Training in progress, step 7000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737580392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb141f64f181f8aaa27c9d3a77af0d93d7afb9857067a90441308d67ea3f00a0
|
| 3 |
size 737580392
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475248442
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd3f4a311baa95b8c3c9a1270d3c59f445a214334d14d8eaebcf84317b8587c7
|
| 3 |
size 1475248442
|
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 sha256:9819055317e0aa1215ad120239bc4cecc175225c0dc18c98ca0bffe9f465133f
|
| 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 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:879c433ff59d472a2c5d7c4da04ae14ac33f2ec2552c8f49d34302050bc28fb0
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -4591,6 +4591,770 @@
|
|
| 4591 |
"eval_spearman_manhattan": 0.8036153637269691,
|
| 4592 |
"eval_steps_per_second": 29.47,
|
| 4593 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4594 |
}
|
| 4595 |
],
|
| 4596 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.280224929709466,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 7000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 4591 |
"eval_spearman_manhattan": 0.8036153637269691,
|
| 4592 |
"eval_steps_per_second": 29.47,
|
| 4593 |
"step": 6000
|
| 4594 |
+
},
|
| 4595 |
+
{
|
| 4596 |
+
"epoch": 2.81630740393627,
|
| 4597 |
+
"grad_norm": 1.460700273513794,
|
| 4598 |
+
"learning_rate": 1.8239807872539834e-05,
|
| 4599 |
+
"loss": 0.1745,
|
| 4600 |
+
"step": 6010
|
| 4601 |
+
},
|
| 4602 |
+
{
|
| 4603 |
+
"epoch": 2.820993439550141,
|
| 4604 |
+
"grad_norm": 1.7924867868423462,
|
| 4605 |
+
"learning_rate": 1.8236879100281163e-05,
|
| 4606 |
+
"loss": 0.151,
|
| 4607 |
+
"step": 6020
|
| 4608 |
+
},
|
| 4609 |
+
{
|
| 4610 |
+
"epoch": 2.8256794751640113,
|
| 4611 |
+
"grad_norm": 1.7853138446807861,
|
| 4612 |
+
"learning_rate": 1.8233950328022493e-05,
|
| 4613 |
+
"loss": 0.1629,
|
| 4614 |
+
"step": 6030
|
| 4615 |
+
},
|
| 4616 |
+
{
|
| 4617 |
+
"epoch": 2.830365510777882,
|
| 4618 |
+
"grad_norm": 1.8576308488845825,
|
| 4619 |
+
"learning_rate": 1.8231021555763825e-05,
|
| 4620 |
+
"loss": 0.173,
|
| 4621 |
+
"step": 6040
|
| 4622 |
+
},
|
| 4623 |
+
{
|
| 4624 |
+
"epoch": 2.8350515463917527,
|
| 4625 |
+
"grad_norm": 1.7521380186080933,
|
| 4626 |
+
"learning_rate": 1.8228092783505155e-05,
|
| 4627 |
+
"loss": 0.1741,
|
| 4628 |
+
"step": 6050
|
| 4629 |
+
},
|
| 4630 |
+
{
|
| 4631 |
+
"epoch": 2.839737582005623,
|
| 4632 |
+
"grad_norm": 1.6762547492980957,
|
| 4633 |
+
"learning_rate": 1.8225164011246488e-05,
|
| 4634 |
+
"loss": 0.1662,
|
| 4635 |
+
"step": 6060
|
| 4636 |
+
},
|
| 4637 |
+
{
|
| 4638 |
+
"epoch": 2.844423617619494,
|
| 4639 |
+
"grad_norm": 1.985397219657898,
|
| 4640 |
+
"learning_rate": 1.8222235238987817e-05,
|
| 4641 |
+
"loss": 0.1889,
|
| 4642 |
+
"step": 6070
|
| 4643 |
+
},
|
| 4644 |
+
{
|
| 4645 |
+
"epoch": 2.8491096532333646,
|
| 4646 |
+
"grad_norm": 2.0703446865081787,
|
| 4647 |
+
"learning_rate": 1.821930646672915e-05,
|
| 4648 |
+
"loss": 0.1772,
|
| 4649 |
+
"step": 6080
|
| 4650 |
+
},
|
| 4651 |
+
{
|
| 4652 |
+
"epoch": 2.853795688847235,
|
| 4653 |
+
"grad_norm": 2.128908395767212,
|
| 4654 |
+
"learning_rate": 1.821637769447048e-05,
|
| 4655 |
+
"loss": 0.1644,
|
| 4656 |
+
"step": 6090
|
| 4657 |
+
},
|
