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 536223056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e99f98def5707de3be1588197fe5096482fac3f483b22d6d05ac701448ef1f6
|
| 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:c36c51441c6a4e72e59a3d4e0e9b5b84bfb5e8d67b647194ab6c6bfde7983c0e
|
| 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 sha256:326c38bef4f14b97646caa84204f32859351159ff635853df88679a10264e29a
|
| 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,
|
|
@@ -5858,6 +5858,456 @@
|
|
| 5858 |
"mean_token_accuracy": 0.7886571526527405,
|
| 5859 |
"num_tokens": 7207013.0,
|
| 5860 |
"step": 6500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5861 |
}
|
| 5862 |
],
|
| 5863 |
"logging_steps": 10,
|
|
@@ -5877,7 +6327,7 @@
|
|
| 5877 |
"attributes": {}
|
| 5878 |
}
|
| 5879 |
},
|
| 5880 |
-
"total_flos":
|
| 5881 |
"train_batch_size": 8,
|
| 5882 |
"trial_name": null,
|
| 5883 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.4104372355430184,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5858 |
"mean_token_accuracy": 0.7886571526527405,
|
| 5859 |
"num_tokens": 7207013.0,
|
| 5860 |
"step": 6500
|
| 5861 |
+
},
|
| 5862 |
+
{
|
| 5863 |
+
"epoch": 1.311706629055007,
|
| 5864 |
+
"grad_norm": 10.0625,
|
| 5865 |
+
"learning_rate": 1.1256632413190946e-05,
|
| 5866 |
+
"loss": 0.7398,
|
| 5867 |
+
"mean_token_accuracy": 0.8139720261096954,
|
| 5868 |
+
"num_tokens": 7217616.0,
|
| 5869 |
+
"step": 6510
|
| 5870 |
+
},
|
| 5871 |
+
{
|
| 5872 |
+
"epoch": 1.313721539391497,
|
| 5873 |
+
"grad_norm": 12.875,
|
| 5874 |
+
"learning_rate": 1.1243199677614347e-05,
|
| 5875 |
+
"loss": 0.8148,
|
| 5876 |
+
"mean_token_accuracy": 0.7918058097362518,
|
| 5877 |
+
"num_tokens": 7228902.0,
|
| 5878 |
+
"step": 6520
|
| 5879 |
+
},
|
| 5880 |
+
{
|
| 5881 |
+
"epoch": 1.315736449727987,
|
| 5882 |
+
"grad_norm": 12.5,
|
| 5883 |
+
"learning_rate": 1.1229766942037747e-05,
|
| 5884 |
+
"loss": 0.849,
|
| 5885 |
+
"mean_token_accuracy": 0.7959416568279266,
|
| 5886 |
+
"num_tokens": 7239105.0,
|
| 5887 |
+
"step": 6530
|
| 5888 |
+
},
|
| 5889 |
+
{
|
| 5890 |
+
"epoch": 1.3177513600644772,
|
| 5891 |
+
"grad_norm": 11.1875,
|
| 5892 |
+
"learning_rate": 1.1216334206461146e-05,
|
| 5893 |
+
"loss": 0.7653,
|
| 5894 |
+
"mean_token_accuracy": 0.8075124859809876,
|
| 5895 |
+
"num_tokens": 7248600.0,
|
| 5896 |
+
"step": 6540
|
| 5897 |
+
},
