Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50623187d5ed0d7748c05449ab95fa89704c299b9b08334a46094e117024af0c
+oid sha256:7bf2f6fae6d682c53bb6d20cc5018520e266440ad62b90f32cd5ce80c99b42dd
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575b73ca69f449cfe67adbceda2d260fe18a97164c66bd0b17099d4771231c99
+oid sha256:dbc80448c76074e07190f7d2e80613ece6439765ea20153bb7872b230ef6542d
 size 325339796

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a388b1d01624e031945e9bb400e94ad30d284639d859e041d88bc9037fbd3e
+oid sha256:b10b3b8081657c8b1d433d319569d1879c00e20e25fd546abad9d8bc8a070fd7
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7df857d6c883df0e7ab0a4d7f10d1b49fdfe185dd902b9eb9bee4d0a7a9c8c6
+oid sha256:10ef469d7e29e825a7d1407503a251c356c50e553499539ba0390d6a767ccd12
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09aea1a1dacf0faf58178cbbc1b67d823fa18b28ccf24853234e7d2c25c3ce0
+oid sha256:a5594cd9cd52ef4c09c5f7c8d3d4506b75b8765fdac7ebc5da63e35ec522f990
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5a2fec68b1dcac3681fa9dc1b0747f1e0e9383db6968fcbb4f9403db80a0d5
+oid sha256:6287ef1a0dc81028b72129aff829fd56e91dcda61967308ecb36f64de0d7bb74
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff4ffb98dec4b7d519362649a25b2a5864ce1fd3746c8b32c229ec85a571b681
+oid sha256:e862de20c6e7a6fac4219d04b0dcd09bad3d6859046be9fae7c985bb25f897b7
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc5c0954766a659d962137f64bbe3f7af0f6b0374e5a0bf7e9789c5eeb70498
+oid sha256:44d619e61d98d7480887d82bf7cd9c82767024fae9c295df89dbf354a65f39db
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c771ff82d2ef34188026942942023ff4b332fee36fb6646b31c9c654849051
+oid sha256:44b3ab492c78aa6bc70fa425ec8faa5fbfe0b1428c023d23037fab6b69a87573
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce56c3b0a7357c41584cbf23c8f399a75e238712757ffc8c8295571bb56ae7c2
+oid sha256:5872e7522b6c1fd9d3c6e4f524154e810c95b6dcb204fab7bbc289a5e9f8f8d1
 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": 0.8881184458732605,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.06737787759685569,
+  "best_metric": 0.8799543380737305,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.08983717012914093,
   "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": 144.711,
       "eval_steps_per_second": 4.525,
       "step": 150
+    },
+    {
+      "epoch": 0.0678270634475014,
+      "grad_norm": 0.245889350771904,
+      "learning_rate": 2.6047368421052634e-05,
+      "loss": 0.9066,
+      "step": 151
+    },
+    {
+      "epoch": 0.06827624929814712,
+      "grad_norm": 0.24444212019443512,
+      "learning_rate": 2.5515789473684213e-05,
+      "loss": 0.9163,
+      "step": 152
+    },
+    {
+      "epoch": 0.06872543514879281,
+      "grad_norm": 0.24982236325740814,
+      "learning_rate": 2.4984210526315788e-05,
+      "loss": 0.8824,
+      "step": 153
+    },
+    {
+      "epoch": 0.06917462099943852,
+      "grad_norm": 0.2683698534965515,
+      "learning_rate": 2.445263157894737e-05,
+      "loss": 0.8958,
+      "step": 154
+    },
+    {
+      "epoch": 0.06962380685008422,
+      "grad_norm": 0.27906811237335205,
+      "learning_rate": 2.3921052631578946e-05,
+      "loss": 0.8996,
+      "step": 155
+    },
+    {
+      "epoch": 0.07007299270072993,
+      "grad_norm": 0.3476739823818207,
+      "learning_rate": 2.3389473684210528e-05,
+      "loss": 0.8366,
+      "step": 156
+    },
+    {
+      "epoch": 0.07052217855137563,
+      "grad_norm": 0.26626768708229065,
+      "learning_rate": 2.2857894736842106e-05,
+      "loss": 0.9163,
+      "step": 157
+    },
+    {
+      "epoch": 0.07097136440202134,
+      "grad_norm": 0.26524534821510315,
+      "learning_rate": 2.2326315789473685e-05,
+      "loss": 0.895,
+      "step": 158
+    },
+    {
+      "epoch": 0.07142055025266704,
+      "grad_norm": 0.26299136877059937,
+      "learning_rate": 2.1794736842105264e-05,