| 4658 |
+
{
|
| 4659 |
+
"epoch": 2.858481724461106,
|
| 4660 |
+
"grad_norm": 2.1612260341644287,
|
| 4661 |
+
"learning_rate": 1.821344892221181e-05,
|
| 4662 |
+
"loss": 0.2097,
|
| 4663 |
+
"step": 6100
|
| 4664 |
+
},
|
| 4665 |
+
{
|
| 4666 |
+
"epoch": 2.8631677600749765,
|
| 4667 |
+
"grad_norm": 2.220729351043701,
|
| 4668 |
+
"learning_rate": 1.8210520149953142e-05,
|
| 4669 |
+
"loss": 0.1746,
|
| 4670 |
+
"step": 6110
|
| 4671 |
+
},
|
| 4672 |
+
{
|
| 4673 |
+
"epoch": 2.8678537956888475,
|
| 4674 |
+
"grad_norm": 2.017711639404297,
|
| 4675 |
+
"learning_rate": 1.820759137769447e-05,
|
| 4676 |
+
"loss": 0.1816,
|
| 4677 |
+
"step": 6120
|
| 4678 |
+
},
|
| 4679 |
+
{
|
| 4680 |
+
"epoch": 2.872539831302718,
|
| 4681 |
+
"grad_norm": 1.7267364263534546,
|
| 4682 |
+
"learning_rate": 1.8204662605435805e-05,
|
| 4683 |
+
"loss": 0.1738,
|
| 4684 |
+
"step": 6130
|
| 4685 |
+
},
|
| 4686 |
+
{
|
| 4687 |
+
"epoch": 2.8772258669165884,
|
| 4688 |
+
"grad_norm": 1.7841973304748535,
|
| 4689 |
+
"learning_rate": 1.8201733833177134e-05,
|
| 4690 |
+
"loss": 0.1598,
|
| 4691 |
+
"step": 6140
|
| 4692 |
+
},
|
| 4693 |
+
{
|
| 4694 |
+
"epoch": 2.8819119025304594,
|
| 4695 |
+
"grad_norm": 1.9603809118270874,
|
| 4696 |
+
"learning_rate": 1.8198805060918464e-05,
|
| 4697 |
+
"loss": 0.1867,
|
| 4698 |
+
"step": 6150
|
| 4699 |
+
},
|
| 4700 |
+
{
|
| 4701 |
+
"epoch": 2.88659793814433,
|
| 4702 |
+
"grad_norm": 2.0242254734039307,
|
| 4703 |
+
"learning_rate": 1.8195876288659796e-05,
|
| 4704 |
+
"loss": 0.164,
|
| 4705 |
+
"step": 6160
|
| 4706 |
+
},
|
| 4707 |
+
{
|
| 4708 |
+
"epoch": 2.891283973758201,
|
| 4709 |
+
"grad_norm": 1.3930503129959106,
|
| 4710 |
+
"learning_rate": 1.8192947516401126e-05,
|
| 4711 |
+
"loss": 0.1469,
|
| 4712 |
+
"step": 6170
|
| 4713 |
+
},
|
| 4714 |
+
{
|
| 4715 |
+
"epoch": 2.8959700093720713,
|
| 4716 |
+
"grad_norm": 1.4639194011688232,
|
| 4717 |
+
"learning_rate": 1.8190018744142455e-05,
|
| 4718 |
+
"loss": 0.1676,
|
| 4719 |
+
"step": 6180
|
| 4720 |
+
},
|
| 4721 |
+
{
|
| 4722 |
+
"epoch": 2.9006560449859418,
|
| 4723 |
+
"grad_norm": 1.9063324928283691,
|
| 4724 |
+
"learning_rate": 1.8187089971883788e-05,
|
| 4725 |
+
"loss": 0.1644,
|
| 4726 |
+
"step": 6190
|
| 4727 |
+
},
|
| 4728 |
+
{
|
| 4729 |
+
"epoch": 2.9053420805998127,
|
| 4730 |
+
"grad_norm": 1.8006539344787598,
|
| 4731 |
+
"learning_rate": 1.8184161199625118e-05,
|
| 4732 |
+
"loss": 0.1695,
|
| 4733 |
+
"step": 6200
|
| 4734 |
+
},
|
| 4735 |
+
{
|
| 4736 |
+
"epoch": 2.910028116213683,
|
| 4737 |
+
"grad_norm": 1.7670259475708008,
|
| 4738 |
+
"learning_rate": 1.8181232427366447e-05,
|
| 4739 |
+
"loss": 0.1624,
|
| 4740 |
+
"step": 6210
|
| 4741 |
+
},
|
| 4742 |
+
{
|
| 4743 |
+
"epoch": 2.914714151827554,
|
| 4744 |
+
"grad_norm": 1.9622496366500854,
|
| 4745 |
+
"learning_rate": 1.817830365510778e-05,
|
| 4746 |
+
"loss": 0.1777,
|
| 4747 |
+
"step": 6220
|
| 4748 |
+
},
|
| 4749 |
+
{
|
| 4750 |
+
"epoch": 2.9194001874414246,
|
| 4751 |
+
"grad_norm": 1.9627212285995483,
|
| 4752 |
+
"learning_rate": 1.817537488284911e-05,
|
| 4753 |
+
"loss": 0.1817,
|
| 4754 |
+
"step": 6230
|
| 4755 |
+
},
|
| 4756 |
+
{
|
| 4757 |
+
"epoch": 2.924086223055295,
|
| 4758 |
+
"grad_norm": 1.9101510047912598,
|
| 4759 |
+
"learning_rate": 1.8172446110590443e-05,
|
| 4760 |
+
"loss": 0.1743,
|
| 4761 |
+
