Training in progress, step 11000, 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 613004648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d7c345217153b5ffddd752365249e312bba97798c34c7461fe730d174535d39
|
| 3 |
size 613004648
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1226096954
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:528a95b443b1dbf7f94d3bb468ca4f53192fe7e23b946971046c87c0b9045e56
|
| 3 |
size 1226096954
|
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 sha256:9b017ee0b8d5b0208434fd4a2a199fc3b93d7395c3472e6edb0f63512bbc20c3
|
| 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 sha256:193283a3db7c41b10c55462d4cd2b8ef19c4b39369364b96fdc0d6e4e4e07810
|
| 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,
|
|
@@ -7647,6 +7647,770 @@
|
|
| 7647 |
"eval_spearman_manhattan": 0.7658321542772971,
|
| 7648 |
"eval_steps_per_second": 37.213,
|
| 7649 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7650 |
}
|
| 7651 |
],
|
| 7652 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.154639175257732,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 11000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 7647 |
"eval_spearman_manhattan": 0.7658321542772971,
|
| 7648 |
"eval_steps_per_second": 37.213,
|
| 7649 |
"step": 10000
|
| 7650 |
+
},
|
| 7651 |
+
{
|
| 7652 |
+
"epoch": 4.690721649484536,
|
| 7653 |
+
"grad_norm": 2.401972532272339,
|
| 7654 |
+
"learning_rate": 9.413659793814434e-06,
|
| 7655 |
+
"loss": 0.1564,
|
| 7656 |
+
"step": 10010
|
| 7657 |
+
},
|
| 7658 |
+
{
|
| 7659 |
+
"epoch": 4.695407685098407,
|
| 7660 |
+
"grad_norm": 1.4866012334823608,
|
| 7661 |
+
"learning_rate": 9.413074039362699e-06,
|
| 7662 |
+
"loss": 0.1573,
|
| 7663 |
+
"step": 10020
|
| 7664 |
+
},
|
| 7665 |
+
{
|
| 7666 |
+
"epoch": 4.700093720712277,
|
| 7667 |
+
"grad_norm": 2.4179933071136475,
|
| 7668 |
+
"learning_rate": 9.412488284910966e-06,
|
| 7669 |
+
"loss": 0.1613,
|
| 7670 |
+
"step": 10030
|
| 7671 |
+
},
|
| 7672 |
+
{
|
| 7673 |
+
"epoch": 4.704779756326148,
|
| 7674 |
+
"grad_norm": 2.4758639335632324,
|
| 7675 |
+
"learning_rate": 9.411902530459233e-06,
|
| 7676 |
+
"loss": 0.1621,
|
| 7677 |
+
"step": 10040
|
| 7678 |
+
},
|
| 7679 |
+
{
|
| 7680 |
+
"epoch": 4.709465791940019,
|
| 7681 |
+
"grad_norm": 2.450495481491089,
|
| 7682 |
+
"learning_rate": 9.411316776007498e-06,
|
| 7683 |
+
"loss": 0.1355,
|
| 7684 |
+
"step": 10050
|
| 7685 |
+
},
|
| 7686 |
+
{
|
| 7687 |
+
"epoch": 4.71415182755389,
|
| 7688 |
+
"grad_norm": 2.5910768508911133,
|
| 7689 |
+
"learning_rate": 9.410731021555765e-06,
|
| 7690 |
+
"loss": 0.1382,
|
| 7691 |
+
"step": 10060
|
| 7692 |
+
},
|
| 7693 |
+
{
|
| 7694 |
+
"epoch": 4.71883786316776,
|
| 7695 |
+
"grad_norm": 3.6344025135040283,
|
| 7696 |
+
"learning_rate": 9.41014526710403e-06,
|
| 7697 |
+
"loss": 0.1609,
|
| 7698 |
+
"step": 10070
|
| 7699 |
+
},
|
| 7700 |
+
{
|
| 7701 |
+
"epoch": 4.723523898781631,
|
| 7702 |
+
"grad_norm": 2.099355697631836,
|
| 7703 |
+
"learning_rate": 9.409559512652297e-06,
|
| 7704 |
+
"loss": 0.1476,
|
| 7705 |
+
"step": 10080
|
| 7706 |
+
},
|
| 7707 |
+
{
|
| 7708 |
+
"epoch": 4.728209934395501,
|
| 7709 |
+
"grad_norm": 2.334122896194458,
|
| 7710 |
+
"learning_rate": 9.408973758200564e-06,
|
| 7711 |
+
"loss": 0.1444,
|
| 7712 |
+
"step": 10090
|
| 7713 |
+
},
|
| 7714 |
+
{
|
