Commit
•
c650132
1
Parent(s):
44865d9
huggingartists
Browse files- README.md +3 -3
- config.json +1 -1
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +5 -1
- tokenizer.json +8 -5
- tokenizer_config.json +10 -1
- trainer_state.json +371 -7
- training_args.bin +2 -2
README.md
CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/taylor-swift")
|
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 Taylor Swift'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/taylor-swift")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2l84tzp2/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 Taylor Swift's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1hy7aa65) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1hy7aa65/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
config.json
CHANGED
@@ -36,7 +36,7 @@
|
|
36 |
}
|
37 |
},
|
38 |
"torch_dtype": "float32",
|
39 |
-
"transformers_version": "4.
|
40 |
"use_cache": true,
|
41 |
"vocab_size": 50257
|
42 |
}
|
|
|
36 |
}
|
37 |
},
|
38 |
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.20.1",
|
40 |
"use_cache": true,
|
41 |
"vocab_size": 50257
|
42 |
}
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 1.
|
|
|
1 |
+
{"eval_loss": 1.3240652084350586, "eval_runtime": 5.3381, "eval_samples_per_second": 42.712, "eval_steps_per_second": 5.433, "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:b0193dabaedc886d2423381b1d4991d098c388ec01408d24cb8525d1c5031eb2
|
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 sha256:2fc77d09c4c454b54d1ca6720bc643fbbdc7dae8b9f46f9dfbe190c61e89c49b
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e35f64d133e2da786674123c81f13fa6ce6316d7e8029fc026e6c67f01baf8b
|
3 |
+
size 510396521
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:664be080bd3dc652f628b2caf10ec5043081add1f81d7f2e4ab19f1da66a9fd6
|
3 |
size 14503
|
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 sha256:8b79408328cb94b5f58b90ffdd8b7127d5992674b5e2cf7df0005f8718053694
|
3 |
size 623
|
special_tokens_map.json
CHANGED
@@ -1 +1,5 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
CHANGED
@@ -5,29 +5,32 @@
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 50256,
|
8 |
-
"special": true,
|
9 |
"content": "<|endoftext|>",
|
10 |
"single_word": false,
|
11 |
"lstrip": false,
|
12 |
"rstrip": false,
|
13 |
-
"normalized": false
|
|
|
14 |
}
|
15 |
],
|
16 |
"normalizer": null,
|
17 |
"pre_tokenizer": {
|
18 |
"type": "ByteLevel",
|
19 |
"add_prefix_space": false,
|
20 |
-
"trim_offsets": true
|
|
|
21 |
},
|
22 |
"post_processor": {
|
23 |
"type": "ByteLevel",
|
24 |
"add_prefix_space": true,
|
25 |
-
"trim_offsets": false
|
|
|
26 |
},
|
27 |
"decoder": {
|
28 |
"type": "ByteLevel",
|
29 |
"add_prefix_space": true,
|
30 |
-
"trim_offsets": true
|
|
|
31 |
},
|
32 |
"model": {
|
33 |
"type": "BPE",
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 50256,
|
|
|
8 |
"content": "<|endoftext|>",
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
}
|
15 |
],
|
16 |
"normalizer": null,
|
17 |
"pre_tokenizer": {
|
18 |
"type": "ByteLevel",
|
19 |
"add_prefix_space": false,
|
20 |
+
"trim_offsets": true,
|
21 |
+
"use_regex": true
|
22 |
},
|
23 |
"post_processor": {
|
24 |
"type": "ByteLevel",
|
25 |
"add_prefix_space": true,
|
26 |
+
"trim_offsets": false,
|
27 |
+
"use_regex": true
|
28 |
},
|
29 |
"decoder": {
|
30 |
"type": "ByteLevel",
|
31 |
"add_prefix_space": true,
|
32 |
+
"trim_offsets": true,
|
33 |
+
"use_regex": true
|
34 |
},
|
35 |
"model": {
|
36 |
"type": "BPE",
|
tokenizer_config.json
CHANGED
@@ -1 +1,10 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "huggingartists/taylor-swift",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "output/taylor-swift/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1414,11 +1414,375 @@
