Training in progress, step 47000, 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 sha256:61861334acc6bb521d776a8a58ed328bbeb2de5c3e2d7d0e5709ba486e23c98d
|
| 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 sha256:73db8243046a9370659a933b5ec361f5ee73427ce04fbf0616ff171f1b1f661a
|
| 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:eeb827995351c3d8f00d3e4a054e55284730f5ad8a94717cbfee647587203dfc
|
| 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:fe00d92c4d85634ea2d18e88e15dc31892cd4d0dfdc0c6cb5734f60c99b54171
|
| 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 sha256:5dd404242a49cfa47d2c8458354d2be2e83dfd17d807cd66825081206266b540
|
| 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 sha256:7c8b06b6abf357322e20ece09b4c2e9484c31738c81c851095e9fd935ec320ec
|
| 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:ea83e001a4a201200c8649056ae9597b15ab7c79e678a157d8ac37e39999806e
|
| 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,
|
|
@@ -16108,6 +16108,356 @@
|
|
| 16108 |
"learning_rate": 0.0004887641698045367,
|
| 16109 |
"loss": 17.8104,
|
| 16110 |
"step": 46000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16111 |
}
|
| 16112 |
],
|
| 16113 |
"logging_steps": 20,
|
|
@@ -16127,7 +16477,7 @@
|
|
| 16127 |
"attributes": {}
|
| 16128 |
}
|
| 16129 |
},
|
| 16130 |
-
"total_flos": 3.
|
| 16131 |
"train_batch_size": 48,
|
| 16132 |
"trial_name": null,
|
| 16133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.06962179073171021,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 47000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16108 |
"learning_rate": 0.0004887641698045367,
|
| 16109 |
"loss": 17.8104,
|
| 16110 |
"step": 46000
|
| 16111 |
+
},
|
| 16112 |
+
{
|
| 16113 |
+
"epoch": 0.06817010232921923,
|
| 16114 |
+
"grad_norm": 7.0,
|
| 16115 |
+
"learning_rate": 0.0004887592308695292,
|
| 16116 |
+
"loss": 17.77,
|
| 16117 |
+
"step": 46020
|
| 16118 |
+
},
|
| 16119 |
+
{
|
| 16120 |
+
"epoch": 0.06819972862314762,
|
| 16121 |
+
"grad_norm": 6.8125,
|
| 16122 |
+
"learning_rate": 0.0004887542919345216,
|
| 16123 |
+
"loss": 17.819,
|
| 16124 |
+
"step": 46040
|
| 16125 |
+
},
|
| 16126 |
+
{
|
| 16127 |
+
"epoch": 0.068229354917076,
|
| 16128 |
+
"grad_norm": 7.78125,
|
| 16129 |
+
"learning_rate": 0.000488749352999514,
|
| 16130 |
+
"loss": 17.7926,
|
| 16131 |
+
"step": 46060
|
| 16132 |
+
},
|
| 16133 |
+
{
|
| 16134 |
+
"epoch": 0.06825898121100439,
|
| 16135 |
+
"grad_norm": 7.03125,
|
| 16136 |
+
"learning_rate": 0.0004887444140645065,
|
| 16137 |
+
"loss": 17.7642,
|
| 16138 |
+
"step": 46080
|
| 16139 |
+
},
|
| 16140 |
+
{
|
