Training in progress, step 24000, checkpoint
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +353 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 304481530
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66b4a4248a7192d139412e5bbbdef81f76412a3e7870379e9f41161e82b7cf85
|
| 3 |
size 304481530
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 402029570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c4621855465aeba5765607198fd192baa4b3edff4f7f1e94053a8afe0453717
|
| 3 |
size 402029570
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc4875c74fc1bd69630e72ea410fe72fed96581a5e0f87ca1c3cd95c11eab4bf
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b36d846027ce6ce2e8aac80bea8c782052ec6f49e3a2f76ef4b1f77548d3332
|
| 3 |
size 14960
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb0c022618aa5ec66f76638c525935e18c5ad2e5013a4144aa553f242b5aa5b6
|
| 3 |
size 14960
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a30898a99fc4282b5436ec16f38dc3882f6deaafcad8cea8a3afee4162fa83cd
|
| 3 |
size 14960
|
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 sha256:02db37ef78671abe18cc3a4d8bd0b184337ca89066c493fb89e665090a600550
|
| 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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -8058,6 +8058,356 @@
|
|
| 8058 |
"learning_rate": 0.0004926855403285216,
|
| 8059 |
"loss": 18.9653,
|
| 8060 |
"step": 23000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8061 |
}
|
| 8062 |
],
|
| 8063 |
"logging_steps": 20,
|
|
@@ -8077,7 +8427,7 @@
|
|
| 8077 |
"attributes": {}
|
| 8078 |
}
|
| 8079 |
},
|
| 8080 |
-
"total_flos": 1.
|
| 8081 |
"train_batch_size": 48,
|
| 8082 |
"trial_name": null,
|
| 8083 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.04679936235868786,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 24000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8058 |
"learning_rate": 0.0004926855403285216,
|
| 8059 |
"loss": 18.9653,
|
| 8060 |
"step": 23000
|
| 8061 |
+
},
|
| 8062 |
+
{
|
| 8063 |
+
"epoch": 0.044888388395708106,
|
| 8064 |
+
"grad_norm": 9.0,
|
| 8065 |
+
"learning_rate": 0.0004926790382976123,
|
| 8066 |
+
"loss": 19.081,
|
| 8067 |
+
"step": 23020
|
| 8068 |
+
},
|
| 8069 |
+
{
|
| 8070 |
+
"epoch": 0.04492738786434035,
|
| 8071 |
+
"grad_norm": 8.625,
|
| 8072 |
+
"learning_rate": 0.0004926725362667029,
|
| 8073 |
+
"loss": 19.0105,
|
| 8074 |
+
"step": 23040
|
| 8075 |
+
},
|
| 8076 |
+
{
|
| 8077 |
+
"epoch": 0.04496638733297259,
|
| 8078 |
+
"grad_norm": 9.4375,
|
| 8079 |
+
"learning_rate": 0.0004926660342357936,
|
| 8080 |
+
"loss": 18.9445,
|
| 8081 |
+