|
| 5898 |
+
{
|
| 5899 |
+
"epoch": 1.3197662704009672,
|
| 5900 |
+
"grad_norm": 11.4375,
|
| 5901 |
+
"learning_rate": 1.1202901470884547e-05,
|
| 5902 |
+
"loss": 0.8824,
|
| 5903 |
+
"mean_token_accuracy": 0.7894264698028565,
|
| 5904 |
+
"num_tokens": 7260572.0,
|
| 5905 |
+
"step": 6550
|
| 5906 |
+
},
|
| 5907 |
+
{
|
| 5908 |
+
"epoch": 1.321781180737457,
|
| 5909 |
+
"grad_norm": 12.1875,
|
| 5910 |
+
"learning_rate": 1.1189468735307947e-05,
|
| 5911 |
+
"loss": 0.8524,
|
| 5912 |
+
"mean_token_accuracy": 0.7949903309345245,
|
| 5913 |
+
"num_tokens": 7270963.0,
|
| 5914 |
+
"step": 6560
|
| 5915 |
+
},
|
| 5916 |
+
{
|
| 5917 |
+
"epoch": 1.3237960910739472,
|
| 5918 |
+
"grad_norm": 13.0,
|
| 5919 |
+
"learning_rate": 1.1176035999731348e-05,
|
| 5920 |
+
"loss": 0.7687,
|
| 5921 |
+
"mean_token_accuracy": 0.8052358329296112,
|
| 5922 |
+
"num_tokens": 7282254.0,
|
| 5923 |
+
"step": 6570
|
| 5924 |
+
},
|
| 5925 |
+
{
|
| 5926 |
+
"epoch": 1.3258110014104372,
|
| 5927 |
+
"grad_norm": 12.1875,
|
| 5928 |
+
"learning_rate": 1.1162603264154745e-05,
|
| 5929 |
+
"loss": 0.771,
|
| 5930 |
+
"mean_token_accuracy": 0.8071496605873107,
|
| 5931 |
+
"num_tokens": 7293472.0,
|
| 5932 |
+
"step": 6580
|
| 5933 |
+
},
|
| 5934 |
+
{
|
| 5935 |
+
"epoch": 1.3278259117469273,
|
| 5936 |
+
"grad_norm": 16.0,
|
| 5937 |
+
"learning_rate": 1.1149170528578145e-05,
|
| 5938 |
+
"loss": 0.7544,
|
| 5939 |
+
"mean_token_accuracy": 0.8064080238342285,
|
| 5940 |
+
"num_tokens": 7302549.0,
|
| 5941 |
+
"step": 6590
|
| 5942 |
+
},
|
| 5943 |
+
{
|
| 5944 |
+
"epoch": 1.3298408220834173,
|
| 5945 |
+
"grad_norm": 11.625,
|
| 5946 |
+
"learning_rate": 1.1135737793001546e-05,
|
| 5947 |
+
"loss": 0.7427,
|
| 5948 |
+
"mean_token_accuracy": 0.8121874392032623,
|
| 5949 |
+
"num_tokens": 7313898.0,
|
| 5950 |
+
"step": 6600
|
| 5951 |
+
},
|
| 5952 |
+
{
|
| 5953 |
+
"epoch": 1.3318557324199074,
|
| 5954 |
+
"grad_norm": 11.4375,
|
| 5955 |
+
"learning_rate": 1.1122305057424945e-05,
|
| 5956 |
+
"loss": 0.8996,
|
| 5957 |
+
"mean_token_accuracy": 0.7810469567775726,
|
| 5958 |
+
"num_tokens": 7324658.0,
|
| 5959 |
+
"step": 6610
|
| 5960 |
+
},
|
| 5961 |
+
{
|
| 5962 |
+
"epoch": 1.3338706427563973,
|
| 5963 |
+
"grad_norm": 11.625,
|
| 5964 |
+
"learning_rate": 1.1108872321848345e-05,
|
| 5965 |
+
"loss": 0.7865,
|
| 5966 |
+
"mean_token_accuracy": 0.806594967842102,
|
| 5967 |
+
