Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc38ee180ed43debc8d213d18880cc8e8c7508ebdb52af9192e5c71006ea235
+oid sha256:ec6c0038e671185de3ed05f31ef02684fb9c7d475a4b20a91409d4abcc05ee6d
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e275a1b3af90b69e1a3d10db50671ef5ab20bd65b80d0caf212c6e910cc740
+oid sha256:c25d370a58c403f4b0899b822ac18c65dadb1f757d61be9a93908dedfcd585e9
 size 325339796

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebebaee0bc937def98bbb7f613f37014998dc13de24a75326b4c4d9a5cc1dd8
+oid sha256:d7adefe56dfe67002caec268e199f810218505166afd417975720b784393d0e0
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5410de0e4bd9526c873111ad9b42d05b203f633ed81559767a0c834cb843e8a
+oid sha256:d79547631575a1cdd0723c02fbac5368b61e5ad60acf928992feaf93de45dbc5
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1d9fc207aa3991d3204c36a33617ea3664944cac27b7114247e9aee338aa9c
+oid sha256:2ff185260bc188fa69d58185a46265eda72639fc3a5af7dd00190457d0183888
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90972a5a7190a5651b7c08653dc7bed943e5f35f07109107e45c14eeb0db5887
+oid sha256:8697e4ee16dbf000420919892e86a92ef99800c827edf6b01a572eca99053d76
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0fd026dbe3916313f41102b98955aca917f706a3de13f2585888075b46ec50
+oid sha256:42ab8200e7ef3d628b1f8f55e863ba3d4d692e6dbfa875549d94e65b551e0bc1
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dca711591804101a9de535ad90b750eb5ee391a01ec8f7582e516345b4128f5
+oid sha256:819cdc4fc64bd75944806aaa1b9827bc78ac354bc85f6f74ccc941332a9ea7ac
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f7a293a7005f2a45716a80060e95eb80f276e3ff90e03d20ae3be0f8adc12e
+oid sha256:90acc22d1da420fdf756f8a1bb3a02810cca2113bea6c1a9b23841d4337be2b0
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4a2c78464d613e136619a3d6600616b184ccdc3a4fc04f53239b738339f0485
+oid sha256:a3faf03426b4b14919a8702f1c5d8086a5963dec0dd911d8d500c2a51372f998
 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": 1.3774456977844238,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.3656307129798903,
+  "best_metric": 1.3683677911758423,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.4875076173065204,
   "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": 138.322,
       "eval_steps_per_second": 4.331,
       "step": 150
+    },
+    {
+      "epoch": 0.36806825106642294,
+      "grad_norm": 0.19675801694393158,
+      "learning_rate": 2.6047368421052634e-05,
+      "loss": 1.5533,
+      "step": 151
+    },
+    {
+      "epoch": 0.3705057891529555,
+      "grad_norm": 0.21547318994998932,
+      "learning_rate": 2.5515789473684213e-05,
+      "loss": 1.5509,
+      "step": 152
+    },
+    {
+      "epoch": 0.37294332723948814,
+      "grad_norm": 0.223504900932312,
+      "learning_rate": 2.4984210526315788e-05,
+      "loss": 1.5848,
+      "step": 153
+    },
+    {
+      "epoch": 0.3753808653260207,
+      "grad_norm": 0.2383584827184677,
+      "learning_rate": 2.445263157894737e-05,
+      "loss": 1.4189,
+      "step": 154
+    },
+    {
+      "epoch": 0.3778184034125533,
+      "grad_norm": 0.25561967492103577,
+      "learning_rate": 2.3921052631578946e-05,
+      "loss": 1.2175,
+      "step": 155
+    },
+    {
+      "epoch": 0.3802559414990859,
+      "grad_norm": 0.28261175751686096,
+      "learning_rate": 2.3389473684210528e-05,
+      "loss": 1.0419,
+      "step": 156
+    },
+    {
+      "epoch": 0.3826934795856185,
+      "grad_norm": 0.19555184245109558,
+      "learning_rate": 2.2857894736842106e-05,
+      "loss": 1.3788,
+      "step": 157
+    },
+    {
+      "epoch": 0.38513101767215113,
+      "grad_norm": 0.18990349769592285,
+      "learning_rate": 2.2326315789473685e-05,
+      "loss": 1.611,
+      "step": 158
+    },
+    {
+      "epoch": 0.3875685557586837,
+      "grad_norm": 0.2016024887561798,
+      "learning_rate": 2.1794736842105264e-05,