|
|
1414 |
"eval_samples_per_second": 21.045,
|
1415 |
"eval_steps_per_second": 2.631,
|
1416 |
"step": 1120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1417 |
}
|
1418 |
],
|
1419 |
-
"max_steps":
|
1420 |
-
"num_train_epochs":
|
1421 |
-
"total_flos":
|
1422 |
"trial_name": null,
|
1423 |
"trial_params": null
|
1424 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3240652084350586,
|
3 |
+
"best_model_checkpoint": "output/taylor-swift/checkpoint-1413",
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 1413,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1414 |
"eval_samples_per_second": 21.045,
|
1415 |
"eval_steps_per_second": 2.631,
|
1416 |
"step": 1120
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 7.17,
|
1420 |
+
"learning_rate": 9.076596574074994e-06,
|
1421 |
+
"loss": 1.4269,
|
1422 |
+
"step": 1125
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 7.2,
|
1426 |
+
"learning_rate": 1.2780475216607764e-05,
|
1427 |
+
"loss": 1.559,
|
1428 |
+
"step": 1130
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 7.23,
|
1432 |
+
"learning_rate": 1.7042649548372873e-05,
|
1433 |
+
"loss": 1.529,
|
1434 |
+
"step": 1135
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 7.26,
|
1438 |
+
"learning_rate": 2.182049015671568e-05,
|
1439 |
+
"loss": 1.6687,
|
1440 |
+
"step": 1140
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 7.29,
|
1444 |
+
"learning_rate": 2.7066210038327817e-05,
|
1445 |
+
"loss": 1.5638,
|
1446 |
+
"step": 1145
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 7.32,
|
1450 |
+
"learning_rate": 3.2727342555268683e-05,
|
1451 |
+
"loss": 1.5554,
|
1452 |
+
"step": 1150
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 7.36,
|
1456 |
+
"learning_rate": 3.874726619575346e-05,
|
1457 |
+
"loss": 1.317,
|
1458 |
+
"step": 1155
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 7.39,
|
1462 |
+
"learning_rate": 4.5065770891153554e-05,
|
1463 |
+
"loss": 1.679,
|
1464 |
+
"step": 1160
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 7.42,
|
1468 |
+
"learning_rate": 5.161966022502662e-05,
|
1469 |
+
"loss": 1.6683,
|
1470 |
+
"step": 1165
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 7.45,
|
1474 |
+
"learning_rate": 5.834338351099537e-05,
|
1475 |
+
"loss": 1.4034,
|
1476 |
+
"step": 1170
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 7.48,
|
1480 |
+
"learning_rate": 6.516969141756308e-05,
|
1481 |
+
"loss": 1.6013,
|
1482 |
+
"step": 1175
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 7.52,
|
1486 |
+
"learning_rate": 7.20303085824368e-05,
|
1487 |
+
"loss": 1.5516,
|
1488 |
+
"step": 1180
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 7.55,
|
1492 |
+
"learning_rate": 7.885661648900452e-05,
|
1493 |
+
"loss": 1.5248,
|
1494 |
+
"step": 1185
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 7.58,
|
1498 |
+
"learning_rate": 8.558033977497326e-05,
|
1499 |
+
"loss": 1.3379,
|
1500 |
+
"step": 1190
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 7.61,
|
1504 |
+
"learning_rate": 9.213422910884634e-05,
|
1505 |
+
"loss": 1.3994,
|
1506 |
+
"step": 1195
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 7.64,
|
1510 |
+
"learning_rate": 9.845273380424641e-05,
|
1511 |
+
"loss": 1.4434,
|
1512 |
+
"step": 1200
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 7.68,
|
1516 |
+
"learning_rate": 0.00010447265744473122,
|
1517 |
+
"loss": 1.6187,
|
1518 |
+
"step": 1205
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 7.71,
|
1522 |
+
"learning_rate": 0.00011013378996167208,
|
1523 |
+
