Evaluation on the test set completed on 2024_09_24.
Browse files- README.md +92 -0
- all_results.json +16 -0
- logs/events.out.tfevents.1727088963.datavisu4 +2 -2
- logs/events.out.tfevents.1727135360.datavisu4 +3 -0
- model.safetensors +1 -1
- test_results.json +11 -0
- train_results.json +9 -0
- trainer_state.json +493 -0
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: microsoft/resnet-50
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Resneteau-50-2024_09_23-batch-size32_freeze
|
| 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 |
+
# Resneteau-50-2024_09_23-batch-size32_freeze
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1906
|
| 22 |
+
- F1 Micro: 0.6954
|
| 23 |
+
- F1 Macro: 0.4462
|
| 24 |
+
- Accuracy: 0.1827
|
| 25 |
+
- Learning Rate: 0.0001
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 0.001
|
| 45 |
+
- train_batch_size: 32
|
| 46 |
+
- eval_batch_size: 32
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 400
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Accuracy | Rate |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|:------:|
|
| 57 |
+
| No log | 1.0 | 273 | 0.2460 | 0.5802 | 0.2267 | 0.0877 | 0.001 |
|
| 58 |
+
| 0.2786 | 2.0 | 546 | 0.2217 | 0.6412 | 0.3160 | 0.1369 | 0.001 |
|
| 59 |
+
| 0.2786 | 3.0 | 819 | 0.2117 | 0.6596 | 0.3581 | 0.1486 | 0.001 |
|
| 60 |
+
| 0.231 | 4.0 | 1092 | 0.2049 | 0.6674 | 0.3831 | 0.1618 | 0.001 |
|
| 61 |
+
| 0.231 | 5.0 | 1365 | 0.2016 | 0.6707 | 0.3965 | 0.1677 | 0.001 |
|
| 62 |
+
| 0.2206 | 6.0 | 1638 | 0.2002 | 0.6720 | 0.4076 | 0.1677 | 0.001 |
|
| 63 |
+
| 0.2206 | 7.0 | 1911 | 0.1976 | 0.6752 | 0.4142 | 0.1746 | 0.001 |
|
| 64 |
+
| 0.2157 | 8.0 | 2184 | 0.1971 | 0.6824 | 0.4281 | 0.1764 | 0.001 |
|
| 65 |
+
| 0.2157 | 9.0 | 2457 | 0.1961 | 0.6845 | 0.4300 | 0.1764 | 0.001 |
|
| 66 |
+
| 0.2127 | 10.0 | 2730 | 0.1944 | 0.6763 | 0.4264 | 0.1805 | 0.001 |
|
| 67 |
+
| 0.2117 | 11.0 | 3003 | 0.1940 | 0.6902 | 0.4391 | 0.1781 | 0.001 |
|
| 68 |
+
| 0.2117 | 12.0 | 3276 | 0.1945 | 0.6939 | 0.4523 | 0.1729 | 0.001 |
|
| 69 |
+
| 0.2107 | 13.0 | 3549 | 0.1936 | 0.6908 | 0.4461 | 0.1795 | 0.001 |
|
| 70 |
+
| 0.2107 | 14.0 | 3822 | 0.1931 | 0.6916 | 0.4424 | 0.1781 | 0.001 |
|
| 71 |
+
| 0.2105 | 15.0 | 4095 | 0.1935 | 0.6936 | 0.4431 | 0.1809 | 0.001 |
|
| 72 |
+
| 0.2105 | 16.0 | 4368 | 0.1931 | 0.6896 | 0.4429 | 0.1805 | 0.001 |
|
| 73 |
+
| 0.2086 | 17.0 | 4641 | 0.1931 | 0.6953 | 0.4411 | 0.1819 | 0.001 |
|
| 74 |
+
| 0.2086 | 18.0 | 4914 | 0.1908 | 0.6984 | 0.4490 | 0.1857 | 0.001 |
|
| 75 |
+
| 0.2101 | 19.0 | 5187 | 0.1925 | 0.6879 | 0.4428 | 0.1812 | 0.001 |
|
| 76 |
+
| 0.2101 | 20.0 | 5460 | 0.1913 | 0.6797 | 0.4357 | 0.1774 | 0.001 |
|
| 77 |
+
| 0.2088 | 21.0 | 5733 | 0.1915 | 0.6958 | 0.4381 | 0.1823 | 0.001 |
|
| 78 |
+
