+
"loss": 0.5353,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.6790123456790124,
|
| 264 |
+
"grad_norm": 4.977638244628906,
|
| 265 |
+
"learning_rate": 4.1563786008230455e-05,
|
| 266 |
+
"loss": 0.3977,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.6995884773662552,
|
| 271 |
+
"grad_norm": 0.7537054419517517,
|
| 272 |
+
"learning_rate": 4.130658436213992e-05,
|
| 273 |
+
"loss": 0.4792,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.720164609053498,
|
| 278 |
+
"grad_norm": 1.4330915212631226,
|
| 279 |
+
"learning_rate": 4.104938271604938e-05,
|
| 280 |
+
"loss": 0.3986,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.7407407407407407,
|
| 285 |
+
"grad_norm": 3.951570510864258,
|
| 286 |
+
"learning_rate": 4.079218106995885e-05,
|
| 287 |
+
"loss": 0.4249,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.7613168724279835,
|
| 292 |
+
"grad_norm": 6.858752727508545,
|
| 293 |
+
"learning_rate": 4.053497942386831e-05,
|
| 294 |
+
"loss": 0.4735,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.7818930041152263,
|
| 299 |
+
"grad_norm": 7.806582927703857,
|
| 300 |
+
"learning_rate": 4.027777777777778e-05,
|
| 301 |
+
"loss": 0.4037,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.8024691358024691,
|
| 306 |
+
"grad_norm": 5.925368309020996,
|
| 307 |
+
"learning_rate": 4.0020576131687245e-05,
|
| 308 |
+
"loss": 0.3997,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.823045267489712,
|
| 313 |
+
"grad_norm": 15.64376163482666,
|
| 314 |
+
"learning_rate": 3.976337448559671e-05,
|
| 315 |
+
"loss": 0.3921,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.823045267489712,
|
| 320 |
+
"eval_accuracy": 0.9183673469387755,
|
| 321 |
+
"eval_loss": 0.3085317313671112,
|
| 322 |
+
"eval_runtime": 5.5462,
|
| 323 |
+
"eval_samples_per_second": 123.689,
|
| 324 |
+
"eval_steps_per_second": 15.506,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8436213991769548,
|
| 329 |
+
"grad_norm": 0.49218544363975525,
|
| 330 |
+
"learning_rate": 3.950617283950617e-05,
|
| 331 |
+
"loss": 0.394,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8641975308641975,
|
| 336 |
+
"grad_norm": 0.5128059983253479,
|
| 337 |
+
"learning_rate": 3.924897119341564e-05,
|
| 338 |
+
"loss": 0.2721,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8847736625514403,
|
| 343 |
+
"grad_norm": 6.586925029754639,
|
| 344 |
+
"learning_rate": 3.89917695473251e-05,
|
| 345 |
+
"loss": 0.4608,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.9053497942386831,
|
| 350 |
+
"grad_norm": 4.243907451629639,
|
| 351 |
+
"learning_rate": 3.873456790123457e-05,
|
| 352 |
+
"loss": 0.4534,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9259259259259259,
|
| 357 |
+
"grad_norm": 0.5013654828071594,
|
| 358 |
+
"learning_rate": 3.8477366255144036e-05,
|
| 359 |
+
"loss": 0.3535,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9465020576131687,
|
| 364 |
+
"grad_norm": 12.352477073669434,
|
| 365 |
+
"learning_rate": 3.8220164609053496e-05,
|
| 366 |
+
"loss": 0.3733,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9670781893004116,
|
| 371 |
+
"grad_norm": 7.122161865234375,
|
| 372 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 373 |
+
"loss": 0.4486,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9876543209876543,
|
| 378 |
+
"grad_norm": 4.856133937835693,
|
| 379 |
+
"learning_rate": 3.770576131687243e-05,
|
| 380 |
+
"loss": 0.4629,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.008230452674897,
|
| 385 |
+
"grad_norm": 0.6018617749214172,
|
| 386 |
+
"learning_rate": 3.74485596707819e-05,
|
| 387 |
+
"loss": 0.2749,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.02880658436214,
|
| 392 |
+
"grad_norm": 8.492673873901367,
|
| 393 |
+
"learning_rate": 3.719135802469136e-05,
|
| 394 |
+
"loss": 0.3695,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.02880658436214,
|
| 399 |
+
"eval_accuracy": 0.9183673469387755,
|
| 400 |
+
"eval_loss": 0.30907005071640015,
|
| 401 |
+
"eval_runtime": 5.8028,
|
| 402 |
+
"eval_samples_per_second": 118.218,
|
| 403 |
+
"eval_steps_per_second": 14.82,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.0493827160493827,
|
| 408 |
+
"grad_norm": 2.352186679840088,
|
| 409 |
+
"learning_rate": 3.6934156378600826e-05,
|
| 410 |
+
"loss": 0.3995,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.0699588477366255,
|
| 415 |
+
"grad_norm": 2.0695996284484863,
|
| 416 |
+
"learning_rate": 3.667695473251029e-05,
|
| 417 |
+
"loss": 0.2422,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.0905349794238683,
|
| 422 |
+
"grad_norm": 0.4764484167098999,
|
| 423 |
+
"learning_rate": 3.6419753086419754e-05,
|
| 424 |
+
"loss": 0.3073,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.1111111111111112,
|
| 429 |
+
"grad_norm": 2.4346959590911865,
|
| 430 |
+
"learning_rate": 3.6162551440329215e-05,
|
| 431 |
+
"loss": 0.279,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.131687242798354,
|
| 436 |
+
"grad_norm": 1.6526964902877808,
|
| 437 |
+