"loss": 1.5693,
|
1524 |
+
"step": 1210
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 7.74,
|
1528 |
+
"learning_rate": 0.00011537950984328424,
|
1529 |
+
"loss": 1.4006,
|
1530 |
+
"step": 1215
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 7.77,
|
1534 |
+
"learning_rate": 0.00012015735045162704,
|
1535 |
+
"loss": 1.7153,
|
1536 |
+
"step": 1220
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 7.8,
|
1540 |
+
"learning_rate": 0.0001244195247833922,
|
1541 |
+
"loss": 1.5277,
|
1542 |
+
"step": 1225
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 7.83,
|
1546 |
+
"learning_rate": 0.00012812340342592494,
|
1547 |
+
"loss": 1.5052,
|
1548 |
+
"step": 1230
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 7.87,
|
1552 |
+
"learning_rate": 0.0001312319409280581,
|
1553 |
+
"loss": 1.548,
|
1554 |
+
"step": 1235
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 7.9,
|
1558 |
+
"learning_rate": 0.00013371404632128166,
|
1559 |
+
"loss": 1.4896,
|
1560 |
+
"step": 1240
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 7.93,
|
1564 |
+
"learning_rate": 0.0001355448940853745,
|
1565 |
+
"loss": 1.5506,
|
1566 |
+
"step": 1245
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 7.96,
|
1570 |
+
"learning_rate": 0.00013670617244827653,
|
1571 |
+
"loss": 1.6902,
|
1572 |
+
"step": 1250
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 7.99,
|
1576 |
+
"learning_rate": 0.0001371862665367597,
|
1577 |
+
"loss": 1.5112,
|
1578 |
+
"step": 1255
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 8.0,
|
1582 |
+
"eval_loss": 1.352002739906311,
|
1583 |
+
"eval_runtime": 5.5761,
|
1584 |
+
"eval_samples_per_second": 40.889,
|
1585 |
+
"eval_steps_per_second": 5.201,
|
1586 |
+
"step": 1256
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 8.03,
|
1590 |
+
"learning_rate": 0.00013698037454606005,
|
1591 |
+
"loss": 1.3097,
|
1592 |
+
"step": 1260
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 8.06,
|
1596 |
+
"learning_rate": 0.0001360905557665658,
|
1597 |
+
"loss": 1.5119,
|
1598 |
+
"step": 1265
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 8.09,
|
1602 |
+
"learning_rate": 0.00013452570998720767,
|
1603 |
+
"loss": 1.2738,
|
1604 |
+
"step": 1270
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 8.12,
|
1608 |
+
"learning_rate": 0.00013230148848155559,
|
1609 |
+
"loss": 1.2764,
|
1610 |
+
"step": 1275
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 8.15,
|
1614 |
+
"learning_rate": 0.00012944013746692,
|
1615 |
+
"loss": 1.2347,
|
1616 |
+
"step": 1280
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 8.18,
|
1620 |
+
"learning_rate": 0.00012597027560214946,
|
1621 |
+
"loss": 1.4534,
|
1622 |
+
"step": 1285
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 8.22,
|
1626 |
+
"learning_rate": 0.00012192660774954517,
|
1627 |
+
"loss": 1.4193,
|
1628 |
+
"step": 1290
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 8.25,
|
1632 |
+
"learning_rate": 0.00011734957786379066,
|
1633 |
+
"loss": 1.5185,
|
1634 |
+
"step": 1295
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 8.28,
|
1638 |
+
"learning_rate": 0.00011228496447963,
|
1639 |
+
"loss": 1.5225,
|
1640 |
+
"step": 1300
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 8.31,
|
1644 |
+
"learning_rate": 0.0001067834228441478,
|
1645 |
+
"loss": 1.8013,
|
1646 |
+
"step": 1305
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 8.34,
|
1650 |
+
"learning_rate": 0.00010089997827314661,
|
1651 |
+
"loss": 1.4035,
|
1652 |
+
"step": 1310
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 8.38,
|
1656 |
+
"learning_rate": 9.469347579898059e-05,
|
1657 |
+
"loss": 1.4431,
|
1658 |
+
"step": 1315