"step": 6240
|
| 4762 |
+
},
|
| 4763 |
+
{
|
| 4764 |
+
"epoch": 2.928772258669166,
|
| 4765 |
+
"grad_norm": 1.890410304069519,
|
| 4766 |
+
"learning_rate": 1.8169517338331772e-05,
|
| 4767 |
+
"loss": 0.152,
|
| 4768 |
+
"step": 6250
|
| 4769 |
+
},
|
| 4770 |
+
{
|
| 4771 |
+
"epoch": 2.928772258669166,
|
| 4772 |
+
"eval_loss": 0.03263232484459877,
|
| 4773 |
+
"eval_pearson_cosine": 0.8153769983260584,
|
| 4774 |
+
"eval_pearson_dot": 0.7414947307896895,
|
| 4775 |
+
"eval_pearson_euclidean": 0.7908278401422209,
|
| 4776 |
+
"eval_pearson_manhattan": 0.7928717466268438,
|
| 4777 |
+
"eval_runtime": 3.1717,
|
| 4778 |
+
"eval_samples_per_second": 472.936,
|
| 4779 |
+
"eval_spearman_cosine": 0.8150926580171975,
|
| 4780 |
+
"eval_spearman_dot": 0.7426551131852436,
|
| 4781 |
+
"eval_spearman_euclidean": 0.8000506096598716,
|
| 4782 |
+
"eval_spearman_manhattan": 0.8018413708002138,
|
| 4783 |
+
"eval_steps_per_second": 29.637,
|
| 4784 |
+
"step": 6250
|
| 4785 |
+
},
|
| 4786 |
+
{
|
| 4787 |
+
"epoch": 2.9334582942830365,
|
| 4788 |
+
"grad_norm": 1.8069051504135132,
|
| 4789 |
+
"learning_rate": 1.8166588566073105e-05,
|
| 4790 |
+
"loss": 0.1915,
|
| 4791 |
+
"step": 6260
|
| 4792 |
+
},
|
| 4793 |
+
{
|
| 4794 |
+
"epoch": 2.9381443298969074,
|
| 4795 |
+
"grad_norm": 1.2744157314300537,
|
| 4796 |
+
"learning_rate": 1.8163659793814434e-05,
|
| 4797 |
+
"loss": 0.1493,
|
| 4798 |
+
"step": 6270
|
| 4799 |
+
},
|
| 4800 |
+
{
|
| 4801 |
+
"epoch": 2.942830365510778,
|
| 4802 |
+
"grad_norm": 1.6674821376800537,
|
| 4803 |
+
"learning_rate": 1.8160731021555767e-05,
|
| 4804 |
+
"loss": 0.1618,
|
| 4805 |
+
"step": 6280
|
| 4806 |
+
},
|
| 4807 |
+
{
|
| 4808 |
+
"epoch": 2.9475164011246484,
|
| 4809 |
+
"grad_norm": 2.0318241119384766,
|
| 4810 |
+
"learning_rate": 1.8157802249297097e-05,
|
| 4811 |
+
"loss": 0.1769,
|
| 4812 |
+
"step": 6290
|
| 4813 |
+
},
|
| 4814 |
+
{
|
| 4815 |
+
"epoch": 2.9522024367385193,
|
| 4816 |
+
"grad_norm": 2.4880385398864746,
|
| 4817 |
+
"learning_rate": 1.8154873477038426e-05,
|
| 4818 |
+
"loss": 0.1886,
|
| 4819 |
+
"step": 6300
|
| 4820 |
+
},
|
| 4821 |
+
{
|
| 4822 |
+
"epoch": 2.95688847235239,
|
| 4823 |
+
"grad_norm": 2.0214920043945312,
|
| 4824 |
+
"learning_rate": 1.815194470477976e-05,
|
| 4825 |
+
"loss": 0.1806,
|
| 4826 |
+
"step": 6310
|
| 4827 |
+
},
|
| 4828 |
+
{
|
| 4829 |
+
"epoch": 2.9615745079662608,
|
| 4830 |
+
"grad_norm": 1.6570240259170532,
|
| 4831 |
+
"learning_rate": 1.814901593252109e-05,
|
| 4832 |
+
"loss": 0.1681,
|
| 4833 |
+
"step": 6320
|
| 4834 |
+
},
|
| 4835 |
+
{
|
| 4836 |
+
"epoch": 2.9662605435801312,
|
| 4837 |
+
"grad_norm": 1.9034634828567505,
|
| 4838 |
+
"learning_rate": 1.814608716026242e-05,
|
| 4839 |
+
"loss": 0.1465,
|
| 4840 |
+
"step": 6330
|
| 4841 |
+
},
|
| 4842 |
+
{
|
| 4843 |
+
"epoch": 2.9709465791940017,
|
| 4844 |
+
"grad_norm": 1.3237876892089844,
|
| 4845 |
+
"learning_rate": 1.814315838800375e-05,
|
| 4846 |
+
"loss": 0.1658,
|
| 4847 |
+
"step": 6340
|
| 4848 |
+
},
|
| 4849 |
+
{
|
| 4850 |
+
"epoch": 2.9756326148078727,
|
| 4851 |
+
"grad_norm": 2.253992795944214,
|
| 4852 |
+
"learning_rate": 1.814022961574508e-05,
|
| 4853 |
+
"loss": 0.1993,
|
| 4854 |
+
"step": 6350
|
| 4855 |
+
},
|
| 4856 |
+
{
|
| 4857 |
+
"epoch": 2.980318650421743,
|
| 4858 |
+
"grad_norm": 1.5123599767684937,
|
| 4859 |
+