"step": 23060
|
| 8082 |
+
},
|
| 8083 |
+
{
|
| 8084 |
+
"epoch": 0.045005386801604826,
|
| 8085 |
+
"grad_norm": 9.0,
|
| 8086 |
+
"learning_rate": 0.0004926595322048842,
|
| 8087 |
+
"loss": 19.0298,
|
| 8088 |
+
"step": 23080
|
| 8089 |
+
},
|
| 8090 |
+
{
|
| 8091 |
+
"epoch": 0.04504438627023707,
|
| 8092 |
+
"grad_norm": 9.1875,
|
| 8093 |
+
"learning_rate": 0.0004926530301739749,
|
| 8094 |
+
"loss": 18.9949,
|
| 8095 |
+
"step": 23100
|
| 8096 |
+
},
|
| 8097 |
+
{
|
| 8098 |
+
"epoch": 0.04508338573886931,
|
| 8099 |
+
"grad_norm": 9.5,
|
| 8100 |
+
"learning_rate": 0.0004926465281430655,
|
| 8101 |
+
"loss": 19.053,
|
| 8102 |
+
"step": 23120
|
| 8103 |
+
},
|
| 8104 |
+
{
|
| 8105 |
+
"epoch": 0.045122385207501545,
|
| 8106 |
+
"grad_norm": 9.0,
|
| 8107 |
+
"learning_rate": 0.0004926400261121561,
|
| 8108 |
+
"loss": 19.0107,
|
| 8109 |
+
"step": 23140
|
| 8110 |
+
},
|
| 8111 |
+
{
|
| 8112 |
+
"epoch": 0.04516138467613379,
|
| 8113 |
+
"grad_norm": 9.6875,
|
| 8114 |
+
"learning_rate": 0.0004926335240812467,
|
| 8115 |
+
"loss": 18.8944,
|
| 8116 |
+
"step": 23160
|
| 8117 |
+
},
|
| 8118 |
+
{
|
| 8119 |
+
"epoch": 0.04520038414476603,
|
| 8120 |
+
"grad_norm": 9.625,
|
| 8121 |
+
"learning_rate": 0.0004926270220503374,
|
| 8122 |
+
"loss": 18.9518,
|
| 8123 |
+
"step": 23180
|
| 8124 |
+
},
|
| 8125 |
+
{
|
| 8126 |
+
"epoch": 0.04523938361339827,
|
| 8127 |
+
"grad_norm": 9.0625,
|
| 8128 |
+
"learning_rate": 0.0004926205200194281,
|
| 8129 |
+
"loss": 18.9757,
|
| 8130 |
+
"step": 23200
|
| 8131 |
+
},
|
| 8132 |
+
{
|
| 8133 |
+
"epoch": 0.045278383082030506,
|
| 8134 |
+
"grad_norm": 9.0625,
|
| 8135 |
+
"learning_rate": 0.0004926140179885187,
|
| 8136 |
+
"loss": 18.9609,
|
| 8137 |
+
"step": 23220
|
| 8138 |
+
},
|
| 8139 |
+
{
|
| 8140 |
+
"epoch": 0.04531738255066275,
|
| 8141 |
+
"grad_norm": 9.1875,
|
| 8142 |
+
"learning_rate": 0.0004926075159576094,
|
| 8143 |
+
"loss": 18.9258,
|
| 8144 |
+
"step": 23240
|
| 8145 |
+
},
|
| 8146 |
+
{
|
| 8147 |
+
"epoch": 0.04535638201929499,
|
| 8148 |
+
"grad_norm": 9.3125,
|
| 8149 |
+
"learning_rate": 0.0004926010139267,
|
| 8150 |
+
"loss": 19.0344,
|
| 8151 |
+
"step": 23260
|
| 8152 |
+
},
|
| 8153 |
+
{
|
| 8154 |
+
"epoch": 0.045395381487927225,
|
| 8155 |
+
"grad_norm": 9.125,
|
| 8156 |
+
"learning_rate": 0.0004925945118957907,
|
| 8157 |
+
"loss": 18.9683,
|
| 8158 |
+
"step": 23280
|
| 8159 |
+
},
|
| 8160 |
+
{
|
| 8161 |
+
"epoch": 0.04543438095655947,
|
| 8162 |
+
"grad_norm": 9.0,
|
| 8163 |
+
"learning_rate": 0.0004925880098648812,
|
| 8164 |
+
"loss": 18.9852,
|
| 8165 |
+
"step": 23300
|
| 8166 |
+