+      "loss": 1.6461,
+      "step": 159
+    },
+    {
+      "epoch": 0.39000609384521634,
+      "grad_norm": 0.21997405588626862,
+      "learning_rate": 2.1263157894736842e-05,
+      "loss": 1.4487,
+      "step": 160
+    },
+    {
+      "epoch": 0.3924436319317489,
+      "grad_norm": 0.2229284793138504,
+      "learning_rate": 2.073157894736842e-05,
+      "loss": 1.254,
+      "step": 161
+    },
+    {
+      "epoch": 0.39488117001828155,
+      "grad_norm": 0.2891606092453003,
+      "learning_rate": 2.0200000000000003e-05,
+      "loss": 1.0513,
+      "step": 162
+    },
+    {
+      "epoch": 0.3973187081048141,
+      "grad_norm": 0.20357653498649597,
+      "learning_rate": 1.966842105263158e-05,
+      "loss": 1.2509,
+      "step": 163
+    },
+    {
+      "epoch": 0.39975624619134675,
+      "grad_norm": 0.18672575056552887,
+      "learning_rate": 1.913684210526316e-05,
+      "loss": 1.593,
+      "step": 164
+    },
+    {
+      "epoch": 0.40219378427787933,
+      "grad_norm": 0.19946973025798798,
+      "learning_rate": 1.8605263157894736e-05,
+      "loss": 1.5572,
+      "step": 165
+    },
+    {
+      "epoch": 0.40463132236441196,
+      "grad_norm": 0.2044389694929123,
+      "learning_rate": 1.8073684210526318e-05,
+      "loss": 1.5125,
+      "step": 166
+    },
+    {
+      "epoch": 0.40706886045094454,
+      "grad_norm": 0.22546714544296265,
+      "learning_rate": 1.7542105263157897e-05,
+      "loss": 1.27,
+      "step": 167
+    },
+    {
+      "epoch": 0.40950639853747717,
+      "grad_norm": 0.25497713685035706,
+      "learning_rate": 1.7010526315789475e-05,
+      "loss": 1.107,
+      "step": 168
+    },
+    {
+      "epoch": 0.41194393662400974,
+      "grad_norm": 0.2625187635421753,
+      "learning_rate": 1.6478947368421054e-05,
+      "loss": 1.2814,
+      "step": 169
+    },
+    {
+      "epoch": 0.4143814747105424,
+      "grad_norm": 0.2016693502664566,
+      "learning_rate": 1.5947368421052633e-05,
+      "loss": 1.5901,
+      "step": 170
+    },
+    {
+      "epoch": 0.41681901279707495,
+      "grad_norm": 0.2098659873008728,
+      "learning_rate": 1.541578947368421e-05,
+      "loss": 1.6413,
+      "step": 171
+    },
+    {
+      "epoch": 0.4192565508836076,
+      "grad_norm": 0.20222246646881104,
+      "learning_rate": 1.4884210526315788e-05,
+      "loss": 1.4643,
+      "step": 172
+    },
+    {
+      "epoch": 0.42169408897014016,
+      "grad_norm": 0.22476032376289368,
+      "learning_rate": 1.4352631578947369e-05,
+      "loss": 1.3609,
+      "step": 173
+    },
+    {
+      "epoch": 0.42413162705667273,
+      "grad_norm": 0.24061191082000732,
+      "learning_rate": 1.3821052631578949e-05,
+      "loss": 1.1617,
+      "step": 174
+    },
+    {
+      "epoch": 0.42656916514320536,
+      "grad_norm": 0.40884625911712646,
+      "learning_rate": 1.3289473684210526e-05,
+      "loss": 1.0098,
+      "step": 175
+    },
+    {
+      "epoch": 0.42900670322973794,
+      "grad_norm": 0.1825111359357834,
+      "learning_rate": 1.2757894736842106e-05,
+      "loss": 1.5618,
+      "step": 176
+    },
+    {
+      "epoch": 0.43144424131627057,
+      "grad_norm": 0.18769165873527527,
+      "learning_rate": 1.2226315789473685e-05,
+      "loss": 1.5326,
+      "step": 177
+    },
+    {
+      "epoch": 0.43388177940280315,
+      "grad_norm": 0.20284990966320038,
+      "learning_rate": 1.1694736842105264e-05,
+      "loss": 1.5483,
+      "step": 178
+    },
+    {
+      "epoch": 0.4363193174893358,
+      "grad_norm": 0.2243083417415619,
+      "learning_rate": 1.1163157894736842e-05,
+      "loss": 1.3821,
+      "step": 179
+    },
+    {
+      "epoch": 0.43875685557586835,
+      "grad_norm": 0.2496405392885208,
+      "learning_rate": 1.0631578947368421e-05,
+      "loss": 1.169,
+      "step": 180
+    },
+    {
+      "epoch": 0.441194393662401,