| 0.2084 | 22.0 | 6006 | 0.1919 | 0.7039 | 0.4535 | 0.1826 | 0.001 |
|
| 79 |
+
| 0.2084 | 23.0 | 6279 | 0.1926 | 0.6907 | 0.4363 | 0.1798 | 0.001 |
|
| 80 |
+
| 0.2083 | 24.0 | 6552 | 0.1919 | 0.6953 | 0.4544 | 0.1805 | 0.001 |
|
| 81 |
+
| 0.2083 | 25.0 | 6825 | 0.1919 | 0.6962 | 0.4466 | 0.1781 | 0.0001 |
|
| 82 |
+
| 0.2076 | 26.0 | 7098 | 0.1912 | 0.6943 | 0.4418 | 0.1823 | 0.0001 |
|
| 83 |
+
| 0.2076 | 27.0 | 7371 | 0.1912 | 0.6972 | 0.4500 | 0.1809 | 0.0001 |
|
| 84 |
+
| 0.2081 | 28.0 | 7644 | 0.1915 | 0.6944 | 0.4454 | 0.1857 | 0.0001 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.44.2
|
| 90 |
+
- Pytorch 2.4.1+cu121
|
| 91 |
+
- Datasets 3.0.0
|
| 92 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 28.0,
|
| 3 |
+
"eval_accuracy": 0.18269896193771626,
|
| 4 |
+
"eval_f1_macro": 0.4461837693265384,
|
| 5 |
+
"eval_f1_micro": 0.6953863257365203,
|
| 6 |
+
"eval_loss": 0.19063615798950195,
|
| 7 |
+
"eval_runtime": 399.8321,
|
| 8 |
+
"eval_samples_per_second": 7.228,
|
| 9 |
+
"eval_steps_per_second": 0.228,
|
| 10 |
+
"learning_rate": 0.0001,
|
| 11 |
+
"total_flos": 2.778404267780425e+19,
|
| 12 |
+
"train_loss": 0.2165746406882549,
|
| 13 |
+
"train_runtime": 45987.1682,
|
| 14 |
+
"train_samples_per_second": 75.812,
|
| 15 |
+
"train_steps_per_second": 2.375
|
| 16 |
+
}
|
logs/events.out.tfevents.1727088963.datavisu4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38beb7081004ec1a70855bc101483c3501307384b29e67fed4db908dd048db87
|
| 3 |
+
size 23795
|
logs/events.out.tfevents.1727135360.datavisu4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc69ea3a5ef5cbcb7a6c1257bc4b779875d6116cb3c538a04571c4395765eac1
|
| 3 |
+
size 40
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94540692
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c68a03c0d36f931cb7ab321664d34a50a968d8bc9f15dcfdd9552ee4b8520a63
|
| 3 |
size 94540692
|
test_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 28.0,
|
| 3 |
+
"eval_accuracy": 0.18269896193771626,
|
| 4 |
+
"eval_f1_macro": 0.4461837693265384,
|
| 5 |
+
"eval_f1_micro": 0.6953863257365203,
|
| 6 |
+
"eval_loss": 0.19063615798950195,
|
| 7 |
+
"eval_runtime": 399.8321,
|
| 8 |
+
"eval_samples_per_second": 7.228,
|
| 9 |
+
"eval_steps_per_second": 0.228,
|
| 10 |
+
"learning_rate": 0.0001
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 28.0,
|
| 3 |
+
"learning_rate": 0.0001,
|
| 4 |
+
"total_flos": 2.778404267780425e+19,
|
| 5 |
+
"train_loss": 0.2165746406882549,
|
| 6 |
+
"train_runtime": 45987.1682,
|
| 7 |
+
"train_samples_per_second": 75.812,
|
| 8 |
+
"train_steps_per_second": 2.375
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,493 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.19081147015094757,
|
| 3 |
+
