Training in progress, step 887, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100198584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82d8bacab76dbcf5eb4f92f5f82c3e20484571fea802ab9933f74589a3eabfb9
|
| 3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50675604
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:494168482585a7bfcbfbcc705c8748da82c9e8a80556079a12a6d8916e7a8125
|
| 3 |
size 50675604
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b85a44ab20a866b548a1f13ff0bee3fdd4760db12bf889cf65646cf2995e841c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -5922,6 +5922,300 @@
|
|
| 5922 |
"learning_rate": 1.6276202219482124e-06,
|
| 5923 |
"loss": 1.0783,
|
| 5924 |
"step": 845
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5925 |
}
|
| 5926 |
],
|
| 5927 |
"logging_steps": 1,
|
|
@@ -5941,7 +6235,7 @@
|
|
| 5941 |
"attributes": {}
|
| 5942 |
}
|
| 5943 |
},
|
| 5944 |
-
"total_flos":
|
| 5945 |
"train_batch_size": 4,
|
| 5946 |
"trial_name": null,
|
| 5947 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9733882030178327,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 887,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 5922 |
"learning_rate": 1.6276202219482124e-06,
|
| 5923 |
"loss": 1.0783,
|
| 5924 |
"step": 845
|
| 5925 |
+
},
|
| 5926 |
+
{
|
| 5927 |
+
"epoch": 0.928395061728395,
|
| 5928 |
+
"grad_norm": 0.14913596212863922,
|
| 5929 |
+
"learning_rate": 1.6029593094944515e-06,
|
| 5930 |
+
"loss": 1.1579,
|
| 5931 |
+
"step": 846
|
| 5932 |
+
},
|
| 5933 |
+
{
|
| 5934 |
+
"epoch": 0.9294924554183813,
|
| 5935 |
+
"grad_norm": 0.14216169714927673,
|
| 5936 |
+
"learning_rate": 1.5782983970406906e-06,
|
| 5937 |
+
"loss": 1.2532,
|
| 5938 |
+
"step": 847
|
| 5939 |
+
},
|
| 5940 |
+
{
|
| 5941 |
+
"epoch": 0.9305898491083676,
|
| 5942 |
+
"grad_norm": 0.12944941222667694,
|
| 5943 |
+
"learning_rate": 1.5536374845869297e-06,
|
| 5944 |
+
"loss": 1.1187,
|
| 5945 |
+
"step": 848
|
| 5946 |
+
},
|
| 5947 |
+
{
|
| 5948 |
+
"epoch": 0.9316872427983539,
|
| 5949 |
+
"grad_norm": 0.15228183567523956,
|
| 5950 |
+
"learning_rate": 1.528976572133169e-06,
|
| 5951 |
+
"loss": 1.0625,
|
| 5952 |
+
"step": 849
|
| 5953 |
+
},
|
| 5954 |
+
{
|
| 5955 |
+
"epoch": 0.9327846364883402,
|
| 5956 |
+
"grad_norm": 0.1437804400920868,
|
| 5957 |
+
"learning_rate": 1.5043156596794082e-06,
|
| 5958 |
+
"loss": 1.0785,
|
| 5959 |
+
"step": 850
|
| 5960 |
+
},
|
| 5961 |
+
{
|
| 5962 |
+
"epoch": 0.9338820301783265,
|
| 5963 |
+
"grad_norm": 0.13705220818519592,
|
| 5964 |
+
"learning_rate": 1.4796547472256475e-06,
|
| 5965 |
+
"loss": 1.1105,
|
| 5966 |
+
"step": 851
|
| 5967 |
+
},
|
| 5968 |
+
{
|
| 5969 |
+
"epoch": 0.9349794238683128,
|
| 5970 |
+
"grad_norm": 0.13792921602725983,
|