"learning_rate": 3.590534979423868e-05,
|
| 438 |
+
"loss": 0.217,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.1522633744855968,
|
| 443 |
+
"grad_norm": 1.5531551837921143,
|
| 444 |
+
"learning_rate": 3.564814814814815e-05,
|
| 445 |
+
"loss": 0.3906,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.1728395061728394,
|
| 450 |
+
"grad_norm": 0.41519421339035034,
|
| 451 |
+
"learning_rate": 3.539094650205762e-05,
|
| 452 |
+
"loss": 0.1809,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.1934156378600824,
|
| 457 |
+
"grad_norm": 8.064279556274414,
|
| 458 |
+
"learning_rate": 3.5133744855967084e-05,
|
| 459 |
+
"loss": 0.2767,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.213991769547325,
|
| 464 |
+
"grad_norm": 0.4536079466342926,
|
| 465 |
+
"learning_rate": 3.4876543209876545e-05,
|
| 466 |
+
"loss": 0.4032,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.2345679012345678,
|
| 471 |
+
"grad_norm": 12.668285369873047,
|
| 472 |
+
"learning_rate": 3.461934156378601e-05,
|
| 473 |
+
"loss": 0.2634,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.2345679012345678,
|
| 478 |
+
"eval_accuracy": 0.9081632653061225,
|
| 479 |
+
"eval_loss": 0.3338664472103119,
|
| 480 |
+
"eval_runtime": 5.3039,
|
| 481 |
+
"eval_samples_per_second": 129.338,
|
| 482 |
+
"eval_steps_per_second": 16.214,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.2551440329218106,
|
| 487 |
+
"grad_norm": 3.9776062965393066,
|
| 488 |
+
"learning_rate": 3.436213991769547e-05,
|
| 489 |
+
"loss": 0.3071,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.2757201646090535,
|
| 494 |
+
"grad_norm": 3.995609760284424,
|
| 495 |
+
"learning_rate": 3.410493827160494e-05,
|
| 496 |
+
"loss": 0.3862,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.2962962962962963,
|
| 501 |
+
"grad_norm": 1.187232255935669,
|
| 502 |
+
"learning_rate": 3.38477366255144e-05,
|
| 503 |
+
"loss": 0.4498,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.316872427983539,
|
| 508 |
+
"grad_norm": 17.8300724029541,
|
| 509 |
+
"learning_rate": 3.3590534979423874e-05,
|
| 510 |
+
"loss": 0.3186,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.337448559670782,
|
| 515 |
+
"grad_norm": 1.6956249475479126,
|
| 516 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 517 |
+
"loss": 0.2368,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.3580246913580247,
|
| 522 |
+
"grad_norm": 0.9367788434028625,
|
| 523 |
+
"learning_rate": 3.30761316872428e-05,
|
| 524 |
+
"loss": 0.4461,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.3786008230452675,
|
| 529 |
+
"grad_norm": 3.084554433822632,
|
| 530 |
+
"learning_rate": 3.281893004115226e-05,
|
| 531 |
+
"loss": 0.3022,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.3991769547325104,
|
| 536 |
+
"grad_norm": 1.4184356927871704,
|
| 537 |
+
"learning_rate": 3.256172839506173e-05,
|
| 538 |
+
"loss": 0.3542,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.4197530864197532,
|
| 543 |
+
"grad_norm": 9.956780433654785,
|
| 544 |
+
"learning_rate": 3.230452674897119e-05,
|
| 545 |
+
"loss": 0.2772,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.4403292181069958,
|
| 550 |
+
"grad_norm": 7.774564266204834,
|
| 551 |
+
"learning_rate": 3.204732510288066e-05,
|
| 552 |
+
"loss": 0.4788,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.4403292181069958,
|
| 557 |
+
"eval_accuracy": 0.9256559766763849,
|
| 558 |
+
"eval_loss": 0.28270086646080017,
|
| 559 |
+
"eval_runtime": 5.1862,
|
| 560 |
+
"eval_samples_per_second": 132.274,
|
| 561 |
+
"eval_steps_per_second": 16.582,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.4609053497942388,
|
| 566 |
+
"grad_norm": 1.6019172668457031,
|
| 567 |
+
"learning_rate": 3.1790123456790125e-05,
|
| 568 |
+
"loss": 0.3656,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.4814814814814814,
|
| 573 |
+
"grad_norm": 0.32796138525009155,
|
| 574 |
+
"learning_rate": 3.153292181069959e-05,
|
| 575 |
+
"loss": 0.291,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.5020576131687244,
|
| 580 |
+
"grad_norm": 6.803758144378662,
|
| 581 |
+
"learning_rate": 3.127572016460906e-05,
|
| 582 |
+
"loss": 0.2756,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.522633744855967,
|
| 587 |
+
"grad_norm": 9.335061073303223,
|
| 588 |
+
"learning_rate": 3.101851851851852e-05,
|
| 589 |
+
"loss": 0.353,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.5432098765432098,
|
| 594 |
+
"grad_norm": 11.15013599395752,
|
| 595 |
+
"learning_rate": 3.076131687242799e-05,
|
| 596 |
+
"loss": 0.3542,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.5637860082304527,
|
| 601 |
+
"grad_norm": 7.025611400604248,
|
| 602 |
+
"learning_rate": 3.050411522633745e-05,
|
| 603 |
+
"loss": 0.3576,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.5843621399176955,
|
| 608 |
+
"grad_norm": 4.891916275024414,
|
| 609 |
+
"learning_rate": 3.0246913580246916e-05,
|
| 610 |
+
"loss": 0.1898,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.6049382716049383,
|