"best_model_checkpoint": "Resneteau-50-2024_09_23-batch-size32_freeze/checkpoint-4914",
|
| 4 |
+
"epoch": 28.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7644,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.08766458766458766,
|
| 14 |
+
"eval_f1_macro": 0.226738844317642,
|
| 15 |
+
"eval_f1_micro": 0.5801698557249565,
|
| 16 |
+
"eval_loss": 0.24598382413387299,
|
| 17 |
+
"eval_runtime": 416.4206,
|
| 18 |
+
"eval_samples_per_second": 6.93,
|
| 19 |
+
"eval_steps_per_second": 0.219,
|
| 20 |
+
"learning_rate": 0.001,
|
| 21 |
+
"step": 273
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.8315018315018317,
|
| 25 |
+
"grad_norm": 0.0508086197078228,
|
| 26 |
+
"learning_rate": 0.001,
|
| 27 |
+
"loss": 0.2786,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_accuracy": 0.13686763686763687,
|
| 33 |
+
"eval_f1_macro": 0.3160165508599939,
|
| 34 |
+
"eval_f1_micro": 0.6411905904944791,
|
| 35 |
+
"eval_loss": 0.22168199717998505,
|
| 36 |
+
"eval_runtime": 395.166,
|
| 37 |
+
"eval_samples_per_second": 7.303,
|
| 38 |
+
"eval_steps_per_second": 0.23,
|
| 39 |
+
"learning_rate": 0.001,
|
| 40 |
+
"step": 546
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"eval_accuracy": 0.14864864864864866,
|
| 45 |
+
"eval_f1_macro": 0.3580673052862397,
|
| 46 |
+
"eval_f1_micro": 0.6595584072466503,
|
| 47 |
+
"eval_loss": 0.21166761219501495,
|
| 48 |
+
"eval_runtime": 401.6658,
|
| 49 |
+
"eval_samples_per_second": 7.185,
|
| 50 |
+
"eval_steps_per_second": 0.227,
|
| 51 |
+
"learning_rate": 0.001,
|
| 52 |
+
"step": 819
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 3.663003663003663,
|
| 56 |
+
"grad_norm": 0.04649221897125244,
|
| 57 |
+
"learning_rate": 0.001,
|
| 58 |
+
"loss": 0.231,
|
| 59 |
+
"step": 1000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_accuracy": 0.16181566181566182,
|
| 64 |
+
"eval_f1_macro": 0.3831121485565155,
|
| 65 |
+
"eval_f1_micro": 0.6673936750272628,
|
| 66 |
+
"eval_loss": 0.20492619276046753,
|
| 67 |
+
"eval_runtime": 411.5182,
|
| 68 |
+
"eval_samples_per_second": 7.013,
|
| 69 |
+
"eval_steps_per_second": 0.221,
|
| 70 |
+
"learning_rate": 0.001,
|
| 71 |
+
"step": 1092
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.0,
|
| 75 |
+
"eval_accuracy": 0.1677061677061677,
|
| 76 |
+
"eval_f1_macro": 0.3964602797407069,
|
| 77 |
+
"eval_f1_micro": 0.6707461695365495,
|
| 78 |
+
"eval_loss": 0.20162147283554077,
|
| 79 |
+
"eval_runtime": 414.4686,
|
| 80 |
+
"eval_samples_per_second": 6.963,
|
| 81 |
+
"eval_steps_per_second": 0.22,
|
| 82 |
+
"learning_rate": 0.001,
|
| 83 |
+
"step": 1365
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.4945054945054945,
|
| 87 |
+
"grad_norm": 0.03698631748557091,
|
| 88 |
+
"learning_rate": 0.001,
|
| 89 |
+
"loss": 0.2206,
|
| 90 |
+