| 5971 |
+
"learning_rate": 1.4549938347718866e-06,
|
| 5972 |
+
"loss": 1.0987,
|
| 5973 |
+
"step": 852
|
| 5974 |
+
},
|
| 5975 |
+
{
|
| 5976 |
+
"epoch": 0.9360768175582991,
|
| 5977 |
+
"grad_norm": 0.12909933924674988,
|
| 5978 |
+
"learning_rate": 1.430332922318126e-06,
|
| 5979 |
+
"loss": 1.0932,
|
| 5980 |
+
"step": 853
|
| 5981 |
+
},
|
| 5982 |
+
{
|
| 5983 |
+
"epoch": 0.9371742112482854,
|
| 5984 |
+
"grad_norm": 0.13667872548103333,
|
| 5985 |
+
"learning_rate": 1.405672009864365e-06,
|
| 5986 |
+
"loss": 1.1542,
|
| 5987 |
+
"step": 854
|
| 5988 |
+
},
|
| 5989 |
+
{
|
| 5990 |
+
"epoch": 0.9382716049382716,
|
| 5991 |
+
"grad_norm": 0.13207869231700897,
|
| 5992 |
+
"learning_rate": 1.3810110974106042e-06,
|
| 5993 |
+
"loss": 1.1891,
|
| 5994 |
+
"step": 855
|
| 5995 |
+
},
|
| 5996 |
+
{
|
| 5997 |
+
"epoch": 0.9393689986282578,
|
| 5998 |
+
"grad_norm": 0.12875591218471527,
|
| 5999 |
+
"learning_rate": 1.3563501849568435e-06,
|
| 6000 |
+
"loss": 1.0372,
|
| 6001 |
+
"step": 856
|
| 6002 |
+
},
|
| 6003 |
+
{
|
| 6004 |
+
"epoch": 0.9404663923182441,
|
| 6005 |
+
"grad_norm": 0.12986066937446594,
|
| 6006 |
+
"learning_rate": 1.3316892725030829e-06,
|
| 6007 |
+
"loss": 1.1259,
|
| 6008 |
+
"step": 857
|
| 6009 |
+
},
|
| 6010 |
+
{
|
| 6011 |
+
"epoch": 0.9415637860082304,
|
| 6012 |
+
"grad_norm": 0.13095685839653015,
|
| 6013 |
+
"learning_rate": 1.307028360049322e-06,
|
| 6014 |
+
"loss": 1.0452,
|
| 6015 |
+
"step": 858
|
| 6016 |
+
},
|
| 6017 |
+
{
|
| 6018 |
+
"epoch": 0.9426611796982167,
|
| 6019 |
+
"grad_norm": 0.13577769696712494,
|
| 6020 |
+
"learning_rate": 1.2823674475955611e-06,
|
| 6021 |
+
"loss": 1.0942,
|
| 6022 |
+
"step": 859
|
| 6023 |
+
},
|
| 6024 |
+
{
|
| 6025 |
+
"epoch": 0.943758573388203,
|
| 6026 |
+
"grad_norm": 0.136579230427742,
|
| 6027 |
+
"learning_rate": 1.2577065351418002e-06,
|
| 6028 |
+
"loss": 1.0996,
|
| 6029 |
+
"step": 860
|
| 6030 |
+
},
|
| 6031 |
+
{
|
| 6032 |
+
"epoch": 0.9448559670781893,
|
| 6033 |
+
"grad_norm": 0.14068828523159027,
|
| 6034 |
+
"learning_rate": 1.2330456226880396e-06,
|
| 6035 |
+
"loss": 1.0527,
|
| 6036 |
+
"step": 861
|
| 6037 |
+
},
|
| 6038 |
+
{
|
| 6039 |
+
"epoch": 0.9459533607681756,
|
| 6040 |
+
"grad_norm": 0.14738546311855316,
|
| 6041 |
+
"learning_rate": 1.208384710234279e-06,
|
| 6042 |
+
"loss": 1.126,
|
| 6043 |
+
"step": 862
|
| 6044 |
+
},
|
| 6045 |
+
{
|
| 6046 |
+
"epoch": 0.9470507544581619,
|
| 6047 |
+
"grad_norm": 0.13700617849826813,
|
| 6048 |
+
"learning_rate": 1.183723797780518e-06,
|
| 6049 |
+
"loss": 1.1714,
|
| 6050 |
+
"step": 863
|
| 6051 |
+
},
|
| 6052 |
+
{
|
| 6053 |
+
"epoch": 0.9481481481481482,
|
| 6054 |
+
"grad_norm": 0.13408678770065308,
|
| 6055 |
+
"learning_rate": 1.1590628853267571e-06,