| 615 |
+
"grad_norm": 4.149532318115234,
|
| 616 |
+
"learning_rate": 2.998971193415638e-05,
|
| 617 |
+
"loss": 0.3467,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.625514403292181,
|
| 622 |
+
"grad_norm": 4.81355094909668,
|
| 623 |
+
"learning_rate": 2.9732510288065847e-05,
|
| 624 |
+
"loss": 0.2927,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.646090534979424,
|
| 629 |
+
"grad_norm": 5.665321350097656,
|
| 630 |
+
"learning_rate": 2.9475308641975308e-05,
|
| 631 |
+
"loss": 0.3337,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.646090534979424,
|
| 636 |
+
"eval_accuracy": 0.934402332361516,
|
| 637 |
+
"eval_loss": 0.24985870718955994,
|
| 638 |
+
"eval_runtime": 11.5489,
|
| 639 |
+
"eval_samples_per_second": 59.4,
|
| 640 |
+
"eval_steps_per_second": 7.447,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.6666666666666665,
|
| 645 |
+
"grad_norm": 5.743719100952148,
|
| 646 |
+
"learning_rate": 2.9218106995884775e-05,
|
| 647 |
+
"loss": 0.2494,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.6872427983539096,
|
| 652 |
+
"grad_norm": 0.2070736289024353,
|
| 653 |
+
"learning_rate": 2.896090534979424e-05,
|
| 654 |
+
"loss": 0.3724,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.7078189300411522,
|
| 659 |
+
"grad_norm": 0.6346050500869751,
|
| 660 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 661 |
+
"loss": 0.4756,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.7283950617283952,
|
| 666 |
+
"grad_norm": 10.402286529541016,
|
| 667 |
+
"learning_rate": 2.8446502057613174e-05,
|
| 668 |
+
"loss": 0.265,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.7489711934156378,
|
| 673 |
+
"grad_norm": 10.685330390930176,
|
| 674 |
+
"learning_rate": 2.8189300411522634e-05,
|
| 675 |
+
"loss": 0.301,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.7695473251028808,
|
| 680 |
+
"grad_norm": 8.265226364135742,
|
| 681 |
+
"learning_rate": 2.79320987654321e-05,
|
| 682 |
+
"loss": 0.3098,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.7901234567901234,
|
| 687 |
+
"grad_norm": 8.33575439453125,
|
| 688 |
+
"learning_rate": 2.7674897119341565e-05,
|
| 689 |
+
"loss": 0.2974,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.8106995884773662,
|
| 694 |
+
"grad_norm": 8.888866424560547,
|
| 695 |
+
"learning_rate": 2.7417695473251033e-05,
|
| 696 |
+
"loss": 0.1666,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.831275720164609,
|
| 701 |
+
"grad_norm": 8.413542747497559,
|
| 702 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 703 |
+
"loss": 0.2286,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.8518518518518519,
|
| 708 |
+
"grad_norm": 1.5029722452163696,
|
| 709 |
+
"learning_rate": 2.690329218106996e-05,
|
| 710 |
+
"loss": 0.34,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.8518518518518519,
|
| 715 |
+
"eval_accuracy": 0.9314868804664723,
|
| 716 |
+
"eval_loss": 0.2585590183734894,
|
| 717 |
+
"eval_runtime": 6.5895,
|
| 718 |
+
"eval_samples_per_second": 104.105,
|
| 719 |
+
"eval_steps_per_second": 13.051,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.8724279835390947,
|
| 724 |
+
"grad_norm": 0.20841029286384583,
|
| 725 |
+
"learning_rate": 2.6646090534979425e-05,
|
| 726 |
+
"loss": 0.275,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.8930041152263375,
|
| 731 |
+
"grad_norm": 9.179852485656738,
|
| 732 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 733 |
+
"loss": 0.2304,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.9135802469135803,
|
| 738 |
+
"grad_norm": 0.9464486241340637,
|
| 739 |
+
"learning_rate": 2.6131687242798352e-05,
|
| 740 |
+
"loss": 0.2368,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.934156378600823,
|
| 745 |
+
"grad_norm": 10.512286186218262,
|
| 746 |
+
"learning_rate": 2.587448559670782e-05,
|
| 747 |
+
"loss": 0.2969,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.954732510288066,
|
| 752 |
+
"grad_norm": 3.54328989982605,
|
| 753 |
+
"learning_rate": 2.5617283950617287e-05,
|
| 754 |
+
"loss": 0.2327,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.9753086419753085,
|
| 759 |
+
"grad_norm": 0.5239406824111938,
|
| 760 |
+
"learning_rate": 2.536008230452675e-05,
|
| 761 |
+
"loss": 0.3048,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.9958847736625516,
|
| 766 |
+
"grad_norm": 0.25483438372612,
|
| 767 |
+
"learning_rate": 2.510288065843622e-05,
|
| 768 |
+
"loss": 0.3584,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.016460905349794,
|
| 773 |
+
"grad_norm": 0.4868137538433075,
|
| 774 |
+
"learning_rate": 2.484567901234568e-05,
|
| 775 |
+
"loss": 0.3359,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.037037037037037,
|
| 780 |
+
"grad_norm": 6.471540927886963,
|
| 781 |
+
"learning_rate": 2.4588477366255143e-05,
|
| 782 |
+
"loss": 0.4194,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.05761316872428,
|
| 787 |
+
"grad_norm": 0.21457789838314056,
|
| 788 |
+
"learning_rate": 2.433127572016461e-05,
|
| 789 |
+