"num_tokens": 7335673.0,
|
| 5968 |
+
"step": 6620
|
| 5969 |
+
},
|
| 5970 |
+
{
|
| 5971 |
+
"epoch": 1.3358855530928873,
|
| 5972 |
+
"grad_norm": 12.6875,
|
| 5973 |
+
"learning_rate": 1.1095439586271746e-05,
|
| 5974 |
+
"loss": 0.9176,
|
| 5975 |
+
"mean_token_accuracy": 0.7800018846988678,
|
| 5976 |
+
"num_tokens": 7347253.0,
|
| 5977 |
+
"step": 6630
|
| 5978 |
+
},
|
| 5979 |
+
{
|
| 5980 |
+
"epoch": 1.3379004634293774,
|
| 5981 |
+
"grad_norm": 12.6875,
|
| 5982 |
+
"learning_rate": 1.1082006850695145e-05,
|
| 5983 |
+
"loss": 0.8083,
|
| 5984 |
+
"mean_token_accuracy": 0.8040257275104523,
|
| 5985 |
+
"num_tokens": 7358476.0,
|
| 5986 |
+
"step": 6640
|
| 5987 |
+
},
|
| 5988 |
+
{
|
| 5989 |
+
"epoch": 1.3399153737658676,
|
| 5990 |
+
"grad_norm": 14.0625,
|
| 5991 |
+
"learning_rate": 1.1068574115118545e-05,
|
| 5992 |
+
"loss": 0.9627,
|
| 5993 |
+
"mean_token_accuracy": 0.7791651308536529,
|
| 5994 |
+
"num_tokens": 7369343.0,
|
| 5995 |
+
"step": 6650
|
| 5996 |
+
},
|
| 5997 |
+
{
|
| 5998 |
+
"epoch": 1.3419302841023575,
|
| 5999 |
+
"grad_norm": 14.375,
|
| 6000 |
+
"learning_rate": 1.1055141379541944e-05,
|
| 6001 |
+
"loss": 0.869,
|
| 6002 |
+
"mean_token_accuracy": 0.791654235124588,
|
| 6003 |
+
"num_tokens": 7380142.0,
|
| 6004 |
+
"step": 6660
|
| 6005 |
+
},
|
| 6006 |
+
{
|
| 6007 |
+
"epoch": 1.3439451944388474,
|
| 6008 |
+
"grad_norm": 16.75,
|
| 6009 |
+
"learning_rate": 1.1041708643965345e-05,
|
| 6010 |
+
"loss": 0.8959,
|
| 6011 |
+
"mean_token_accuracy": 0.7814781248569489,
|
| 6012 |
+
"num_tokens": 7391681.0,
|
| 6013 |
+
"step": 6670
|
| 6014 |
+
},
|
| 6015 |
+
{
|
| 6016 |
+
"epoch": 1.3459601047753376,
|
| 6017 |
+
"grad_norm": 25.75,
|
| 6018 |
+
"learning_rate": 1.1028275908388743e-05,
|
| 6019 |
+
"loss": 0.7937,
|
| 6020 |
+
"mean_token_accuracy": 0.8048185467720032,
|
| 6021 |
+
"num_tokens": 7402373.0,
|
| 6022 |
+
"step": 6680
|
| 6023 |
+
},
|
| 6024 |
+
{
|
| 6025 |
+
"epoch": 1.3479750151118275,
|
| 6026 |
+
"grad_norm": 11.25,
|
| 6027 |
+
"learning_rate": 1.1014843172812144e-05,
|
| 6028 |
+
"loss": 0.8797,
|
| 6029 |
+
"mean_token_accuracy": 0.7896045446395874,
|
| 6030 |
+
"num_tokens": 7412646.0,
|
| 6031 |
+
"step": 6690
|
| 6032 |
+
},
|
| 6033 |
+
{
|
| 6034 |
+
"epoch": 1.3499899254483174,
|
| 6035 |
+
"grad_norm": 11.5625,
|
| 6036 |
+
"learning_rate": 1.1001410437235544e-05,
|
| 6037 |
+
"loss": 0.7739,
|
| 6038 |