| 7715 |
+
"epoch": 4.7328959700093725,
|
| 7716 |
+
"grad_norm": 2.061877965927124,
|
| 7717 |
+
"learning_rate": 9.408388003748829e-06,
|
| 7718 |
+
"loss": 0.1507,
|
| 7719 |
+
"step": 10100
|
| 7720 |
+
},
|
| 7721 |
+
{
|
| 7722 |
+
"epoch": 4.737582005623243,
|
| 7723 |
+
"grad_norm": 1.8726963996887207,
|
| 7724 |
+
"learning_rate": 9.407802249297096e-06,
|
| 7725 |
+
"loss": 0.1546,
|
| 7726 |
+
"step": 10110
|
| 7727 |
+
},
|
| 7728 |
+
{
|
| 7729 |
+
"epoch": 4.742268041237113,
|
| 7730 |
+
"grad_norm": 2.147475004196167,
|
| 7731 |
+
"learning_rate": 9.407216494845361e-06,
|
| 7732 |
+
"loss": 0.1378,
|
| 7733 |
+
"step": 10120
|
| 7734 |
+
},
|
| 7735 |
+
{
|
| 7736 |
+
"epoch": 4.746954076850984,
|
| 7737 |
+
"grad_norm": 2.2211480140686035,
|
| 7738 |
+
"learning_rate": 9.406630740393628e-06,
|
| 7739 |
+
"loss": 0.1636,
|
| 7740 |
+
"step": 10130
|
| 7741 |
+
},
|
| 7742 |
+
{
|
| 7743 |
+
"epoch": 4.751640112464854,
|
| 7744 |
+
"grad_norm": 2.4492108821868896,
|
| 7745 |
+
"learning_rate": 9.406044985941893e-06,
|
| 7746 |
+
"loss": 0.1485,
|
| 7747 |
+
"step": 10140
|
| 7748 |
+
},
|
| 7749 |
+
{
|
| 7750 |
+
"epoch": 4.756326148078726,
|
| 7751 |
+
"grad_norm": 2.647960662841797,
|
| 7752 |
+
"learning_rate": 9.40545923149016e-06,
|
| 7753 |
+
"loss": 0.1518,
|
| 7754 |
+
"step": 10150
|
| 7755 |
+
},
|
| 7756 |
+
{
|
| 7757 |
+
"epoch": 4.761012183692596,
|
| 7758 |
+
"grad_norm": 2.5408220291137695,
|
| 7759 |
+
"learning_rate": 9.404873477038427e-06,
|
| 7760 |
+
"loss": 0.1088,
|
| 7761 |
+
"step": 10160
|
| 7762 |
+
},
|
| 7763 |
+
{
|
| 7764 |
+
"epoch": 4.765698219306467,
|
| 7765 |
+
"grad_norm": 2.3026010990142822,
|
| 7766 |
+
"learning_rate": 9.404287722586692e-06,
|
| 7767 |
+
"loss": 0.1414,
|
| 7768 |
+
"step": 10170
|
| 7769 |
+
},
|
| 7770 |
+
{
|
| 7771 |
+
"epoch": 4.770384254920337,
|
| 7772 |
+
"grad_norm": 2.1535961627960205,
|
| 7773 |
+
"learning_rate": 9.403701968134958e-06,
|
| 7774 |
+
"loss": 0.1438,
|
| 7775 |
+
"step": 10180
|
| 7776 |
+
},
|
| 7777 |
+
{
|
| 7778 |
+
"epoch": 4.775070290534208,
|
| 7779 |
+
"grad_norm": 2.3178975582122803,
|
| 7780 |
+
"learning_rate": 9.403116213683224e-06,
|
| 7781 |
+
"loss": 0.1579,
|
| 7782 |
+
"step": 10190
|
| 7783 |
+
},
|
| 7784 |
+
{
|
| 7785 |
+
"epoch": 4.779756326148079,
|
| 7786 |
+
"grad_norm": 1.7218929529190063,
|
| 7787 |
+
"learning_rate": 9.402530459231491e-06,
|
| 7788 |
+
"loss": 0.1565,
|
| 7789 |
+
"step": 10200
|
| 7790 |
+
},
|
| 7791 |
+
{
|
| 7792 |
+
"epoch": 4.78444236176195,
|
| 7793 |
+
"grad_norm": 1.7112232446670532,
|
| 7794 |
+
"learning_rate": 9.401944704779757e-06,
|
| 7795 |
+
"loss": 0.1576,
|
| 7796 |
+
"step": 10210
|
| 7797 |
+
},
|
| 7798 |
+
{
|
| 7799 |
+
"epoch": 4.78912839737582,
|
| 7800 |
+
"grad_norm": 2.9099996089935303,
|
| 7801 |
+
"learning_rate": 9.401358950328024e-06,
|
| 7802 |
+
"loss": 0.1404,
|
| 7803 |
+
"step": 10220
|
| 7804 |
+
},
|
| 7805 |
+
{
|
| 7806 |
+
"epoch": 4.793814432989691,
|
| 7807 |
+
"grad_norm": 2.4656243324279785,
|
| 7808 |
+
"learning_rate": 9.400773195876289e-06,
|
| 7809 |
+
"loss": 0.1537,
|
| 7810 |
+
"step": 10230
|
| 7811 |
+
},
|
| 7812 |
+
{
|
| 7813 |
+
"epoch": 4.798500468603561,
|
| 7814 |
+
"grad_norm": 2.836191415786743,
|
| 7815 |
+
"learning_rate": 9.400187441424556e-06,
|
| 7816 |
+
"loss": 0.1444,
|
| 7817 |
+
"step": 10240