| 16141 |
+
"epoch": 0.06828860750493278,
|
| 16142 |
+
"grad_norm": 8.25,
|
| 16143 |
+
"learning_rate": 0.0004887394751294989,
|
| 16144 |
+
"loss": 17.8077,
|
| 16145 |
+
"step": 46100
|
| 16146 |
+
},
|
| 16147 |
+
{
|
| 16148 |
+
"epoch": 0.06831823379886116,
|
| 16149 |
+
"grad_norm": 7.3125,
|
| 16150 |
+
"learning_rate": 0.0004887345361944914,
|
| 16151 |
+
"loss": 17.7471,
|
| 16152 |
+
"step": 46120
|
| 16153 |
+
},
|
| 16154 |
+
{
|
| 16155 |
+
"epoch": 0.06834786009278955,
|
| 16156 |
+
"grad_norm": 7.28125,
|
| 16157 |
+
"learning_rate": 0.0004887295972594838,
|
| 16158 |
+
"loss": 17.7648,
|
| 16159 |
+
"step": 46140
|
| 16160 |
+
},
|
| 16161 |
+
{
|
| 16162 |
+
"epoch": 0.06837748638671794,
|
| 16163 |
+
"grad_norm": 7.34375,
|
| 16164 |
+
"learning_rate": 0.0004887246583244763,
|
| 16165 |
+
"loss": 17.6991,
|
| 16166 |
+
"step": 46160
|
| 16167 |
+
},
|
| 16168 |
+
{
|
| 16169 |
+
"epoch": 0.06840711268064632,
|
| 16170 |
+
"grad_norm": 7.78125,
|
| 16171 |
+
"learning_rate": 0.0004887197193894687,
|
| 16172 |
+
"loss": 17.75,
|
| 16173 |
+
"step": 46180
|
| 16174 |
+
},
|
| 16175 |
+
{
|
| 16176 |
+
"epoch": 0.06843673897457471,
|
| 16177 |
+
"grad_norm": 7.6875,
|
| 16178 |
+
"learning_rate": 0.000488714780454461,
|
| 16179 |
+
"loss": 17.7536,
|
| 16180 |
+
"step": 46200
|
| 16181 |
+
},
|
| 16182 |
+
{
|
| 16183 |
+
"epoch": 0.0684663652685031,
|
| 16184 |
+
"grad_norm": 6.875,
|
| 16185 |
+
"learning_rate": 0.0004887098415194534,
|
| 16186 |
+
"loss": 17.7599,
|
| 16187 |
+
"step": 46220
|
| 16188 |
+
},
|
| 16189 |
+
{
|
| 16190 |
+
"epoch": 0.06849599156243148,
|
| 16191 |
+
"grad_norm": 7.96875,
|
| 16192 |
+
"learning_rate": 0.000488704902584446,
|
| 16193 |
+
"loss": 17.7974,
|
| 16194 |
+
"step": 46240
|
| 16195 |
+
},
|
| 16196 |
+
{
|
| 16197 |
+
"epoch": 0.06852561785635988,
|
| 16198 |
+
"grad_norm": 7.3125,
|
| 16199 |
+
"learning_rate": 0.0004886999636494383,
|
| 16200 |
+
"loss": 17.7135,
|
| 16201 |
+
"step": 46260
|
| 16202 |
+
},
|
| 16203 |
+
{
|
| 16204 |
+
"epoch": 0.06855524415028827,
|
| 16205 |
+
"grad_norm": 6.59375,
|
| 16206 |
+
"learning_rate": 0.0004886950247144307,
|
| 16207 |
+
"loss": 17.7284,
|
| 16208 |
+
"step": 46280
|
| 16209 |
+
},
|
| 16210 |
+
{
|
| 16211 |
+
"epoch": 0.06858487044421666,
|
| 16212 |
+
"grad_norm": 7.78125,
|
| 16213 |
+
"learning_rate": 0.0004886900857794232,
|
| 16214 |
+
"loss": 17.7145,
|
| 16215 |
+
"step": 46300
|
| 16216 |
+
},
|
| 16217 |
+
{
|
| 16218 |
+
"epoch": 0.06861449673814504,
|
| 16219 |
+
"grad_norm": 7.71875,
|
| 16220 |
+
"learning_rate": 0.0004886851468444156,
|
| 16221 |
+
"loss": 17.7295,
|
