Training in progress, step 9000, 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 536223056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ab362d2b3f9dedf1f0f43335f7b06eefee0b16e014fc83df80bc46c1b6044cf
|
| 3 |
size 536223056
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1072594443
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b116e5cf316372406a0b75f20675173ce00a1448ad26470e8baba7a28543337c
|
| 3 |
size 1072594443
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:553711fa7348e1460e8e11ff55c1e2ba08096c9266ea56894e269e1a647bd7f3
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 1.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -7658,6 +7658,456 @@
|
|
| 7658 |
"mean_token_accuracy": 0.7890658736228943,
|
| 7659 |
"num_tokens": 9414095.0,
|
| 7660 |
"step": 8500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7661 |
}
|
| 7662 |
],
|
| 7663 |
"logging_steps": 10,
|
|
@@ -7677,7 +8127,7 @@
|
|
| 7677 |
"attributes": {}
|
| 7678 |
}
|
| 7679 |
},
|
| 7680 |
-
"total_flos": 1.
|
| 7681 |
"train_batch_size": 8,
|
| 7682 |
"trial_name": null,
|
| 7683 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.8134193028410235,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7658 |
"mean_token_accuracy": 0.7890658736228943,
|
| 7659 |
"num_tokens": 9414095.0,
|
| 7660 |
"step": 8500
|
| 7661 |
+
},
|
| 7662 |
+
{
|
| 7663 |
+
"epoch": 1.7146886963530124,
|
| 7664 |
+
"grad_norm": 10.6875,
|
| 7665 |
+
"learning_rate": 8.570085297870913e-06,
|
| 7666 |
+
"loss": 0.7469,
|
| 7667 |
+
"mean_token_accuracy": 0.8128379642963409,
|
| 7668 |
+
"num_tokens": 9425228.0,
|
| 7669 |
+
"step": 8510
|
| 7670 |
+
},
|
| 7671 |
+
{
|
| 7672 |
+
"epoch": 1.7167036066895023,
|
| 7673 |
+
"grad_norm": 11.5625,
|
| 7674 |
+
"learning_rate": 8.556652562294312e-06,
|
| 7675 |
+
"loss": 0.8635,
|
| 7676 |
+
"mean_token_accuracy": 0.7921235024929046,
|
| 7677 |
+
"num_tokens": 9436032.0,
|
| 7678 |
+
"step": 8520
|
| 7679 |
+
},
|
| 7680 |
+
{
|
| 7681 |
+
"epoch": 1.7187185170259922,
|
| 7682 |
+
"grad_norm": 11.5,
|
| 7683 |
+
"learning_rate": 8.54321982671771e-06,
|
| 7684 |
+
"loss": 0.888,
|
| 7685 |
+
"mean_token_accuracy": 0.7825378775596619,
|
| 7686 |
+
"num_tokens": 9447102.0,
|
| 7687 |
+
"step": 8530
|
| 7688 |
+
},
|
| 7689 |
+
{
|
| 7690 |
+
"epoch": 1.7207334273624824,
|
| 7691 |
+
"grad_norm": 13.25,
|
| 7692 |
+
"learning_rate": 8.529787091141111e-06,
|
| 7693 |