"step": 1500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.0,
|
| 94 |
+
"eval_accuracy": 0.1677061677061677,
|
| 95 |
+
"eval_f1_macro": 0.40758628553731013,
|
| 96 |
+
"eval_f1_micro": 0.6719734660033168,
|
| 97 |
+
"eval_loss": 0.20019273459911346,
|
| 98 |
+
"eval_runtime": 422.4235,
|
| 99 |
+
"eval_samples_per_second": 6.832,
|
| 100 |
+
"eval_steps_per_second": 0.215,
|
| 101 |
+
"learning_rate": 0.001,
|
| 102 |
+
"step": 1638
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.0,
|
| 106 |
+
"eval_accuracy": 0.17463617463617465,
|
| 107 |
+
"eval_f1_macro": 0.4142080471846538,
|
| 108 |
+
"eval_f1_micro": 0.6751762240426747,
|
| 109 |
+
"eval_loss": 0.19761690497398376,
|
| 110 |
+
"eval_runtime": 419.1011,
|
| 111 |
+
"eval_samples_per_second": 6.886,
|
| 112 |
+
"eval_steps_per_second": 0.217,
|
| 113 |
+
"learning_rate": 0.001,
|
| 114 |
+
"step": 1911
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 7.326007326007326,
|
| 118 |
+
"grad_norm": 0.05039607360959053,
|
| 119 |
+
"learning_rate": 0.001,
|
| 120 |
+
"loss": 0.2157,
|
| 121 |
+
"step": 2000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"eval_accuracy": 0.17636867636867637,
|
| 126 |
+
"eval_f1_macro": 0.42809095916498113,
|
| 127 |
+
"eval_f1_micro": 0.6823529411764706,
|
| 128 |
+
"eval_loss": 0.19706940650939941,
|
| 129 |
+
"eval_runtime": 419.7988,
|
| 130 |
+
"eval_samples_per_second": 6.875,
|
| 131 |
+
"eval_steps_per_second": 0.217,
|
| 132 |
+
"learning_rate": 0.001,
|
| 133 |
+
"step": 2184
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 9.0,
|
| 137 |
+
"eval_accuracy": 0.17636867636867637,
|
| 138 |
+
"eval_f1_macro": 0.43000179684162393,
|
| 139 |
+
"eval_f1_micro": 0.6844589857443328,
|
| 140 |
+
"eval_loss": 0.19613835215568542,
|
| 141 |
+
"eval_runtime": 418.2306,
|
| 142 |
+
"eval_samples_per_second": 6.9,
|
| 143 |
+
"eval_steps_per_second": 0.218,
|
| 144 |
+
"learning_rate": 0.001,
|
| 145 |
+
"step": 2457
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 9.157509157509157,
|
| 149 |
+
"grad_norm": 0.05213358625769615,
|
| 150 |
+
"learning_rate": 0.001,
|
| 151 |
+
"loss": 0.2127,
|
| 152 |
+
"step": 2500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"eval_accuracy": 0.18052668052668053,
|
| 157 |
+
"eval_f1_macro": 0.4264062108185488,
|
| 158 |
+
"eval_f1_micro": 0.676261056657901,
|
| 159 |
+
"eval_loss": 0.19443827867507935,
|
| 160 |
+
"eval_runtime": 412.2909,
|
| 161 |
+
"eval_samples_per_second": 7.0,
|
| 162 |
+
"eval_steps_per_second": 0.221,
|
| 163 |
+
"learning_rate": 0.001,
|
| 164 |
+
"step": 2730
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.989010989010989,
|
| 168 |
+
"grad_norm": 0.035016052424907684,
|
| 169 |
+
"learning_rate": 0.001,
|
| 170 |
+
"loss": 0.2117,
|
| 171 |
+