"loss": 0.2424,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 2.05761316872428,
|
| 794 |
+
"eval_accuracy": 0.9402332361516035,
|
| 795 |
+
"eval_loss": 0.2248041331768036,
|
| 796 |
+
"eval_runtime": 5.6496,
|
| 797 |
+
"eval_samples_per_second": 121.424,
|
| 798 |
+
"eval_steps_per_second": 15.222,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 2.078189300411523,
|
| 803 |
+
"grad_norm": 0.2115119844675064,
|
| 804 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 805 |
+
"loss": 0.1537,
|
| 806 |
+
"step": 1010
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.0987654320987654,
|
| 810 |
+
"grad_norm": 0.7327996492385864,
|
| 811 |
+
"learning_rate": 2.381687242798354e-05,
|
| 812 |
+
"loss": 0.1881,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.119341563786008,
|
| 817 |
+
"grad_norm": 11.874442100524902,
|
| 818 |
+
"learning_rate": 2.3559670781893005e-05,
|
| 819 |
+
"loss": 0.2633,
|
| 820 |
+
"step": 1030
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.139917695473251,
|
| 824 |
+
"grad_norm": 0.2526969015598297,
|
| 825 |
+
"learning_rate": 2.3302469135802473e-05,
|
| 826 |
+
"loss": 0.1868,
|
| 827 |
+
"step": 1040
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 2.1604938271604937,
|
| 831 |
+
"grad_norm": 0.23793959617614746,
|
| 832 |
+
"learning_rate": 2.3045267489711937e-05,
|
| 833 |
+
"loss": 0.2138,
|
| 834 |
+
"step": 1050
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.1810699588477367,
|
| 838 |
+
"grad_norm": 0.319592148065567,
|
| 839 |
+
"learning_rate": 2.27880658436214e-05,
|
| 840 |
+
"loss": 0.1997,
|
| 841 |
+
"step": 1060
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 2.2016460905349793,
|
| 845 |
+
"grad_norm": 0.14912565052509308,
|
| 846 |
+
"learning_rate": 2.2530864197530865e-05,
|
| 847 |
+
"loss": 0.284,
|
| 848 |
+
"step": 1070
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.2222222222222223,
|
| 852 |
+
"grad_norm": 5.384796142578125,
|
| 853 |
+
"learning_rate": 2.2273662551440332e-05,
|
| 854 |
+
"loss": 0.299,
|
| 855 |
+
"step": 1080
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.242798353909465,
|
| 859 |
+
"grad_norm": 5.962587356567383,
|
| 860 |
+
"learning_rate": 2.2016460905349796e-05,
|
| 861 |
+
"loss": 0.18,
|
| 862 |
+
"step": 1090
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.263374485596708,
|
| 866 |
+
"grad_norm": 0.7156618237495422,
|
| 867 |
+
"learning_rate": 2.175925925925926e-05,
|
| 868 |
+
"loss": 0.1559,
|
| 869 |
+
"step": 1100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.263374485596708,
|
| 873 |
+
"eval_accuracy": 0.934402332361516,
|
| 874 |
+
"eval_loss": 0.2332872599363327,
|
| 875 |
+
"eval_runtime": 5.7482,
|
| 876 |
+
"eval_samples_per_second": 119.342,
|
| 877 |
+
"eval_steps_per_second": 14.961,
|
| 878 |
+
"step": 1100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.2839506172839505,
|
| 882 |
+
"grad_norm": 6.270691394805908,
|
| 883 |
+
"learning_rate": 2.152777777777778e-05,
|
| 884 |
+
"loss": 0.2359,
|
| 885 |
+
"step": 1110
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.3045267489711936,
|
| 889 |
+
"grad_norm": 2.6105377674102783,
|
| 890 |
+
"learning_rate": 2.1270576131687244e-05,
|
| 891 |
+
"loss": 0.3313,
|
| 892 |
+
"step": 1120
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.325102880658436,
|
| 896 |
+
"grad_norm": 0.20199181139469147,
|
| 897 |
+
"learning_rate": 2.101337448559671e-05,
|
| 898 |
+
"loss": 0.1454,
|
| 899 |
+
"step": 1130
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.3456790123456788,
|
| 903 |
+
"grad_norm": 11.37586498260498,
|
| 904 |
+
"learning_rate": 2.0756172839506175e-05,
|
| 905 |
+
"loss": 0.4299,
|
| 906 |
+
"step": 1140
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.366255144032922,
|
| 910 |
+
"grad_norm": 0.4003171920776367,
|
| 911 |
+
"learning_rate": 2.049897119341564e-05,
|
| 912 |
+
"loss": 0.1871,
|
| 913 |
+
"step": 1150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.386831275720165,
|
| 917 |
+
"grad_norm": 0.5666722059249878,
|
| 918 |
+
"learning_rate": 2.0241769547325103e-05,
|
| 919 |
+
"loss": 0.3776,
|
| 920 |
+
"step": 1160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.4074074074074074,
|
| 924 |
+
"grad_norm": 13.603349685668945,
|
| 925 |
+
"learning_rate": 1.998456790123457e-05,
|
| 926 |
+
"loss": 0.3819,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.42798353909465,
|
| 931 |
+
"grad_norm": 0.16143706440925598,
|
| 932 |
+
"learning_rate": 1.9727366255144034e-05,
|
| 933 |
+
"loss": 0.4033,
|
| 934 |
+
"step": 1180
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.448559670781893,
|
| 938 |
+
"grad_norm": 5.120613098144531,
|
| 939 |
+
"learning_rate": 1.9470164609053498e-05,
|
| 940 |
+
"loss": 0.2198,
|
| 941 |
+
"step": 1190
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.4691358024691357,
|
| 945 |
+
"grad_norm": 2.5423364639282227,
|
| 946 |
+
"learning_rate": 1.9212962962962962e-05,
|
| 947 |
+
"loss": 0.351,
|
| 948 |
+
"step": 1200
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.4691358024691357,