"learning_rate": 1.813730084348641e-05,
|
| 4860 |
+
"loss": 0.1713,
|
| 4861 |
+
"step": 6360
|
| 4862 |
+
},
|
| 4863 |
+
{
|
| 4864 |
+
"epoch": 2.985004686035614,
|
| 4865 |
+
"grad_norm": 2.3374693393707275,
|
| 4866 |
+
"learning_rate": 1.8134372071227743e-05,
|
| 4867 |
+
"loss": 0.1545,
|
| 4868 |
+
"step": 6370
|
| 4869 |
+
},
|
| 4870 |
+
{
|
| 4871 |
+
"epoch": 2.9896907216494846,
|
| 4872 |
+
"grad_norm": 1.5885390043258667,
|
| 4873 |
+
"learning_rate": 1.8131443298969072e-05,
|
| 4874 |
+
"loss": 0.1689,
|
| 4875 |
+
"step": 6380
|
| 4876 |
+
},
|
| 4877 |
+
{
|
| 4878 |
+
"epoch": 2.994376757263355,
|
| 4879 |
+
"grad_norm": 2.09841251373291,
|
| 4880 |
+
"learning_rate": 1.8128514526710402e-05,
|
| 4881 |
+
"loss": 0.199,
|
| 4882 |
+
"step": 6390
|
| 4883 |
+
},
|
| 4884 |
+
{
|
| 4885 |
+
"epoch": 2.999062792877226,
|
| 4886 |
+
"grad_norm": 1.7730973958969116,
|
| 4887 |
+
"learning_rate": 1.8125585754451735e-05,
|
| 4888 |
+
"loss": 0.1674,
|
| 4889 |
+
"step": 6400
|
| 4890 |
+
},
|
| 4891 |
+
{
|
| 4892 |
+
"epoch": 3.0037488284910965,
|
| 4893 |
+
"grad_norm": 1.6908677816390991,
|
| 4894 |
+
"learning_rate": 1.8122656982193064e-05,
|
| 4895 |
+
"loss": 0.1177,
|
| 4896 |
+
"step": 6410
|
| 4897 |
+
},
|
| 4898 |
+
{
|
| 4899 |
+
"epoch": 3.0084348641049674,
|
| 4900 |
+
"grad_norm": 1.376086711883545,
|
| 4901 |
+
"learning_rate": 1.8119728209934397e-05,
|
| 4902 |
+
"loss": 0.1203,
|
| 4903 |
+
"step": 6420
|
| 4904 |
+
},
|
| 4905 |
+
{
|
| 4906 |
+
"epoch": 3.013120899718838,
|
| 4907 |
+
"grad_norm": 1.7540253400802612,
|
| 4908 |
+
"learning_rate": 1.8116799437675727e-05,
|
| 4909 |
+
"loss": 0.1133,
|
| 4910 |
+
"step": 6430
|
| 4911 |
+
},
|
| 4912 |
+
{
|
| 4913 |
+
"epoch": 3.0178069353327084,
|
| 4914 |
+
"grad_norm": 1.0979869365692139,
|
| 4915 |
+
"learning_rate": 1.811387066541706e-05,
|
| 4916 |
+
"loss": 0.0976,
|
| 4917 |
+
"step": 6440
|
| 4918 |
+
},
|
| 4919 |
+
{
|
| 4920 |
+
"epoch": 3.0224929709465793,
|
| 4921 |
+
"grad_norm": 1.4160518646240234,
|
| 4922 |
+
"learning_rate": 1.811094189315839e-05,
|
| 4923 |
+
"loss": 0.1084,
|
| 4924 |
+
"step": 6450
|
| 4925 |
+
},
|
| 4926 |
+
{
|
| 4927 |
+
"epoch": 3.02717900656045,
|
| 4928 |
+
"grad_norm": 1.0536082983016968,
|
| 4929 |
+
"learning_rate": 1.8108013120899722e-05,
|
| 4930 |
+
"loss": 0.0951,
|
| 4931 |
+
"step": 6460
|
| 4932 |
+
},
|
| 4933 |
+
{
|
| 4934 |
+
"epoch": 3.0318650421743207,
|
| 4935 |
+
"grad_norm": 1.4449706077575684,
|
| 4936 |
+
"learning_rate": 1.810508434864105e-05,
|
| 4937 |
+
"loss": 0.1148,
|
| 4938 |
+
"step": 6470
|
| 4939 |
+
},
|
| 4940 |
+
{
|
| 4941 |
+
"epoch": 3.036551077788191,
|
| 4942 |
+
"grad_norm": 1.9929163455963135,
|
| 4943 |
+
"learning_rate": 1.8102155576382384e-05,
|
| 4944 |
+
"loss": 0.1092,
|
| 4945 |
+
"step": 6480
|
| 4946 |
+
},
|
| 4947 |
+
{
|
| 4948 |
+
"epoch": 3.0412371134020617,
|
| 4949 |
+
"grad_norm": 1.5023281574249268,
|
| 4950 |
+
"learning_rate": 1.8099226804123714e-05,
|
| 4951 |
+
"loss": 0.1366,
|
| 4952 |
+
"step": 6490
|
| 4953 |
+
},
|
| 4954 |
+
{
|
| 4955 |
+
"epoch": 3.0459231490159326,
|
| 4956 |
+
"grad_norm": 1.0478644371032715,
|
| 4957 |
+
"learning_rate": 1.8096298031865043e-05,
|
| 4958 |
+
"loss": 0.1,
|
| 4959 |
+
"step": 6500
|
| 4960 |
+
},
|
| 4961 |
+
{
|
| 4962 |
+
"epoch": 3.0459231490159326,
|
| 4963 |
+
"eval_loss": 0.03124774619936943,