+      "grad_norm": 0.31328126788139343,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 1.0108,
+      "step": 181
+    },
+    {
+      "epoch": 0.44363193174893356,
+      "grad_norm": 0.2052682787179947,
+      "learning_rate": 9.56842105263158e-06,
+      "loss": 1.4298,
+      "step": 182
+    },
+    {
+      "epoch": 0.4460694698354662,
+      "grad_norm": 0.2013900876045227,
+      "learning_rate": 9.036842105263159e-06,
+      "loss": 1.6362,
+      "step": 183
+    },
+    {
+      "epoch": 0.44850700792199877,
+      "grad_norm": 0.20970705151557922,
+      "learning_rate": 8.505263157894738e-06,
+      "loss": 1.5724,
+      "step": 184
+    },
+    {
+      "epoch": 0.4509445460085314,
+      "grad_norm": 0.21226783096790314,
+      "learning_rate": 7.973684210526316e-06,
+      "loss": 1.4368,
+      "step": 185
+    },
+    {
+      "epoch": 0.453382084095064,
+      "grad_norm": 0.2563309669494629,
+      "learning_rate": 7.442105263157894e-06,
+      "loss": 1.2902,
+      "step": 186
+    },
+    {
+      "epoch": 0.4558196221815966,
+      "grad_norm": 0.2750256359577179,
+      "learning_rate": 6.9105263157894745e-06,
+      "loss": 1.0861,
+      "step": 187
+    },
+    {
+      "epoch": 0.4582571602681292,
+      "grad_norm": 0.24909748136997223,
+      "learning_rate": 6.378947368421053e-06,
+      "loss": 1.4973,
+      "step": 188
+    },
+    {
+      "epoch": 0.4606946983546618,
+      "grad_norm": 0.18944765627384186,
+      "learning_rate": 5.847368421052632e-06,
+      "loss": 1.5647,
+      "step": 189
+    },
+    {
+      "epoch": 0.4631322364411944,
+      "grad_norm": 0.20208123326301575,
+      "learning_rate": 5.315789473684211e-06,
+      "loss": 1.5891,
+      "step": 190
+    },
+    {
+      "epoch": 0.465569774527727,
+      "grad_norm": 0.21481601893901825,
+      "learning_rate": 4.78421052631579e-06,
+      "loss": 1.5697,
+      "step": 191
+    },
+    {
+      "epoch": 0.4680073126142596,
+      "grad_norm": 0.21407796442508698,
+      "learning_rate": 4.252631578947369e-06,
+      "loss": 1.241,
+      "step": 192
+    },
+    {
+      "epoch": 0.4704448507007922,
+      "grad_norm": 0.25740694999694824,
+      "learning_rate": 3.721052631578947e-06,
+      "loss": 1.0902,
+      "step": 193
+    },
+    {
+      "epoch": 0.4728823887873248,
+      "grad_norm": 0.25215446949005127,
+      "learning_rate": 3.1894736842105266e-06,
+      "loss": 1.1151,
+      "step": 194
+    },
+    {
+      "epoch": 0.4753199268738574,
+      "grad_norm": 0.18287619948387146,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 1.6266,
+      "step": 195
+    },
+    {
+      "epoch": 0.47775746496039,
+      "grad_norm": 0.18589036166667938,
+      "learning_rate": 2.1263157894736844e-06,
+      "loss": 1.4951,
+      "step": 196
+    },
+    {
+      "epoch": 0.4801950030469226,
+      "grad_norm": 0.20675720274448395,
+      "learning_rate": 1.5947368421052633e-06,
+      "loss": 1.4876,
+      "step": 197
+    },
+    {
+      "epoch": 0.4826325411334552,
+      "grad_norm": 0.21417765319347382,
+      "learning_rate": 1.0631578947368422e-06,
+      "loss": 1.3639,
+      "step": 198
+    },
+    {
+      "epoch": 0.4850700792199878,
+      "grad_norm": 0.2406492680311203,
+      "learning_rate": 5.315789473684211e-07,
+      "loss": 1.1792,
+      "step": 199
+    },
+    {
+      "epoch": 0.4875076173065204,
+      "grad_norm": 0.39091214537620544,
+      "learning_rate": 0.0,
+      "loss": 0.9728,
+      "step": 200
+    },
+    {
+      "epoch": 0.4875076173065204,
+      "eval_loss": 1.3683677911758423,
+      "eval_runtime": 39.8875,
+      "eval_samples_per_second": 138.515,
+      "eval_steps_per_second": 4.337,
+      "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": 1.612127291792425e+18,
+  "total_flos": 2.1496148923766538e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null