| 16222 |
+
"step": 46320
|
| 16223 |
+
},
|
| 16224 |
+
{
|
| 16225 |
+
"epoch": 0.06864412303207343,
|
| 16226 |
+
"grad_norm": 7.09375,
|
| 16227 |
+
"learning_rate": 0.0004886802079094081,
|
| 16228 |
+
"loss": 17.747,
|
| 16229 |
+
"step": 46340
|
| 16230 |
+
},
|
| 16231 |
+
{
|
| 16232 |
+
"epoch": 0.06867374932600182,
|
| 16233 |
+
"grad_norm": 7.5,
|
| 16234 |
+
"learning_rate": 0.0004886752689744005,
|
| 16235 |
+
"loss": 17.7722,
|
| 16236 |
+
"step": 46360
|
| 16237 |
+
},
|
| 16238 |
+
{
|
| 16239 |
+
"epoch": 0.0687033756199302,
|
| 16240 |
+
"grad_norm": 6.34375,
|
| 16241 |
+
"learning_rate": 0.0004886703300393929,
|
| 16242 |
+
"loss": 17.6833,
|
| 16243 |
+
"step": 46380
|
| 16244 |
+
},
|
| 16245 |
+
{
|
| 16246 |
+
"epoch": 0.06873300191385859,
|
| 16247 |
+
"grad_norm": 7.03125,
|
| 16248 |
+
"learning_rate": 0.0004886653911043854,
|
| 16249 |
+
"loss": 17.7234,
|
| 16250 |
+
"step": 46400
|
| 16251 |
+
},
|
| 16252 |
+
{
|
| 16253 |
+
"epoch": 0.06876262820778697,
|
| 16254 |
+
"grad_norm": 6.4375,
|
| 16255 |
+
"learning_rate": 0.0004886604521693778,
|
| 16256 |
+
"loss": 17.7592,
|
| 16257 |
+
"step": 46420
|
| 16258 |
+
},
|
| 16259 |
+
{
|
| 16260 |
+
"epoch": 0.06879225450171536,
|
| 16261 |
+
"grad_norm": 7.40625,
|
| 16262 |
+
"learning_rate": 0.0004886555132343702,
|
| 16263 |
+
"loss": 17.7566,
|
| 16264 |
+
"step": 46440
|
| 16265 |
+
},
|
| 16266 |
+
{
|
| 16267 |
+
"epoch": 0.06882188079564375,
|
| 16268 |
+
"grad_norm": 7.53125,
|
| 16269 |
+
"learning_rate": 0.0004886505742993627,
|
| 16270 |
+
"loss": 17.7591,
|
| 16271 |
+
"step": 46460
|
| 16272 |
+
},
|
| 16273 |
+
{
|
| 16274 |
+
"epoch": 0.06885150708957213,
|
| 16275 |
+
"grad_norm": 7.09375,
|
| 16276 |
+
"learning_rate": 0.0004886456353643551,
|
| 16277 |
+
"loss": 17.7118,
|
| 16278 |
+
"step": 46480
|
| 16279 |
+
},
|
| 16280 |
+
{
|
| 16281 |
+
"epoch": 0.06888113338350052,
|
| 16282 |
+
"grad_norm": 7.53125,
|
| 16283 |
+
"learning_rate": 0.0004886406964293476,
|
| 16284 |
+
"loss": 17.7433,
|
| 16285 |
+
"step": 46500
|
| 16286 |
+
},
|
| 16287 |
+
{
|
| 16288 |
+
"epoch": 0.0689107596774289,
|
| 16289 |
+
"grad_norm": 7.5,
|
| 16290 |
+
"learning_rate": 0.00048863575749434,
|
| 16291 |
+
"loss": 17.6708,
|
| 16292 |
+
"step": 46520
|
| 16293 |
+
},
|
| 16294 |
+
{
|
| 16295 |
+
"epoch": 0.0689403859713573,
|
| 16296 |
+
"grad_norm": 7.25,
|
| 16297 |
+
"learning_rate": 0.0004886308185593324,
|
| 16298 |
+
"loss": 17.6743,
|
| 16299 |
+
"step": 46540
|
| 16300 |
+
},
|
| 16301 |
+
{
|
| 16302 |
+
"epoch": 0.06897001226528568,
|
| 16303 |
+
"grad_norm": 6.625,
|
| 16304 |
+
"learning_rate": 0.0004886258796243249,
