Commit
•
92ed093
1
Parent(s):
082acb6
huggingartists
Browse files- README.md +3 -3
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- trainer_state.json +93 -7
- training_args.bin +1 -1
README.md
CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/morgenshtern")
|
46 |
```
|
47 |
|
48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on MORGENSHTERN's lyrics.
|
53 |
|
54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
55 |
|
56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
57 |
|
58 |
## How to use
|
59 |
|
|
|
45 |
dataset = load_dataset("huggingartists/morgenshtern")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/m9zgb2vd/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on MORGENSHTERN's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/ys11x7xp) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/ys11x7xp/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 1.
|
|
|
1 |
+
{"eval_loss": 1.1428929567337036, "eval_runtime": 7.9754, "eval_samples_per_second": 21.441, "eval_steps_per_second": 2.758, "epoch": 12.0}
|
flax_model.msgpack
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497764120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:355b1113b602cec6460d0f66c7318d9309a2d51638c83d166b18454dad89bd5c
|
3 |
size 497764120
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995604017
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b59045dfc4ed4d02f26069b5cc05179d371e5fa764cb055d1a830e8c0382acd4
|
3 |
size 995604017
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510403817
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dc5e091ec6cb7f165ce89c1bc5ddd005d9d36c5598145f3b40df6a6b9c583cb
|
3 |
size 510403817
|
rng_state.pth
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:c63f55fe8fef4a486cd65797398129fb611c4447a861094695f459a188101b5d
|
3 |
+
size 14631
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e825854d4daee9b3baa1369de3bcfdc0baa5bcd259634286f62b5236f6992a0f
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "output/morgenshtern/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1408,11 +1408,97 @@
|
|
1408 |
"eval_samples_per_second": 21.247,
|
1409 |
"eval_steps_per_second": 2.709,
|
1410 |
"step": 1078
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1411 |
}
|
1412 |
],
|
1413 |
-
"max_steps":
|
1414 |
-
"num_train_epochs":
|
1415 |
-
"total_flos":
|
1416 |
"trial_name": null,
|
1417 |
"trial_params": null
|
1418 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.1428929567337036,
|
3 |
+
"best_model_checkpoint": "output/morgenshtern/checkpoint-1140",
|
4 |
+
"epoch": 12.0,
|
5 |
+
"global_step": 1140,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1408 |
"eval_samples_per_second": 21.247,
|
1409 |
"eval_steps_per_second": 2.709,
|
1410 |
"step": 1078
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 11.37,
|
1414 |
+
"learning_rate": 4.1043693868806304e-05,
|
1415 |
+
"loss": 1.1875,
|
1416 |
+
"step": 1080
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 11.42,
|
1420 |
+
"learning_rate": 5.17596955821411e-05,
|
1421 |
+
"loss": 1.3125,
|
1422 |
+
"step": 1085
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 11.47,
|
1426 |
+
"learning_rate": 6.293505690059783e-05,
|
1427 |
+
"loss": 1.2444,
|
1428 |
+
"step": 1090
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 11.53,
|
1432 |
+
"learning_rate": 7.426494309940222e-05,
|
1433 |
+
"loss": 1.3268,
|
1434 |
+
"step": 1095
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 11.58,
|
1438 |
+
"learning_rate": 8.544030441785894e-05,
|
1439 |
+
"loss": 1.3066,
|
1440 |
+
"step": 1100
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 11.63,
|
1444 |
+
"learning_rate": 9.615630613119375e-05,
|
1445 |
+
"loss": 1.2542,
|
1446 |
+
"step": 1105
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 11.68,
|
1450 |
+
"learning_rate": 0.00010612064364719844,
|
1451 |
+
"loss": 1.246,
|
1452 |
+
"step": 1110
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 11.74,
|
1456 |
+
"learning_rate": 0.00011506151581352574,
|
1457 |
+
"loss": 1.2672,
|
1458 |
+
"step": 1115
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 11.79,
|
1462 |
+
"learning_rate": 0.00012273503894459246,
|
1463 |
+
"loss": 1.2702,
|
1464 |
+
"step": 1120
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 11.84,
|
1468 |
+
"learning_rate": 0.00012893189933276523,
|
1469 |
+
"loss": 1.3417,
|
1470 |
+
"step": 1125
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 11.89,
|
1474 |
+
"learning_rate": 0.00013348306278066356,
|
1475 |
+
"loss": 1.2473,
|
1476 |
+
"step": 1130
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 11.95,
|
1480 |
+
"learning_rate": 0.00013626438541342674,
|
1481 |
+
"loss": 1.1708,
|
1482 |
+
"step": 1135
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 12.0,
|
1486 |
+
"learning_rate": 0.0001372,
|
1487 |
+
"loss": 1.1564,
|
1488 |
+
"step": 1140
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 12.0,
|
1492 |
+
"eval_loss": 1.1428929567337036,
|
1493 |
+
"eval_runtime": 7.9608,
|
1494 |
+
"eval_samples_per_second": 21.48,
|
1495 |
+
"eval_steps_per_second": 2.764,
|
1496 |
+
"step": 1140
|
1497 |
}
|
1498 |
],
|
1499 |
+
"max_steps": 1140,
|
1500 |
+
"num_train_epochs": 12,
|
1501 |
+
"total_flos": 1182346444800000.0,
|
1502 |
"trial_name": null,
|
1503 |
"trial_params": null
|
1504 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2671
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54fa34a299d69d7a3304670c0272e7c9b90a901c33b2a0c579d8b695f9d47857
|
3 |
size 2671
|