|
| 4964 |
+
"eval_pearson_cosine": 0.819439330096543,
|
| 4965 |
+
"eval_pearson_dot": 0.756545112697367,
|
| 4966 |
+
"eval_pearson_euclidean": 0.7885948455069851,
|
| 4967 |
+
"eval_pearson_manhattan": 0.790849549554963,
|
| 4968 |
+
"eval_runtime": 3.2845,
|
| 4969 |
+
"eval_samples_per_second": 456.685,
|
| 4970 |
+
"eval_spearman_cosine": 0.8189547958390648,
|
| 4971 |
+
"eval_spearman_dot": 0.7570952217597201,
|
| 4972 |
+
"eval_spearman_euclidean": 0.7971512626570622,
|
| 4973 |
+
"eval_spearman_manhattan": 0.7989572580196979,
|
| 4974 |
+
"eval_steps_per_second": 28.619,
|
| 4975 |
+
"step": 6500
|
| 4976 |
+
},
|
| 4977 |
+
{
|
| 4978 |
+
"epoch": 3.050609184629803,
|
| 4979 |
+
"grad_norm": 1.7084600925445557,
|
| 4980 |
+
"learning_rate": 1.8093369259606376e-05,
|
| 4981 |
+
"loss": 0.1258,
|
| 4982 |
+
"step": 6510
|
| 4983 |
+
},
|
| 4984 |
+
{
|
| 4985 |
+
"epoch": 3.055295220243674,
|
| 4986 |
+
"grad_norm": 1.9885269403457642,
|
| 4987 |
+
"learning_rate": 1.8090440487347706e-05,
|
| 4988 |
+
"loss": 0.1275,
|
| 4989 |
+
"step": 6520
|
| 4990 |
+
},
|
| 4991 |
+
{
|
| 4992 |
+
"epoch": 3.0599812558575445,
|
| 4993 |
+
"grad_norm": 1.5580956935882568,
|
| 4994 |
+
"learning_rate": 1.8087511715089035e-05,
|
| 4995 |
+
"loss": 0.1147,
|
| 4996 |
+
"step": 6530
|
| 4997 |
+
},
|
| 4998 |
+
{
|
| 4999 |
+
"epoch": 3.064667291471415,
|
| 5000 |
+
"grad_norm": 1.2762457132339478,
|
| 5001 |
+
"learning_rate": 1.8084582942830368e-05,
|
| 5002 |
+
"loss": 0.1087,
|
| 5003 |
+
"step": 6540
|
| 5004 |
+
},
|
| 5005 |
+
{
|
| 5006 |
+
"epoch": 3.069353327085286,
|
| 5007 |
+
"grad_norm": 1.7397170066833496,
|
| 5008 |
+
"learning_rate": 1.8081654170571698e-05,
|
| 5009 |
+
"loss": 0.107,
|
| 5010 |
+
"step": 6550
|
| 5011 |
+
},
|
| 5012 |
+
{
|
| 5013 |
+
"epoch": 3.0740393626991565,
|
| 5014 |
+
"grad_norm": 1.6765695810317993,
|
| 5015 |
+
"learning_rate": 1.8078725398313027e-05,
|
| 5016 |
+
"loss": 0.1389,
|
| 5017 |
+
"step": 6560
|
| 5018 |
+
},
|
| 5019 |
+
{
|
| 5020 |
+
"epoch": 3.0787253983130274,
|
| 5021 |
+
"grad_norm": 1.6627321243286133,
|
| 5022 |
+
"learning_rate": 1.807579662605436e-05,
|
| 5023 |
+
"loss": 0.1315,
|
| 5024 |
+
"step": 6570
|
| 5025 |
+
},
|
| 5026 |
+
{
|
| 5027 |
+
"epoch": 3.083411433926898,
|
| 5028 |
+
"grad_norm": 1.4617902040481567,
|
| 5029 |
+
"learning_rate": 1.807286785379569e-05,
|
| 5030 |
+
"loss": 0.1003,
|
| 5031 |
+
"step": 6580
|
| 5032 |
+
},
|
| 5033 |
+
{
|
| 5034 |
+
"epoch": 3.0880974695407684,
|
| 5035 |
+
"grad_norm": 1.4063915014266968,
|
| 5036 |
+
"learning_rate": 1.806993908153702e-05,
|
| 5037 |
+
"loss": 0.1256,
|
| 5038 |
+
"step": 6590
|
| 5039 |
+
},
|
| 5040 |
+
{
|
| 5041 |
+
"epoch": 3.0927835051546393,
|
| 5042 |
+
"grad_norm": 1.4291496276855469,
|
| 5043 |
+
"learning_rate": 1.8067010309278352e-05,
|
| 5044 |
+
"loss": 0.0952,
|
| 5045 |
+
"step": 6600
|
| 5046 |
+
},
|
| 5047 |
+
{
|
| 5048 |
+
"epoch": 3.0974695407685098,
|
| 5049 |
+
"grad_norm": 1.7208278179168701,
|
| 5050 |
+
"learning_rate": 1.806408153701968e-05,
|
| 5051 |
+
"loss": 0.1232,
|
| 5052 |
+
"step": 6610
|
| 5053 |
+
},
|
| 5054 |
+
{
|
| 5055 |
+
"epoch": 3.1021555763823807,
|
| 5056 |
+
"grad_norm": 1.4286062717437744,
|
| 5057 |
+
"learning_rate": 1.8061152764761014e-05,
|
| 5058 |
+
"loss": 0.1162,
|
| 5059 |
+
"step": 6620
|
| 5060 |
+
},
|
| 5061 |