+      "loss": 0.8973,
+      "step": 159
+    },
+    {
+      "epoch": 0.07186973610331275,
+      "grad_norm": 0.2615616023540497,
+      "learning_rate": 2.1263157894736842e-05,
+      "loss": 0.901,
+      "step": 160
+    },
+    {
+      "epoch": 0.07231892195395845,
+      "grad_norm": 0.2764776945114136,
+      "learning_rate": 2.073157894736842e-05,
+      "loss": 0.8718,
+      "step": 161
+    },
+    {
+      "epoch": 0.07276810780460416,
+      "grad_norm": 0.30812153220176697,
+      "learning_rate": 2.0200000000000003e-05,
+      "loss": 0.877,
+      "step": 162
+    },
+    {
+      "epoch": 0.07321729365524986,
+      "grad_norm": 0.2510615289211273,
+      "learning_rate": 1.966842105263158e-05,
+      "loss": 0.8739,
+      "step": 163
+    },
+    {
+      "epoch": 0.07366647950589557,
+      "grad_norm": 0.24000753462314606,
+      "learning_rate": 1.913684210526316e-05,
+      "loss": 0.913,
+      "step": 164
+    },
+    {
+      "epoch": 0.07411566535654127,
+      "grad_norm": 0.24215757846832275,
+      "learning_rate": 1.8605263157894736e-05,
+      "loss": 0.9063,
+      "step": 165
+    },
+    {
+      "epoch": 0.07456485120718698,
+      "grad_norm": 0.26448169350624084,
+      "learning_rate": 1.8073684210526318e-05,
+      "loss": 0.8805,
+      "step": 166
+    },
+    {
+      "epoch": 0.07501403705783267,
+      "grad_norm": 0.2861745357513428,
+      "learning_rate": 1.7542105263157897e-05,
+      "loss": 0.9049,
+      "step": 167
+    },
+    {
+      "epoch": 0.07546322290847839,
+      "grad_norm": 0.30888983607292175,
+      "learning_rate": 1.7010526315789475e-05,
+      "loss": 0.867,
+      "step": 168
+    },
+    {
+      "epoch": 0.07591240875912408,
+      "grad_norm": 0.27784985303878784,
+      "learning_rate": 1.6478947368421054e-05,
+      "loss": 0.8749,
+      "step": 169
+    },
+    {
+      "epoch": 0.0763615946097698,
+      "grad_norm": 0.2495727688074112,
+      "learning_rate": 1.5947368421052633e-05,
+      "loss": 0.8959,
+      "step": 170
+    },
+    {
+      "epoch": 0.07681078046041549,
+      "grad_norm": 0.24338717758655548,
+      "learning_rate": 1.541578947368421e-05,
+      "loss": 0.8821,
+      "step": 171
+    },
+    {
+      "epoch": 0.0772599663110612,
+      "grad_norm": 0.25039950013160706,
+      "learning_rate": 1.4884210526315788e-05,
+      "loss": 0.8733,
+      "step": 172
+    },
+    {
+      "epoch": 0.0777091521617069,
+      "grad_norm": 0.27508071064949036,
+      "learning_rate": 1.4352631578947369e-05,
+      "loss": 0.9056,
+      "step": 173
+    },
+    {
+      "epoch": 0.07815833801235261,
+      "grad_norm": 0.2863399386405945,
+      "learning_rate": 1.3821052631578949e-05,
+      "loss": 0.8748,
+      "step": 174
+    },
+    {
+      "epoch": 0.07860752386299831,
+      "grad_norm": 0.3646789491176605,
+      "learning_rate": 1.3289473684210526e-05,
+      "loss": 0.8383,
+      "step": 175
+    },
+    {
+      "epoch": 0.07905670971364402,
+      "grad_norm": 0.2623049020767212,
+      "learning_rate": 1.2757894736842106e-05,
+      "loss": 0.8969,
+      "step": 176
+    },
+    {
+      "epoch": 0.07950589556428972,
+      "grad_norm": 0.26813623309135437,
+      "learning_rate": 1.2226315789473685e-05,
+      "loss": 0.899,
+      "step": 177
+    },
+    {
+      "epoch": 0.07995508141493543,
+      "grad_norm": 0.2505576014518738,
+      "learning_rate": 1.1694736842105264e-05,
+      "loss": 0.8629,
+      "step": 178
+    },
+    {
+      "epoch": 0.08040426726558113,
+      "grad_norm": 0.25836649537086487,
+      "learning_rate": 1.1163157894736842e-05,
+      "loss": 0.8929,
+      "step": 179
+    },
+    {
+      "epoch": 0.08085345311622684,
+      "grad_norm": 0.27238643169403076,
+      "learning_rate": 1.0631578947368421e-05,
+      "loss": 0.8732,
+      "step": 180
+    },
+    {
+      "epoch": 0.08130263896687254,