|
| 952 |
+
"eval_accuracy": 0.9358600583090378,
|
| 953 |
+
"eval_loss": 0.24949392676353455,
|
| 954 |
+
"eval_runtime": 5.7687,
|
| 955 |
+
"eval_samples_per_second": 118.918,
|
| 956 |
+
"eval_steps_per_second": 14.908,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.4897119341563787,
|
| 961 |
+
"grad_norm": 0.5970525741577148,
|
| 962 |
+
"learning_rate": 1.895576131687243e-05,
|
| 963 |
+
"loss": 0.0758,
|
| 964 |
+
"step": 1210
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.5102880658436213,
|
| 968 |
+
"grad_norm": 0.23254498839378357,
|
| 969 |
+
"learning_rate": 1.8698559670781893e-05,
|
| 970 |
+
"loss": 0.4038,
|
| 971 |
+
"step": 1220
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.5308641975308643,
|
| 975 |
+
"grad_norm": 0.7684284448623657,
|
| 976 |
+
"learning_rate": 1.8441358024691357e-05,
|
| 977 |
+
"loss": 0.3073,
|
| 978 |
+
"step": 1230
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.551440329218107,
|
| 982 |
+
"grad_norm": 2.35357403755188,
|
| 983 |
+
"learning_rate": 1.8184156378600824e-05,
|
| 984 |
+
"loss": 0.2705,
|
| 985 |
+
"step": 1240
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.57201646090535,
|
| 989 |
+
"grad_norm": 15.403181076049805,
|
| 990 |
+
"learning_rate": 1.792695473251029e-05,
|
| 991 |
+
"loss": 0.3099,
|
| 992 |
+
"step": 1250
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.5925925925925926,
|
| 996 |
+
"grad_norm": 9.536227226257324,
|
| 997 |
+
"learning_rate": 1.7669753086419756e-05,
|
| 998 |
+
"loss": 0.1969,
|
| 999 |
+
"step": 1260
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.613168724279835,
|
| 1003 |
+
"grad_norm": 0.228355273604393,
|
| 1004 |
+
"learning_rate": 1.741255144032922e-05,
|
| 1005 |
+
"loss": 0.2381,
|
| 1006 |
+
"step": 1270
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.633744855967078,
|
| 1010 |
+
"grad_norm": 7.860360145568848,
|
| 1011 |
+
"learning_rate": 1.7155349794238684e-05,
|
| 1012 |
+
"loss": 0.3721,
|
| 1013 |
+
"step": 1280
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.6543209876543212,
|
| 1017 |
+
"grad_norm": 13.305447578430176,
|
| 1018 |
+
"learning_rate": 1.6898148148148148e-05,
|
| 1019 |
+
"loss": 0.2834,
|
| 1020 |
+
"step": 1290
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.674897119341564,
|
| 1024 |
+
"grad_norm": 0.13963976502418518,
|
| 1025 |
+
"learning_rate": 1.6640946502057615e-05,
|
| 1026 |
+
"loss": 0.2206,
|
| 1027 |
+
"step": 1300
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.674897119341564,
|
| 1031 |
+
"eval_accuracy": 0.924198250728863,
|
| 1032 |
+
"eval_loss": 0.26219838857650757,
|
| 1033 |
+
"eval_runtime": 5.6243,
|
| 1034 |
+
"eval_samples_per_second": 121.97,
|
| 1035 |
+
"eval_steps_per_second": 15.291,
|
| 1036 |
+
"step": 1300
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 2.6954732510288064,
|
| 1040 |
+
"grad_norm": 7.862311840057373,
|
| 1041 |
+
"learning_rate": 1.638374485596708e-05,
|
| 1042 |
+
"loss": 0.2344,
|
| 1043 |
+
"step": 1310
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.7160493827160495,
|
| 1047 |
+
"grad_norm": 2.6695802211761475,
|
| 1048 |
+
"learning_rate": 1.6126543209876543e-05,
|
| 1049 |
+
"loss": 0.3519,
|
| 1050 |
+
"step": 1320
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.736625514403292,
|
| 1054 |
+
"grad_norm": 1.0053679943084717,
|
| 1055 |
+
"learning_rate": 1.5869341563786007e-05,
|
| 1056 |
+
"loss": 0.1638,
|
| 1057 |
+
"step": 1330
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 2.757201646090535,
|
| 1061 |
+
"grad_norm": 9.059231758117676,
|
| 1062 |
+
"learning_rate": 1.5612139917695474e-05,
|
| 1063 |
+
"loss": 0.1577,
|
| 1064 |
+
"step": 1340
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 2.7777777777777777,
|
| 1068 |
+
"grad_norm": 6.931950569152832,
|
| 1069 |
+
"learning_rate": 1.5354938271604938e-05,
|
| 1070 |
+
"loss": 0.1858,
|
| 1071 |
+
"step": 1350
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 2.7983539094650207,
|
| 1075 |
+
"grad_norm": 2.1699206829071045,
|
| 1076 |
+
"learning_rate": 1.5097736625514405e-05,
|
| 1077 |
+
"loss": 0.1309,
|
| 1078 |
+
"step": 1360
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 2.8189300411522633,
|
| 1082 |
+
"grad_norm": 2.3047924041748047,
|
| 1083 |
+
"learning_rate": 1.4840534979423871e-05,
|
| 1084 |
+
"loss": 0.1979,
|
| 1085 |
+
"step": 1370
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 2.8395061728395063,
|
| 1089 |
+
"grad_norm": 6.254756927490234,
|
| 1090 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 1091 |
+
"loss": 0.1391,
|
| 1092 |
+
"step": 1380
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 2.860082304526749,
|
| 1096 |
+
"grad_norm": 20.224390029907227,
|
| 1097 |
+
"learning_rate": 1.43261316872428e-05,
|
| 1098 |
+
"loss": 0.1719,
|
| 1099 |
+
"step": 1390
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 2.8806584362139915,
|
| 1103 |
+
"grad_norm": 17.755252838134766,
|
| 1104 |
+
"learning_rate": 1.4068930041152264e-05,
