Training in progress, step 178, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48667a3f5e8d45adf9b3a5bc4d99e4093d37dda4179fc54708a6d5a51c989f42
+oid sha256:40910984199e37b8832e1b9394258f344437c7cb5736f851b3ae6cfc1b7900bb
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78526bf31568dc5220e0224254ad37404f5e683bd673a2dc47a7f6f3fc5f4588
+oid sha256:f60588678a7b957f1ceddbde33a19af62e1b2bdcd214b87166dc072dee85e033
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acbf5a601b038c4ddbad3e552c5b4b8cc418f2eb4cd467d1b6c247ff7ac119a2
+oid sha256:91a5ebf60ce76ef014d840ccf73dfc8cecd03bf3ae54d4f1b60d63f15d2d4d30
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a2565b517521bc90f234688292b4fb403b8dc152393237bf90f1b83bcf7c9d
+oid sha256:c0bac060e984caa244fb63b5692ab9e2838bd0ccab458a78a7e36c395ca1e463
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.575272560119629,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.5316455696202533,
+  "epoch": 3.0042194092827006,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 178,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,202 @@
       "eval_samples_per_second": 13.825,
       "eval_steps_per_second": 3.456,
       "step": 150
+    },
+    {
+      "epoch": 2.548523206751055,
+      "grad_norm": 1.1742887496948242,
+      "learning_rate": 3.119414452281158e-06,
+      "loss": 1.4312,
+      "step": 151
+    },
+    {
+      "epoch": 2.5654008438818563,
+      "grad_norm": 1.2395821809768677,
+      "learning_rate": 2.8971151623847587e-06,
+      "loss": 1.3603,
+      "step": 152
+    },
+    {
+      "epoch": 2.5822784810126582,
+      "grad_norm": 1.2646101713180542,
+      "learning_rate": 2.682544768909717e-06,
+      "loss": 1.2588,
+      "step": 153
+    },
+    {
+      "epoch": 2.59915611814346,
+      "grad_norm": 1.3966846466064453,
+      "learning_rate": 2.475778302439524e-06,
+      "loss": 1.2442,
+      "step": 154
+    },
+    {
+      "epoch": 2.6160337552742616,
+      "grad_norm": 1.3285683393478394,
+      "learning_rate": 2.2768880646947268e-06,
+      "loss": 1.0874,
+      "step": 155
+    },
+    {
+      "epoch": 2.632911392405063,
+      "grad_norm": 1.4226495027542114,
+      "learning_rate": 2.0859436032505952e-06,
+      "loss": 1.1626,
+      "step": 156
+    },
+    {
+      "epoch": 2.649789029535865,
+      "grad_norm": 1.4059271812438965,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 1.0403,
+      "step": 157
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.5901901721954346,
+      "learning_rate": 1.7281562838948966e-06,
+      "loss": 1.1862,
+      "step": 158
+    },
+    {
+      "epoch": 2.6835443037974684,
+      "grad_norm": 1.655456304550171,
+      "learning_rate": 1.5614385364000228e-06,
+      "loss": 1.0067,
+      "step": 159
+    },
+    {
+      "epoch": 2.70042194092827,
+      "grad_norm": 1.878291368484497,
+      "learning_rate": 1.4029167422908107e-06,
+      "loss": 0.9148,
+      "step": 160
+    },
+    {
+      "epoch": 2.717299578059072,
+      "grad_norm": 1.3151243925094604,
+      "learning_rate": 1.25264633317885e-06,
+      "loss": 1.3873,
+      "step": 161
+    },
+    {
+      "epoch": 2.7341772151898733,
+      "grad_norm": 0.8847647905349731,
+      "learning_rate": 1.1106798553464804e-06,
+      "loss": 1.2541,
+      "step": 162
+    },
+    {
+      "epoch": 2.7510548523206753,
+      "grad_norm": 1.044076681137085,
+      "learning_rate": 9.770669513725128e-07,
+      "loss": 1.3151,
+      "step": 163
+    },
+    {
+      "epoch": 2.7679324894514767,
+      "grad_norm": 1.1881113052368164,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 1.4205,
+      "step": 164
+    },
+    {
+      "epoch": 2.7848101265822782,
+      "grad_norm": 1.2184456586837769,
+      "learning_rate": 7.350858136652261e-07,
+      "loss": 1.3638,
+      "step": 165
+    },
+    {
+      "epoch": 2.80168776371308,
+      "grad_norm": 1.2968173027038574,
+      "learning_rate": 6.268021954544096e-07,
+      "loss": 1.3385,
+      "step": 166
+    },
+    {
+      "epoch": 2.818565400843882,
+      "grad_norm": 1.3255001306533813,
+      "learning_rate": 5.270413525587909e-07,
+      "loss": 1.183,
+      "step": 167
+    },
+    {
+      "epoch": 2.8354430379746836,
+      "grad_norm": 1.3924806118011475,
+      "learning_rate": 4.358381691677932e-07,
+      "loss": 1.2142,
+      "step": 168
+    },
+    {
+      "epoch": 2.852320675105485,
+      "grad_norm": 1.4584044218063354,
+      "learning_rate": 3.5322453704410286e-07,
+      "loss": 1.1021,
+      "step": 169
+    },
+    {
+      "epoch": 2.869198312236287,
+      "grad_norm": 1.4159401655197144,
+      "learning_rate": 2.7922934437178695e-07,
+      "loss": 1.1629,
+      "step": 170
+    },
+    {
+      "epoch": 2.8860759493670884,
+      "grad_norm": 1.5566120147705078,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 1.1423,
+      "step": 171
+    },
+    {
+      "epoch": 2.9029535864978904,
+      "grad_norm": 1.5879220962524414,
+      "learning_rate": 1.571947526689349e-07,
+      "loss": 1.1142,
+      "step": 172
+    },
+    {
+      "epoch": 2.919831223628692,
+      "grad_norm": 1.6786341667175293,
+      "learning_rate": 1.0919802647165466e-07,
+      "loss": 1.1623,
+      "step": 173
+    },
+    {
+      "epoch": 2.9367088607594938,
+      "grad_norm": 1.908385992050171,
+      "learning_rate": 6.990507047049676e-08,
+      "loss": 1.1101,
+      "step": 174
+    },
+    {
+      "epoch": 2.9535864978902953,
+      "grad_norm": 1.2793887853622437,
+      "learning_rate": 3.9329624554584884e-08,
+      "loss": 1.2816,
+      "step": 175
+    },
+    {
+      "epoch": 2.970464135021097,
+      "grad_norm": 1.131956934928894,
+      "learning_rate": 1.7482380290034794e-08,
+      "loss": 1.0629,
+      "step": 176
+    },
+    {
+      "epoch": 2.9873417721518987,
+      "grad_norm": 1.540653109550476,
+      "learning_rate": 4.370977181339386e-09,
+      "loss": 1.2563,
+      "step": 177
+    },
+    {
+      "epoch": 3.0042194092827006,
+      "grad_norm": 4.293990135192871,
+      "learning_rate": 0.0,
+      "loss": 1.8858,
+      "step": 178
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1308,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.146163234439168e+17,
+  "total_flos": 2.5509571695476736e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null