"step": 3000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 11.0,
|
| 175 |
+
"eval_accuracy": 0.1781011781011781,
|
| 176 |
+
"eval_f1_macro": 0.43914447135579204,
|
| 177 |
+
"eval_f1_micro": 0.6902341199514971,
|
| 178 |
+
"eval_loss": 0.19399969279766083,
|
| 179 |
+
"eval_runtime": 415.1772,
|
| 180 |
+
"eval_samples_per_second": 6.951,
|
| 181 |
+
"eval_steps_per_second": 0.219,
|
| 182 |
+
"learning_rate": 0.001,
|
| 183 |
+
"step": 3003
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 12.0,
|
| 187 |
+
"eval_accuracy": 0.1729036729036729,
|
| 188 |
+
"eval_f1_macro": 0.45234247782022446,
|
| 189 |
+
"eval_f1_micro": 0.6938511326860841,
|
| 190 |
+
"eval_loss": 0.19451384246349335,
|
| 191 |
+
"eval_runtime": 421.6946,
|
| 192 |
+
"eval_samples_per_second": 6.844,
|
| 193 |
+
"eval_steps_per_second": 0.216,
|
| 194 |
+
"learning_rate": 0.001,
|
| 195 |
+
"step": 3276
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.820512820512821,
|
| 199 |
+
"grad_norm": 0.051621340215206146,
|
| 200 |
+
"learning_rate": 0.001,
|
| 201 |
+
"loss": 0.2107,
|
| 202 |
+
"step": 3500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 13.0,
|
| 206 |
+
"eval_accuracy": 0.1794871794871795,
|
| 207 |
+
"eval_f1_macro": 0.44605482120784584,
|
| 208 |
+
"eval_f1_micro": 0.6907971453892439,
|
| 209 |
+
"eval_loss": 0.19363747537136078,
|
| 210 |
+
"eval_runtime": 400.266,
|
| 211 |
+
"eval_samples_per_second": 7.21,
|
| 212 |
+
"eval_steps_per_second": 0.227,
|
| 213 |
+
"learning_rate": 0.001,
|
| 214 |
+
"step": 3549
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 14.0,
|
| 218 |
+
"eval_accuracy": 0.1781011781011781,
|
| 219 |
+
"eval_f1_macro": 0.44244925103284655,
|
| 220 |
+
"eval_f1_micro": 0.6916442548455903,
|
| 221 |
+
"eval_loss": 0.1931454837322235,
|
| 222 |
+
"eval_runtime": 399.4345,
|
| 223 |
+
"eval_samples_per_second": 7.225,
|
| 224 |
+
"eval_steps_per_second": 0.228,
|
| 225 |
+
"learning_rate": 0.001,
|
| 226 |
+
"step": 3822
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 14.652014652014651,
|
| 230 |
+
"grad_norm": 0.044662874191999435,
|
| 231 |
+
"learning_rate": 0.001,
|
| 232 |
+
"loss": 0.2105,
|
| 233 |
+
"step": 4000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"eval_accuracy": 0.18087318087318088,
|
| 238 |
+
"eval_f1_macro": 0.44307178033824657,
|
| 239 |
+
"eval_f1_micro": 0.6936180088187515,
|
| 240 |
+
"eval_loss": 0.1935158371925354,
|
| 241 |
+
"eval_runtime": 402.2391,
|
| 242 |
+
"eval_samples_per_second": 7.175,
|
| 243 |
+
"eval_steps_per_second": 0.226,
|
| 244 |
+
"learning_rate": 0.001,
|
| 245 |
+
"step": 4095
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 16.0,
|
| 249 |
+
"eval_accuracy": 0.18052668052668053,
|
| 250 |
+
"eval_f1_macro": 0.4428841041517678,
|
| 251 |
+
"eval_f1_micro": 0.6895936942854461,
