Model save
Browse files- README.md +55 -55
- all_results.json +5 -5
- train_results.json +5 -5
README.md
CHANGED
|
@@ -5,18 +5,18 @@ base_model: gpt2
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
#
|
| 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 |
|
|
@@ -46,58 +46,58 @@ The following hyperparameters were used during training:
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch | Step
|
| 50 |
-
|
| 51 |
-
| 0.
|
| 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 |
|
| 102 |
|
| 103 |
### Framework versions
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
+
- name: Se124M100KInfMinimalist
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
# Se124M100KInfMinimalist
|
| 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: 0.5392
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 0.1691 | 1.0 | 1860 | 0.6314 |
|
| 52 |
+
| 0.1598 | 2.0 | 3720 | 0.6036 |
|
| 53 |
+
| 0.1539 | 3.0 | 5580 | 0.5906 |
|
| 54 |
+
| 0.153 | 4.0 | 7440 | 0.5836 |
|
| 55 |
+
| 0.1507 | 5.0 | 9300 | 0.5790 |
|
| 56 |
+
| 0.1483 | 6.0 | 11160 | 0.5746 |
|
| 57 |
+
| 0.149 | 7.0 | 13020 | 0.5703 |
|
| 58 |
+
| 0.1485 | 8.0 | 14880 | 0.5684 |
|
| 59 |
+
| 0.1462 | 9.0 | 16740 | 0.5656 |
|
| 60 |
+
| 0.1469 | 10.0 | 18600 | 0.5630 |
|
| 61 |
+
| 0.1449 | 11.0 | 20460 | 0.5617 |
|
| 62 |
+
| 0.1469 | 12.0 | 22320 | 0.5581 |
|
| 63 |
+
| 0.1456 | 13.0 | 24180 | 0.5575 |
|
| 64 |
+
| 0.1459 | 14.0 | 26040 | 0.5547 |
|
| 65 |
+
| 0.1432 | 15.0 | 27900 | 0.5544 |
|
| 66 |
+
| 0.1429 | 16.0 | 29760 | 0.5540 |
|
| 67 |
+
| 0.1431 | 17.0 | 31620 | 0.5523 |
|
| 68 |
+
| 0.1432 | 18.0 | 33480 | 0.5512 |
|
| 69 |
+
| 0.1423 | 19.0 | 35340 | 0.5519 |
|
| 70 |
+
| 0.1429 | 20.0 | 37200 | 0.5506 |
|
| 71 |
+
| 0.1429 | 21.0 | 39060 | 0.5490 |
|
| 72 |
+
| 0.1441 | 22.0 | 40920 | 0.5477 |
|
| 73 |
+
| 0.1426 | 23.0 | 42780 | 0.5476 |
|
| 74 |
+
| 0.1436 | 24.0 | 44640 | 0.5463 |
|
| 75 |
+
| 0.1419 | 25.0 | 46500 | 0.5462 |
|
| 76 |
+
| 0.1399 | 26.0 | 48360 | 0.5449 |
|
| 77 |
+
| 0.1412 | 27.0 | 50220 | 0.5452 |
|
| 78 |
+
| 0.14 | 28.0 | 52080 | 0.5440 |
|
| 79 |
+
| 0.1396 | 29.0 | 53940 | 0.5440 |
|
| 80 |
+
| 0.1402 | 30.0 | 55800 | 0.5440 |
|
| 81 |
+
| 0.1404 | 31.0 | 57660 | 0.5437 |
|
| 82 |
+
| 0.1415 | 32.0 | 59520 | 0.5427 |
|
| 83 |
+
| 0.1406 | 33.0 | 61380 | 0.5420 |
|
| 84 |
+
| 0.1387 | 34.0 | 63240 | 0.5422 |
|
| 85 |
+
| 0.1392 | 35.0 | 65100 | 0.5420 |
|
| 86 |
+
| 0.1404 | 36.0 | 66960 | 0.5420 |
|
| 87 |
+
| 0.1436 | 37.0 | 68820 | 0.5411 |
|
| 88 |
+
| 0.1424 | 38.0 | 70680 | 0.5415 |
|
| 89 |
+
| 0.141 | 39.0 | 72540 | 0.5407 |
|
| 90 |
+
| 0.1402 | 40.0 | 74400 | 0.5403 |
|
| 91 |
+
| 0.1412 | 41.0 | 76260 | 0.5407 |
|
| 92 |
+
| 0.139 | 42.0 | 78120 | 0.5403 |
|
| 93 |
+
| 0.1357 | 43.0 | 79980 | 0.5401 |
|
| 94 |
+
| 0.1396 | 44.0 | 81840 | 0.5397 |
|
| 95 |
+
| 0.1398 | 45.0 | 83700 | 0.5394 |
|
| 96 |
+
| 0.1385 | 46.0 | 85560 | 0.5395 |
|
| 97 |
+
| 0.1408 | 47.0 | 87420 | 0.5396 |
|
| 98 |
+
| 0.1371 | 48.0 | 89280 | 0.5392 |
|
| 99 |
+
| 0.1418 | 49.0 | 91140 | 0.5393 |
|
| 100 |
+
| 0.1382 | 50.0 | 93000 | 0.5392 |
|
| 101 |
|
| 102 |
|
| 103 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -5,9 +5,9 @@
|
|
| 5 |
"eval_samples_per_second": 160.588,
|
| 6 |
"eval_steps_per_second": 5.02,
|
| 7 |
"perplexity": 1.619794707189944,
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 9.
|
| 13 |
}
|
|
|
|
| 5 |
"eval_samples_per_second": 160.588,
|
| 6 |
"eval_steps_per_second": 5.02,
|
| 7 |
"perplexity": 1.619794707189944,
|
| 8 |
+
"total_flos": 1.950556483878912e+17,
|
| 9 |
+
"train_loss": 0.14462488290315034,
|
| 10 |
+
"train_runtime": 9614.4477,
|
| 11 |
+
"train_samples_per_second": 309.503,
|
| 12 |
+
"train_steps_per_second": 9.673
|
| 13 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 50.0,
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 9.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 50.0,
|
| 3 |
+
"total_flos": 1.950556483878912e+17,
|
| 4 |
+
"train_loss": 0.14462488290315034,
|
| 5 |
+
"train_runtime": 9614.4477,
|
| 6 |
+
"train_samples_per_second": 309.503,
|
| 7 |
+
"train_steps_per_second": 9.673
|
| 8 |
}
|