|
| 7818 |
+
},
|
| 7819 |
+
{
|
| 7820 |
+
"epoch": 4.803186504217432,
|
| 7821 |
+
"grad_norm": 1.7375587224960327,
|
| 7822 |
+
"learning_rate": 9.399601686972821e-06,
|
| 7823 |
+
"loss": 0.148,
|
| 7824 |
+
"step": 10250
|
| 7825 |
+
},
|
| 7826 |
+
{
|
| 7827 |
+
"epoch": 4.803186504217432,
|
| 7828 |
+
"eval_loss": 0.04357453063130379,
|
| 7829 |
+
"eval_pearson_cosine": 0.7816648988028874,
|
| 7830 |
+
"eval_pearson_dot": 0.617140121100384,
|
| 7831 |
+
"eval_pearson_euclidean": 0.7424818050017805,
|
| 7832 |
+
"eval_pearson_manhattan": 0.74207686822308,
|
| 7833 |
+
"eval_runtime": 40.6143,
|
| 7834 |
+
"eval_samples_per_second": 36.933,
|
| 7835 |
+
"eval_spearman_cosine": 0.7855171487091146,
|
| 7836 |
+
"eval_spearman_dot": 0.623924985286794,
|
| 7837 |
+
"eval_spearman_euclidean": 0.7600678672581802,
|
| 7838 |
+
"eval_spearman_manhattan": 0.7596066338339531,
|
| 7839 |
+
"eval_steps_per_second": 36.933,
|
| 7840 |
+
"step": 10250
|
| 7841 |
+
},
|
| 7842 |
+
{
|
| 7843 |
+
"epoch": 4.807872539831303,
|
| 7844 |
+
"grad_norm": 2.1630876064300537,
|
| 7845 |
+
"learning_rate": 9.399015932521088e-06,
|
| 7846 |
+
"loss": 0.1382,
|
| 7847 |
+
"step": 10260
|
| 7848 |
+
},
|
| 7849 |
+
{
|
| 7850 |
+
"epoch": 4.812558575445173,
|
| 7851 |
+
"grad_norm": 2.035651445388794,
|
| 7852 |
+
"learning_rate": 9.398430178069355e-06,
|
| 7853 |
+
"loss": 0.1449,
|
| 7854 |
+
"step": 10270
|
| 7855 |
+
},
|
| 7856 |
+
{
|
| 7857 |
+
"epoch": 4.817244611059044,
|
| 7858 |
+
"grad_norm": 3.047879219055176,
|
| 7859 |
+
"learning_rate": 9.39784442361762e-06,
|
| 7860 |
+
"loss": 0.1438,
|
| 7861 |
+
"step": 10280
|
| 7862 |
+
},
|
| 7863 |
+
{
|
| 7864 |
+
"epoch": 4.821930646672914,
|
| 7865 |
+
"grad_norm": 3.29184889793396,
|
| 7866 |
+
"learning_rate": 9.397258669165887e-06,
|
| 7867 |
+
"loss": 0.1794,
|
| 7868 |
+
"step": 10290
|
| 7869 |
+
},
|
| 7870 |
+
{
|
| 7871 |
+
"epoch": 4.826616682286786,
|
| 7872 |
+
"grad_norm": 2.301718235015869,
|
| 7873 |
+
"learning_rate": 9.396672914714152e-06,
|
| 7874 |
+
"loss": 0.1511,
|
| 7875 |
+
"step": 10300
|
| 7876 |
+
},
|
| 7877 |
+
{
|
| 7878 |
+
"epoch": 4.831302717900656,
|
| 7879 |
+
"grad_norm": 3.2951526641845703,
|
| 7880 |
+
"learning_rate": 9.396087160262419e-06,
|
| 7881 |
+
"loss": 0.1624,
|
| 7882 |
+
"step": 10310
|
| 7883 |
+
},
|
| 7884 |
+
{
|
| 7885 |
+
"epoch": 4.835988753514527,
|
| 7886 |
+
"grad_norm": 2.597886800765991,
|
| 7887 |
+
"learning_rate": 9.395501405810686e-06,
|
| 7888 |
+
"loss": 0.1464,
|
| 7889 |
+
"step": 10320
|
| 7890 |
+
},
|
| 7891 |
+
{
|
| 7892 |
+
"epoch": 4.840674789128397,
|
| 7893 |
+
"grad_norm": 2.1214399337768555,
|
| 7894 |
+
"learning_rate": 9.394915651358951e-06,
|
| 7895 |
+
"loss": 0.1434,
|
| 7896 |
+
"step": 10330
|
| 7897 |
+
},
|
| 7898 |
+
{
|
| 7899 |
+
"epoch": 4.845360824742268,
|
| 7900 |
+
"grad_norm": 2.453712224960327,
|
| 7901 |
+
"learning_rate": 9.394329896907216e-06,
|
| 7902 |
+
"loss": 0.145,
|
| 7903 |
+
"step": 10340
|
| 7904 |
+
},
|
| 7905 |
+
{
|
| 7906 |
+
"epoch": 4.850046860356139,
|
| 7907 |
+
"grad_norm": 1.6721562147140503,
|
| 7908 |
+
"learning_rate": 9.393744142455483e-06,
|
| 7909 |
+
"loss": 0.1481,
|
| 7910 |
+
"step": 10350
|
| 7911 |
+
},
|
| 7912 |
+
{
|
| 7913 |
+
"epoch": 4.85473289597001,
|
| 7914 |
+
"grad_norm": 3.1657016277313232,
|
| 7915 |
+