+      "grad_norm": 0.33109569549560547,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 0.8555,
+      "step": 181
+    },
+    {
+      "epoch": 0.08175182481751825,
+      "grad_norm": 0.24706503748893738,
+      "learning_rate": 9.56842105263158e-06,
+      "loss": 0.8922,
+      "step": 182
+    },
+    {
+      "epoch": 0.08220101066816396,
+      "grad_norm": 0.24443064630031586,
+      "learning_rate": 9.036842105263159e-06,
+      "loss": 0.9011,
+      "step": 183
+    },
+    {
+      "epoch": 0.08265019651880966,
+      "grad_norm": 0.24768005311489105,
+      "learning_rate": 8.505263157894738e-06,
+      "loss": 0.91,
+      "step": 184
+    },
+    {
+      "epoch": 0.08309938236945537,
+      "grad_norm": 0.2456647902727127,
+      "learning_rate": 7.973684210526316e-06,
+      "loss": 0.8728,
+      "step": 185
+    },
+    {
+      "epoch": 0.08354856822010107,
+      "grad_norm": 0.2784600555896759,
+      "learning_rate": 7.442105263157894e-06,
+      "loss": 0.8891,
+      "step": 186
+    },
+    {
+      "epoch": 0.08399775407074678,
+      "grad_norm": 0.3673495948314667,
+      "learning_rate": 6.9105263157894745e-06,
+      "loss": 0.8639,
+      "step": 187
+    },
+    {
+      "epoch": 0.08444693992139247,
+      "grad_norm": 0.253378301858902,
+      "learning_rate": 6.378947368421053e-06,
+      "loss": 0.8923,
+      "step": 188
+    },
+    {
+      "epoch": 0.08489612577203819,
+      "grad_norm": 0.23032832145690918,
+      "learning_rate": 5.847368421052632e-06,
+      "loss": 0.9097,
+      "step": 189
+    },
+    {
+      "epoch": 0.08534531162268388,
+      "grad_norm": 0.24500040709972382,
+      "learning_rate": 5.315789473684211e-06,
+      "loss": 0.9037,
+      "step": 190
+    },
+    {
+      "epoch": 0.0857944974733296,
+      "grad_norm": 0.2614372670650482,
+      "learning_rate": 4.78421052631579e-06,
+      "loss": 0.9011,
+      "step": 191
+    },
+    {
+      "epoch": 0.08624368332397529,
+      "grad_norm": 0.2819826900959015,
+      "learning_rate": 4.252631578947369e-06,
+      "loss": 0.8751,
+      "step": 192
+    },
+    {
+      "epoch": 0.086692869174621,
+      "grad_norm": 0.29293060302734375,
+      "learning_rate": 3.721052631578947e-06,
+      "loss": 0.8822,
+      "step": 193
+    },
+    {
+      "epoch": 0.0871420550252667,
+      "grad_norm": 0.2739028036594391,
+      "learning_rate": 3.1894736842105266e-06,
+      "loss": 0.8568,
+      "step": 194
+    },
+    {
+      "epoch": 0.08759124087591241,
+      "grad_norm": 0.23401287198066711,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 0.8958,
+      "step": 195
+    },
+    {
+      "epoch": 0.08804042672655811,
+      "grad_norm": 0.23881946504116058,
+      "learning_rate": 2.1263157894736844e-06,
+      "loss": 0.8922,
+      "step": 196
+    },
+    {
+      "epoch": 0.08848961257720382,
+      "grad_norm": 0.2490690052509308,
+      "learning_rate": 1.5947368421052633e-06,
+      "loss": 0.8816,
+      "step": 197
+    },
+    {
+      "epoch": 0.08893879842784952,
+      "grad_norm": 0.26390817761421204,
+      "learning_rate": 1.0631578947368422e-06,
+      "loss": 0.8778,
+      "step": 198
+    },
+    {
+      "epoch": 0.08938798427849523,
+      "grad_norm": 0.27074772119522095,
+      "learning_rate": 5.315789473684211e-07,
+      "loss": 0.8248,
+      "step": 199
+    },
+    {
+      "epoch": 0.08983717012914093,
+      "grad_norm": 0.3729373812675476,
+      "learning_rate": 0.0,
+      "loss": 0.8088,
+      "step": 200
+    },
+    {
+      "epoch": 0.08983717012914093,
+      "eval_loss": 0.8799543380737305,
+      "eval_runtime": 207.3734,
+      "eval_samples_per_second": 144.642,
+      "eval_steps_per_second": 4.523,
+      "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": 1.6149211250688e+18,
+  "total_flos": 2.1532281667584e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null