},
|
| 8167 |
+
{
|
| 8168 |
+
"epoch": 0.04547338042519171,
|
| 8169 |
+
"grad_norm": 9.875,
|
| 8170 |
+
"learning_rate": 0.0004925815078339719,
|
| 8171 |
+
"loss": 18.8897,
|
| 8172 |
+
"step": 23320
|
| 8173 |
+
},
|
| 8174 |
+
{
|
| 8175 |
+
"epoch": 0.045512379893823944,
|
| 8176 |
+
"grad_norm": 10.3125,
|
| 8177 |
+
"learning_rate": 0.0004925750058030625,
|
| 8178 |
+
"loss": 18.9442,
|
| 8179 |
+
"step": 23340
|
| 8180 |
+
},
|
| 8181 |
+
{
|
| 8182 |
+
"epoch": 0.045551379362456186,
|
| 8183 |
+
"grad_norm": 7.9375,
|
| 8184 |
+
"learning_rate": 0.0004925685037721532,
|
| 8185 |
+
"loss": 18.8775,
|
| 8186 |
+
"step": 23360
|
| 8187 |
+
},
|
| 8188 |
+
{
|
| 8189 |
+
"epoch": 0.04559037883108843,
|
| 8190 |
+
"grad_norm": 9.625,
|
| 8191 |
+
"learning_rate": 0.0004925620017412439,
|
| 8192 |
+
"loss": 18.8892,
|
| 8193 |
+
"step": 23380
|
| 8194 |
+
},
|
| 8195 |
+
{
|
| 8196 |
+
"epoch": 0.04562937829972066,
|
| 8197 |
+
"grad_norm": 8.4375,
|
| 8198 |
+
"learning_rate": 0.0004925554997103345,
|
| 8199 |
+
"loss": 18.8647,
|
| 8200 |
+
"step": 23400
|
| 8201 |
+
},
|
| 8202 |
+
{
|
| 8203 |
+
"epoch": 0.045668377768352905,
|
| 8204 |
+
"grad_norm": 9.3125,
|
| 8205 |
+
"learning_rate": 0.0004925489976794252,
|
| 8206 |
+
"loss": 18.8749,
|
| 8207 |
+
"step": 23420
|
| 8208 |
+
},
|
| 8209 |
+
{
|
| 8210 |
+
"epoch": 0.04570737723698515,
|
| 8211 |
+
"grad_norm": 9.3125,
|
| 8212 |
+
"learning_rate": 0.0004925424956485158,
|
| 8213 |
+
"loss": 19.0213,
|
| 8214 |
+
"step": 23440
|
| 8215 |
+
},
|
| 8216 |
+
{
|
| 8217 |
+
"epoch": 0.04574637670561739,
|
| 8218 |
+
"grad_norm": 9.0,
|
| 8219 |
+
"learning_rate": 0.0004925359936176065,
|
| 8220 |
+
"loss": 18.902,
|
| 8221 |
+
"step": 23460
|
| 8222 |
+
},
|
| 8223 |
+
{
|
| 8224 |
+
"epoch": 0.045785376174249624,
|
| 8225 |
+
"grad_norm": 8.5,
|
| 8226 |
+
"learning_rate": 0.0004925294915866971,
|
| 8227 |
+
"loss": 18.9389,
|
| 8228 |
+
"step": 23480
|
| 8229 |
+
},
|
| 8230 |
+
{
|
| 8231 |
+
"epoch": 0.045824375642881866,
|
| 8232 |
+
"grad_norm": 9.0,
|
| 8233 |
+
"learning_rate": 0.0004925229895557878,
|
| 8234 |
+
"loss": 18.9333,
|
| 8235 |
+
"step": 23500
|
| 8236 |
+
},
|
| 8237 |
+
{
|
| 8238 |
+
"epoch": 0.04586337511151411,
|
| 8239 |
+
"grad_norm": 8.0625,
|
| 8240 |
+
"learning_rate": 0.0004925164875248785,
|
| 8241 |
+
"loss": 18.8777,
|
| 8242 |
+
"step": 23520
|
| 8243 |
+
},
|
| 8244 |
+
{
|
| 8245 |
+
"epoch": 0.04590237458014634,
|
| 8246 |
+
"grad_norm": 10.1875,
|
| 8247 |
+
"learning_rate": 0.000492509985493969,
|
| 8248 |
+
"loss": 18.92,
|
| 8249 |
+
"step": 23540
|
| 8250 |
+
},
|
| 8251 |
+
