Training in progress, step 10345, 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 2384234968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70673c4b3a23c350c3d34964ccf5e6d071a142d9fed0284db5f78da9fe543e09
|
| 3 |
size 2384234968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4768662910
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:592af7aba28b8c635fdc8123da87f1a25c80f7f6ef5d578a1399d7cbe6c53fdd
|
| 3 |
size 4768662910
|
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 sha256:9139898b21e9040c38ef91d3deb1fcf3a1358aa4f9c7c7522299d4b1a4f3fc86
|
| 3 |
size 1064
|
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": 0.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -9008,6 +9008,312 @@
|
|
| 9008 |
"mean_token_accuracy": 0.968175146728754,
|
| 9009 |
"num_tokens": 40960000.0,
|
| 9010 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9011 |
}
|
| 9012 |
],
|
| 9013 |
"logging_steps": 10,
|
|
@@ -9022,12 +9328,12 @@
|
|
| 9022 |
"should_evaluate": false,
|
| 9023 |
"should_log": false,
|
| 9024 |
"should_save": true,
|
| 9025 |
-
"should_training_stop":
|
| 9026 |
},
|
| 9027 |
"attributes": {}
|
| 9028 |
}
|
| 9029 |
},
|
| 9030 |
-
"total_flos": 1.
|
| 9031 |
"train_batch_size": 1,
|
| 9032 |
"trial_name": null,
|
| 9033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9999516698081291,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 10345,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9008 |
"mean_token_accuracy": 0.968175146728754,
|
| 9009 |
"num_tokens": 40960000.0,
|
| 9010 |
"step": 10000
|
| 9011 |
+
},
|
| 9012 |
+
{
|
| 9013 |
+
"epoch": 0.9675704412546517,
|
| 9014 |
+
"grad_norm": 0.6231664419174194,
|
| 9015 |
+
"learning_rate": 1.804511278195489e-06,
|
| 9016 |
+
"loss": 0.1437,
|
| 9017 |
+
"mean_token_accuracy": 0.9698630094528198,
|
| 9018 |
+
"num_tokens": 41000960.0,
|
| 9019 |
+
"step": 10010
|
| 9020 |
+
},
|
| 9021 |
+
{
|
| 9022 |
+
"epoch": 0.9685370450920691,
|
| 9023 |
+
"grad_norm": 0.767872154712677,
|
| 9024 |
+
"learning_rate": 1.7508055853920516e-06,
|
| 9025 |
+
"loss": 0.1313,
|
| 9026 |
+
"mean_token_accuracy": 0.9726271979510784,
|
| 9027 |
+
"num_tokens": 41041920.0,
|
| 9028 |
+
"step": 10020
|
| 9029 |
+
},
|
| 9030 |
+
{
|
| 9031 |
+
"epoch": 0.9695036489294863,
|
| 9032 |
+
"grad_norm": 0.7130146622657776,
|
| 9033 |
+
"learning_rate": 1.6970998925886145e-06,
|
| 9034 |
+
"loss": 0.1165,
|
| 9035 |
+
"mean_token_accuracy": 0.9753179997205734,
|
| 9036 |
+
"num_tokens": 41082880.0,
|
| 9037 |
+
"step": 10030
|
| 9038 |
+
},
|
| 9039 |
+
{
|
| 9040 |
+
