Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5690ea1cc3b4f77fb1272737f6f44e25b61190b2ae279507e455d4380bc72cb0
+oid sha256:75384ded93691056a4c4d66108b5a381ad8f1a4206fce46818f57319711683b5
 size 1101095848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3191df4a7ebff57f52d56f1d1b3ee4c763f5856dbbb43e365e7e17785ced576c
+oid sha256:87948ff20c546169bb01d98777834cf787fd807b936d83032482d2073870d938
 size 559894228

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c51e49fb86ba5e5a976543873eff8e814384029ff1af4f68a9bc25a4a98cae
+oid sha256:cb1f3116219696737693cc163501b5c6063c7f3c171b078cd94b995dc7895104
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa6bcc52407518f698c633b9792c002cb5dd8257f93073027d9022c42ab4e3d
+oid sha256:2253e3f770ee094eadd180118ee6d216e9ad21066d91c74fb1d778a716ee5673
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4800c31be139610de71b2612a2d85e49bc96885e2d6d4e8268edcc912daa1a00
+oid sha256:b3dbfb86967403571289f6177e844fc07aac0a2589a948b94e8884f00f306aac
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283704e7ccdeab26b2e2c3313c52d2e3b6822da48736ddb43c2368b99fa5a0e2
+oid sha256:21db0e351d0df8ab8e4063c8b830ec14e8de3d830f2cd69f6222868220610bbb
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83ad033682a41f481e8df8c27def5b22cc4a92978d1b43dc606344eebd6b9b5
+oid sha256:af3110e42e6fa390395ddf1848268d06650afa848c6d67eaf9555fb6d8116849
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a264aedcd0e51c366e6d0b581e19f9ee47878ad72496e46cb3b8bfe7c9af72e
+oid sha256:a78b4df3e4f76b69cfb1e07d58f0c81218e6165de1b90bbb7f57e53e1d7c49ff
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf21450405cc8a747a5ef1603a4263e93598e50feacb88fa11424eba61791f68
+oid sha256:5a92cbcf079d4c51f0c1c56532e5a6d1ab892c77e0f70d16eac89c85cdc3bce9
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4582a283ba0351ea18e55d621845e95f011517edfcc228afb139ac83800ae3a2
+oid sha256:762a297b29e3e5cddb3f3316d110bb9381faacc97044168f70e570fbbc9c3558
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d606eeb1aa97b417de3c30d0a970be83ac979e2c7cc0fa41135c63d459909e5
+oid sha256:ba4af3b1b4fa156d60adeec70df709d1741ac2f3147c676ab2805007313fc707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3877754807472229,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.24174053182917002,
+  "best_metric": 0.33371686935424805,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.32232070910556004,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,364 @@
       "eval_samples_per_second": 61.376,
       "eval_steps_per_second": 1.924,
       "step": 150
+    },
+    {
+      "epoch": 0.24335213537469783,
+      "grad_norm": 0.40307724475860596,
+      "learning_rate": 2.6047368421052634e-05,
+      "loss": 0.5158,
+      "step": 151
+    },
+    {
+      "epoch": 0.24496373892022563,
+      "grad_norm": 0.47922101616859436,
+      "learning_rate": 2.5515789473684213e-05,
+      "loss": 0.5136,
+      "step": 152
+    },
+    {
+      "epoch": 0.2465753424657534,
+      "grad_norm": 0.5659621357917786,
+      "learning_rate": 2.4984210526315788e-05,
+      "loss": 0.3903,
+      "step": 153
+    },
+    {
+      "epoch": 0.24818694601128122,
+      "grad_norm": 0.6030014753341675,
+      "learning_rate": 2.445263157894737e-05,
+      "loss": 0.3398,
+      "step": 154
+    },
+    {
+      "epoch": 0.24979854955680902,
+      "grad_norm": 0.6882525086402893,
+      "learning_rate": 2.3921052631578946e-05,
+      "loss": 0.2735,
+      "step": 155
+    },
+    {
+      "epoch": 0.25141015310233683,
+      "grad_norm": 0.9658460021018982,
+      "learning_rate": 2.3389473684210528e-05,
+      "loss": 0.2586,
+      "step": 156
+    },
+    {
+      "epoch": 0.25302175664786464,
+      "grad_norm": 0.5281833410263062,
+      "learning_rate": 2.2857894736842106e-05,
+      "loss": 0.5193,
+      "step": 157
+    },
+    {
+      "epoch": 0.25463336019339244,
+      "grad_norm": 0.6106149554252625,
+      "learning_rate": 2.2326315789473685e-05,