"learning_rate": 9.393158388003748e-06,
|
| 7916 |
+
"loss": 0.1661,
|
| 7917 |
+
"step": 10360
|
| 7918 |
+
},
|
| 7919 |
+
{
|
| 7920 |
+
"epoch": 4.85941893158388,
|
| 7921 |
+
"grad_norm": 2.637096881866455,
|
| 7922 |
+
"learning_rate": 9.392572633552015e-06,
|
| 7923 |
+
"loss": 0.1445,
|
| 7924 |
+
"step": 10370
|
| 7925 |
+
},
|
| 7926 |
+
{
|
| 7927 |
+
"epoch": 4.8641049671977505,
|
| 7928 |
+
"grad_norm": 2.9260575771331787,
|
| 7929 |
+
"learning_rate": 9.391986879100282e-06,
|
| 7930 |
+
"loss": 0.1446,
|
| 7931 |
+
"step": 10380
|
| 7932 |
+
},
|
| 7933 |
+
{
|
| 7934 |
+
"epoch": 4.868791002811621,
|
| 7935 |
+
"grad_norm": 2.740488052368164,
|
| 7936 |
+
"learning_rate": 9.391401124648548e-06,
|
| 7937 |
+
"loss": 0.1233,
|
| 7938 |
+
"step": 10390
|
| 7939 |
+
},
|
| 7940 |
+
{
|
| 7941 |
+
"epoch": 4.873477038425492,
|
| 7942 |
+
"grad_norm": 3.028416156768799,
|
| 7943 |
+
"learning_rate": 9.390815370196814e-06,
|
| 7944 |
+
"loss": 0.1496,
|
| 7945 |
+
"step": 10400
|
| 7946 |
+
},
|
| 7947 |
+
{
|
| 7948 |
+
"epoch": 4.878163074039363,
|
| 7949 |
+
"grad_norm": 2.666135787963867,
|
| 7950 |
+
"learning_rate": 9.39022961574508e-06,
|
| 7951 |
+
"loss": 0.1509,
|
| 7952 |
+
"step": 10410
|
| 7953 |
+
},
|
| 7954 |
+
{
|
| 7955 |
+
"epoch": 4.882849109653233,
|
| 7956 |
+
"grad_norm": 1.6811872720718384,
|
| 7957 |
+
"learning_rate": 9.389643861293347e-06,
|
| 7958 |
+
"loss": 0.1288,
|
| 7959 |
+
"step": 10420
|
| 7960 |
+
},
|
| 7961 |
+
{
|
| 7962 |
+
"epoch": 4.887535145267104,
|
| 7963 |
+
"grad_norm": 3.225088357925415,
|
| 7964 |
+
"learning_rate": 9.389058106841614e-06,
|
| 7965 |
+
"loss": 0.1674,
|
| 7966 |
+
"step": 10430
|
| 7967 |
+
},
|
| 7968 |
+
{
|
| 7969 |
+
"epoch": 4.892221180880974,
|
| 7970 |
+
"grad_norm": 2.038783311843872,
|
| 7971 |
+
"learning_rate": 9.388472352389879e-06,
|
| 7972 |
+
"loss": 0.1628,
|
| 7973 |
+
"step": 10440
|
| 7974 |
+
},
|
| 7975 |
+
{
|
| 7976 |
+
"epoch": 4.896907216494846,
|
| 7977 |
+
"grad_norm": 2.5650861263275146,
|
| 7978 |
+
"learning_rate": 9.387886597938146e-06,
|
| 7979 |
+
"loss": 0.1423,
|
| 7980 |
+
"step": 10450
|
| 7981 |
+
},
|
| 7982 |
+
{
|
| 7983 |
+
"epoch": 4.901593252108716,
|
| 7984 |
+
"grad_norm": 2.9860751628875732,
|
| 7985 |
+
"learning_rate": 9.387300843486411e-06,
|
| 7986 |
+
"loss": 0.14,
|
| 7987 |
+
"step": 10460
|
| 7988 |
+
},
|
| 7989 |
+
{
|
| 7990 |
+
"epoch": 4.906279287722587,
|
| 7991 |
+
"grad_norm": 2.6722230911254883,
|
| 7992 |
+
"learning_rate": 9.386715089034678e-06,
|
| 7993 |
+
"loss": 0.1416,
|
| 7994 |
+
"step": 10470
|
| 7995 |
+
},
|
| 7996 |
+
{
|
| 7997 |
+
"epoch": 4.910965323336457,
|
| 7998 |
+
"grad_norm": 2.631300926208496,
|
| 7999 |
+
"learning_rate": 9.386129334582945e-06,
|
| 8000 |
+
"loss": 0.1482,
|
| 8001 |
+
"step": 10480
|
| 8002 |
+
},
|
| 8003 |
+
{
|
| 8004 |
+
"epoch": 4.915651358950328,
|
| 8005 |
+
"grad_norm": 2.792668104171753,
|
| 8006 |
+
"learning_rate": 9.38554358013121e-06,
|
| 8007 |
+
"loss": 0.1639,
|
| 8008 |
+
"step": 10490
|
| 8009 |
+
},
|
| 8010 |
+
{
|
| 8011 |
+
"epoch": 4.920337394564199,
|
| 8012 |
+
"grad_norm": 2.3472137451171875,
|
| 8013 |
+
"learning_rate": 9.384957825679475e-06,
|
| 8014 |
+
"loss": 0.1382,
|
| 8015 |
+
"step": 10500
|
| 8016 |
+
},
|
| 8017 |
+
{
|
| 8018 |
+
"epoch": 4.920337394564199,
|
| 8019 |
+
"eval_loss": 0.04462406784296036,