|
| 1105 |
+
"loss": 0.3814,
|
| 1106 |
+
"step": 1400
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.8806584362139915,
|
| 1110 |
+
"eval_accuracy": 0.9154518950437318,
|
| 1111 |
+
"eval_loss": 0.31383997201919556,
|
| 1112 |
+
"eval_runtime": 5.7706,
|
| 1113 |
+
"eval_samples_per_second": 118.878,
|
| 1114 |
+
"eval_steps_per_second": 14.903,
|
| 1115 |
+
"step": 1400
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.9012345679012346,
|
| 1119 |
+
"grad_norm": 9.217977523803711,
|
| 1120 |
+
"learning_rate": 1.381172839506173e-05,
|
| 1121 |
+
"loss": 0.4575,
|
| 1122 |
+
"step": 1410
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.9218106995884776,
|
| 1126 |
+
"grad_norm": 13.919651985168457,
|
| 1127 |
+
"learning_rate": 1.3554526748971194e-05,
|
| 1128 |
+
"loss": 0.2728,
|
| 1129 |
+
"step": 1420
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.94238683127572,
|
| 1133 |
+
"grad_norm": 1.9513192176818848,
|
| 1134 |
+
"learning_rate": 1.329732510288066e-05,
|
| 1135 |
+
"loss": 0.1897,
|
| 1136 |
+
"step": 1430
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.962962962962963,
|
| 1140 |
+
"grad_norm": 0.12064926326274872,
|
| 1141 |
+
"learning_rate": 1.3040123456790124e-05,
|
| 1142 |
+
"loss": 0.1415,
|
| 1143 |
+
"step": 1440
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.983539094650206,
|
| 1147 |
+
"grad_norm": 0.1655590832233429,
|
| 1148 |
+
"learning_rate": 1.278292181069959e-05,
|
| 1149 |
+
"loss": 0.1414,
|
| 1150 |
+
"step": 1450
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.0041152263374484,
|
| 1154 |
+
"grad_norm": 10.342666625976562,
|
| 1155 |
+
"learning_rate": 1.2525720164609053e-05,
|
| 1156 |
+
"loss": 0.2966,
|
| 1157 |
+
"step": 1460
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.0246913580246915,
|
| 1161 |
+
"grad_norm": 0.5797888040542603,
|
| 1162 |
+
"learning_rate": 1.2268518518518519e-05,
|
| 1163 |
+
"loss": 0.1845,
|
| 1164 |
+
"step": 1470
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.045267489711934,
|
| 1168 |
+
"grad_norm": 7.389481544494629,
|
| 1169 |
+
"learning_rate": 1.2011316872427984e-05,
|
| 1170 |
+
"loss": 0.2512,
|
| 1171 |
+
"step": 1480
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.065843621399177,
|
| 1175 |
+
"grad_norm": 0.2333269566297531,
|
| 1176 |
+
"learning_rate": 1.1754115226337448e-05,
|
| 1177 |
+
"loss": 0.4019,
|
| 1178 |
+
"step": 1490
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.0864197530864197,
|
| 1182 |
+
"grad_norm": 4.2674241065979,
|
| 1183 |
+
"learning_rate": 1.1496913580246914e-05,
|
| 1184 |
+
"loss": 0.2141,
|
| 1185 |
+
"step": 1500
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.0864197530864197,
|
| 1189 |
+
"eval_accuracy": 0.9314868804664723,
|
| 1190 |
+
"eval_loss": 0.261305034160614,
|
| 1191 |
+
"eval_runtime": 5.7707,
|
| 1192 |
+
"eval_samples_per_second": 118.877,
|
| 1193 |
+
"eval_steps_per_second": 14.903,
|
| 1194 |
+
"step": 1500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 3.1069958847736627,
|
| 1198 |
+
"grad_norm": 0.2830299437046051,
|
| 1199 |
+
"learning_rate": 1.1239711934156378e-05,
|
| 1200 |
+
"loss": 0.2904,
|
| 1201 |
+
"step": 1510
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 3.1275720164609053,
|
| 1205 |
+
"grad_norm": 0.17907337844371796,
|
| 1206 |
+
"learning_rate": 1.0982510288065845e-05,
|
| 1207 |
+
"loss": 0.1494,
|
| 1208 |
+
"step": 1520
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 3.148148148148148,
|
| 1212 |
+
"grad_norm": 9.283103942871094,
|
| 1213 |
+
"learning_rate": 1.072530864197531e-05,
|
| 1214 |
+
"loss": 0.0753,
|
| 1215 |
+
"step": 1530
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 3.168724279835391,
|
| 1219 |
+
"grad_norm": 0.2662203907966614,
|
| 1220 |
+
"learning_rate": 1.0468106995884775e-05,
|
| 1221 |
+
"loss": 0.2067,
|
| 1222 |
+
"step": 1540
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 3.1893004115226335,
|
| 1226 |
+
"grad_norm": 6.983056545257568,
|
| 1227 |
+
"learning_rate": 1.0210905349794239e-05,
|
| 1228 |
+
"loss": 0.173,
|
| 1229 |
+
"step": 1550
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 3.2098765432098766,
|
| 1233 |
+
"grad_norm": 4.426745414733887,
|
| 1234 |
+
"learning_rate": 9.953703703703704e-06,
|
| 1235 |
+
"loss": 0.2352,
|
| 1236 |
+
"step": 1560
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 3.230452674897119,
|
| 1240 |
+
"grad_norm": 2.4332549571990967,
|
| 1241 |
+
"learning_rate": 9.696502057613168e-06,
|
| 1242 |
+
"loss": 0.1356,
|
| 1243 |
+
"step": 1570
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 3.251028806584362,
|
| 1247 |
+
"grad_norm": 0.45729583501815796,
|
| 1248 |
+
"learning_rate": 9.439300411522634e-06,
|
| 1249 |
+
"loss": 0.3083,
|
| 1250 |
+
"step": 1580
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 3.271604938271605,
|
| 1254 |
+
"grad_norm": 0.12547095119953156,
|
| 1255 |
+
"learning_rate": 9.1820987654321e-06,
|
| 1256 |
+
"loss": 0.1432,
|
| 1257 |
+
"step": 1590