+
"loss": 0.774,
|
| 7694 |
+
"mean_token_accuracy": 0.809429943561554,
|
| 7695 |
+
"num_tokens": 9456885.0,
|
| 7696 |
+
"step": 8540
|
| 7697 |
+
},
|
| 7698 |
+
{
|
| 7699 |
+
"epoch": 1.7227483376989725,
|
| 7700 |
+
"grad_norm": 10.9375,
|
| 7701 |
+
"learning_rate": 8.516354355564512e-06,
|
| 7702 |
+
"loss": 0.8615,
|
| 7703 |
+
"mean_token_accuracy": 0.7885714650154114,
|
| 7704 |
+
"num_tokens": 9469044.0,
|
| 7705 |
+
"step": 8550
|
| 7706 |
+
},
|
| 7707 |
+
{
|
| 7708 |
+
"epoch": 1.7247632480354624,
|
| 7709 |
+
"grad_norm": 11.75,
|
| 7710 |
+
"learning_rate": 8.502921619987912e-06,
|
| 7711 |
+
"loss": 0.844,
|
| 7712 |
+
"mean_token_accuracy": 0.7914490044116974,
|
| 7713 |
+
"num_tokens": 9480822.0,
|
| 7714 |
+
"step": 8560
|
| 7715 |
+
},
|
| 7716 |
+
{
|
| 7717 |
+
"epoch": 1.7267781583719524,
|
| 7718 |
+
"grad_norm": 12.0,
|
| 7719 |
+
"learning_rate": 8.489488884411311e-06,
|
| 7720 |
+
"loss": 0.8777,
|
| 7721 |
+
"mean_token_accuracy": 0.7846565127372742,
|
| 7722 |
+
"num_tokens": 9491344.0,
|
| 7723 |
+
"step": 8570
|
| 7724 |
+
},
|
| 7725 |
+
{
|
| 7726 |
+
"epoch": 1.7287930687084425,
|
| 7727 |
+
"grad_norm": 12.0,
|
| 7728 |
+
"learning_rate": 8.47605614883471e-06,
|
| 7729 |
+
"loss": 0.739,
|
| 7730 |
+
"mean_token_accuracy": 0.8153780162334442,
|
| 7731 |
+
"num_tokens": 9501669.0,
|
| 7732 |
+
"step": 8580
|
| 7733 |
+
},
|
| 7734 |
+
{
|
| 7735 |
+
"epoch": 1.7308079790449327,
|
| 7736 |
+
"grad_norm": 12.25,
|
| 7737 |
+
"learning_rate": 8.46262341325811e-06,
|
| 7738 |
+
"loss": 0.8505,
|
| 7739 |
+
"mean_token_accuracy": 0.7858089745044708,
|
| 7740 |
+
"num_tokens": 9512619.0,
|
| 7741 |
+
"step": 8590
|
| 7742 |
+
},
|
| 7743 |
+
{
|
| 7744 |
+
"epoch": 1.7328228893814224,
|
| 7745 |
+
"grad_norm": 11.0,
|
| 7746 |
+
"learning_rate": 8.44919067768151e-06,
|
| 7747 |
+
"loss": 0.9526,
|
| 7748 |
+
"mean_token_accuracy": 0.7702113807201385,
|
| 7749 |
+
"num_tokens": 9525285.0,
|
| 7750 |
+
"step": 8600
|
| 7751 |
+
},
|
| 7752 |
+
{
|
| 7753 |
+
"epoch": 1.7348377997179125,
|
| 7754 |
+
"grad_norm": 12.3125,
|
| 7755 |
+
"learning_rate": 8.43575794210491e-06,
|
| 7756 |
+
"loss": 0.8298,
|
| 7757 |
+
"mean_token_accuracy": 0.7936967372894287,
|
| 7758 |
+
"num_tokens": 9536607.0,
|
| 7759 |
+
"step": 8610
|
| 7760 |
+
},
|
| 7761 |
+
{
|
| 7762 |
+
"epoch": 1.7368527100544027,
|
| 7763 |
+
"grad_norm": 11.875,
|
| 7764 |
+
"learning_rate": 8.42232520652831e-06,