+
{
|
| 5062 |
+
"epoch": 3.106841611996251,
|
| 5063 |
+
"grad_norm": 1.6473411321640015,
|
| 5064 |
+
"learning_rate": 1.8058223992502344e-05,
|
| 5065 |
+
"loss": 0.1132,
|
| 5066 |
+
"step": 6630
|
| 5067 |
+
},
|
| 5068 |
+
{
|
| 5069 |
+
"epoch": 3.1115276476101217,
|
| 5070 |
+
"grad_norm": 1.6076815128326416,
|
| 5071 |
+
"learning_rate": 1.8055295220243677e-05,
|
| 5072 |
+
"loss": 0.1224,
|
| 5073 |
+
"step": 6640
|
| 5074 |
+
},
|
| 5075 |
+
{
|
| 5076 |
+
"epoch": 3.1162136832239926,
|
| 5077 |
+
"grad_norm": 1.4402363300323486,
|
| 5078 |
+
"learning_rate": 1.8052366447985006e-05,
|
| 5079 |
+
"loss": 0.1149,
|
| 5080 |
+
"step": 6650
|
| 5081 |
+
},
|
| 5082 |
+
{
|
| 5083 |
+
"epoch": 3.120899718837863,
|
| 5084 |
+
"grad_norm": 1.2964081764221191,
|
| 5085 |
+
"learning_rate": 1.804943767572634e-05,
|
| 5086 |
+
"loss": 0.1084,
|
| 5087 |
+
"step": 6660
|
| 5088 |
+
},
|
| 5089 |
+
{
|
| 5090 |
+
"epoch": 3.125585754451734,
|
| 5091 |
+
"grad_norm": 1.4852274656295776,
|
| 5092 |
+
"learning_rate": 1.804650890346767e-05,
|
| 5093 |
+
"loss": 0.1299,
|
| 5094 |
+
"step": 6670
|
| 5095 |
+
},
|
| 5096 |
+
{
|
| 5097 |
+
"epoch": 3.1302717900656045,
|
| 5098 |
+
"grad_norm": 1.2311766147613525,
|
| 5099 |
+
"learning_rate": 1.8043580131208998e-05,
|
| 5100 |
+
"loss": 0.112,
|
| 5101 |
+
"step": 6680
|
| 5102 |
+
},
|
| 5103 |
+
{
|
| 5104 |
+
"epoch": 3.134957825679475,
|
| 5105 |
+
"grad_norm": 1.7571637630462646,
|
| 5106 |
+
"learning_rate": 1.804065135895033e-05,
|
| 5107 |
+
"loss": 0.1128,
|
| 5108 |
+
"step": 6690
|
| 5109 |
+
},
|
| 5110 |
+
{
|
| 5111 |
+
"epoch": 3.139643861293346,
|
| 5112 |
+
"grad_norm": 2.1391453742980957,
|
| 5113 |
+
"learning_rate": 1.803772258669166e-05,
|
| 5114 |
+
"loss": 0.1323,
|
| 5115 |
+
"step": 6700
|
| 5116 |
+
},
|
| 5117 |
+
{
|
| 5118 |
+
"epoch": 3.1443298969072164,
|
| 5119 |
+
"grad_norm": 1.5623685121536255,
|
| 5120 |
+
"learning_rate": 1.803479381443299e-05,
|
| 5121 |
+
"loss": 0.1139,
|
| 5122 |
+
"step": 6710
|
| 5123 |
+
},
|
| 5124 |
+
{
|
| 5125 |
+
"epoch": 3.1490159325210874,
|
| 5126 |
+
"grad_norm": 1.7942404747009277,
|
| 5127 |
+
"learning_rate": 1.8031865042174323e-05,
|
| 5128 |
+
"loss": 0.1426,
|
| 5129 |
+
"step": 6720
|
| 5130 |
+
},
|
| 5131 |
+
{
|
| 5132 |
+
"epoch": 3.153701968134958,
|
| 5133 |
+
"grad_norm": 1.410545825958252,
|
| 5134 |
+
"learning_rate": 1.8028936269915652e-05,
|
| 5135 |
+
"loss": 0.1056,
|
| 5136 |
+
"step": 6730
|
| 5137 |
+
},
|
| 5138 |
+
{
|
| 5139 |
+
"epoch": 3.1583880037488283,
|
| 5140 |
+
"grad_norm": 1.8002315759658813,
|
| 5141 |
+
"learning_rate": 1.8026007497656982e-05,
|
| 5142 |
+
"loss": 0.1256,
|
| 5143 |
+
"step": 6740
|
| 5144 |
+
},
|
| 5145 |
+
{
|
| 5146 |
+
"epoch": 3.1630740393626993,
|
| 5147 |
+
"grad_norm": 1.1960804462432861,
|
| 5148 |
+
"learning_rate": 1.8023078725398315e-05,
|
| 5149 |
+
"loss": 0.1075,
|
| 5150 |
+
"step": 6750
|
| 5151 |
+
},
|
| 5152 |
+
{
|
| 5153 |
+
"epoch": 3.1630740393626993,
|
| 5154 |
+
"eval_loss": 0.031751763075590134,
|
| 5155 |
+
"eval_pearson_cosine": 0.818392251131673,
|
| 5156 |
+
"eval_pearson_dot": 0.7566814090378315,
|
| 5157 |
+
"eval_pearson_euclidean": 0.7928479508679516,
|
| 5158 |
+
"eval_pearson_manhattan": 0.7948564653512236,
|
| 5159 |
+
"eval_runtime": 3.2248,
|
| 5160 |
+
"eval_samples_per_second": 465.151,
|
| 5161 |
+