+
"mean_token_accuracy": 0.8085869729518891,
|
| 6039 |
+
"num_tokens": 7423087.0,
|
| 6040 |
+
"step": 6700
|
| 6041 |
+
},
|
| 6042 |
+
{
|
| 6043 |
+
"epoch": 1.3520048357848076,
|
| 6044 |
+
"grad_norm": 42.5,
|
| 6045 |
+
"learning_rate": 1.0987977701658943e-05,
|
| 6046 |
+
"loss": 0.8267,
|
| 6047 |
+
"mean_token_accuracy": 0.7931196630001068,
|
| 6048 |
+
"num_tokens": 7433496.0,
|
| 6049 |
+
"step": 6710
|
| 6050 |
+
},
|
| 6051 |
+
{
|
| 6052 |
+
"epoch": 1.3540197461212977,
|
| 6053 |
+
"grad_norm": 11.625,
|
| 6054 |
+
"learning_rate": 1.0974544966082344e-05,
|
| 6055 |
+
"loss": 0.7688,
|
| 6056 |
+
"mean_token_accuracy": 0.8101352214813232,
|
| 6057 |
+
"num_tokens": 7444890.0,
|
| 6058 |
+
"step": 6720
|
| 6059 |
+
},
|
| 6060 |
+
{
|
| 6061 |
+
"epoch": 1.3560346564577876,
|
| 6062 |
+
"grad_norm": 9.9375,
|
| 6063 |
+
"learning_rate": 1.0961112230505744e-05,
|
| 6064 |
+
"loss": 0.8294,
|
| 6065 |
+
"mean_token_accuracy": 0.7928038239479065,
|
| 6066 |
+
"num_tokens": 7456497.0,
|
| 6067 |
+
"step": 6730
|
| 6068 |
+
},
|
| 6069 |
+
{
|
| 6070 |
+
"epoch": 1.3580495667942776,
|
| 6071 |
+
"grad_norm": 13.0,
|
| 6072 |
+
"learning_rate": 1.0947679494929145e-05,
|
| 6073 |
+
"loss": 0.8978,
|
| 6074 |
+
"mean_token_accuracy": 0.7794729173183441,
|
| 6075 |
+
"num_tokens": 7466678.0,
|
| 6076 |
+
"step": 6740
|
| 6077 |
+
},
|
| 6078 |
+
{
|
| 6079 |
+
"epoch": 1.3600644771307677,
|
| 6080 |
+
"grad_norm": 12.0625,
|
| 6081 |
+
"learning_rate": 1.0934246759352542e-05,
|
| 6082 |
+
"loss": 0.8052,
|
| 6083 |
+
"mean_token_accuracy": 0.8050779700279236,
|
| 6084 |
+
"num_tokens": 7477058.0,
|
| 6085 |
+
"step": 6750
|
| 6086 |
+
},
|
| 6087 |
+
{
|
| 6088 |
+
"epoch": 1.3620793874672577,
|
| 6089 |
+
"grad_norm": 11.75,
|
| 6090 |
+
"learning_rate": 1.0920814023775943e-05,
|
| 6091 |
+
"loss": 0.8537,
|
| 6092 |
+
"mean_token_accuracy": 0.7877449512481689,
|
| 6093 |
+
"num_tokens": 7487077.0,
|
| 6094 |
+
"step": 6760
|
| 6095 |
+
},
|
| 6096 |
+
{
|
| 6097 |
+
"epoch": 1.3640942978037478,
|
| 6098 |
+
"grad_norm": 14.0,
|
| 6099 |
+
"learning_rate": 1.0907381288199343e-05,
|
| 6100 |
+
"loss": 0.8519,
|
| 6101 |
+
"mean_token_accuracy": 0.7857004582881928,
|
| 6102 |
+
"num_tokens": 7497355.0,
|
| 6103 |
+
"step": 6770
|
| 6104 |
+
},
|
| 6105 |
+
{
|
| 6106 |
+
"epoch": 1.3661092081402377,
|
| 6107 |
+
"grad_norm": 10.4375,
|
| 6108 |
+