|
| 7765 |
+
"loss": 0.8394,
|
| 7766 |
+
"mean_token_accuracy": 0.7899468779563904,
|
| 7767 |
+
"num_tokens": 9547548.0,
|
| 7768 |
+
"step": 8620
|
| 7769 |
+
},
|
| 7770 |
+
{
|
| 7771 |
+
"epoch": 1.7388676203908926,
|
| 7772 |
+
"grad_norm": 10.875,
|
| 7773 |
+
"learning_rate": 8.40889247095171e-06,
|
| 7774 |
+
"loss": 0.7908,
|
| 7775 |
+
"mean_token_accuracy": 0.7996328830718994,
|
| 7776 |
+
"num_tokens": 9559379.0,
|
| 7777 |
+
"step": 8630
|
| 7778 |
+
},
|
| 7779 |
+
{
|
| 7780 |
+
"epoch": 1.7408825307273825,
|
| 7781 |
+
"grad_norm": 11.5,
|
| 7782 |
+
"learning_rate": 8.39545973537511e-06,
|
| 7783 |
+
"loss": 0.7211,
|
| 7784 |
+
"mean_token_accuracy": 0.815495389699936,
|
| 7785 |
+
"num_tokens": 9569522.0,
|
| 7786 |
+
"step": 8640
|
| 7787 |
+
},
|
| 7788 |
+
{
|
| 7789 |
+
"epoch": 1.7428974410638727,
|
| 7790 |
+
"grad_norm": 13.4375,
|
| 7791 |
+
"learning_rate": 8.382026999798509e-06,
|
| 7792 |
+
"loss": 0.8985,
|
| 7793 |
+
"mean_token_accuracy": 0.7802120566368103,
|
| 7794 |
+
"num_tokens": 9580936.0,
|
| 7795 |
+
"step": 8650
|
| 7796 |
+
},
|
| 7797 |
+
{
|
| 7798 |
+
"epoch": 1.7449123514003628,
|
| 7799 |
+
"grad_norm": 11.625,
|
| 7800 |
+
"learning_rate": 8.36859426422191e-06,
|
| 7801 |
+
"loss": 0.8709,
|
| 7802 |
+
"mean_token_accuracy": 0.7891122341156006,
|
| 7803 |
+
"num_tokens": 9592276.0,
|
| 7804 |
+
"step": 8660
|
| 7805 |
+
},
|
| 7806 |
+
{
|
| 7807 |
+
"epoch": 1.7469272617368528,
|
| 7808 |
+
"grad_norm": 11.4375,
|
| 7809 |
+
"learning_rate": 8.35516152864531e-06,
|
| 7810 |
+
"loss": 0.8361,
|
| 7811 |
+
"mean_token_accuracy": 0.7939860701560975,
|
| 7812 |
+
"num_tokens": 9603087.0,
|
| 7813 |
+
"step": 8670
|
| 7814 |
+
},
|
| 7815 |
+
{
|
| 7816 |
+
"epoch": 1.7489421720733427,
|
| 7817 |
+
"grad_norm": 10.75,
|
| 7818 |
+
"learning_rate": 8.34172879306871e-06,
|
| 7819 |
+
"loss": 0.7678,
|
| 7820 |
+
"mean_token_accuracy": 0.8116808116436005,
|
| 7821 |
+
"num_tokens": 9613559.0,
|
| 7822 |
+
"step": 8680
|
| 7823 |
+
},
|
| 7824 |
+
{
|
| 7825 |
+
"epoch": 1.7509570824098328,
|
| 7826 |
+
"grad_norm": 11.6875,
|
| 7827 |
+
"learning_rate": 8.328296057492109e-06,
|
| 7828 |
+
"loss": 0.7728,
|
| 7829 |
+
"mean_token_accuracy": 0.8031215369701385,
|
| 7830 |
+
"num_tokens": 9625395.0,
|
| 7831 |
+
"step": 8690
|
| 7832 |
+
},
|
| 7833 |
+
{
|
| 7834 |
+
"epoch": 1.7529719927463228,
|
| 7835 |
+
"grad_norm": 13.6875,