"epoch": 0.9704702527669035,
|
| 9041 |
+
"grad_norm": 0.6905496716499329,
|
| 9042 |
+
"learning_rate": 1.6433941997851776e-06,
|
| 9043 |
+
"loss": 0.1549,
|
| 9044 |
+
"mean_token_accuracy": 0.9695450082421303,
|
| 9045 |
+
"num_tokens": 41123840.0,
|
| 9046 |
+
"step": 10040
|
| 9047 |
+
},
|
| 9048 |
+
{
|
| 9049 |
+
"epoch": 0.9714368566043207,
|
| 9050 |
+
"grad_norm": 0.9023261070251465,
|
| 9051 |
+
"learning_rate": 1.5896885069817402e-06,
|
| 9052 |
+
"loss": 0.1334,
|
| 9053 |
+
"mean_token_accuracy": 0.9723825827240944,
|
| 9054 |
+
"num_tokens": 41164800.0,
|
| 9055 |
+
"step": 10050
|
| 9056 |
+
},
|
| 9057 |
+
{
|
| 9058 |
+
"epoch": 0.972403460441738,
|
| 9059 |
+
"grad_norm": 0.7522259950637817,
|
| 9060 |
+
"learning_rate": 1.5359828141783029e-06,
|
| 9061 |
+
"loss": 0.1305,
|
| 9062 |
+
"mean_token_accuracy": 0.9732142813503742,
|
| 9063 |
+
"num_tokens": 41205760.0,
|
| 9064 |
+
"step": 10060
|
| 9065 |
+
},
|
| 9066 |
+
{
|
| 9067 |
+
"epoch": 0.9733700642791552,
|
| 9068 |
+
"grad_norm": 0.7042533755302429,
|
| 9069 |
+
"learning_rate": 1.4822771213748658e-06,
|
| 9070 |
+
"loss": 0.1328,
|
| 9071 |
+
"mean_token_accuracy": 0.9719422683119774,
|
| 9072 |
+
"num_tokens": 41246720.0,
|
| 9073 |
+
"step": 10070
|
| 9074 |
+
},
|
| 9075 |
+
{
|
| 9076 |
+
"epoch": 0.9743366681165724,
|
| 9077 |
+
"grad_norm": 0.6883172392845154,
|
| 9078 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 9079 |
+
"loss": 0.1244,
|
| 9080 |
+
"mean_token_accuracy": 0.973972599953413,
|
| 9081 |
+
"num_tokens": 41287680.0,
|
| 9082 |
+
"step": 10080
|
| 9083 |
+
},
|
| 9084 |
+
{
|
| 9085 |
+
"epoch": 0.9753032719539897,
|
| 9086 |
+
"grad_norm": 0.7336052656173706,
|
| 9087 |
+
"learning_rate": 1.3748657357679915e-06,
|
| 9088 |
+
"loss": 0.1481,
|
| 9089 |
+
"mean_token_accuracy": 0.9694471590220928,
|
| 9090 |
+
"num_tokens": 41328640.0,
|
| 9091 |
+
"step": 10090
|
| 9092 |
+
},
|
| 9093 |
+
{
|
| 9094 |
+
"epoch": 0.9762698757914069,
|
| 9095 |
+
"grad_norm": 0.7422951459884644,
|
| 9096 |
+
"learning_rate": 1.3211600429645542e-06,
|
| 9097 |
+
"loss": 0.1391,
|
| 9098 |
+
"mean_token_accuracy": 0.9710861049592495,
|
| 9099 |
+
"num_tokens": 41369600.0,
|
| 9100 |
+
"step": 10100
|
| 9101 |
+
},
|
| 9102 |
+
{
|
| 9103 |
+
"epoch": 0.9772364796288241,
|
| 9104 |
+
"grad_norm": 0.6071293354034424,
|
| 9105 |
+
"learning_rate": 1.2674543501611172e-06,
|
| 9106 |
+
"loss": 0.1317,
|
| 9107 |
+
"mean_token_accuracy": 0.9728718191385269,
|
| 9108 |
+
"num_tokens": 41410560.0,
|
| 9109 |
+
"step": 10110
|
| 9110 |
+
},
|
| 9111 |
+
{
|
| 9112 |
+