+      "loss": 0.4958,
+      "step": 158
+    },
+    {
+      "epoch": 0.25624496373892025,
+      "grad_norm": 0.7677047252655029,
+      "learning_rate": 2.1794736842105264e-05,
+      "loss": 0.4363,
+      "step": 159
+    },
+    {
+      "epoch": 0.257856567284448,
+      "grad_norm": 0.655020534992218,
+      "learning_rate": 2.1263157894736842e-05,
+      "loss": 0.3346,
+      "step": 160
+    },
+    {
+      "epoch": 0.2594681708299758,
+      "grad_norm": 0.7973310351371765,
+      "learning_rate": 2.073157894736842e-05,
+      "loss": 0.3355,
+      "step": 161
+    },
+    {
+      "epoch": 0.2610797743755036,
+      "grad_norm": 0.9603102207183838,
+      "learning_rate": 2.0200000000000003e-05,
+      "loss": 0.2597,
+      "step": 162
+    },
+    {
+      "epoch": 0.2626913779210314,
+      "grad_norm": 0.5082424879074097,
+      "learning_rate": 1.966842105263158e-05,
+      "loss": 0.4856,
+      "step": 163
+    },
+    {
+      "epoch": 0.26430298146655923,
+      "grad_norm": 0.47313550114631653,
+      "learning_rate": 1.913684210526316e-05,
+      "loss": 0.521,
+      "step": 164
+    },
+    {
+      "epoch": 0.26591458501208703,
+      "grad_norm": 0.5528334379196167,
+      "learning_rate": 1.8605263157894736e-05,
+      "loss": 0.4273,
+      "step": 165
+    },
+    {
+      "epoch": 0.26752618855761484,
+      "grad_norm": 0.6417384743690491,
+      "learning_rate": 1.8073684210526318e-05,
+      "loss": 0.377,
+      "step": 166
+    },
+    {
+      "epoch": 0.26913779210314265,
+      "grad_norm": 0.7294735908508301,
+      "learning_rate": 1.7542105263157897e-05,
+      "loss": 0.3155,
+      "step": 167
+    },
+    {
+      "epoch": 0.27074939564867045,
+      "grad_norm": 0.8516286611557007,
+      "learning_rate": 1.7010526315789475e-05,
+      "loss": 0.2491,
+      "step": 168
+    },
+    {
+      "epoch": 0.2723609991941982,
+      "grad_norm": 0.5871580839157104,
+      "learning_rate": 1.6478947368421054e-05,
+      "loss": 0.408,
+      "step": 169
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 0.5080535411834717,
+      "learning_rate": 1.5947368421052633e-05,
+      "loss": 0.5006,
+      "step": 170
+    },
+    {
+      "epoch": 0.2755842062852538,
+      "grad_norm": 0.572222113609314,
+      "learning_rate": 1.541578947368421e-05,
+      "loss": 0.4072,
+      "step": 171
+    },
+    {
+      "epoch": 0.2771958098307816,
+      "grad_norm": 0.6648744940757751,
+      "learning_rate": 1.4884210526315788e-05,
+      "loss": 0.3782,
+      "step": 172
+    },
+    {
+      "epoch": 0.27880741337630943,
+      "grad_norm": 0.7872058153152466,
+      "learning_rate": 1.4352631578947369e-05,
+      "loss": 0.3245,
+      "step": 173
+    },
+    {
+      "epoch": 0.28041901692183724,
+      "grad_norm": 0.8955470323562622,
+      "learning_rate": 1.3821052631578949e-05,
+      "loss": 0.2479,
+      "step": 174
+    },
+    {
+      "epoch": 0.28203062046736505,
+      "grad_norm": 1.2318774461746216,
+      "learning_rate": 1.3289473684210526e-05,
+      "loss": 0.2326,
+      "step": 175
+    },
+    {
+      "epoch": 0.28364222401289285,
+      "grad_norm": 0.4534154534339905,
+      "learning_rate": 1.2757894736842106e-05,
+      "loss": 0.4958,
+      "step": 176
+    },
+    {
+      "epoch": 0.2852538275584206,
+      "grad_norm": 0.5369049906730652,
+      "learning_rate": 1.2226315789473685e-05,
+      "loss": 0.4478,
+      "step": 177
+    },
+    {
+      "epoch": 0.2868654311039484,
+      "grad_norm": 0.6685469746589661,
+      "learning_rate": 1.1694736842105264e-05,
+      "loss": 0.3742,
+      "step": 178
+    },
+    {
+      "epoch": 0.2884770346494762,
+      "grad_norm": 0.666946530342102,
+      "learning_rate": 1.1163157894736842e-05,
+      "loss": 0.3135,
+      "step": 179
+    },
+    {
+      "epoch": 0.290088638195004,
+      "grad_norm": 0.7749336361885071,
+      "learning_rate": 1.0631578947368421e-05,
+      "loss": 0.2429,
+      "step": 180