|
| 7836 |
+
"learning_rate": 8.314863321915508e-06,
|
| 7837 |
+
"loss": 0.7771,
|
| 7838 |
+
"mean_token_accuracy": 0.802968579530716,
|
| 7839 |
+
"num_tokens": 9636437.0,
|
| 7840 |
+
"step": 8700
|
| 7841 |
+
},
|
| 7842 |
+
{
|
| 7843 |
+
"epoch": 1.7549869030828127,
|
| 7844 |
+
"grad_norm": 12.5,
|
| 7845 |
+
"learning_rate": 8.301430586338909e-06,
|
| 7846 |
+
"loss": 0.8337,
|
| 7847 |
+
"mean_token_accuracy": 0.79465811252594,
|
| 7848 |
+
"num_tokens": 9647693.0,
|
| 7849 |
+
"step": 8710
|
| 7850 |
+
},
|
| 7851 |
+
{
|
| 7852 |
+
"epoch": 1.7570018134193028,
|
| 7853 |
+
"grad_norm": 12.375,
|
| 7854 |
+
"learning_rate": 8.287997850762309e-06,
|
| 7855 |
+
"loss": 0.9093,
|
| 7856 |
+
"mean_token_accuracy": 0.7816155433654786,
|
| 7857 |
+
"num_tokens": 9659058.0,
|
| 7858 |
+
"step": 8720
|
| 7859 |
+
},
|
| 7860 |
+
{
|
| 7861 |
+
"epoch": 1.759016723755793,
|
| 7862 |
+
"grad_norm": 10.125,
|
| 7863 |
+
"learning_rate": 8.274565115185708e-06,
|
| 7864 |
+
"loss": 0.8053,
|
| 7865 |
+
"mean_token_accuracy": 0.7992358326911926,
|
| 7866 |
+
"num_tokens": 9671229.0,
|
| 7867 |
+
"step": 8730
|
| 7868 |
+
},
|
| 7869 |
+
{
|
| 7870 |
+
"epoch": 1.761031634092283,
|
| 7871 |
+
"grad_norm": 13.1875,
|
| 7872 |
+
"learning_rate": 8.261132379609108e-06,
|
| 7873 |
+
"loss": 0.9656,
|
| 7874 |
+
"mean_token_accuracy": 0.7700483322143554,
|
| 7875 |
+
"num_tokens": 9682074.0,
|
| 7876 |
+
"step": 8740
|
| 7877 |
+
},
|
| 7878 |
+
{
|
| 7879 |
+
"epoch": 1.7630465444287728,
|
| 7880 |
+
"grad_norm": 12.625,
|
| 7881 |
+
"learning_rate": 8.247699644032507e-06,
|
| 7882 |
+
"loss": 0.775,
|
| 7883 |
+
"mean_token_accuracy": 0.8076685547828675,
|
| 7884 |
+
"num_tokens": 9692580.0,
|
| 7885 |
+
"step": 8750
|
| 7886 |
+
},
|
| 7887 |
+
{
|
| 7888 |
+
"epoch": 1.765061454765263,
|
| 7889 |
+
"grad_norm": 13.3125,
|
| 7890 |
+
"learning_rate": 8.234266908455908e-06,
|
| 7891 |
+
"loss": 0.7936,
|
| 7892 |
+
"mean_token_accuracy": 0.8011666655540466,
|
| 7893 |
+
"num_tokens": 9703690.0,
|
| 7894 |
+
"step": 8760
|
| 7895 |
+
},
|
| 7896 |
+
{
|
| 7897 |
+
"epoch": 1.767076365101753,
|
| 7898 |
+
"grad_norm": 12.625,
|
| 7899 |
+
"learning_rate": 8.220834172879307e-06,
|
| 7900 |
+
"loss": 0.7932,
|
| 7901 |
+
"mean_token_accuracy": 0.8000261068344117,
|
| 7902 |
+
"num_tokens": 9715172.0,
|
| 7903 |
+
"step": 8770
|
| 7904 |
+
},
|
| 7905 |
+
{
|
| 7906 |
+
"epoch": 1.7690912754382428,