"epoch": 0.9782030834662414,
|
| 9113 |
+
"grad_norm": 0.7155930995941162,
|
| 9114 |
+
"learning_rate": 1.21374865735768e-06,
|
| 9115 |
+
"loss": 0.1362,
|
| 9116 |
+
"mean_token_accuracy": 0.9724804274737835,
|
| 9117 |
+
"num_tokens": 41451520.0,
|
| 9118 |
+
"step": 10120
|
| 9119 |
+
},
|
| 9120 |
+
{
|
| 9121 |
+
"epoch": 0.9791696873036586,
|
| 9122 |
+
"grad_norm": 0.6978849172592163,
|
| 9123 |
+
"learning_rate": 1.1600429645542428e-06,
|
| 9124 |
+
"loss": 0.1461,
|
| 9125 |
+
"mean_token_accuracy": 0.9695205435156822,
|
| 9126 |
+
"num_tokens": 41492480.0,
|
| 9127 |
+
"step": 10130
|
| 9128 |
+
},
|
| 9129 |
+
{
|
| 9130 |
+
"epoch": 0.9801362911410758,
|
| 9131 |
+
"grad_norm": 0.6737282872200012,
|
| 9132 |
+
"learning_rate": 1.1063372717508057e-06,
|
| 9133 |
+
"loss": 0.1475,
|
| 9134 |
+
"mean_token_accuracy": 0.9696183927357197,
|
| 9135 |
+
"num_tokens": 41533440.0,
|
| 9136 |
+
"step": 10140
|
| 9137 |
+
},
|
| 9138 |
+
{
|
| 9139 |
+
"epoch": 0.981102894978493,
|
| 9140 |
+
"grad_norm": 0.8504825234413147,
|
| 9141 |
+
"learning_rate": 1.0526315789473685e-06,
|
| 9142 |
+
"loss": 0.1474,
|
| 9143 |
+
"mean_token_accuracy": 0.9688845336437225,
|
| 9144 |
+
"num_tokens": 41574400.0,
|
| 9145 |
+
"step": 10150
|
| 9146 |
+
},
|
| 9147 |
+
{
|
| 9148 |
+
"epoch": 0.9820694988159103,
|
| 9149 |
+
"grad_norm": 0.7281203269958496,
|
| 9150 |
+
"learning_rate": 9.989258861439314e-07,
|
| 9151 |
+
"loss": 0.1525,
|
| 9152 |
+
"mean_token_accuracy": 0.9684197634458542,
|
| 9153 |
+
"num_tokens": 41615360.0,
|
| 9154 |
+
"step": 10160
|
| 9155 |
+
},
|
| 9156 |
+
{
|
| 9157 |
+
"epoch": 0.9830361026533275,
|
| 9158 |
+
"grad_norm": 0.686882734298706,
|
| 9159 |
+
"learning_rate": 9.452201933404941e-07,
|
| 9160 |
+
"loss": 0.1371,
|
| 9161 |
+
"mean_token_accuracy": 0.971844419836998,
|
| 9162 |
+
"num_tokens": 41656320.0,
|
| 9163 |
+
"step": 10170
|
| 9164 |
+
},
|
| 9165 |
+
{
|
| 9166 |
+
"epoch": 0.9840027064907447,
|
| 9167 |
+
"grad_norm": 0.6194028854370117,
|
| 9168 |
+
"learning_rate": 8.91514500537057e-07,
|
| 9169 |
+
"loss": 0.14,
|
| 9170 |
+
"mean_token_accuracy": 0.9716487258672715,
|
| 9171 |
+
"num_tokens": 41697280.0,
|
| 9172 |
+
"step": 10180
|
| 9173 |
+
},
|
| 9174 |
+
{
|
| 9175 |
+
"epoch": 0.984969310328162,
|
| 9176 |
+
"grad_norm": 0.7701581716537476,
|
| 9177 |
+
"learning_rate": 8.378088077336197e-07,
|
| 9178 |
+
"loss": 0.1333,
|
| 9179 |
+
"mean_token_accuracy": 0.9725048907101155,
|
| 9180 |
+
"num_tokens": 41738240.0,
|
| 9181 |
+
"step": 10190
|
| 9182 |
+
},
|
| 9183 |
+
{
|
| 9184 |
+
"epoch": 0.9859359141655792,
|