"eval_spearman_cosine": 0.8181084179548533,
|
| 5162 |
+
"eval_spearman_dot": 0.7582501700895796,
|
| 5163 |
+
"eval_spearman_euclidean": 0.801587599060446,
|
| 5164 |
+
"eval_spearman_manhattan": 0.8030998382251602,
|
| 5165 |
+
"eval_steps_per_second": 29.149,
|
| 5166 |
+
"step": 6750
|
| 5167 |
+
},
|
| 5168 |
+
{
|
| 5169 |
+
"epoch": 3.1677600749765698,
|
| 5170 |
+
"grad_norm": 1.8303911685943604,
|
| 5171 |
+
"learning_rate": 1.8020149953139644e-05,
|
| 5172 |
+
"loss": 0.1148,
|
| 5173 |
+
"step": 6760
|
| 5174 |
+
},
|
| 5175 |
+
{
|
| 5176 |
+
"epoch": 3.1724461105904407,
|
| 5177 |
+
"grad_norm": 0.8495842814445496,
|
| 5178 |
+
"learning_rate": 1.8017221180880977e-05,
|
| 5179 |
+
"loss": 0.1118,
|
| 5180 |
+
"step": 6770
|
| 5181 |
+
},
|
| 5182 |
+
{
|
| 5183 |
+
"epoch": 3.177132146204311,
|
| 5184 |
+
"grad_norm": 1.8021464347839355,
|
| 5185 |
+
"learning_rate": 1.8014292408622307e-05,
|
| 5186 |
+
"loss": 0.1171,
|
| 5187 |
+
"step": 6780
|
| 5188 |
+
},
|
| 5189 |
+
{
|
| 5190 |
+
"epoch": 3.1818181818181817,
|
| 5191 |
+
"grad_norm": 1.4046647548675537,
|
| 5192 |
+
"learning_rate": 1.8011363636363636e-05,
|
| 5193 |
+
"loss": 0.1126,
|
| 5194 |
+
"step": 6790
|
| 5195 |
+
},
|
| 5196 |
+
{
|
| 5197 |
+
"epoch": 3.1865042174320526,
|
| 5198 |
+
"grad_norm": 1.425398349761963,
|
| 5199 |
+
"learning_rate": 1.800843486410497e-05,
|
| 5200 |
+
"loss": 0.0897,
|
| 5201 |
+
"step": 6800
|
| 5202 |
+
},
|
| 5203 |
+
{
|
| 5204 |
+
"epoch": 3.191190253045923,
|
| 5205 |
+
"grad_norm": 1.938445806503296,
|
| 5206 |
+
"learning_rate": 1.80055060918463e-05,
|
| 5207 |
+
"loss": 0.1173,
|
| 5208 |
+
"step": 6810
|
| 5209 |
+
},
|
| 5210 |
+
{
|
| 5211 |
+
"epoch": 3.195876288659794,
|
| 5212 |
+
"grad_norm": 1.9677798748016357,
|
| 5213 |
+
"learning_rate": 1.800257731958763e-05,
|
| 5214 |
+
"loss": 0.1113,
|
| 5215 |
+
"step": 6820
|
| 5216 |
+
},
|
| 5217 |
+
{
|
| 5218 |
+
"epoch": 3.2005623242736645,
|
| 5219 |
+
"grad_norm": 1.0695815086364746,
|
| 5220 |
+
"learning_rate": 1.799964854732896e-05,
|
| 5221 |
+
"loss": 0.1251,
|
| 5222 |
+
"step": 6830
|
| 5223 |
+
},
|
| 5224 |
+
{
|
| 5225 |
+
"epoch": 3.205248359887535,
|
| 5226 |
+
"grad_norm": 1.5036897659301758,
|
| 5227 |
+
"learning_rate": 1.7996719775070294e-05,
|
| 5228 |
+
"loss": 0.1077,
|
| 5229 |
+
"step": 6840
|
| 5230 |
+
},
|
| 5231 |
+
{
|
| 5232 |
+
"epoch": 3.209934395501406,
|
| 5233 |
+
"grad_norm": 1.0521790981292725,
|
| 5234 |
+
"learning_rate": 1.7993791002811623e-05,
|
| 5235 |
+
"loss": 0.1121,
|
| 5236 |
+
"step": 6850
|
| 5237 |
+
},
|
| 5238 |
+
{
|
| 5239 |
+
"epoch": 3.2146204311152764,
|
| 5240 |
+
"grad_norm": 1.6036179065704346,
|
| 5241 |
+
"learning_rate": 1.7990862230552956e-05,
|
| 5242 |
+
"loss": 0.1087,
|
| 5243 |
+
"step": 6860
|
| 5244 |
+
},
|
| 5245 |
+
{
|
| 5246 |
+
"epoch": 3.2193064667291473,
|
| 5247 |
+
"grad_norm": 1.5137251615524292,
|
| 5248 |
+
"learning_rate": 1.7987933458294286e-05,
|
| 5249 |
+
"loss": 0.1227,
|
| 5250 |
+
"step": 6870
|
| 5251 |
+
},
|
| 5252 |
+
{
|
| 5253 |
+
"epoch": 3.223992502343018,
|
| 5254 |
+
"grad_norm": 1.7321174144744873,
|
| 5255 |
+
"learning_rate": 1.7985004686035615e-05,
|
| 5256 |
+
"loss": 0.1165,
|
| 5257 |
+
"step": 6880
|
| 5258 |
+
},
|
| 5259 |
+
{
|
| 5260 |
+
"epoch": 3.2286785379568883,
|
| 5261 |
+
"grad_norm": 1.744694709777832,
|
| 5262 |
+