|
| 8020 |
+
"eval_pearson_cosine": 0.7824275239321139,
|
| 8021 |
+
"eval_pearson_dot": 0.6329557539240795,
|
| 8022 |
+
"eval_pearson_euclidean": 0.7443049370608668,
|
| 8023 |
+
"eval_pearson_manhattan": 0.7436570805807037,
|
| 8024 |
+
"eval_runtime": 39.5855,
|
| 8025 |
+
"eval_samples_per_second": 37.893,
|
| 8026 |
+
"eval_spearman_cosine": 0.7871549274543737,
|
| 8027 |
+
"eval_spearman_dot": 0.6424130372572389,
|
| 8028 |
+
"eval_spearman_euclidean": 0.7624881768092765,
|
| 8029 |
+
"eval_spearman_manhattan": 0.7619956515478402,
|
| 8030 |
+
"eval_steps_per_second": 37.893,
|
| 8031 |
+
"step": 10500
|
| 8032 |
+
},
|
| 8033 |
+
{
|
| 8034 |
+
"epoch": 4.9250234301780695,
|
| 8035 |
+
"grad_norm": 2.011869192123413,
|
| 8036 |
+
"learning_rate": 9.384372071227742e-06,
|
| 8037 |
+
"loss": 0.1682,
|
| 8038 |
+
"step": 10510
|
| 8039 |
+
},
|
| 8040 |
+
{
|
| 8041 |
+
"epoch": 4.92970946579194,
|
| 8042 |
+
"grad_norm": 2.2601213455200195,
|
| 8043 |
+
"learning_rate": 9.383786316776007e-06,
|
| 8044 |
+
"loss": 0.1386,
|
| 8045 |
+
"step": 10520
|
| 8046 |
+
},
|
| 8047 |
+
{
|
| 8048 |
+
"epoch": 4.9343955014058105,
|
| 8049 |
+
"grad_norm": 3.00738263130188,
|
| 8050 |
+
"learning_rate": 9.383200562324274e-06,
|
| 8051 |
+
"loss": 0.1712,
|
| 8052 |
+
"step": 10530
|
| 8053 |
+
},
|
| 8054 |
+
{
|
| 8055 |
+
"epoch": 4.939081537019681,
|
| 8056 |
+
"grad_norm": 2.7528035640716553,
|
| 8057 |
+
"learning_rate": 9.382614807872541e-06,
|
| 8058 |
+
"loss": 0.163,
|
| 8059 |
+
"step": 10540
|
| 8060 |
+
},
|
| 8061 |
+
{
|
| 8062 |
+
"epoch": 4.943767572633552,
|
| 8063 |
+
"grad_norm": 2.2604238986968994,
|
| 8064 |
+
"learning_rate": 9.382029053420806e-06,
|
| 8065 |
+
"loss": 0.1638,
|
| 8066 |
+
"step": 10550
|
| 8067 |
+
},
|
| 8068 |
+
{
|
| 8069 |
+
"epoch": 4.948453608247423,
|
| 8070 |
+
"grad_norm": 2.3817455768585205,
|
| 8071 |
+
"learning_rate": 9.381443298969073e-06,
|
| 8072 |
+
"loss": 0.1478,
|
| 8073 |
+
"step": 10560
|
| 8074 |
+
},
|
| 8075 |
+
{
|
| 8076 |
+
"epoch": 4.953139643861293,
|
| 8077 |
+
"grad_norm": 2.392261028289795,
|
| 8078 |
+
"learning_rate": 9.380857544517338e-06,
|
| 8079 |
+
"loss": 0.1521,
|
| 8080 |
+
"step": 10570
|
| 8081 |
+
},
|
| 8082 |
+
{
|
| 8083 |
+
"epoch": 4.957825679475164,
|
| 8084 |
+
"grad_norm": 2.8620009422302246,
|
| 8085 |
+
"learning_rate": 9.380271790065605e-06,
|
| 8086 |
+
"loss": 0.1477,
|
| 8087 |
+
"step": 10580
|
| 8088 |
+
},
|
| 8089 |
+
{
|
| 8090 |
+
"epoch": 4.962511715089034,
|
| 8091 |
+
"grad_norm": 2.658115863800049,
|
| 8092 |
+
"learning_rate": 9.379686035613872e-06,
|
| 8093 |
+
"loss": 0.1251,
|
| 8094 |
+
"step": 10590
|
| 8095 |
+
},
|
| 8096 |
+
{
|
| 8097 |
+
"epoch": 4.967197750702906,
|
| 8098 |
+
"grad_norm": 2.8949685096740723,
|
| 8099 |
+
"learning_rate": 9.379100281162138e-06,
|
| 8100 |
+
"loss": 0.1595,
|
| 8101 |
+
"step": 10600
|
| 8102 |
+
},
|
| 8103 |
+
{
|
| 8104 |
+
"epoch": 4.971883786316776,
|
| 8105 |
+
"grad_norm": 2.472933292388916,
|
| 8106 |
+
"learning_rate": 9.378514526710404e-06,
|
| 8107 |
+
"loss": 0.1611,
|
| 8108 |
+
"step": 10610
|
| 8109 |
+
},
|
| 8110 |
+
{
|
| 8111 |
+
"epoch": 4.976569821930647,
|
| 8112 |
+
"grad_norm": 2.650047540664673,
|
| 8113 |
+
"learning_rate": 9.37792877225867e-06,
|
| 8114 |
+
"loss": 0.1483,
|
| 8115 |
+
"step": 10620
|
| 8116 |
+
},
|
| 8117 |