| 9185 |
+
"grad_norm": 0.6333341002464294,
|
| 9186 |
+
"learning_rate": 7.841031149301827e-07,
|
| 9187 |
+
"loss": 0.1553,
|
| 9188 |
+
"mean_token_accuracy": 0.9693982377648354,
|
| 9189 |
+
"num_tokens": 41779200.0,
|
| 9190 |
+
"step": 10200
|
| 9191 |
+
},
|
| 9192 |
+
{
|
| 9193 |
+
"epoch": 0.9869025180029964,
|
| 9194 |
+
"grad_norm": 0.7522182464599609,
|
| 9195 |
+
"learning_rate": 7.303974221267455e-07,
|
| 9196 |
+
"loss": 0.136,
|
| 9197 |
+
"mean_token_accuracy": 0.9721624210476876,
|
| 9198 |
+
"num_tokens": 41820160.0,
|
| 9199 |
+
"step": 10210
|
| 9200 |
+
},
|
| 9201 |
+
{
|
| 9202 |
+
"epoch": 0.9878691218404138,
|
| 9203 |
+
"grad_norm": 0.7271556258201599,
|
| 9204 |
+
"learning_rate": 6.766917293233083e-07,
|
| 9205 |
+
"loss": 0.1372,
|
| 9206 |
+
"mean_token_accuracy": 0.9710371807217598,
|
| 9207 |
+
"num_tokens": 41861120.0,
|
| 9208 |
+
"step": 10220
|
| 9209 |
+
},
|
| 9210 |
+
{
|
| 9211 |
+
"epoch": 0.988835725677831,
|
| 9212 |
+
"grad_norm": 0.6557773351669312,
|
| 9213 |
+
"learning_rate": 6.229860365198711e-07,
|
| 9214 |
+
"loss": 0.1551,
|
| 9215 |
+
"mean_token_accuracy": 0.9677837543189526,
|
| 9216 |
+
"num_tokens": 41902080.0,
|
| 9217 |
+
"step": 10230
|
| 9218 |
+
},
|
| 9219 |
+
{
|
| 9220 |
+
"epoch": 0.9898023295152482,
|
| 9221 |
+
"grad_norm": 0.6414600014686584,
|
| 9222 |
+
"learning_rate": 5.69280343716434e-07,
|
| 9223 |
+
"loss": 0.1355,
|
| 9224 |
+
"mean_token_accuracy": 0.9722602687776088,
|
| 9225 |
+
"num_tokens": 41943040.0,
|
| 9226 |
+
"step": 10240
|
| 9227 |
+
},
|
| 9228 |
+
{
|
| 9229 |
+
"epoch": 0.9907689333526654,
|
| 9230 |
+
"grad_norm": 0.6378936767578125,
|
| 9231 |
+
"learning_rate": 5.155746509129967e-07,
|
| 9232 |
+
"loss": 0.1462,
|
| 9233 |
+
"mean_token_accuracy": 0.9706457868218422,
|
| 9234 |
+
"num_tokens": 41984000.0,
|
| 9235 |
+
"step": 10250
|
| 9236 |
+
},
|
| 9237 |
+
{
|
| 9238 |
+
"epoch": 0.9917355371900827,
|
| 9239 |
+
"grad_norm": 0.7637057304382324,
|
| 9240 |
+
"learning_rate": 4.618689581095596e-07,
|
| 9241 |
+
"loss": 0.1509,
|
| 9242 |
+
"mean_token_accuracy": 0.9690313085913658,
|
| 9243 |
+
"num_tokens": 42024960.0,
|
| 9244 |
+
"step": 10260
|
| 9245 |
+
},
|
| 9246 |
+
{
|
| 9247 |
+
"epoch": 0.9927021410274999,
|
| 9248 |
+
"grad_norm": 0.8268054127693176,
|
| 9249 |
+
"learning_rate": 4.081632653061225e-07,
|
| 9250 |
+
"loss": 0.1434,
|
| 9251 |
+
"mean_token_accuracy": 0.969985318928957,
|
| 9252 |
+
"num_tokens": 42065920.0,
|
| 9253 |
+
"step": 10270
|
| 9254 |
+
},
|
| 9255 |
+
{
|
| 9256 |
+
"epoch": 0.9936687448649171,
|
| 9257 |
+