{
|
| 8252 |
+
"epoch": 0.045941374048778585,
|
| 8253 |
+
"grad_norm": 8.5625,
|
| 8254 |
+
"learning_rate": 0.0004925034834630597,
|
| 8255 |
+
"loss": 18.8384,
|
| 8256 |
+
"step": 23560
|
| 8257 |
+
},
|
| 8258 |
+
{
|
| 8259 |
+
"epoch": 0.04598037351741083,
|
| 8260 |
+
"grad_norm": 9.25,
|
| 8261 |
+
"learning_rate": 0.0004924969814321503,
|
| 8262 |
+
"loss": 18.8315,
|
| 8263 |
+
"step": 23580
|
| 8264 |
+
},
|
| 8265 |
+
{
|
| 8266 |
+
"epoch": 0.04601937298604306,
|
| 8267 |
+
"grad_norm": 9.375,
|
| 8268 |
+
"learning_rate": 0.000492490479401241,
|
| 8269 |
+
"loss": 18.9058,
|
| 8270 |
+
"step": 23600
|
| 8271 |
+
},
|
| 8272 |
+
{
|
| 8273 |
+
"epoch": 0.046058372454675305,
|
| 8274 |
+
"grad_norm": 9.9375,
|
| 8275 |
+
"learning_rate": 0.0004924839773703316,
|
| 8276 |
+
"loss": 18.9039,
|
| 8277 |
+
"step": 23620
|
| 8278 |
+
},
|
| 8279 |
+
{
|
| 8280 |
+
"epoch": 0.04609737192330755,
|
| 8281 |
+
"grad_norm": 9.6875,
|
| 8282 |
+
"learning_rate": 0.0004924774753394223,
|
| 8283 |
+
"loss": 18.9109,
|
| 8284 |
+
"step": 23640
|
| 8285 |
+
},
|
| 8286 |
+
{
|
| 8287 |
+
"epoch": 0.04613637139193978,
|
| 8288 |
+
"grad_norm": 9.125,
|
| 8289 |
+
"learning_rate": 0.000492470973308513,
|
| 8290 |
+
"loss": 18.8286,
|
| 8291 |
+
"step": 23660
|
| 8292 |
+
},
|
| 8293 |
+
{
|
| 8294 |
+
"epoch": 0.046175370860572024,
|
| 8295 |
+
"grad_norm": 9.0625,
|
| 8296 |
+
"learning_rate": 0.0004924644712776036,
|
| 8297 |
+
"loss": 18.8554,
|
| 8298 |
+
"step": 23680
|
| 8299 |
+
},
|
| 8300 |
+
{
|
| 8301 |
+
"epoch": 0.046214370329204266,
|
| 8302 |
+
"grad_norm": 8.5,
|
| 8303 |
+
"learning_rate": 0.0004924579692466943,
|
| 8304 |
+
"loss": 18.9488,
|
| 8305 |
+
"step": 23700
|
| 8306 |
+
},
|
| 8307 |
+
{
|
| 8308 |
+
"epoch": 0.04625336979783651,
|
| 8309 |
+
"grad_norm": 8.875,
|
| 8310 |
+
"learning_rate": 0.0004924514672157849,
|
| 8311 |
+
"loss": 18.89,
|
| 8312 |
+
"step": 23720
|
| 8313 |
+
},
|
| 8314 |
+
{
|
| 8315 |
+
"epoch": 0.04629236926646874,
|
| 8316 |
+
"grad_norm": 8.0625,
|
| 8317 |
+
"learning_rate": 0.0004924449651848756,
|
| 8318 |
+
"loss": 18.901,
|
| 8319 |
+
"step": 23740
|
| 8320 |
+
},
|
| 8321 |
+
{
|
| 8322 |
+
"epoch": 0.046331368735100985,
|
| 8323 |
+
"grad_norm": 9.125,
|
| 8324 |
+
"learning_rate": 0.0004924384631539661,
|
| 8325 |
+
"loss": 18.8675,
|
| 8326 |
+
"step": 23760
|
| 8327 |
+
},
|
| 8328 |
+
{
|
| 8329 |
+
"epoch": 0.04637036820373323,
|
| 8330 |
+
"grad_norm": 10.9375,
|
| 8331 |
+
"learning_rate": 0.0004924319611230568,
|
| 8332 |
+
"loss": 18.8375,
|
| 8333 |
+
"step": 23780
|
| 8334 |
+
},
|
| 8335 |
+
{
|
| 8336 |
+