"learning_rate": 1.0893948552622742e-05,
|
| 6109 |
+
"loss": 0.796,
|
| 6110 |
+
"mean_token_accuracy": 0.7996562838554382,
|
| 6111 |
+
"num_tokens": 7508344.0,
|
| 6112 |
+
"step": 6780
|
| 6113 |
+
},
|
| 6114 |
+
{
|
| 6115 |
+
"epoch": 1.3681241184767279,
|
| 6116 |
+
"grad_norm": 11.75,
|
| 6117 |
+
"learning_rate": 1.0880515817046142e-05,
|
| 6118 |
+
"loss": 0.8427,
|
| 6119 |
+
"mean_token_accuracy": 0.7912454545497895,
|
| 6120 |
+
"num_tokens": 7519520.0,
|
| 6121 |
+
"step": 6790
|
| 6122 |
+
},
|
| 6123 |
+
{
|
| 6124 |
+
"epoch": 1.3701390288132178,
|
| 6125 |
+
"grad_norm": 9.25,
|
| 6126 |
+
"learning_rate": 1.0867083081469543e-05,
|
| 6127 |
+
"loss": 0.8216,
|
| 6128 |
+
"mean_token_accuracy": 0.7908532798290253,
|
| 6129 |
+
"num_tokens": 7531198.0,
|
| 6130 |
+
"step": 6800
|
| 6131 |
+
},
|
| 6132 |
+
{
|
| 6133 |
+
"epoch": 1.3721539391497077,
|
| 6134 |
+
"grad_norm": 10.625,
|
| 6135 |
+
"learning_rate": 1.085365034589294e-05,
|
| 6136 |
+
"loss": 0.8054,
|
| 6137 |
+
"mean_token_accuracy": 0.8009598433971405,
|
| 6138 |
+
"num_tokens": 7542242.0,
|
| 6139 |
+
"step": 6810
|
| 6140 |
+
},
|
| 6141 |
+
{
|
| 6142 |
+
"epoch": 1.3741688494861979,
|
| 6143 |
+
"grad_norm": 11.8125,
|
| 6144 |
+
"learning_rate": 1.084021761031634e-05,
|
| 6145 |
+
"loss": 0.8353,
|
| 6146 |
+
"mean_token_accuracy": 0.7952351868152618,
|
| 6147 |
+
"num_tokens": 7553773.0,
|
| 6148 |
+
"step": 6820
|
| 6149 |
+
},
|
| 6150 |
+
{
|
| 6151 |
+
"epoch": 1.3761837598226878,
|
| 6152 |
+
"grad_norm": 14.4375,
|
| 6153 |
+
"learning_rate": 1.0826784874739741e-05,
|
| 6154 |
+
"loss": 0.7143,
|
| 6155 |
+
"mean_token_accuracy": 0.8181480646133423,
|
| 6156 |
+
"num_tokens": 7563382.0,
|
| 6157 |
+
"step": 6830
|
| 6158 |
+
},
|
| 6159 |
+
{
|
| 6160 |
+
"epoch": 1.378198670159178,
|
| 6161 |
+
"grad_norm": 10.3125,
|
| 6162 |
+
"learning_rate": 1.0813352139163142e-05,
|
| 6163 |
+
"loss": 0.8876,
|
| 6164 |
+
"mean_token_accuracy": 0.7816132783889771,
|
| 6165 |
+
"num_tokens": 7575581.0,
|
| 6166 |
+
"step": 6840
|
| 6167 |
+
},
|
| 6168 |
+
{
|
| 6169 |
+
"epoch": 1.380213580495668,
|
| 6170 |
+
"grad_norm": 10.4375,
|
| 6171 |
+
"learning_rate": 1.079991940358654e-05,
|
| 6172 |
+
"loss": 0.8494,
|
| 6173 |
+
"mean_token_accuracy": 0.7854238271713256,
|
| 6174 |
+
"num_tokens": 7587514.0,
|
| 6175 |
+
"step": 6850
|
| 6176 |
+
},
|
| 6177 |
+
{
|
| 6178 |
+
"epoch": 1.382228490832158,
|