"learning_rate": 1.7982075913776945e-05,
|
| 5263 |
+
"loss": 0.1164,
|
| 5264 |
+
"step": 6890
|
| 5265 |
+
},
|
| 5266 |
+
{
|
| 5267 |
+
"epoch": 3.2333645735707592,
|
| 5268 |
+
"grad_norm": 1.5463277101516724,
|
| 5269 |
+
"learning_rate": 1.7979147141518278e-05,
|
| 5270 |
+
"loss": 0.1047,
|
| 5271 |
+
"step": 6900
|
| 5272 |
+
},
|
| 5273 |
+
{
|
| 5274 |
+
"epoch": 3.2380506091846297,
|
| 5275 |
+
"grad_norm": 1.663386583328247,
|
| 5276 |
+
"learning_rate": 1.7976218369259607e-05,
|
| 5277 |
+
"loss": 0.102,
|
| 5278 |
+
"step": 6910
|
| 5279 |
+
},
|
| 5280 |
+
{
|
| 5281 |
+
"epoch": 3.2427366447985007,
|
| 5282 |
+
"grad_norm": 1.3090193271636963,
|
| 5283 |
+
"learning_rate": 1.7973289597000937e-05,
|
| 5284 |
+
"loss": 0.1206,
|
| 5285 |
+
"step": 6920
|
| 5286 |
+
},
|
| 5287 |
+
{
|
| 5288 |
+
"epoch": 3.247422680412371,
|
| 5289 |
+
"grad_norm": 1.535120964050293,
|
| 5290 |
+
"learning_rate": 1.797036082474227e-05,
|
| 5291 |
+
"loss": 0.1131,
|
| 5292 |
+
"step": 6930
|
| 5293 |
+
},
|
| 5294 |
+
{
|
| 5295 |
+
"epoch": 3.2521087160262416,
|
| 5296 |
+
"grad_norm": 2.086014986038208,
|
| 5297 |
+
"learning_rate": 1.79674320524836e-05,
|
| 5298 |
+
"loss": 0.1237,
|
| 5299 |
+
"step": 6940
|
| 5300 |
+
},
|
| 5301 |
+
{
|
| 5302 |
+
"epoch": 3.2567947516401126,
|
| 5303 |
+
"grad_norm": 1.6445001363754272,
|
| 5304 |
+
"learning_rate": 1.7964503280224932e-05,
|
| 5305 |
+
"loss": 0.1079,
|
| 5306 |
+
"step": 6950
|
| 5307 |
+
},
|
| 5308 |
+
{
|
| 5309 |
+
"epoch": 3.261480787253983,
|
| 5310 |
+
"grad_norm": 1.4344754219055176,
|
| 5311 |
+
"learning_rate": 1.796157450796626e-05,
|
| 5312 |
+
"loss": 0.1077,
|
| 5313 |
+
"step": 6960
|
| 5314 |
+
},
|
| 5315 |
+
{
|
| 5316 |
+
"epoch": 3.266166822867854,
|
| 5317 |
+
"grad_norm": 0.9027751088142395,
|
| 5318 |
+
"learning_rate": 1.7958645735707594e-05,
|
| 5319 |
+
"loss": 0.0977,
|
| 5320 |
+
"step": 6970
|
| 5321 |
+
},
|
| 5322 |
+
{
|
| 5323 |
+
"epoch": 3.2708528584817245,
|
| 5324 |
+
"grad_norm": 1.6101003885269165,
|
| 5325 |
+
"learning_rate": 1.7955716963448924e-05,
|
| 5326 |
+
"loss": 0.1233,
|
| 5327 |
+
"step": 6980
|
| 5328 |
+
},
|
| 5329 |
+
{
|
| 5330 |
+
"epoch": 3.275538894095595,
|
| 5331 |
+
"grad_norm": 1.6779502630233765,
|
| 5332 |
+
"learning_rate": 1.7952788191190253e-05,
|
| 5333 |
+
"loss": 0.1259,
|
| 5334 |
+
"step": 6990
|
| 5335 |
+
},
|
| 5336 |
+
{
|
| 5337 |
+
"epoch": 3.280224929709466,
|
| 5338 |
+
"grad_norm": 1.1465091705322266,
|
| 5339 |
+
"learning_rate": 1.7949859418931586e-05,
|
| 5340 |
+
"loss": 0.0971,
|
| 5341 |
+
"step": 7000
|
| 5342 |
+
},
|
| 5343 |
+
{
|
| 5344 |
+
"epoch": 3.280224929709466,
|
| 5345 |
+
"eval_loss": 0.031160470098257065,
|
| 5346 |
+
"eval_pearson_cosine": 0.8183441854138493,
|
| 5347 |
+
"eval_pearson_dot": 0.756100708061723,
|
| 5348 |
+
"eval_pearson_euclidean": 0.7881792865072583,
|
| 5349 |
+
"eval_pearson_manhattan": 0.7905067817277995,
|
| 5350 |
+
"eval_runtime": 3.3694,
|
| 5351 |
+
"eval_samples_per_second": 445.183,
|
| 5352 |
+
"eval_spearman_cosine": 0.8175806864862152,
|
| 5353 |
+
"eval_spearman_dot": 0.7571609305062721,
|
| 5354 |
+
"eval_spearman_euclidean": 0.7969525723417172,
|
| 5355 |
+
"eval_spearman_manhattan": 0.7992497485259732,
|
| 5356 |
+
"eval_steps_per_second": 27.898,
|
| 5357 |
+
"step": 7000
|
| 5358 |
}
|
| 5359 |
],
|
| 5360 |
"logging_steps": 10,
|