|
| 7907 |
+
"grad_norm": 13.375,
|
| 7908 |
+
"learning_rate": 8.207401437302707e-06,
|
| 7909 |
+
"loss": 0.8277,
|
| 7910 |
+
"mean_token_accuracy": 0.7993273079395294,
|
| 7911 |
+
"num_tokens": 9726400.0,
|
| 7912 |
+
"step": 8780
|
| 7913 |
+
},
|
| 7914 |
+
{
|
| 7915 |
+
"epoch": 1.771106185774733,
|
| 7916 |
+
"grad_norm": 14.9375,
|
| 7917 |
+
"learning_rate": 8.193968701726108e-06,
|
| 7918 |
+
"loss": 0.8041,
|
| 7919 |
+
"mean_token_accuracy": 0.801609891653061,
|
| 7920 |
+
"num_tokens": 9738233.0,
|
| 7921 |
+
"step": 8790
|
| 7922 |
+
},
|
| 7923 |
+
{
|
| 7924 |
+
"epoch": 1.7731210961112231,
|
| 7925 |
+
"grad_norm": 13.5625,
|
| 7926 |
+
"learning_rate": 8.180535966149506e-06,
|
| 7927 |
+
"loss": 0.9014,
|
| 7928 |
+
"mean_token_accuracy": 0.7815512001514435,
|
| 7929 |
+
"num_tokens": 9749323.0,
|
| 7930 |
+
"step": 8800
|
| 7931 |
+
},
|
| 7932 |
+
{
|
| 7933 |
+
"epoch": 1.775136006447713,
|
| 7934 |
+
"grad_norm": 10.5,
|
| 7935 |
+
"learning_rate": 8.167103230572907e-06,
|
| 7936 |
+
"loss": 0.7797,
|
| 7937 |
+
"mean_token_accuracy": 0.7976033747196197,
|
| 7938 |
+
"num_tokens": 9760814.0,
|
| 7939 |
+
"step": 8810
|
| 7940 |
+
},
|
| 7941 |
+
{
|
| 7942 |
+
"epoch": 1.777150916784203,
|
| 7943 |
+
"grad_norm": 13.125,
|
| 7944 |
+
"learning_rate": 8.153670494996306e-06,
|
| 7945 |
+
"loss": 0.7727,
|
| 7946 |
+
"mean_token_accuracy": 0.8090618014335632,
|
| 7947 |
+
"num_tokens": 9771342.0,
|
| 7948 |
+
"step": 8820
|
| 7949 |
+
},
|
| 7950 |
+
{
|
| 7951 |
+
"epoch": 1.7791658271206932,
|
| 7952 |
+
"grad_norm": 11.625,
|
| 7953 |
+
"learning_rate": 8.140237759419706e-06,
|
| 7954 |
+
"loss": 0.7791,
|
| 7955 |
+
"mean_token_accuracy": 0.805637001991272,
|
| 7956 |
+
"num_tokens": 9781975.0,
|
| 7957 |
+
"step": 8830
|
| 7958 |
+
},
|
| 7959 |
+
{
|
| 7960 |
+
"epoch": 1.7811807374571833,
|
| 7961 |
+
"grad_norm": 12.0,
|
| 7962 |
+
"learning_rate": 8.126805023843107e-06,
|
| 7963 |
+
"loss": 0.7841,
|
| 7964 |
+
"mean_token_accuracy": 0.8054970562458038,
|
| 7965 |
+
"num_tokens": 9793656.0,
|
| 7966 |
+
"step": 8840
|
| 7967 |
+
},
|
| 7968 |
+
{
|
| 7969 |
+
"epoch": 1.7831956477936732,
|
| 7970 |
+
"grad_norm": 10.4375,
|
| 7971 |
+
"learning_rate": 8.113372288266507e-06,
|
| 7972 |
+
"loss": 0.8201,
|
| 7973 |
+
"mean_token_accuracy": 0.7929071843624115,
|
| 7974 |
+
"num_tokens": 9804717.0,
|
| 7975 |
+
"step": 8850
|
| 7976 |
+
},
|
| 7977 |
+
{
|