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 8.41,
|
1662 |
+
"learning_rate": 8.82259916143434e-05,
|
1663 |
+
"loss": 1.3074,
|
1664 |
+
"step": 1320
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 8.44,
|
1668 |
+
"learning_rate": 8.1562212198643e-05,
|
1669 |
+
"loss": 1.3587,
|
1670 |
+
"step": 1325
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 8.47,
|
1674 |
+
"learning_rate": 7.476878733681043e-05,
|
1675 |
+
"loss": 1.5297,
|
1676 |
+
"step": 1330
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 8.5,
|
1680 |
+
"learning_rate": 6.791366350152217e-05,
|
1681 |
+
"loss": 1.2815,
|
1682 |
+
"step": 1335
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 8.54,
|
1686 |
+
"learning_rate": 6.106540426620946e-05,
|
1687 |
+
"loss": 1.5607,
|
1688 |
+
"step": 1340
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 8.57,
|
1692 |
+
"learning_rate": 5.4292504545952105e-05,
|
1693 |
+
"loss": 1.1765,
|
1694 |
+
"step": 1345
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 8.6,
|
1698 |
+
"learning_rate": 4.766270552507704e-05,
|
1699 |
+
"loss": 1.5363,
|
1700 |
+
"step": 1350
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 8.63,
|
1704 |
+
"learning_rate": 4.124231712342338e-05,
|
1705 |
+
"loss": 1.4107,
|
1706 |
+
"step": 1355
|
1707 |
+
},
|
1708 |
+
{
|
1709 |
+
"epoch": 8.66,
|
1710 |
+
"learning_rate": 3.509555477782507e-05,
|
1711 |
+
"loss": 1.4608,
|
1712 |
+
"step": 1360
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 8.69,
|
1716 |
+
"learning_rate": 2.928389717219465e-05,
|
1717 |
+
"loss": 1.3783,
|
1718 |
+
"step": 1365
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 8.73,
|
1722 |
+
"learning_rate": 2.386547134005838e-05,
|
1723 |
+
"loss": 1.2348,
|
1724 |
+
"step": 1370
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 8.76,
|
1728 |
+
"learning_rate": 1.889447128962836e-05,
|
1729 |
+
"loss": 1.5068,
|
1730 |
+
"step": 1375
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 8.79,
|
1734 |
+
"learning_rate": 1.4420615966203568e-05,
|
1735 |
+
"loss": 1.3345,
|
1736 |
+
"step": 1380
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 8.82,
|
1740 |
+
"learning_rate": 1.0488651973253671e-05,
|
1741 |
+
"loss": 1.2429,
|
1742 |
+
"step": 1385
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 8.85,
|
1746 |
+
"learning_rate": 7.13790602586542e-06,
|
1747 |
+
"loss": 1.3129,
|
1748 |
+
"step": 1390
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 8.89,
|
1752 |
+
"learning_rate": 4.401891612830206e-06,
|
1753 |
+
"loss": 1.2724,
|
1754 |
+
"step": 1395
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 8.92,
|
1758 |
+
"learning_rate": 2.307973801450113e-06,
|
1759 |
+
"loss": 1.3608,
|
1760 |
+
"step": 1400
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 8.95,
|
1764 |
+
"learning_rate": 8.770955376250992e-07,
|
1765 |
+
"loss": 1.4328,
|
1766 |
+
"step": 1405
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 8.98,
|
1770 |
+
"learning_rate": 1.2356817870921626e-07,
|
1771 |
+
"loss": 1.3714,
|
1772 |
+
"step": 1410
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 9.0,
|
1776 |
+
"eval_loss": 1.3240652084350586,
|
1777 |
+
"eval_runtime": 5.3842,
|
1778 |
+
"eval_samples_per_second": 42.346,
|
1779 |
+
"eval_steps_per_second": 5.386,
|
1780 |
+
"step": 1413
|
1781 |
}
|
1782 |
],
|
1783 |
+
"max_steps": 1884,
|
1784 |
+
"num_train_epochs": 12,
|
1785 |
+
"total_flos": 1473164476416000.0,
|
1786 |
"trial_name": null,
|
1787 |
"trial_params": null
|
1788 |
}
|
training_args.bin
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:c178f13ee8a4a4e92389f456bb271b331e24a800185642959a69b718d48e7169
|
3 |
+
size 3311
|