|
| 16305 |
+
"loss": 17.8227,
|
| 16306 |
+
"step": 46560
|
| 16307 |
+
},
|
| 16308 |
+
{
|
| 16309 |
+
"epoch": 0.06899963855921408,
|
| 16310 |
+
"grad_norm": 6.75,
|
| 16311 |
+
"learning_rate": 0.0004886209406893173,
|
| 16312 |
+
"loss": 17.6357,
|
| 16313 |
+
"step": 46580
|
| 16314 |
+
},
|
| 16315 |
+
{
|
| 16316 |
+
"epoch": 0.06902926485314247,
|
| 16317 |
+
"grad_norm": 7.59375,
|
| 16318 |
+
"learning_rate": 0.0004886160017543097,
|
| 16319 |
+
"loss": 17.7412,
|
| 16320 |
+
"step": 46600
|
| 16321 |
+
},
|
| 16322 |
+
{
|
| 16323 |
+
"epoch": 0.06905889114707085,
|
| 16324 |
+
"grad_norm": 7.4375,
|
| 16325 |
+
"learning_rate": 0.0004886110628193022,
|
| 16326 |
+
"loss": 17.6527,
|
| 16327 |
+
"step": 46620
|
| 16328 |
+
},
|
| 16329 |
+
{
|
| 16330 |
+
"epoch": 0.06908851744099924,
|
| 16331 |
+
"grad_norm": 6.5625,
|
| 16332 |
+
"learning_rate": 0.0004886061238842946,
|
| 16333 |
+
"loss": 17.7538,
|
| 16334 |
+
"step": 46640
|
| 16335 |
+
},
|
| 16336 |
+
{
|
| 16337 |
+
"epoch": 0.06911814373492763,
|
| 16338 |
+
"grad_norm": 6.84375,
|
| 16339 |
+
"learning_rate": 0.000488601184949287,
|
| 16340 |
+
"loss": 17.6942,
|
| 16341 |
+
"step": 46660
|
| 16342 |
+
},
|
| 16343 |
+
{
|
| 16344 |
+
"epoch": 0.06914777002885601,
|
| 16345 |
+
"grad_norm": 7.25,
|
| 16346 |
+
"learning_rate": 0.0004885962460142795,
|
| 16347 |
+
"loss": 17.7382,
|
| 16348 |
+
"step": 46680
|
| 16349 |
+
},
|
| 16350 |
+
{
|
| 16351 |
+
"epoch": 0.0691773963227844,
|
| 16352 |
+
"grad_norm": 7.0,
|
| 16353 |
+
"learning_rate": 0.0004885913070792719,
|
| 16354 |
+
"loss": 17.6836,
|
| 16355 |
+
"step": 46700
|
| 16356 |
+
},
|
| 16357 |
+
{
|
| 16358 |
+
"epoch": 0.06920702261671278,
|
| 16359 |
+
"grad_norm": 8.25,
|
| 16360 |
+
"learning_rate": 0.0004885863681442644,
|
| 16361 |
+
"loss": 17.7226,
|
| 16362 |
+
"step": 46720
|
| 16363 |
+
},
|
| 16364 |
+
{
|
| 16365 |
+
"epoch": 0.06923664891064117,
|
| 16366 |
+
"grad_norm": 7.03125,
|
| 16367 |
+
"learning_rate": 0.0004885814292092568,
|
| 16368 |
+
"loss": 17.759,
|
| 16369 |
+
"step": 46740
|
| 16370 |
+
},
|
| 16371 |
+
{
|
| 16372 |
+
"epoch": 0.06926627520456956,
|
| 16373 |
+
"grad_norm": 7.25,
|
| 16374 |
+
"learning_rate": 0.0004885764902742493,
|
| 16375 |
+
"loss": 17.7323,
|
| 16376 |
+
"step": 46760
|
| 16377 |
+
},
|
| 16378 |
+
{
|
| 16379 |
+
"epoch": 0.06929590149849794,
|
| 16380 |
+
"grad_norm": 7.28125,
|
| 16381 |
+
"learning_rate": 0.0004885715513392417,
|
| 16382 |
+
"loss": 17.618,
|
| 16383 |
+
"step": 46780
|
| 16384 |
+
},
|
| 16385 |
+
{
|
| 16386 |
+
"epoch": 0.06932552779242633,
|
| 16387 |
+
"grad_norm": 6.75,