+
{
|
| 8118 |
+
"epoch": 4.981255857544517,
|
| 8119 |
+
"grad_norm": 2.293938398361206,
|
| 8120 |
+
"learning_rate": 9.377343017806937e-06,
|
| 8121 |
+
"loss": 0.1535,
|
| 8122 |
+
"step": 10630
|
| 8123 |
+
},
|
| 8124 |
+
{
|
| 8125 |
+
"epoch": 4.985941893158388,
|
| 8126 |
+
"grad_norm": 2.1445188522338867,
|
| 8127 |
+
"learning_rate": 9.376757263355202e-06,
|
| 8128 |
+
"loss": 0.1562,
|
| 8129 |
+
"step": 10640
|
| 8130 |
+
},
|
| 8131 |
+
{
|
| 8132 |
+
"epoch": 4.990627928772259,
|
| 8133 |
+
"grad_norm": 1.898871660232544,
|
| 8134 |
+
"learning_rate": 9.376171508903469e-06,
|
| 8135 |
+
"loss": 0.16,
|
| 8136 |
+
"step": 10650
|
| 8137 |
+
},
|
| 8138 |
+
{
|
| 8139 |
+
"epoch": 4.9953139643861295,
|
| 8140 |
+
"grad_norm": 1.8987932205200195,
|
| 8141 |
+
"learning_rate": 9.375585754451734e-06,
|
| 8142 |
+
"loss": 0.1348,
|
| 8143 |
+
"step": 10660
|
| 8144 |
+
},
|
| 8145 |
+
{
|
| 8146 |
+
"epoch": 5.0,
|
| 8147 |
+
"grad_norm": 1.9247934818267822,
|
| 8148 |
+
"learning_rate": 9.375000000000001e-06,
|
| 8149 |
+
"loss": 0.1357,
|
| 8150 |
+
"step": 10670
|
| 8151 |
+
},
|
| 8152 |
+
{
|
| 8153 |
+
"epoch": 5.0046860356138705,
|
| 8154 |
+
"grad_norm": 2.254408836364746,
|
| 8155 |
+
"learning_rate": 9.374414245548266e-06,
|
| 8156 |
+
"loss": 0.0979,
|
| 8157 |
+
"step": 10680
|
| 8158 |
+
},
|
| 8159 |
+
{
|
| 8160 |
+
"epoch": 5.009372071227741,
|
| 8161 |
+
"grad_norm": 2.336634874343872,
|
| 8162 |
+
"learning_rate": 9.373828491096533e-06,
|
| 8163 |
+
"loss": 0.1008,
|
| 8164 |
+
"step": 10690
|
| 8165 |
+
},
|
| 8166 |
+
{
|
| 8167 |
+
"epoch": 5.014058106841612,
|
| 8168 |
+
"grad_norm": 2.0158193111419678,
|
| 8169 |
+
"learning_rate": 9.3732427366448e-06,
|
| 8170 |
+
"loss": 0.1206,
|
| 8171 |
+
"step": 10700
|
| 8172 |
+
},
|
| 8173 |
+
{
|
| 8174 |
+
"epoch": 5.018744142455483,
|
| 8175 |
+
"grad_norm": 2.12335205078125,
|
| 8176 |
+
"learning_rate": 9.372656982193065e-06,
|
| 8177 |
+
"loss": 0.1153,
|
| 8178 |
+
"step": 10710
|
| 8179 |
+
},
|
| 8180 |
+
{
|
| 8181 |
+
"epoch": 5.023430178069353,
|
| 8182 |
+
"grad_norm": 1.9908068180084229,
|
| 8183 |
+
"learning_rate": 9.372071227741332e-06,
|
| 8184 |
+
"loss": 0.096,
|
| 8185 |
+
"step": 10720
|
| 8186 |
+
},
|
| 8187 |
+
{
|
| 8188 |
+
"epoch": 5.028116213683224,
|
| 8189 |
+
"grad_norm": 2.713801145553589,
|
| 8190 |
+
"learning_rate": 9.371485473289597e-06,
|
| 8191 |
+
"loss": 0.1183,
|
| 8192 |
+
"step": 10730
|
| 8193 |
+
},
|
| 8194 |
+
{
|
| 8195 |
+
"epoch": 5.032802249297094,
|
| 8196 |
+
"grad_norm": 1.922958493232727,
|
| 8197 |
+
"learning_rate": 9.370899718837864e-06,
|
| 8198 |
+
"loss": 0.0975,
|
| 8199 |
+
"step": 10740
|
| 8200 |
+
},
|
| 8201 |
+
{
|
| 8202 |
+
"epoch": 5.037488284910966,
|
| 8203 |
+
"grad_norm": 1.787152647972107,
|
| 8204 |
+
"learning_rate": 9.37031396438613e-06,
|
| 8205 |
+
"loss": 0.1109,
|
| 8206 |
+
"step": 10750
|
| 8207 |
+
},
|
| 8208 |
+
{
|
| 8209 |
+
"epoch": 5.037488284910966,
|
| 8210 |
+
"eval_loss": 0.042590245604515076,
|
| 8211 |
+
"eval_pearson_cosine": 0.7796460620464813,
|
| 8212 |
+
"eval_pearson_dot": 0.6195124617279077,
|
| 8213 |
+
"eval_pearson_euclidean": 0.7433733944090761,
|
| 8214 |
+
"eval_pearson_manhattan": 0.7430945401829945,
|
| 8215 |
+
"eval_runtime": 39.7087,
|
| 8216 |
+
"eval_samples_per_second": 37.775,
|
| 8217 |
+