|
| 252 |
+
"eval_loss": 0.19309590756893158,
|
| 253 |
+
"eval_runtime": 394.2567,
|
| 254 |
+
"eval_samples_per_second": 7.32,
|
| 255 |
+
"eval_steps_per_second": 0.231,
|
| 256 |
+
"learning_rate": 0.001,
|
| 257 |
+
"step": 4368
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 16.483516483516482,
|
| 261 |
+
"grad_norm": 0.041027914732694626,
|
| 262 |
+
"learning_rate": 0.001,
|
| 263 |
+
"loss": 0.2086,
|
| 264 |
+
"step": 4500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 17.0,
|
| 268 |
+
"eval_accuracy": 0.18191268191268192,
|
| 269 |
+
"eval_f1_macro": 0.4411042424961882,
|
| 270 |
+
"eval_f1_micro": 0.6953186376449928,
|
| 271 |
+
"eval_loss": 0.19311168789863586,
|
| 272 |
+
"eval_runtime": 406.8435,
|
| 273 |
+
"eval_samples_per_second": 7.094,
|
| 274 |
+
"eval_steps_per_second": 0.224,
|
| 275 |
+
"learning_rate": 0.001,
|
| 276 |
+
"step": 4641
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 18.0,
|
| 280 |
+
"eval_accuracy": 0.18572418572418573,
|
| 281 |
+
"eval_f1_macro": 0.4490480976278912,
|
| 282 |
+
"eval_f1_micro": 0.6983818770226538,
|
| 283 |
+
"eval_loss": 0.19081147015094757,
|
| 284 |
+
"eval_runtime": 398.4396,
|
| 285 |
+
"eval_samples_per_second": 7.243,
|
| 286 |
+
"eval_steps_per_second": 0.228,
|
| 287 |
+
"learning_rate": 0.001,
|
| 288 |
+
"step": 4914
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.315018315018314,
|
| 292 |
+
"grad_norm": 0.05783214792609215,
|
| 293 |
+
"learning_rate": 0.001,
|
| 294 |
+
"loss": 0.2101,
|
| 295 |
+
"step": 5000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 19.0,
|
| 299 |
+
"eval_accuracy": 0.1812196812196812,
|
| 300 |
+
"eval_f1_macro": 0.4428453523216445,
|
| 301 |
+
"eval_f1_micro": 0.6878854936673101,
|
| 302 |
+
"eval_loss": 0.19249168038368225,
|
| 303 |
+
"eval_runtime": 397.6758,
|
| 304 |
+
"eval_samples_per_second": 7.257,
|
| 305 |
+
"eval_steps_per_second": 0.229,
|
| 306 |
+
"learning_rate": 0.001,
|
| 307 |
+
"step": 5187
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 20.0,
|
| 311 |
+
"eval_accuracy": 0.1774081774081774,
|
| 312 |
+
"eval_f1_macro": 0.43568338344914237,
|
| 313 |
+
"eval_f1_micro": 0.6796580216840999,
|
| 314 |
+
"eval_loss": 0.19134406745433807,
|
| 315 |
+
"eval_runtime": 404.3345,
|
| 316 |
+
"eval_samples_per_second": 7.138,
|
| 317 |
+
"eval_steps_per_second": 0.225,
|
| 318 |
+
"learning_rate": 0.001,
|
| 319 |
+
"step": 5460
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 20.146520146520146,
|
| 323 |
+
"grad_norm": 0.04509862884879112,
|
| 324 |
+
"learning_rate": 0.001,
|
| 325 |
+
"loss": 0.2088,
|
| 326 |
+
"step": 5500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 21.0,
|
| 330 |
+
"eval_accuracy": 0.18225918225918225,
|
| 331 |
+