| 6179 |
+
"grad_norm": 10.1875,
|
| 6180 |
+
"learning_rate": 1.0786486668009941e-05,
|
| 6181 |
+
"loss": 0.8978,
|
| 6182 |
+
"mean_token_accuracy": 0.7826396405696869,
|
| 6183 |
+
"num_tokens": 7599849.0,
|
| 6184 |
+
"step": 6860
|
| 6185 |
+
},
|
| 6186 |
+
{
|
| 6187 |
+
"epoch": 1.384243401168648,
|
| 6188 |
+
"grad_norm": 10.25,
|
| 6189 |
+
"learning_rate": 1.0773053932433342e-05,
|
| 6190 |
+
"loss": 0.7709,
|
| 6191 |
+
"mean_token_accuracy": 0.8018522441387177,
|
| 6192 |
+
"num_tokens": 7611329.0,
|
| 6193 |
+
"step": 6870
|
| 6194 |
+
},
|
| 6195 |
+
{
|
| 6196 |
+
"epoch": 1.386258311505138,
|
| 6197 |
+
"grad_norm": 12.625,
|
| 6198 |
+
"learning_rate": 1.075962119685674e-05,
|
| 6199 |
+
"loss": 0.8472,
|
| 6200 |
+
"mean_token_accuracy": 0.7918815612792969,
|
| 6201 |
+
"num_tokens": 7621873.0,
|
| 6202 |
+
"step": 6880
|
| 6203 |
+
},
|
| 6204 |
+
{
|
| 6205 |
+
"epoch": 1.388273221841628,
|
| 6206 |
+
"grad_norm": 14.75,
|
| 6207 |
+
"learning_rate": 1.0746188461280141e-05,
|
| 6208 |
+
"loss": 0.9434,
|
| 6209 |
+
"mean_token_accuracy": 0.7729089677333831,
|
| 6210 |
+
"num_tokens": 7633787.0,
|
| 6211 |
+
"step": 6890
|
| 6212 |
+
},
|
| 6213 |
+
{
|
| 6214 |
+
"epoch": 1.3902881321781182,
|
| 6215 |
+
"grad_norm": 11.9375,
|
| 6216 |
+
"learning_rate": 1.0732755725703542e-05,
|
| 6217 |
+
"loss": 0.8285,
|
| 6218 |
+
"mean_token_accuracy": 0.7966946125030517,
|
| 6219 |
+
"num_tokens": 7643889.0,
|
| 6220 |
+
"step": 6900
|
| 6221 |
+
},
|
| 6222 |
+
{
|
| 6223 |
+
"epoch": 1.3923030425146081,
|
| 6224 |
+
"grad_norm": 11.9375,
|
| 6225 |
+
"learning_rate": 1.0719322990126942e-05,
|
| 6226 |
+
"loss": 0.8414,
|
| 6227 |
+
"mean_token_accuracy": 0.7909166395664216,
|
| 6228 |
+
"num_tokens": 7655243.0,
|
| 6229 |
+
"step": 6910
|
| 6230 |
+
},
|
| 6231 |
+
{
|
| 6232 |
+
"epoch": 1.394317952851098,
|
| 6233 |
+
"grad_norm": 11.6875,
|
| 6234 |
+
"learning_rate": 1.070589025455034e-05,
|
| 6235 |
+
"loss": 0.7375,
|
| 6236 |
+
"mean_token_accuracy": 0.8181369364261627,
|
| 6237 |
+
"num_tokens": 7666042.0,
|
| 6238 |
+
"step": 6920
|
| 6239 |
+
},
|
| 6240 |
+
{
|
| 6241 |
+
"epoch": 1.3963328631875882,
|
| 6242 |
+
"grad_norm": 8.4375,
|
| 6243 |
+
"learning_rate": 1.069245751897374e-05,
|
| 6244 |
+
"loss": 0.8464,
|
| 6245 |
+
"mean_token_accuracy": 0.797934228181839,
|
| 6246 |
+
"num_tokens": 7676887.0,
|
| 6247 |
+
"step": 6930
|
| 6248 |
+
},