"eval_spearman_cosine": 0.7845566035417548,
|
| 8218 |
+
"eval_spearman_dot": 0.6248763613915714,
|
| 8219 |
+
"eval_spearman_euclidean": 0.7601630737316083,
|
| 8220 |
+
"eval_spearman_manhattan": 0.7599814027838542,
|
| 8221 |
+
"eval_steps_per_second": 37.775,
|
| 8222 |
+
"step": 10750
|
| 8223 |
+
},
|
| 8224 |
+
{
|
| 8225 |
+
"epoch": 5.042174320524836,
|
| 8226 |
+
"grad_norm": 2.3772122859954834,
|
| 8227 |
+
"learning_rate": 9.369728209934396e-06,
|
| 8228 |
+
"loss": 0.1063,
|
| 8229 |
+
"step": 10760
|
| 8230 |
+
},
|
| 8231 |
+
{
|
| 8232 |
+
"epoch": 5.046860356138707,
|
| 8233 |
+
"grad_norm": 2.4249303340911865,
|
| 8234 |
+
"learning_rate": 9.369142455482663e-06,
|
| 8235 |
+
"loss": 0.0909,
|
| 8236 |
+
"step": 10770
|
| 8237 |
+
},
|
| 8238 |
+
{
|
| 8239 |
+
"epoch": 5.051546391752577,
|
| 8240 |
+
"grad_norm": 2.354619264602661,
|
| 8241 |
+
"learning_rate": 9.368556701030928e-06,
|
| 8242 |
+
"loss": 0.1121,
|
| 8243 |
+
"step": 10780
|
| 8244 |
+
},
|
| 8245 |
+
{
|
| 8246 |
+
"epoch": 5.056232427366448,
|
| 8247 |
+
"grad_norm": 2.3761093616485596,
|
| 8248 |
+
"learning_rate": 9.367970946579195e-06,
|
| 8249 |
+
"loss": 0.0962,
|
| 8250 |
+
"step": 10790
|
| 8251 |
+
},
|
| 8252 |
+
{
|
| 8253 |
+
"epoch": 5.060918462980319,
|
| 8254 |
+
"grad_norm": 1.9781490564346313,
|
| 8255 |
+
"learning_rate": 9.36738519212746e-06,
|
| 8256 |
+
"loss": 0.1159,
|
| 8257 |
+
"step": 10800
|
| 8258 |
+
},
|
| 8259 |
+
{
|
| 8260 |
+
"epoch": 5.0656044985941895,
|
| 8261 |
+
"grad_norm": 2.9498939514160156,
|
| 8262 |
+
"learning_rate": 9.366799437675728e-06,
|
| 8263 |
+
"loss": 0.1046,
|
| 8264 |
+
"step": 10810
|
| 8265 |
+
},
|
| 8266 |
+
{
|
| 8267 |
+
"epoch": 5.07029053420806,
|
| 8268 |
+
"grad_norm": 1.618909478187561,
|
| 8269 |
+
"learning_rate": 9.366213683223993e-06,
|
| 8270 |
+
"loss": 0.1145,
|
| 8271 |
+
"step": 10820
|
| 8272 |
+
},
|
| 8273 |
+
{
|
| 8274 |
+
"epoch": 5.0749765698219305,
|
| 8275 |
+
"grad_norm": 1.5350381135940552,
|
| 8276 |
+
"learning_rate": 9.36562792877226e-06,
|
| 8277 |
+
"loss": 0.125,
|
| 8278 |
+
"step": 10830
|
| 8279 |
+
},
|
| 8280 |
+
{
|
| 8281 |
+
"epoch": 5.079662605435801,
|
| 8282 |
+
"grad_norm": 2.1376562118530273,
|
| 8283 |
+
"learning_rate": 9.365042174320525e-06,
|
| 8284 |
+
"loss": 0.11,
|
| 8285 |
+
"step": 10840
|
| 8286 |
+
},
|
| 8287 |
+
{
|
| 8288 |
+
"epoch": 5.084348641049672,
|
| 8289 |
+
"grad_norm": 2.638848066329956,
|
| 8290 |
+
"learning_rate": 9.364456419868792e-06,
|
| 8291 |
+
"loss": 0.1257,
|
| 8292 |
+
"step": 10850
|
| 8293 |
+
},
|
| 8294 |
+
{
|
| 8295 |
+
"epoch": 5.089034676663543,
|
| 8296 |
+
"grad_norm": 2.5730180740356445,
|
| 8297 |
+
"learning_rate": 9.363870665417057e-06,
|
| 8298 |
+
"loss": 0.1131,
|
| 8299 |
+
"step": 10860
|
| 8300 |
+
},
|
| 8301 |
+
{
|
| 8302 |
+
"epoch": 5.093720712277413,
|
| 8303 |
+
"grad_norm": 1.658488392829895,
|
| 8304 |
+
"learning_rate": 9.363284910965324e-06,
|
| 8305 |
+
"loss": 0.1095,
|
| 8306 |
+
"step": 10870
|
| 8307 |
+
},
|
| 8308 |
+
{
|
| 8309 |
+
"epoch": 5.098406747891284,
|
| 8310 |
+
"grad_norm": 2.5831501483917236,
|
| 8311 |
+
"learning_rate": 9.362699156513591e-06,
|
| 8312 |
+
"loss": 0.1159,
|
| 8313 |
+
"step": 10880
|
| 8314 |
+
},
|
| 8315 |
+
{
|
| 8316 |
+
"epoch": 5.103092783505154,
|
| 8317 |
+
"grad_norm": 1.3760308027267456,
|
| 8318 |
+