"grad_norm": 0.685546338558197,
|
| 9258 |
+
"learning_rate": 3.544575725026853e-07,
|
| 9259 |
+
"loss": 0.1458,
|
| 9260 |
+
"mean_token_accuracy": 0.9699608586728573,
|
| 9261 |
+
"num_tokens": 42106880.0,
|
| 9262 |
+
"step": 10280
|
| 9263 |
+
},
|
| 9264 |
+
{
|
| 9265 |
+
"epoch": 0.9946353487023344,
|
| 9266 |
+
"grad_norm": 0.6523056626319885,
|
| 9267 |
+
"learning_rate": 3.007518796992482e-07,
|
| 9268 |
+
"loss": 0.1334,
|
| 9269 |
+
"mean_token_accuracy": 0.9717954970896244,
|
| 9270 |
+
"num_tokens": 42147840.0,
|
| 9271 |
+
"step": 10290
|
| 9272 |
+
},
|
| 9273 |
+
{
|
| 9274 |
+
"epoch": 0.9956019525397516,
|
| 9275 |
+
"grad_norm": 0.6793970465660095,
|
| 9276 |
+
"learning_rate": 2.47046186895811e-07,
|
| 9277 |
+
"loss": 0.1371,
|
| 9278 |
+
"mean_token_accuracy": 0.9715264149010181,
|
| 9279 |
+
"num_tokens": 42188800.0,
|
| 9280 |
+
"step": 10300
|
| 9281 |
+
},
|
| 9282 |
+
{
|
| 9283 |
+
"epoch": 0.9965685563771688,
|
| 9284 |
+
"grad_norm": 0.6603143215179443,
|
| 9285 |
+
"learning_rate": 1.933404940923738e-07,
|
| 9286 |
+
"loss": 0.1116,
|
| 9287 |
+
"mean_token_accuracy": 0.9765166319906712,
|
| 9288 |
+
"num_tokens": 42229760.0,
|
| 9289 |
+
"step": 10310
|
| 9290 |
+
},
|
| 9291 |
+
{
|
| 9292 |
+
"epoch": 0.9975351602145861,
|
| 9293 |
+
"grad_norm": 0.7608389258384705,
|
| 9294 |
+
"learning_rate": 1.3963480128893664e-07,
|
| 9295 |
+
"loss": 0.141,
|
| 9296 |
+
"mean_token_accuracy": 0.9707680970430375,
|
| 9297 |
+
"num_tokens": 42270720.0,
|
| 9298 |
+
"step": 10320
|
| 9299 |
+
},
|
| 9300 |
+
{
|
| 9301 |
+
"epoch": 0.9985017640520033,
|
| 9302 |
+
"grad_norm": 0.7448744177818298,
|
| 9303 |
+
"learning_rate": 8.592910848549947e-08,
|
| 9304 |
+
"loss": 0.1155,
|
| 9305 |
+
"mean_token_accuracy": 0.9754892319440842,
|
| 9306 |
+
"num_tokens": 42311680.0,
|
| 9307 |
+
"step": 10330
|
| 9308 |
+
},
|
| 9309 |
+
{
|
| 9310 |
+
"epoch": 0.9994683678894205,
|
| 9311 |
+
"grad_norm": 0.7076250910758972,
|
| 9312 |
+
"learning_rate": 3.2223415682062296e-08,
|
| 9313 |
+
"loss": 0.1324,
|
| 9314 |
+
"mean_token_accuracy": 0.9716731876134872,
|
| 9315 |
+
"num_tokens": 42352640.0,
|
| 9316 |
+
"step": 10340
|
| 9317 |
}
|
| 9318 |
],
|
| 9319 |
"logging_steps": 10,
|
|
|
|
| 9328 |
"should_evaluate": false,
|
| 9329 |
"should_log": false,
|
| 9330 |
"should_save": true,
|
| 9331 |
+
"should_training_stop": true
|
| 9332 |
},
|
| 9333 |
"attributes": {}
|
| 9334 |
}
|
| 9335 |
},
|
| 9336 |
+
"total_flos": 1.1198388221509632e+17,
|
| 9337 |
"train_batch_size": 1,
|
| 9338 |
"trial_name": null,
|
| 9339 |
"trial_params": null
|