| 7978 |
+
"epoch": 1.7852105581301632,
|
| 7979 |
+
"grad_norm": 13.1875,
|
| 7980 |
+
"learning_rate": 8.099939552689906e-06,
|
| 7981 |
+
"loss": 0.8184,
|
| 7982 |
+
"mean_token_accuracy": 0.7929362654685974,
|
| 7983 |
+
"num_tokens": 9815462.0,
|
| 7984 |
+
"step": 8860
|
| 7985 |
+
},
|
| 7986 |
+
{
|
| 7987 |
+
"epoch": 1.7872254684666533,
|
| 7988 |
+
"grad_norm": 10.5,
|
| 7989 |
+
"learning_rate": 8.086506817113305e-06,
|
| 7990 |
+
"loss": 0.8737,
|
| 7991 |
+
"mean_token_accuracy": 0.7850127279758453,
|
| 7992 |
+
"num_tokens": 9827212.0,
|
| 7993 |
+
"step": 8870
|
| 7994 |
+
},
|
| 7995 |
+
{
|
| 7996 |
+
"epoch": 1.7892403788031432,
|
| 7997 |
+
"grad_norm": 9.5625,
|
| 7998 |
+
"learning_rate": 8.073074081536706e-06,
|
| 7999 |
+
"loss": 0.8605,
|
| 8000 |
+
"mean_token_accuracy": 0.7867051362991333,
|
| 8001 |
+
"num_tokens": 9839656.0,
|
| 8002 |
+
"step": 8880
|
| 8003 |
+
},
|
| 8004 |
+
{
|
| 8005 |
+
"epoch": 1.7912552891396332,
|
| 8006 |
+
"grad_norm": 10.375,
|
| 8007 |
+
"learning_rate": 8.059641345960104e-06,
|
| 8008 |
+
"loss": 0.8143,
|
| 8009 |
+
"mean_token_accuracy": 0.8001775145530701,
|
| 8010 |
+
"num_tokens": 9851032.0,
|
| 8011 |
+
"step": 8890
|
| 8012 |
+
},
|
| 8013 |
+
{
|
| 8014 |
+
"epoch": 1.7932701994761233,
|
| 8015 |
+
"grad_norm": 11.5625,
|
| 8016 |
+
"learning_rate": 8.046208610383505e-06,
|
| 8017 |
+
"loss": 0.8651,
|
| 8018 |
+
"mean_token_accuracy": 0.7894278347492218,
|
| 8019 |
+
"num_tokens": 9863136.0,
|
| 8020 |
+
"step": 8900
|
| 8021 |
+
},
|
| 8022 |
+
{
|
| 8023 |
+
"epoch": 1.7952851098126135,
|
| 8024 |
+
"grad_norm": 11.1875,
|
| 8025 |
+
"learning_rate": 8.032775874806906e-06,
|
| 8026 |
+
"loss": 0.7915,
|
| 8027 |
+
"mean_token_accuracy": 0.8040505468845367,
|
| 8028 |
+
"num_tokens": 9874065.0,
|
| 8029 |
+
"step": 8910
|
| 8030 |
+
},
|
| 8031 |
+
{
|
| 8032 |
+
"epoch": 1.7973000201491034,
|
| 8033 |
+
"grad_norm": 11.5,
|
| 8034 |
+
"learning_rate": 8.019343139230304e-06,
|
| 8035 |
+
"loss": 0.7863,
|
| 8036 |
+
"mean_token_accuracy": 0.804164183139801,
|
| 8037 |
+
"num_tokens": 9884180.0,
|
| 8038 |
+
"step": 8920
|
| 8039 |
+
},
|
| 8040 |
+
{
|
| 8041 |
+
"epoch": 1.7993149304855933,
|
| 8042 |
+
"grad_norm": 12.1875,
|
| 8043 |
+
"learning_rate": 8.005910403653705e-06,
|
| 8044 |
+
"loss": 0.7998,
|
| 8045 |
+
"mean_token_accuracy": 0.8023830056190491,
|
| 8046 |
+
"num_tokens": 9893817.0,
|
| 8047 |
+