"learning_rate": 9.362113402061856e-06,
|
| 8319 |
+
"loss": 0.1052,
|
| 8320 |
+
"step": 10890
|
| 8321 |
+
},
|
| 8322 |
+
{
|
| 8323 |
+
"epoch": 5.107778819119026,
|
| 8324 |
+
"grad_norm": 1.529236078262329,
|
| 8325 |
+
"learning_rate": 9.361527647610123e-06,
|
| 8326 |
+
"loss": 0.1132,
|
| 8327 |
+
"step": 10900
|
| 8328 |
+
},
|
| 8329 |
+
{
|
| 8330 |
+
"epoch": 5.112464854732896,
|
| 8331 |
+
"grad_norm": 1.9166224002838135,
|
| 8332 |
+
"learning_rate": 9.360941893158388e-06,
|
| 8333 |
+
"loss": 0.1142,
|
| 8334 |
+
"step": 10910
|
| 8335 |
+
},
|
| 8336 |
+
{
|
| 8337 |
+
"epoch": 5.117150890346767,
|
| 8338 |
+
"grad_norm": 2.521615505218506,
|
| 8339 |
+
"learning_rate": 9.360356138706655e-06,
|
| 8340 |
+
"loss": 0.1222,
|
| 8341 |
+
"step": 10920
|
| 8342 |
+
},
|
| 8343 |
+
{
|
| 8344 |
+
"epoch": 5.121836925960637,
|
| 8345 |
+
"grad_norm": 2.1560580730438232,
|
| 8346 |
+
"learning_rate": 9.359770384254922e-06,
|
| 8347 |
+
"loss": 0.1081,
|
| 8348 |
+
"step": 10930
|
| 8349 |
+
},
|
| 8350 |
+
{
|
| 8351 |
+
"epoch": 5.126522961574508,
|
| 8352 |
+
"grad_norm": 1.3674089908599854,
|
| 8353 |
+
"learning_rate": 9.359184629803187e-06,
|
| 8354 |
+
"loss": 0.1198,
|
| 8355 |
+
"step": 10940
|
| 8356 |
+
},
|
| 8357 |
+
{
|
| 8358 |
+
"epoch": 5.131208997188379,
|
| 8359 |
+
"grad_norm": 2.396967649459839,
|
| 8360 |
+
"learning_rate": 9.358598875351454e-06,
|
| 8361 |
+
"loss": 0.1101,
|
| 8362 |
+
"step": 10950
|
| 8363 |
+
},
|
| 8364 |
+
{
|
| 8365 |
+
"epoch": 5.1358950328022495,
|
| 8366 |
+
"grad_norm": 1.6446019411087036,
|
| 8367 |
+
"learning_rate": 9.35801312089972e-06,
|
| 8368 |
+
"loss": 0.096,
|
| 8369 |
+
"step": 10960
|
| 8370 |
+
},
|
| 8371 |
+
{
|
| 8372 |
+
"epoch": 5.14058106841612,
|
| 8373 |
+
"grad_norm": 2.565040349960327,
|
| 8374 |
+
"learning_rate": 9.357427366447985e-06,
|
| 8375 |
+
"loss": 0.1047,
|
| 8376 |
+
"step": 10970
|
| 8377 |
+
},
|
| 8378 |
+
{
|
| 8379 |
+
"epoch": 5.14526710402999,
|
| 8380 |
+
"grad_norm": 1.8515427112579346,
|
| 8381 |
+
"learning_rate": 9.356841611996252e-06,
|
| 8382 |
+
"loss": 0.0955,
|
| 8383 |
+
"step": 10980
|
| 8384 |
+
},
|
| 8385 |
+
{
|
| 8386 |
+
"epoch": 5.149953139643861,
|
| 8387 |
+
"grad_norm": 2.294940233230591,
|
| 8388 |
+
"learning_rate": 9.356255857544518e-06,
|
| 8389 |
+
"loss": 0.1212,
|
| 8390 |
+
"step": 10990
|
| 8391 |
+
},
|
| 8392 |
+
{
|
| 8393 |
+
"epoch": 5.154639175257732,
|
| 8394 |
+
"grad_norm": 1.995937466621399,
|
| 8395 |
+
"learning_rate": 9.355670103092784e-06,
|
| 8396 |
+
"loss": 0.1009,
|
| 8397 |
+
"step": 11000
|
| 8398 |
+
},
|
| 8399 |
+
{
|
| 8400 |
+
"epoch": 5.154639175257732,
|
| 8401 |
+
"eval_loss": 0.04305338114500046,
|
| 8402 |
+
"eval_pearson_cosine": 0.780686355713101,
|
| 8403 |
+
"eval_pearson_dot": 0.6237317182336994,
|
| 8404 |
+
"eval_pearson_euclidean": 0.7427541562137776,
|
| 8405 |
+
"eval_pearson_manhattan": 0.7423336637021691,
|
| 8406 |
+
"eval_runtime": 40.3116,
|
| 8407 |
+
"eval_samples_per_second": 37.21,
|
| 8408 |
+
"eval_spearman_cosine": 0.7834710778584321,
|
| 8409 |
+
"eval_spearman_dot": 0.637744309819412,
|
| 8410 |
+
"eval_spearman_euclidean": 0.7591336014689473,
|
| 8411 |
+
"eval_spearman_manhattan": 0.7590724893258253,
|
| 8412 |
+
"eval_steps_per_second": 37.21,
|
| 8413 |
+
"step": 11000
|
| 8414 |
}
|
| 8415 |
],
|
| 8416 |
"logging_steps": 10,
|