"eval_f1_macro": 0.4381469652060519,
|
| 332 |
+
"eval_f1_micro": 0.6957772621809745,
|
| 333 |
+
"eval_loss": 0.19149190187454224,
|
| 334 |
+
"eval_runtime": 403.3745,
|
| 335 |
+
"eval_samples_per_second": 7.155,
|
| 336 |
+
"eval_steps_per_second": 0.226,
|
| 337 |
+
"learning_rate": 0.001,
|
| 338 |
+
"step": 5733
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 21.978021978021978,
|
| 342 |
+
"grad_norm": 0.04410397261381149,
|
| 343 |
+
"learning_rate": 0.001,
|
| 344 |
+
"loss": 0.2084,
|
| 345 |
+
"step": 6000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.0,
|
| 349 |
+
"eval_accuracy": 0.1826056826056826,
|
| 350 |
+
"eval_f1_macro": 0.4534807464842353,
|
| 351 |
+
"eval_f1_micro": 0.7038712011577424,
|
| 352 |
+
"eval_loss": 0.19192616641521454,
|
| 353 |
+
"eval_runtime": 394.3882,
|
| 354 |
+
"eval_samples_per_second": 7.318,
|
| 355 |
+
"eval_steps_per_second": 0.231,
|
| 356 |
+
"learning_rate": 0.001,
|
| 357 |
+
"step": 6006
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 23.0,
|
| 361 |
+
"eval_accuracy": 0.17983367983367984,
|
| 362 |
+
"eval_f1_macro": 0.4363028843794499,
|
| 363 |
+
"eval_f1_micro": 0.6907461850762985,
|
| 364 |
+
"eval_loss": 0.19255639612674713,
|
| 365 |
+
"eval_runtime": 404.3195,
|
| 366 |
+
"eval_samples_per_second": 7.138,
|
| 367 |
+
"eval_steps_per_second": 0.225,
|
| 368 |
+
"learning_rate": 0.001,
|
| 369 |
+
"step": 6279
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 23.80952380952381,
|
| 373 |
+
"grad_norm": 0.0686459094285965,
|
| 374 |
+
"learning_rate": 0.001,
|
| 375 |
+
"loss": 0.2083,
|
| 376 |
+
"step": 6500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 24.0,
|
| 380 |
+
"eval_accuracy": 0.18052668052668053,
|
| 381 |
+
"eval_f1_macro": 0.45443118252910614,
|
| 382 |
+
"eval_f1_micro": 0.6952745610758312,
|
| 383 |
+
"eval_loss": 0.19186602532863617,
|
| 384 |
+
"eval_runtime": 397.0622,
|
| 385 |
+
"eval_samples_per_second": 7.268,
|
| 386 |
+
"eval_steps_per_second": 0.229,
|
| 387 |
+
"learning_rate": 0.001,
|
| 388 |
+
"step": 6552
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 25.0,
|
| 392 |
+
"eval_accuracy": 0.1781011781011781,
|
| 393 |
+
"eval_f1_macro": 0.4465566917300777,
|
| 394 |
+
"eval_f1_micro": 0.6961779911373708,
|
| 395 |
+
"eval_loss": 0.19193170964717865,
|
| 396 |
+
"eval_runtime": 397.2293,
|
| 397 |
+
"eval_samples_per_second": 7.265,
|
| 398 |
+
"eval_steps_per_second": 0.229,
|
| 399 |
+
"learning_rate": 0.0001,
|
| 400 |
+
"step": 6825
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 25.641025641025642,
|
| 404 |
+
"grad_norm": 0.04814450815320015,
|
| 405 |
+
"learning_rate": 0.0001,
|
| 406 |
+
"loss": 0.2076,
|
| 407 |
+
"step": 7000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 26.0,
|
| 411 |
+
