Model save
Browse files- README.md +56 -54
- adapter_model.safetensors +1 -1
- all_results.json +6 -6
- tokenizer.json +6 -1
- train_results.json +6 -6
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -36,9 +36,11 @@ More information needed
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.0005
|
| 39 |
-
- train_batch_size:
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
|
|
|
|
|
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: cosine
|
| 44 |
- lr_scheduler_warmup_steps: 200
|
|
@@ -47,58 +49,58 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
-
| Training Loss | Epoch
|
| 51 |
-
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
|
| 103 |
|
| 104 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6709
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.0005
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 32
|
| 44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_steps: 200
|
|
|
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-------:|:-----:|:---------------:|
|
| 54 |
+
| 0.8989 | 1.0 | 267 | 0.7585 |
|
| 55 |
+
| 0.7706 | 2.0 | 534 | 0.7264 |
|
| 56 |
+
| 0.7441 | 3.0 | 801 | 0.7160 |
|
| 57 |
+
| 0.7327 | 4.0 | 1068 | 0.7091 |
|
| 58 |
+
| 0.7175 | 5.0 | 1335 | 0.7024 |
|
| 59 |
+
| 0.7118 | 6.0 | 1602 | 0.6990 |
|
| 60 |
+
| 0.7079 | 7.0 | 1869 | 0.6931 |
|
| 61 |
+
| 0.6982 | 8.0 | 2136 | 0.6904 |
|
| 62 |
+
| 0.6977 | 9.0 | 2403 | 0.6891 |
|
| 63 |
+
| 0.6971 | 10.0 | 2670 | 0.6869 |
|
| 64 |
+
| 0.6992 | 11.0 | 2937 | 0.6850 |
|
| 65 |
+
| 0.6889 | 12.0 | 3204 | 0.6849 |
|
| 66 |
+
| 0.6924 | 13.0 | 3471 | 0.6845 |
|
| 67 |
+
| 0.6894 | 14.0 | 3738 | 0.6834 |
|
| 68 |
+
| 0.6886 | 15.0 | 4005 | 0.6791 |
|
| 69 |
+
| 0.6906 | 16.0 | 4272 | 0.6812 |
|
| 70 |
+
| 0.6868 | 17.0 | 4539 | 0.6796 |
|
| 71 |
+
| 0.6852 | 18.0 | 4806 | 0.6789 |
|
| 72 |
+
| 0.6797 | 19.0 | 5073 | 0.6784 |
|
| 73 |
+
| 0.6813 | 20.0 | 5340 | 0.6775 |
|
| 74 |
+
| 0.6823 | 21.0 | 5607 | 0.6776 |
|
| 75 |
+
| 0.6803 | 22.0 | 5874 | 0.6758 |
|
| 76 |
+
| 0.6782 | 23.0 | 6141 | 0.6768 |
|
| 77 |
+
| 0.6786 | 24.0 | 6408 | 0.6747 |
|
| 78 |
+
| 0.677 | 25.0 | 6675 | 0.6740 |
|
| 79 |
+
| 0.68 | 26.0 | 6942 | 0.6742 |
|
| 80 |
+
| 0.6733 | 27.0 | 7209 | 0.6735 |
|
| 81 |
+
| 0.6744 | 28.0 | 7476 | 0.6734 |
|
| 82 |
+
| 0.6746 | 29.0 | 7743 | 0.6737 |
|
| 83 |
+
| 0.674 | 30.0 | 8010 | 0.6753 |
|
| 84 |
+
| 0.6694 | 31.0 | 8277 | 0.6731 |
|
| 85 |
+
| 0.6731 | 32.0 | 8544 | 0.6734 |
|
| 86 |
+
| 0.6683 | 33.0 | 8811 | 0.6723 |
|
| 87 |
+
| 0.6712 | 34.0 | 9078 | 0.6723 |
|
| 88 |
+
| 0.668 | 35.0 | 9345 | 0.6720 |
|
| 89 |
+
| 0.6647 | 36.0 | 9612 | 0.6723 |
|
| 90 |
+
| 0.664 | 37.0 | 9879 | 0.6713 |
|
| 91 |
+
| 0.6707 | 38.0 | 10146 | 0.6724 |
|
| 92 |
+
| 0.6704 | 39.0 | 10413 | 0.6715 |
|
| 93 |
+
| 0.6675 | 40.0 | 10680 | 0.6715 |
|
| 94 |
+
| 0.6673 | 41.0 | 10947 | 0.6718 |
|
| 95 |
+
| 0.6656 | 42.0 | 11214 | 0.6713 |
|
| 96 |
+
| 0.6659 | 43.0 | 11481 | 0.6715 |
|
| 97 |
+
| 0.667 | 44.0 | 11748 | 0.6714 |
|
| 98 |
+
| 0.6596 | 45.0 | 12015 | 0.6709 |
|
| 99 |
+
| 0.6673 | 46.0 | 12282 | 0.6710 |
|
| 100 |
+
| 0.6666 | 47.0 | 12549 | 0.6710 |
|
| 101 |
+
| 0.6661 | 48.0 | 12816 | 0.6709 |
|
| 102 |
+
| 0.6637 | 49.0 | 13083 | 0.6709 |
|
| 103 |
+
| 0.665 | 49.8143 | 13300 | 0.6709 |
|
| 104 |
|
| 105 |
|
| 106 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 309980480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b04f408d064cb4f79b978c5bb2f2defecabff3f3874a4e8df5930e22ee4b90f7
|
| 3 |
size 309980480
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_loss": 0.6701372861862183,
|
| 4 |
"eval_runtime": 3.1131,
|
| 5 |
"eval_samples_per_second": 587.189,
|
| 6 |
"eval_steps_per_second": 73.559,
|
| 7 |
"perplexity": 1.9545056288417388,
|
| 8 |
-
"total_flos": 2.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 49.814258911819884,
|
| 3 |
"eval_loss": 0.6701372861862183,
|
| 4 |
"eval_runtime": 3.1131,
|
| 5 |
"eval_samples_per_second": 587.189,
|
| 6 |
"eval_steps_per_second": 73.559,
|
| 7 |
"perplexity": 1.9545056288417388,
|
| 8 |
+
"total_flos": 2.18714101825536e+16,
|
| 9 |
+
"train_loss": 0.6980596797627614,
|
| 10 |
+
"train_runtime": 3389.5401,
|
| 11 |
+
"train_samples_per_second": 125.799,
|
| 12 |
+
"train_steps_per_second": 3.924
|
| 13 |
}
|
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 1024,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 2.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 49.814258911819884,
|
| 3 |
+
"total_flos": 2.18714101825536e+16,
|
| 4 |
+
"train_loss": 0.6980596797627614,
|
| 5 |
+
"train_runtime": 3389.5401,
|
| 6 |
+
"train_samples_per_second": 125.799,
|
| 7 |
+
"train_steps_per_second": 3.924
|
| 8 |
}
|