|
| 6056 |
+
"loss": 1.1135,
|
| 6057 |
+
"step": 864
|
| 6058 |
+
},
|
| 6059 |
+
{
|
| 6060 |
+
"epoch": 0.9492455418381345,
|
| 6061 |
+
"grad_norm": 0.1358562856912613,
|
| 6062 |
+
"learning_rate": 1.1344019728729965e-06,
|
| 6063 |
+
"loss": 1.0761,
|
| 6064 |
+
"step": 865
|
| 6065 |
+
},
|
| 6066 |
+
{
|
| 6067 |
+
"epoch": 0.9503429355281207,
|
| 6068 |
+
"grad_norm": 0.15928462147712708,
|
| 6069 |
+
"learning_rate": 1.1097410604192356e-06,
|
| 6070 |
+
"loss": 1.0841,
|
| 6071 |
+
"step": 866
|
| 6072 |
+
},
|
| 6073 |
+
{
|
| 6074 |
+
"epoch": 0.951440329218107,
|
| 6075 |
+
"grad_norm": 0.14678318798542023,
|
| 6076 |
+
"learning_rate": 1.0850801479654747e-06,
|
| 6077 |
+
"loss": 1.0772,
|
| 6078 |
+
"step": 867
|
| 6079 |
+
},
|
| 6080 |
+
{
|
| 6081 |
+
"epoch": 0.9525377229080932,
|
| 6082 |
+
"grad_norm": 0.12827463448047638,
|
| 6083 |
+
"learning_rate": 1.060419235511714e-06,
|
| 6084 |
+
"loss": 1.1324,
|
| 6085 |
+
"step": 868
|
| 6086 |
+
},
|
| 6087 |
+
{
|
| 6088 |
+
"epoch": 0.9536351165980795,
|
| 6089 |
+
"grad_norm": 0.14437751471996307,
|
| 6090 |
+
"learning_rate": 1.0357583230579532e-06,
|
| 6091 |
+
"loss": 1.2083,
|
| 6092 |
+
"step": 869
|
| 6093 |
+
},
|
| 6094 |
+
{
|
| 6095 |
+
"epoch": 0.9547325102880658,
|
| 6096 |
+
"grad_norm": 0.14573253691196442,
|
| 6097 |
+
"learning_rate": 1.0110974106041925e-06,
|
| 6098 |
+
"loss": 1.0288,
|
| 6099 |
+
"step": 870
|
| 6100 |
+
},
|
| 6101 |
+
{
|
| 6102 |
+
"epoch": 0.9558299039780521,
|
| 6103 |
+
"grad_norm": 0.148457869887352,
|
| 6104 |
+
"learning_rate": 9.864364981504316e-07,
|
| 6105 |
+
"loss": 1.1433,
|
| 6106 |
+
"step": 871
|
| 6107 |
+
},
|
| 6108 |
+
{
|
| 6109 |
+
"epoch": 0.9569272976680384,
|
| 6110 |
+
"grad_norm": 0.1432981789112091,
|
| 6111 |
+
"learning_rate": 9.617755856966707e-07,
|
| 6112 |
+
"loss": 1.1222,
|
| 6113 |
+
"step": 872
|
| 6114 |
+
},
|
| 6115 |
+
{
|
| 6116 |
+
"epoch": 0.9580246913580247,
|
| 6117 |
+
"grad_norm": 0.14053548872470856,
|
| 6118 |
+
"learning_rate": 9.371146732429101e-07,
|
| 6119 |
+
"loss": 1.1193,
|
| 6120 |
+
"step": 873
|
| 6121 |
+
},
|
| 6122 |
+
{
|
| 6123 |
+
"epoch": 0.959122085048011,
|
| 6124 |
+
"grad_norm": 0.13648538291454315,
|
| 6125 |
+
"learning_rate": 9.124537607891493e-07,
|
| 6126 |
+
"loss": 1.1411,
|
| 6127 |
+
"step": 874
|
| 6128 |
+
},
|
| 6129 |
+
{
|
| 6130 |
+
"epoch": 0.9602194787379973,
|
| 6131 |
+
"grad_norm": 0.15301236510276794,
|
| 6132 |
+
"learning_rate": 8.877928483353884e-07,
|
| 6133 |
+
"loss": 1.1395,
|
| 6134 |
+
"step": 875
|
| 6135 |
+
},
|
| 6136 |
+
{
|
| 6137 |
+
"epoch": 0.9613168724279836,
|
| 6138 |
+
"grad_norm": 0.1504426896572113,
|
| 6139 |
+
"learning_rate": 8.631319358816277e-07,
|
| 6140 |
+
"loss": 1.1447,
|
| 6141 |
