Training in progress, step 212, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 639691872
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f3ae69127fc293d24c01e08524b58c279e8c5f0ae7b6c7a1ef22f6be3e77291
|
3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 325339796
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdcf04cb6bf4c0b0d7b9f8f1eb99e7b5124bbb4f4b8805d7916763277c22a05b
|
3 |
size 325339796
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27cc510000b450ada0ab6c2ce09449d46c05dfdfaf1135374ca981c94e122f97
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b80340678794eceb27a8ea7f91bc6361013d570f26cb607a0c954f150a1a4c00
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.1042157411575317,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1447,6 +1447,90 @@
|
|
1447 |
"eval_samples_per_second": 9.275,
|
1448 |
"eval_steps_per_second": 2.338,
|
1449 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1450 |
}
|
1451 |
],
|
1452 |
"logging_steps": 1,
|
@@ -1470,12 +1554,12 @@
|
|
1470 |
"should_evaluate": false,
|
1471 |
"should_log": false,
|
1472 |
"should_save": true,
|
1473 |
-
"should_training_stop":
|
1474 |
},
|
1475 |
"attributes": {}
|
1476 |
}
|
1477 |
},
|
1478 |
-
"total_flos": 2.
|
1479 |
"train_batch_size": 8,
|
1480 |
"trial_name": null,
|
1481 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.1042157411575317,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
4 |
+
"epoch": 1.0023640661938533,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 212,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1447 |
"eval_samples_per_second": 9.275,
|
1448 |
"eval_steps_per_second": 2.338,
|
1449 |
"step": 200
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.950354609929078,
|
1453 |
+
"grad_norm": 0.3739728331565857,
|
1454 |
+
"learning_rate": 7.29899235565934e-07,
|
1455 |
+
"loss": 1.1624,
|
1456 |
+
"step": 201
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 0.9550827423167849,
|
1460 |
+
"grad_norm": 0.35657617449760437,
|
1461 |
+
"learning_rate": 6.034780129621664e-07,
|
1462 |
+
"loss": 1.0881,
|
1463 |
+
"step": 202
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 0.9598108747044918,
|
1467 |
+
"grad_norm": 0.37702855467796326,
|
1468 |
+
"learning_rate": 4.890044990165321e-07,
|
1469 |
+
"loss": 1.1991,
|
1470 |
+
"step": 203
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 0.9645390070921985,
|
1474 |
+
"grad_norm": 0.3940827250480652,
|
1475 |
+
"learning_rate": 3.8650638183617694e-07,
|
1476 |
+
"loss": 1.1217,
|
1477 |
+
"step": 204
|
1478 |
+
},
|
1479 |
+
{
|
1480 |
+
"epoch": 0.9692671394799054,
|
1481 |
+
"grad_norm": 0.3676983118057251,
|
1482 |
+
"learning_rate": 2.9600845299737056e-07,
|
1483 |
+
"loss": 1.0818,
|
1484 |
+
"step": 205
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 0.9739952718676123,
|
1488 |
+
"grad_norm": 0.399383008480072,
|
1489 |
+
"learning_rate": 2.1753260154906973e-07,
|
1490 |
+
"loss": 1.0898,
|
1491 |
+
"step": 206
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.9787234042553191,
|
1495 |
+
"grad_norm": 0.3540259599685669,
|
1496 |
+
"learning_rate": 1.5109780871853663e-07,
|
1497 |
+
"loss": 1.0337,
|
1498 |
+
"step": 207
|
1499 |
+
},
|
1500 |
+
{
|
1501 |
+
"epoch": 0.983451536643026,
|
1502 |
+
"grad_norm": 0.3893062174320221,
|
1503 |
+
"learning_rate": 9.672014332028356e-08,
|
1504 |
+
"loss": 0.9161,
|
1505 |
+
"step": 208
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 0.9881796690307328,
|
1509 |
+
"grad_norm": 0.39612168073654175,
|
1510 |
+
"learning_rate": 5.4412757869459763e-08,
|
1511 |
+
"loss": 1.0683,
|
1512 |
+
"step": 209
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 0.9929078014184397,
|
1516 |
+
"grad_norm": 0.443149209022522,
|
1517 |
+
"learning_rate": 2.4185885400596075e-08,
|
1518 |
+
"loss": 1.0856,
|
1519 |
+
"step": 210
|
1520 |
+
},
|
1521 |
+
{
|
1522 |
+
"epoch": 0.9976359338061466,
|
1523 |
+
"grad_norm": 0.46631062030792236,
|
1524 |
+
"learning_rate": 6.04683699252373e-09,
|
1525 |
+
"loss": 1.101,
|
1526 |
+
"step": 211
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 1.0023640661938533,
|
1530 |
+
"grad_norm": 0.9580826759338379,
|
1531 |
+
"learning_rate": 0.0,
|
1532 |
+
"loss": 1.865,
|
1533 |
+
"step": 212
|
1534 |
}
|
1535 |
],
|
1536 |
"logging_steps": 1,
|
|
|
1554 |
"should_evaluate": false,
|
1555 |
"should_log": false,
|
1556 |
"should_save": true,
|
1557 |
+
"should_training_stop": true
|
1558 |
},
|
1559 |
"attributes": {}
|
1560 |
}
|
1561 |
},
|
1562 |
+
"total_flos": 2.8356191188942848e+17,
|
1563 |
"train_batch_size": 8,
|
1564 |
"trial_name": null,
|
1565 |
"trial_params": null
|