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 3.292181069958848,
|
| 1261 |
+
"grad_norm": 0.8154440522193909,
|
| 1262 |
+
"learning_rate": 8.924897119341565e-06,
|
| 1263 |
+
"loss": 0.112,
|
| 1264 |
+
"step": 1600
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 3.292181069958848,
|
| 1268 |
+
"eval_accuracy": 0.9402332361516035,
|
| 1269 |
+
"eval_loss": 0.22655406594276428,
|
| 1270 |
+
"eval_runtime": 5.8164,
|
| 1271 |
+
"eval_samples_per_second": 117.942,
|
| 1272 |
+
"eval_steps_per_second": 14.786,
|
| 1273 |
+
"step": 1600
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 3.3127572016460904,
|
| 1277 |
+
"grad_norm": 0.14023926854133606,
|
| 1278 |
+
"learning_rate": 8.66769547325103e-06,
|
| 1279 |
+
"loss": 0.1534,
|
| 1280 |
+
"step": 1610
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 3.3333333333333335,
|
| 1284 |
+
"grad_norm": 6.381242275238037,
|
| 1285 |
+
"learning_rate": 8.410493827160495e-06,
|
| 1286 |
+
"loss": 0.1949,
|
| 1287 |
+
"step": 1620
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 3.353909465020576,
|
| 1291 |
+
"grad_norm": 0.39883196353912354,
|
| 1292 |
+
"learning_rate": 8.153292181069959e-06,
|
| 1293 |
+
"loss": 0.1436,
|
| 1294 |
+
"step": 1630
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 3.374485596707819,
|
| 1298 |
+
"grad_norm": 3.331747055053711,
|
| 1299 |
+
"learning_rate": 7.896090534979424e-06,
|
| 1300 |
+
"loss": 0.2292,
|
| 1301 |
+
"step": 1640
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 3.3950617283950617,
|
| 1305 |
+
"grad_norm": 0.16310296952724457,
|
| 1306 |
+
"learning_rate": 7.63888888888889e-06,
|
| 1307 |
+
"loss": 0.1053,
|
| 1308 |
+
"step": 1650
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 3.4156378600823043,
|
| 1312 |
+
"grad_norm": 13.472603797912598,
|
| 1313 |
+
"learning_rate": 7.381687242798355e-06,
|
| 1314 |
+
"loss": 0.1804,
|
| 1315 |
+
"step": 1660
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 3.4362139917695473,
|
| 1319 |
+
"grad_norm": 5.14309549331665,
|
| 1320 |
+
"learning_rate": 7.12448559670782e-06,
|
| 1321 |
+
"loss": 0.1998,
|
| 1322 |
+
"step": 1670
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 3.45679012345679,
|
| 1326 |
+
"grad_norm": 6.7929511070251465,
|
| 1327 |
+
"learning_rate": 6.8672839506172845e-06,
|
| 1328 |
+
"loss": 0.2037,
|
| 1329 |
+
"step": 1680
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.477366255144033,
|
| 1333 |
+
"grad_norm": 1.212302327156067,
|
| 1334 |
+
"learning_rate": 6.635802469135803e-06,
|
| 1335 |
+
"loss": 0.0803,
|
| 1336 |
+
"step": 1690
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 3.4979423868312756,
|
| 1340 |
+
"grad_norm": 0.1481838822364807,
|
| 1341 |
+
"learning_rate": 6.3786008230452675e-06,
|
| 1342 |
+
"loss": 0.0631,
|
| 1343 |
+
"step": 1700
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 3.4979423868312756,
|
| 1347 |
+
"eval_accuracy": 0.9402332361516035,
|
| 1348 |
+
"eval_loss": 0.22551974654197693,
|
| 1349 |
+
"eval_runtime": 5.7428,
|
| 1350 |
+
"eval_samples_per_second": 119.454,
|
| 1351 |
+
"eval_steps_per_second": 14.975,
|
| 1352 |
+
"step": 1700
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 3.5185185185185186,
|
| 1356 |
+
"grad_norm": 0.26120343804359436,
|
| 1357 |
+
"learning_rate": 6.121399176954733e-06,
|
| 1358 |
+
"loss": 0.3273,
|
| 1359 |
+
"step": 1710
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 3.539094650205761,
|
| 1363 |
+
"grad_norm": 11.670561790466309,
|
| 1364 |
+
"learning_rate": 5.864197530864198e-06,
|
| 1365 |
+
"loss": 0.2464,
|
| 1366 |
+
"step": 1720
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 3.5596707818930042,
|
| 1370 |
+
"grad_norm": 3.529303550720215,
|
| 1371 |
+
"learning_rate": 5.606995884773663e-06,
|
| 1372 |
+
"loss": 0.2335,
|
| 1373 |
+
"step": 1730
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 3.580246913580247,
|
| 1377 |
+
"grad_norm": 5.341615200042725,
|
| 1378 |
+
"learning_rate": 5.3497942386831275e-06,
|
| 1379 |
+
"loss": 0.1774,
|
| 1380 |
+
"step": 1740
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 3.60082304526749,
|
| 1384 |
+
"grad_norm": 11.935771942138672,
|
| 1385 |
+
"learning_rate": 5.092592592592592e-06,
|
| 1386 |
+
"loss": 0.1993,
|
| 1387 |
+
"step": 1750
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 3.6213991769547325,
|
| 1391 |
+
"grad_norm": 7.190194606781006,
|
| 1392 |
+
"learning_rate": 4.835390946502058e-06,
|
| 1393 |
+
"loss": 0.2104,
|
| 1394 |
+
"step": 1760
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 3.6419753086419755,
|
| 1398 |
+
"grad_norm": 0.41313230991363525,
|
| 1399 |
+
"learning_rate": 4.578189300411523e-06,
|
| 1400 |
+
"loss": 0.193,
|
| 1401 |
+
"step": 1770
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 3.662551440329218,
|
| 1405 |
+
"grad_norm": 0.33850809931755066,
|
| 1406 |
+
"learning_rate": 4.3209876543209875e-06,
|
| 1407 |
+
"loss": 0.2527,
|
| 1408 |
+
"step": 1780
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 3.6831275720164607,