+
"step": 876
|
| 6142 |
+
},
|
| 6143 |
+
{
|
| 6144 |
+
"epoch": 0.9624142661179699,
|
| 6145 |
+
"grad_norm": 0.15618982911109924,
|
| 6146 |
+
"learning_rate": 8.384710234278669e-07,
|
| 6147 |
+
"loss": 1.1235,
|
| 6148 |
+
"step": 877
|
| 6149 |
+
},
|
| 6150 |
+
{
|
| 6151 |
+
"epoch": 0.9635116598079561,
|
| 6152 |
+
"grad_norm": 0.1426519900560379,
|
| 6153 |
+
"learning_rate": 8.138101109741062e-07,
|
| 6154 |
+
"loss": 1.1242,
|
| 6155 |
+
"step": 878
|
| 6156 |
+
},
|
| 6157 |
+
{
|
| 6158 |
+
"epoch": 0.9646090534979423,
|
| 6159 |
+
"grad_norm": 0.1583835482597351,
|
| 6160 |
+
"learning_rate": 7.891491985203453e-07,
|
| 6161 |
+
"loss": 1.0598,
|
| 6162 |
+
"step": 879
|
| 6163 |
+
},
|
| 6164 |
+
{
|
| 6165 |
+
"epoch": 0.9657064471879286,
|
| 6166 |
+
"grad_norm": 0.14297567307949066,
|
| 6167 |
+
"learning_rate": 7.644882860665845e-07,
|
| 6168 |
+
"loss": 1.0291,
|
| 6169 |
+
"step": 880
|
| 6170 |
+
},
|
| 6171 |
+
{
|
| 6172 |
+
"epoch": 0.9668038408779149,
|
| 6173 |
+
"grad_norm": 0.14067769050598145,
|
| 6174 |
+
"learning_rate": 7.398273736128238e-07,
|
| 6175 |
+
"loss": 1.1746,
|
| 6176 |
+
"step": 881
|
| 6177 |
+
},
|
| 6178 |
+
{
|
| 6179 |
+
"epoch": 0.9679012345679012,
|
| 6180 |
+
"grad_norm": 0.1404830813407898,
|
| 6181 |
+
"learning_rate": 7.15166461159063e-07,
|
| 6182 |
+
"loss": 1.1294,
|
| 6183 |
+
"step": 882
|
| 6184 |
+
},
|
| 6185 |
+
{
|
| 6186 |
+
"epoch": 0.9689986282578875,
|
| 6187 |
+
"grad_norm": 0.1324174553155899,
|
| 6188 |
+
"learning_rate": 6.905055487053021e-07,
|
| 6189 |
+
"loss": 1.1089,
|
| 6190 |
+
"step": 883
|
| 6191 |
+
},
|
| 6192 |
+
{
|
| 6193 |
+
"epoch": 0.9700960219478738,
|
| 6194 |
+
"grad_norm": 0.13488321006298065,
|
| 6195 |
+
"learning_rate": 6.658446362515414e-07,
|
| 6196 |
+
"loss": 1.1228,
|
| 6197 |
+
"step": 884
|
| 6198 |
+
},
|
| 6199 |
+
{
|
| 6200 |
+
"epoch": 0.9711934156378601,
|
| 6201 |
+
"grad_norm": 0.13472045958042145,
|
| 6202 |
+
"learning_rate": 6.411837237977806e-07,
|
| 6203 |
+
"loss": 1.0933,
|
| 6204 |
+
"step": 885
|
| 6205 |
+
},
|
| 6206 |
+
{
|
| 6207 |
+
"epoch": 0.9722908093278464,
|
| 6208 |
+
"grad_norm": 0.14468832314014435,
|
| 6209 |
+
"learning_rate": 6.165228113440198e-07,
|
| 6210 |
+
"loss": 1.0767,
|
| 6211 |
+
"step": 886
|
| 6212 |
+
},
|
| 6213 |
+
{
|
| 6214 |
+
"epoch": 0.9733882030178327,
|
| 6215 |
+
"grad_norm": 0.13993267714977264,
|
| 6216 |
+
"learning_rate": 5.91861898890259e-07,
|
| 6217 |
+
"loss": 1.1123,
|
| 6218 |
+
"step": 887
|
| 6219 |
}
|
| 6220 |
],
|
| 6221 |
"logging_steps": 1,
|
|
|
|
| 6235 |
"attributes": {}
|
| 6236 |
}
|
| 6237 |
},
|
| 6238 |
+
"total_flos": 9.202552775203185e+17,
|
| 6239 |
"train_batch_size": 4,
|
| 6240 |
"trial_name": null,
|
| 6241 |
"trial_params": null
|