"step": 8930
|
| 8048 |
+
},
|
| 8049 |
+
{
|
| 8050 |
+
"epoch": 1.8013298408220835,
|
| 8051 |
+
"grad_norm": 12.5,
|
| 8052 |
+
"learning_rate": 7.992477668077104e-06,
|
| 8053 |
+
"loss": 0.8189,
|
| 8054 |
+
"mean_token_accuracy": 0.8001566708087922,
|
| 8055 |
+
"num_tokens": 9904272.0,
|
| 8056 |
+
"step": 8940
|
| 8057 |
+
},
|
| 8058 |
+
{
|
| 8059 |
+
"epoch": 1.8033447511585734,
|
| 8060 |
+
"grad_norm": 10.3125,
|
| 8061 |
+
"learning_rate": 7.979044932500504e-06,
|
| 8062 |
+
"loss": 0.8199,
|
| 8063 |
+
"mean_token_accuracy": 0.79620281457901,
|
| 8064 |
+
"num_tokens": 9915875.0,
|
| 8065 |
+
"step": 8950
|
| 8066 |
+
},
|
| 8067 |
+
{
|
| 8068 |
+
"epoch": 1.8053596614950633,
|
| 8069 |
+
"grad_norm": 9.3125,
|
| 8070 |
+
"learning_rate": 7.965612196923905e-06,
|
| 8071 |
+
"loss": 0.8058,
|
| 8072 |
+
"mean_token_accuracy": 0.7988872945308685,
|
| 8073 |
+
"num_tokens": 9927434.0,
|
| 8074 |
+
"step": 8960
|
| 8075 |
+
},
|
| 8076 |
+
{
|
| 8077 |
+
"epoch": 1.8073745718315535,
|
| 8078 |
+
"grad_norm": 16.5,
|
| 8079 |
+
"learning_rate": 7.952179461347304e-06,
|
| 8080 |
+
"loss": 0.8912,
|
| 8081 |
+
"mean_token_accuracy": 0.785044139623642,
|
| 8082 |
+
"num_tokens": 9936917.0,
|
| 8083 |
+
"step": 8970
|
| 8084 |
+
},
|
| 8085 |
+
{
|
| 8086 |
+
"epoch": 1.8093894821680436,
|
| 8087 |
+
"grad_norm": 9.5,
|
| 8088 |
+
"learning_rate": 7.938746725770704e-06,
|
| 8089 |
+
"loss": 0.73,
|
| 8090 |
+
"mean_token_accuracy": 0.8187473714351654,
|
| 8091 |
+
"num_tokens": 9947903.0,
|
| 8092 |
+
"step": 8980
|
| 8093 |
+
},
|
| 8094 |
+
{
|
| 8095 |
+
"epoch": 1.8114043925045336,
|
| 8096 |
+
"grad_norm": 10.5625,
|
| 8097 |
+
"learning_rate": 7.925313990194103e-06,
|
| 8098 |
+
"loss": 0.7863,
|
| 8099 |
+
"mean_token_accuracy": 0.8035355567932129,
|
| 8100 |
+
"num_tokens": 9957362.0,
|
| 8101 |
+
"step": 8990
|
| 8102 |
+
},
|
| 8103 |
+
{
|
| 8104 |
+
"epoch": 1.8134193028410235,
|
| 8105 |
+
"grad_norm": 11.8125,
|
| 8106 |
+
"learning_rate": 7.911881254617504e-06,
|
| 8107 |
+
"loss": 0.9173,
|
| 8108 |
+
"mean_token_accuracy": 0.7758583545684814,
|
| 8109 |
+
"num_tokens": 9969639.0,
|
| 8110 |
+
"step": 9000
|
| 8111 |
}
|
| 8112 |
],
|
| 8113 |
"logging_steps": 10,
|
|
|
|
| 8127 |
"attributes": {}
|
| 8128 |
}
|
| 8129 |
},
|
| 8130 |
+
"total_flos": 1.2065001216479232e+16,
|
| 8131 |
"train_batch_size": 8,
|
| 8132 |
"trial_name": null,
|
| 8133 |
"trial_params": null
|