|
| 16388 |
+
"learning_rate": 0.000488566612404234,
|
| 16389 |
+
"loss": 17.7459,
|
| 16390 |
+
"step": 46800
|
| 16391 |
+
},
|
| 16392 |
+
{
|
| 16393 |
+
"epoch": 0.06935515408635472,
|
| 16394 |
+
"grad_norm": 6.96875,
|
| 16395 |
+
"learning_rate": 0.0004885616734692264,
|
| 16396 |
+
"loss": 17.6692,
|
| 16397 |
+
"step": 46820
|
| 16398 |
+
},
|
| 16399 |
+
{
|
| 16400 |
+
"epoch": 0.0693847803802831,
|
| 16401 |
+
"grad_norm": 6.5,
|
| 16402 |
+
"learning_rate": 0.000488556734534219,
|
| 16403 |
+
"loss": 17.7568,
|
| 16404 |
+
"step": 46840
|
| 16405 |
+
},
|
| 16406 |
+
{
|
| 16407 |
+
"epoch": 0.06941440667421149,
|
| 16408 |
+
"grad_norm": 8.375,
|
| 16409 |
+
"learning_rate": 0.0004885517955992113,
|
| 16410 |
+
"loss": 17.6868,
|
| 16411 |
+
"step": 46860
|
| 16412 |
+
},
|
| 16413 |
+
{
|
| 16414 |
+
"epoch": 0.06944403296813988,
|
| 16415 |
+
"grad_norm": 7.375,
|
| 16416 |
+
"learning_rate": 0.0004885468566642037,
|
| 16417 |
+
"loss": 17.6687,
|
| 16418 |
+
"step": 46880
|
| 16419 |
+
},
|
| 16420 |
+
{
|
| 16421 |
+
"epoch": 0.06947365926206828,
|
| 16422 |
+
"grad_norm": 6.6875,
|
| 16423 |
+
"learning_rate": 0.0004885419177291962,
|
| 16424 |
+
"loss": 17.6522,
|
| 16425 |
+
"step": 46900
|
| 16426 |
+
},
|
| 16427 |
+
{
|
| 16428 |
+
"epoch": 0.06950328555599666,
|
| 16429 |
+
"grad_norm": 7.71875,
|
| 16430 |
+
"learning_rate": 0.0004885369787941886,
|
| 16431 |
+
"loss": 17.7001,
|
| 16432 |
+
"step": 46920
|
| 16433 |
+
},
|
| 16434 |
+
{
|
| 16435 |
+
"epoch": 0.06953291184992505,
|
| 16436 |
+
"grad_norm": 8.875,
|
| 16437 |
+
"learning_rate": 0.0004885320398591811,
|
| 16438 |
+
"loss": 17.6782,
|
| 16439 |
+
"step": 46940
|
| 16440 |
+
},
|
| 16441 |
+
{
|
| 16442 |
+
"epoch": 0.06956253814385344,
|
| 16443 |
+
"grad_norm": 7.0,
|
| 16444 |
+
"learning_rate": 0.0004885271009241735,
|
| 16445 |
+
"loss": 17.6051,
|
| 16446 |
+
"step": 46960
|
| 16447 |
+
},
|
| 16448 |
+
{
|
| 16449 |
+
"epoch": 0.06959216443778182,
|
| 16450 |
+
"grad_norm": 6.5,
|
| 16451 |
+
"learning_rate": 0.0004885221619891659,
|
| 16452 |
+
"loss": 17.7128,
|
| 16453 |
+
"step": 46980
|
| 16454 |
+
},
|
| 16455 |
+
{
|
| 16456 |
+
"epoch": 0.06962179073171021,
|
| 16457 |
+
"grad_norm": 7.21875,
|
| 16458 |
+
"learning_rate": 0.0004885172230541584,
|
| 16459 |
+
"loss": 17.6774,
|
| 16460 |
+
"step": 47000
|
| 16461 |
}
|
| 16462 |
],
|
| 16463 |
"logging_steps": 20,
|
|
|
|
| 16477 |
"attributes": {}
|
| 16478 |
}
|
| 16479 |
},
|
| 16480 |
+
"total_flos": 3.4553025468416655e+19,
|
| 16481 |
"train_batch_size": 48,
|
| 16482 |
"trial_name": null,
|
| 16483 |
"trial_params": null
|