|
| 6249 |
+
{
|
| 6250 |
+
"epoch": 1.3983477735240781,
|
| 6251 |
+
"grad_norm": 12.625,
|
| 6252 |
+
"learning_rate": 1.067902478339714e-05,
|
| 6253 |
+
"loss": 0.8094,
|
| 6254 |
+
"mean_token_accuracy": 0.7948006153106689,
|
| 6255 |
+
"num_tokens": 7688051.0,
|
| 6256 |
+
"step": 6940
|
| 6257 |
+
},
|
| 6258 |
+
{
|
| 6259 |
+
"epoch": 1.4003626838605683,
|
| 6260 |
+
"grad_norm": 10.9375,
|
| 6261 |
+
"learning_rate": 1.0665592047820539e-05,
|
| 6262 |
+
"loss": 0.8955,
|
| 6263 |
+
"mean_token_accuracy": 0.782581114768982,
|
| 6264 |
+
"num_tokens": 7699480.0,
|
| 6265 |
+
"step": 6950
|
| 6266 |
+
},
|
| 6267 |
+
{
|
| 6268 |
+
"epoch": 1.4023775941970582,
|
| 6269 |
+
"grad_norm": 12.375,
|
| 6270 |
+
"learning_rate": 1.065215931224394e-05,
|
| 6271 |
+
"loss": 0.8763,
|
| 6272 |
+
"mean_token_accuracy": 0.7808327317237854,
|
| 6273 |
+
"num_tokens": 7710853.0,
|
| 6274 |
+
"step": 6960
|
| 6275 |
+
},
|
| 6276 |
+
{
|
| 6277 |
+
"epoch": 1.4043925045335484,
|
| 6278 |
+
"grad_norm": 12.875,
|
| 6279 |
+
"learning_rate": 1.063872657666734e-05,
|
| 6280 |
+
"loss": 0.8204,
|
| 6281 |
+
"mean_token_accuracy": 0.8006475508213043,
|
| 6282 |
+
"num_tokens": 7722290.0,
|
| 6283 |
+
"step": 6970
|
| 6284 |
+
},
|
| 6285 |
+
{
|
| 6286 |
+
"epoch": 1.4064074148700383,
|
| 6287 |
+
"grad_norm": 10.625,
|
| 6288 |
+
"learning_rate": 1.0625293841090737e-05,
|
| 6289 |
+
"loss": 0.839,
|
| 6290 |
+
"mean_token_accuracy": 0.7950416922569274,
|
| 6291 |
+
"num_tokens": 7733653.0,
|
| 6292 |
+
"step": 6980
|
| 6293 |
+
},
|
| 6294 |
+
{
|
| 6295 |
+
"epoch": 1.4084223252065282,
|
| 6296 |
+
"grad_norm": 12.75,
|
| 6297 |
+
"learning_rate": 1.0611861105514138e-05,
|
| 6298 |
+
"loss": 0.8964,
|
| 6299 |
+
"mean_token_accuracy": 0.7838905036449433,
|
| 6300 |
+
"num_tokens": 7744184.0,
|
| 6301 |
+
"step": 6990
|
| 6302 |
+
},
|
| 6303 |
+
{
|
| 6304 |
+
"epoch": 1.4104372355430184,
|
| 6305 |
+
"grad_norm": 12.0,
|
| 6306 |
+
"learning_rate": 1.0598428369937538e-05,
|
| 6307 |
+
"loss": 0.7874,
|
| 6308 |
+
"mean_token_accuracy": 0.7988959193229676,
|
| 6309 |
+
"num_tokens": 7754571.0,
|
| 6310 |
+
"step": 7000
|
| 6311 |
}
|
| 6312 |
],
|
| 6313 |
"logging_steps": 10,
|
|
|
|
| 6327 |
"attributes": {}
|
| 6328 |
}
|
| 6329 |
},
|
| 6330 |
+
"total_flos": 9382261075611648.0,
|
| 6331 |
"train_batch_size": 8,
|
| 6332 |
"trial_name": null,
|
| 6333 |
"trial_params": null
|