+    },
+    {
+      "epoch": 0.29170024174053183,
+      "grad_norm": 1.028951644897461,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 0.2296,
+      "step": 181
+    },
+    {
+      "epoch": 0.29331184528605964,
+      "grad_norm": 0.46223780512809753,
+      "learning_rate": 9.56842105263158e-06,
+      "loss": 0.4958,
+      "step": 182
+    },
+    {
+      "epoch": 0.29492344883158744,
+      "grad_norm": 0.518415093421936,
+      "learning_rate": 9.036842105263159e-06,
+      "loss": 0.4638,
+      "step": 183
+    },
+    {
+      "epoch": 0.29653505237711525,
+      "grad_norm": 0.6299134492874146,
+      "learning_rate": 8.505263157894738e-06,
+      "loss": 0.3941,
+      "step": 184
+    },
+    {
+      "epoch": 0.29814665592264306,
+      "grad_norm": 0.6578340530395508,
+      "learning_rate": 7.973684210526316e-06,
+      "loss": 0.3176,
+      "step": 185
+    },
+    {
+      "epoch": 0.2997582594681708,
+      "grad_norm": 0.8014324903488159,
+      "learning_rate": 7.442105263157894e-06,
+      "loss": 0.2383,
+      "step": 186
+    },
+    {
+      "epoch": 0.3013698630136986,
+      "grad_norm": 0.9844911694526672,
+      "learning_rate": 6.9105263157894745e-06,
+      "loss": 0.219,
+      "step": 187
+    },
+    {
+      "epoch": 0.3029814665592264,
+      "grad_norm": 0.5260629653930664,
+      "learning_rate": 6.378947368421053e-06,
+      "loss": 0.4447,
+      "step": 188
+    },
+    {
+      "epoch": 0.3045930701047542,
+      "grad_norm": 0.5315889120101929,
+      "learning_rate": 5.847368421052632e-06,
+      "loss": 0.4569,
+      "step": 189
+    },
+    {
+      "epoch": 0.30620467365028203,
+      "grad_norm": 0.6365461349487305,
+      "learning_rate": 5.315789473684211e-06,
+      "loss": 0.4326,
+      "step": 190
+    },
+    {
+      "epoch": 0.30781627719580984,
+      "grad_norm": 0.658093273639679,
+      "learning_rate": 4.78421052631579e-06,
+      "loss": 0.33,
+      "step": 191
+    },
+    {
+      "epoch": 0.30942788074133765,
+      "grad_norm": 0.7685239911079407,
+      "learning_rate": 4.252631578947369e-06,
+      "loss": 0.2842,
+      "step": 192
+    },
+    {
+      "epoch": 0.31103948428686545,
+      "grad_norm": 0.8007004261016846,
+      "learning_rate": 3.721052631578947e-06,
+      "loss": 0.1996,
+      "step": 193
+    },
+    {
+      "epoch": 0.3126510878323932,
+      "grad_norm": 0.6490435004234314,
+      "learning_rate": 3.1894736842105266e-06,
+      "loss": 0.3936,
+      "step": 194
+    },
+    {
+      "epoch": 0.314262691377921,
+      "grad_norm": 0.5127969980239868,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 0.4567,
+      "step": 195
+    },
+    {
+      "epoch": 0.3158742949234488,
+      "grad_norm": 0.6253898739814758,
+      "learning_rate": 2.1263157894736844e-06,
+      "loss": 0.4243,
+      "step": 196
+    },
+    {
+      "epoch": 0.3174858984689766,
+      "grad_norm": 0.6929444074630737,
+      "learning_rate": 1.5947368421052633e-06,
+      "loss": 0.3584,
+      "step": 197
+    },
+    {
+      "epoch": 0.31909750201450443,
+      "grad_norm": 0.8625342845916748,
+      "learning_rate": 1.0631578947368422e-06,
+      "loss": 0.29,
+      "step": 198
+    },
+    {
+      "epoch": 0.32070910556003224,
+      "grad_norm": 0.9054241180419922,
+      "learning_rate": 5.315789473684211e-07,
+      "loss": 0.2209,
+      "step": 199
+    },
+    {
+      "epoch": 0.32232070910556004,
+      "grad_norm": 1.2763004302978516,
+      "learning_rate": 0.0,
+      "loss": 0.2273,
+      "step": 200
+    },
+    {
+      "epoch": 0.32232070910556004,
+      "eval_loss": 0.33371686935424805,
+      "eval_runtime": 137.2091,
+      "eval_samples_per_second": 60.914,
+      "eval_steps_per_second": 1.909,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1470,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.365940959064883e+18,
+  "total_flos": 4.4879212787531776e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null