"epoch": 0.04640936767236546,
|
| 8337 |
+
"grad_norm": 10.125,
|
| 8338 |
+
"learning_rate": 0.0004924254590921474,
|
| 8339 |
+
"loss": 18.8213,
|
| 8340 |
+
"step": 23800
|
| 8341 |
+
},
|
| 8342 |
+
{
|
| 8343 |
+
"epoch": 0.046448367140997704,
|
| 8344 |
+
"grad_norm": 8.5625,
|
| 8345 |
+
"learning_rate": 0.0004924189570612381,
|
| 8346 |
+
"loss": 18.8256,
|
| 8347 |
+
"step": 23820
|
| 8348 |
+
},
|
| 8349 |
+
{
|
| 8350 |
+
"epoch": 0.046487366609629946,
|
| 8351 |
+
"grad_norm": 9.9375,
|
| 8352 |
+
"learning_rate": 0.0004924124550303288,
|
| 8353 |
+
"loss": 18.9225,
|
| 8354 |
+
"step": 23840
|
| 8355 |
+
},
|
| 8356 |
+
{
|
| 8357 |
+
"epoch": 0.04652636607826218,
|
| 8358 |
+
"grad_norm": 9.375,
|
| 8359 |
+
"learning_rate": 0.0004924059529994194,
|
| 8360 |
+
"loss": 18.8879,
|
| 8361 |
+
"step": 23860
|
| 8362 |
+
},
|
| 8363 |
+
{
|
| 8364 |
+
"epoch": 0.04656536554689442,
|
| 8365 |
+
"grad_norm": 9.0625,
|
| 8366 |
+
"learning_rate": 0.0004923994509685101,
|
| 8367 |
+
"loss": 18.7802,
|
| 8368 |
+
"step": 23880
|
| 8369 |
+
},
|
| 8370 |
+
{
|
| 8371 |
+
"epoch": 0.046604365015526665,
|
| 8372 |
+
"grad_norm": 10.25,
|
| 8373 |
+
"learning_rate": 0.0004923929489376007,
|
| 8374 |
+
"loss": 18.7438,
|
| 8375 |
+
"step": 23900
|
| 8376 |
+
},
|
| 8377 |
+
{
|
| 8378 |
+
"epoch": 0.0466433644841589,
|
| 8379 |
+
"grad_norm": 10.4375,
|
| 8380 |
+
"learning_rate": 0.0004923864469066913,
|
| 8381 |
+
"loss": 18.8514,
|
| 8382 |
+
"step": 23920
|
| 8383 |
+
},
|
| 8384 |
+
{
|
| 8385 |
+
"epoch": 0.04668236395279114,
|
| 8386 |
+
"grad_norm": 9.0625,
|
| 8387 |
+
"learning_rate": 0.0004923799448757819,
|
| 8388 |
+
"loss": 18.8762,
|
| 8389 |
+
"step": 23940
|
| 8390 |
+
},
|
| 8391 |
+
{
|
| 8392 |
+
"epoch": 0.046721363421423384,
|
| 8393 |
+
"grad_norm": 9.75,
|
| 8394 |
+
"learning_rate": 0.0004923734428448726,
|
| 8395 |
+
"loss": 18.9164,
|
| 8396 |
+
"step": 23960
|
| 8397 |
+
},
|
| 8398 |
+
{
|
| 8399 |
+
"epoch": 0.046760362890055626,
|
| 8400 |
+
"grad_norm": 8.9375,
|
| 8401 |
+
"learning_rate": 0.0004923669408139632,
|
| 8402 |
+
"loss": 18.8688,
|
| 8403 |
+
"step": 23980
|
| 8404 |
+
},
|
| 8405 |
+
{
|
| 8406 |
+
"epoch": 0.04679936235868786,
|
| 8407 |
+
"grad_norm": 8.625,
|
| 8408 |
+
"learning_rate": 0.0004923604387830539,
|
| 8409 |
+
"loss": 18.9094,
|
| 8410 |
+
"step": 24000
|
| 8411 |
}
|
| 8412 |
],
|
| 8413 |
"logging_steps": 20,
|
|
|
|
| 8427 |
"attributes": {}
|
| 8428 |
}
|
| 8429 |
},
|
| 8430 |
+
"total_flos": 1.7643985261266207e+19,
|
| 8431 |
"train_batch_size": 48,
|
| 8432 |
"trial_name": null,
|
| 8433 |
"trial_params": null
|