|
| 1412 |
+
"grad_norm": 7.03388786315918,
|
| 1413 |
+
"learning_rate": 4.063786008230453e-06,
|
| 1414 |
+
"loss": 0.2271,
|
| 1415 |
+
"step": 1790
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 3.7037037037037037,
|
| 1419 |
+
"grad_norm": 1.179168939590454,
|
| 1420 |
+
"learning_rate": 3.806584362139918e-06,
|
| 1421 |
+
"loss": 0.1986,
|
| 1422 |
+
"step": 1800
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 3.7037037037037037,
|
| 1426 |
+
"eval_accuracy": 0.9416909620991254,
|
| 1427 |
+
"eval_loss": 0.22252099215984344,
|
| 1428 |
+
"eval_runtime": 5.7883,
|
| 1429 |
+
"eval_samples_per_second": 118.516,
|
| 1430 |
+
"eval_steps_per_second": 14.858,
|
| 1431 |
+
"step": 1800
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.7242798353909468,
|
| 1435 |
+
"grad_norm": 5.670774459838867,
|
| 1436 |
+
"learning_rate": 3.5493827160493827e-06,
|
| 1437 |
+
"loss": 0.1168,
|
| 1438 |
+
"step": 1810
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 3.7448559670781894,
|
| 1442 |
+
"grad_norm": 2.660778045654297,
|
| 1443 |
+
"learning_rate": 3.2921810699588483e-06,
|
| 1444 |
+
"loss": 0.1296,
|
| 1445 |
+
"step": 1820
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.765432098765432,
|
| 1449 |
+
"grad_norm": 5.741485118865967,
|
| 1450 |
+
"learning_rate": 3.034979423868313e-06,
|
| 1451 |
+
"loss": 0.222,
|
| 1452 |
+
"step": 1830
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 3.786008230452675,
|
| 1456 |
+
"grad_norm": 18.328266143798828,
|
| 1457 |
+
"learning_rate": 2.777777777777778e-06,
|
| 1458 |
+
"loss": 0.1688,
|
| 1459 |
+
"step": 1840
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 3.8065843621399176,
|
| 1463 |
+
"grad_norm": 13.7136869430542,
|
| 1464 |
+
"learning_rate": 2.5205761316872427e-06,
|
| 1465 |
+
"loss": 0.2308,
|
| 1466 |
+
"step": 1850
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 3.8271604938271606,
|
| 1470 |
+
"grad_norm": 7.43013858795166,
|
| 1471 |
+
"learning_rate": 2.263374485596708e-06,
|
| 1472 |
+
"loss": 0.1076,
|
| 1473 |
+
"step": 1860
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.847736625514403,
|
| 1477 |
+
"grad_norm": 0.5525858402252197,
|
| 1478 |
+
"learning_rate": 2.0061728395061727e-06,
|
| 1479 |
+
"loss": 0.2191,
|
| 1480 |
+
"step": 1870
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 3.8683127572016462,
|
| 1484 |
+
"grad_norm": 17.919668197631836,
|
| 1485 |
+
"learning_rate": 1.748971193415638e-06,
|
| 1486 |
+
"loss": 0.3505,
|
| 1487 |
+
"step": 1880
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.888888888888889,
|
| 1491 |
+
"grad_norm": 0.1572398841381073,
|
| 1492 |
+
"learning_rate": 1.491769547325103e-06,
|
| 1493 |
+
"loss": 0.1558,
|
| 1494 |
+
"step": 1890
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 3.909465020576132,
|
| 1498 |
+
"grad_norm": 16.84402084350586,
|
| 1499 |
+
"learning_rate": 1.234567901234568e-06,
|
| 1500 |
+
"loss": 0.2345,
|
| 1501 |
+
"step": 1900
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 3.909465020576132,
|
| 1505 |
+
"eval_accuracy": 0.9373177842565598,
|
| 1506 |
+
"eval_loss": 0.2235153466463089,
|
| 1507 |
+
"eval_runtime": 5.8914,
|
| 1508 |
+
"eval_samples_per_second": 116.44,
|
| 1509 |
+
"eval_steps_per_second": 14.597,
|
| 1510 |
+
"step": 1900
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 3.9300411522633745,
|
| 1514 |
+
"grad_norm": 8.612730026245117,
|
| 1515 |
+
"learning_rate": 9.773662551440331e-07,
|
| 1516 |
+
"loss": 0.2431,
|
| 1517 |
+
"step": 1910
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 3.950617283950617,
|
| 1521 |
+
"grad_norm": 14.113691329956055,
|
| 1522 |
+
"learning_rate": 7.20164609053498e-07,
|
| 1523 |
+
"loss": 0.1582,
|
| 1524 |
+
"step": 1920
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 3.97119341563786,
|
| 1528 |
+
"grad_norm": 18.373720169067383,
|
| 1529 |
+
"learning_rate": 4.6296296296296297e-07,
|
| 1530 |
+
"loss": 0.3902,
|
| 1531 |
+
"step": 1930
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 3.991769547325103,
|
| 1535 |
+
"grad_norm": 0.15571478009223938,
|
| 1536 |
+
"learning_rate": 2.0576131687242802e-07,
|
| 1537 |
+
"loss": 0.1868,
|
| 1538 |
+
"step": 1940
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 4.0,
|
| 1542 |
+
"step": 1944,
|
| 1543 |
+
"total_flos": 1.2048994477712425e+18,
|
| 1544 |
+
"train_loss": 0.3544519797212793,
|
| 1545 |
+
"train_runtime": 505.606,
|
| 1546 |
+
"train_samples_per_second": 30.751,
|
| 1547 |
+
"train_steps_per_second": 3.845
|
| 1548 |
+
}
|
| 1549 |
+
],
|
| 1550 |
+
"logging_steps": 10,
|
| 1551 |
+
"max_steps": 1944,
|
| 1552 |
+
"num_input_tokens_seen": 0,
|
| 1553 |
+
"num_train_epochs": 4,
|
| 1554 |
+
"save_steps": 100,
|
| 1555 |
+
"total_flos": 1.2048994477712425e+18,
|
| 1556 |
+
"train_batch_size": 8,
|
| 1557 |
+
"trial_name": null,
|
| 1558 |
+
"trial_params": null
|
| 1559 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d007e07ddc3a1e8e5651fde477bf71022d14fbea752379650dc256c5d0cf134a
|
| 3 |
+
size 4984
|