"eval_accuracy": 0.18225918225918225,
|
| 412 |
+
"eval_f1_macro": 0.441825214268795,
|
| 413 |
+
"eval_f1_micro": 0.6942802624842929,
|
| 414 |
+
"eval_loss": 0.19118554890155792,
|
| 415 |
+
"eval_runtime": 398.0912,
|
| 416 |
+
"eval_samples_per_second": 7.25,
|
| 417 |
+
"eval_steps_per_second": 0.229,
|
| 418 |
+
"learning_rate": 0.0001,
|
| 419 |
+
"step": 7098
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 27.0,
|
| 423 |
+
"eval_accuracy": 0.18087318087318088,
|
| 424 |
+
"eval_f1_macro": 0.449975636684123,
|
| 425 |
+
"eval_f1_micro": 0.6971996137398262,
|
| 426 |
+
"eval_loss": 0.19123922288417816,
|
| 427 |
+
"eval_runtime": 398.8223,
|
| 428 |
+
"eval_samples_per_second": 7.236,
|
| 429 |
+
"eval_steps_per_second": 0.228,
|
| 430 |
+
"learning_rate": 0.0001,
|
| 431 |
+
"step": 7371
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 27.47252747252747,
|
| 435 |
+
"grad_norm": 0.05590255931019783,
|
| 436 |
+
"learning_rate": 0.0001,
|
| 437 |
+
"loss": 0.2081,
|
| 438 |
+
"step": 7500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 28.0,
|
| 442 |
+
"eval_accuracy": 0.18572418572418573,
|
| 443 |
+
"eval_f1_macro": 0.44543509037683293,
|
| 444 |
+
"eval_f1_micro": 0.6943913469159402,
|
| 445 |
+
"eval_loss": 0.19151046872138977,
|
| 446 |
+
"eval_runtime": 405.2259,
|
| 447 |
+
"eval_samples_per_second": 7.122,
|
| 448 |
+
"eval_steps_per_second": 0.225,
|
| 449 |
+
"learning_rate": 0.0001,
|
| 450 |
+
"step": 7644
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 28.0,
|
| 454 |
+
"learning_rate": 0.0001,
|
| 455 |
+
"step": 7644,
|
| 456 |
+
"total_flos": 2.778404267780425e+19,
|
| 457 |
+
"train_loss": 0.2165746406882549,
|
| 458 |
+
"train_runtime": 45987.1682,
|
| 459 |
+
"train_samples_per_second": 75.812,
|
| 460 |
+
"train_steps_per_second": 2.375
|
| 461 |
+
}
|
| 462 |
+
],
|
| 463 |
+
"logging_steps": 500,
|
| 464 |
+
"max_steps": 109200,
|
| 465 |
+
"num_input_tokens_seen": 0,
|
| 466 |
+
"num_train_epochs": 400,
|
| 467 |
+
"save_steps": 500,
|
| 468 |
+
"stateful_callbacks": {
|
| 469 |
+
"EarlyStoppingCallback": {
|
| 470 |
+
"args": {
|
| 471 |
+
"early_stopping_patience": 10,
|
| 472 |
+
"early_stopping_threshold": 0.0
|
| 473 |
+
},
|
| 474 |
+
"attributes": {
|
| 475 |
+
"early_stopping_patience_counter": 0
|
| 476 |
+
}
|
| 477 |
+
},
|
| 478 |
+
"TrainerControl": {
|
| 479 |
+
"args": {
|
| 480 |
+
"should_epoch_stop": false,
|
| 481 |
+
"should_evaluate": false,
|
| 482 |
+
"should_log": false,
|
| 483 |
+
"should_save": true,
|
| 484 |
+
"should_training_stop": true
|
| 485 |
+
},
|
| 486 |
+
"attributes": {}
|
| 487 |
+
}
|
| 488 |
+
},
|
| 489 |
+
"total_flos": 2.778404267780425e+19,
|
| 490 |
+
"train_batch_size": 32,
|
| 491 |
+
"trial_name": null,
|
| 492 |
+
"trial_params": null
|
| 493 |
+
}
|