Training in progress, step 179, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ace9af73431e935adf694459f4fb140979eb0b6cc3d57294c7a62b6d0341a4
+oid sha256:ccc804e5eadeca84041fd55d2033bf6f8a8dc678ee1dd5ddde6e11734c2cdde2
 size 377538512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814deb0adef9194647f2e398152dc67e1aa18ccda77b8b7a07a8e65be1d5b612
+oid sha256:1d6e11155a44a97b432efb7faf44c5608d755e496d083a770eed4a51e55b7474
 size 755298706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84cd003aaa730788d92e37b4b16afec4f3bb70fc863900013e55e8daa39deae6
+oid sha256:962066de7c3f04162344390eb135e78867c9120ee7b3f3e6e12940b96b166f17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b51e72d1903ca68c6dc0fa25a4c4a1878547b32209aff48060f61c55b96c821
+oid sha256:82231717c38bfa9a3adf7221ec4f479d22ed3028e22a7f158ca46dbae060dd20
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.112830400466919,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.5271966527196654,
+  "epoch": 3.02092050209205,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 179,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,209 @@
       "eval_samples_per_second": 15.404,
       "eval_steps_per_second": 7.778,
       "step": 150
+    },
+    {
+      "epoch": 2.5439330543933054,
+      "grad_norm": 3.7901535034179688,
+      "learning_rate": 7.458579343331995e-06,
+      "loss": 2.1281,
+      "step": 151
+    },
+    {
+      "epoch": 2.560669456066946,
+      "grad_norm": 4.6874284744262695,
+      "learning_rate": 6.947819411632223e-06,
+      "loss": 2.1111,
+      "step": 152
+    },
+    {
+      "epoch": 2.577405857740586,
+      "grad_norm": 5.268611431121826,
+      "learning_rate": 6.45386633755894e-06,
+      "loss": 2.1562,
+      "step": 153
+    },
+    {
+      "epoch": 2.594142259414226,
+      "grad_norm": 4.474716663360596,
+      "learning_rate": 5.976912952204017e-06,
+      "loss": 2.0612,
+      "step": 154
+    },
+    {
+      "epoch": 2.6108786610878663,
+      "grad_norm": 4.056868076324463,
+      "learning_rate": 5.51714545026264e-06,
+      "loss": 2.0663,
+      "step": 155
+    },
+    {
+      "epoch": 2.6276150627615062,
+      "grad_norm": 4.0478410720825195,
+      "learning_rate": 5.074743317346009e-06,
+      "loss": 2.1473,
+      "step": 156
+    },
+    {
+      "epoch": 2.6443514644351467,
+      "grad_norm": 4.919065475463867,
+      "learning_rate": 4.649879259913137e-06,
+      "loss": 2.2772,
+      "step": 157
+    },
+    {
+      "epoch": 2.6610878661087867,
+      "grad_norm": 5.8553009033203125,
+      "learning_rate": 4.242719137849077e-06,
+      "loss": 2.2277,
+      "step": 158
+    },
+    {
+      "epoch": 2.6778242677824267,
+      "grad_norm": 4.565273284912109,
+      "learning_rate": 3.853421899715992e-06,
+      "loss": 2.1619,
+      "step": 159
+    },
+    {
+      "epoch": 2.694560669456067,
+      "grad_norm": 5.8820672035217285,
+      "learning_rate": 3.4821395207022766e-06,
+      "loss": 2.3529,
+      "step": 160
+    },
+    {
+      "epoch": 2.711297071129707,
+      "grad_norm": 4.277231693267822,
+      "learning_rate": 3.1290169432939553e-06,
+      "loss": 1.8477,
+      "step": 161
+    },
+    {
+      "epoch": 2.7280334728033475,
+      "grad_norm": 3.0754568576812744,
+      "learning_rate": 2.794192020691544e-06,
+      "loss": 1.5382,
+      "step": 162
+    },
+    {
+      "epoch": 2.7447698744769875,
+      "grad_norm": 3.2562501430511475,
+      "learning_rate": 2.4777954629944477e-06,
+      "loss": 1.9528,
+      "step": 163
+    },
+    {
+      "epoch": 2.7615062761506275,
+      "grad_norm": 3.871128559112549,
+      "learning_rate": 2.179950786173879e-06,
+      "loss": 2.0672,
+      "step": 164
+    },
+    {
+      "epoch": 2.778242677824268,
+      "grad_norm": 4.168922424316406,
+      "learning_rate": 1.9007742638543102e-06,
+      "loss": 2.1496,
+      "step": 165
+    },
+    {
+      "epoch": 2.794979079497908,
+      "grad_norm": 3.756467819213867,
+      "learning_rate": 1.6403748819221466e-06,
+      "loss": 2.1622,
+      "step": 166
+    },
+    {
+      "epoch": 2.8117154811715483,
+      "grad_norm": 4.428233623504639,
+      "learning_rate": 1.3988542959794627e-06,
+      "loss": 2.2344,
+      "step": 167
+    },
+    {
+      "epoch": 2.8284518828451883,
+      "grad_norm": 4.9569244384765625,
+      "learning_rate": 1.1763067916593262e-06,
+      "loss": 2.2759,
+      "step": 168
+    },
+    {
+      "epoch": 2.8451882845188283,
+      "grad_norm": 4.619340419769287,
+      "learning_rate": 9.728192478182574e-07,
+      "loss": 2.1422,
+      "step": 169
+    },
+    {
+      "epoch": 2.8619246861924688,
+      "grad_norm": 4.764113426208496,
+      "learning_rate": 7.884711026201585e-07,
+      "loss": 2.1994,
+      "step": 170
+    },
+    {
+      "epoch": 2.8786610878661087,
+      "grad_norm": 5.418850421905518,
+      "learning_rate": 6.233343225249933e-07,
+      "loss": 2.175,
+      "step": 171
+    },
+    {
+      "epoch": 2.895397489539749,
+      "grad_norm": 5.899227142333984,
+      "learning_rate": 4.774733741942206e-07,
+      "loss": 2.1539,
+      "step": 172
+    },
+    {
+      "epoch": 2.912133891213389,
+      "grad_norm": 5.732656002044678,
+      "learning_rate": 3.5094519932415417e-07,
+      "loss": 2.3507,
+      "step": 173
+    },
+    {
+      "epoch": 2.928870292887029,
+      "grad_norm": 6.25728702545166,
+      "learning_rate": 2.437991924167937e-07,
+      "loss": 2.6018,
+      "step": 174
+    },
+    {
+      "epoch": 2.9456066945606696,
+      "grad_norm": 4.794129371643066,
+      "learning_rate": 1.560771814970885e-07,
+      "loss": 2.1829,
+      "step": 175
+    },
+    {
+      "epoch": 2.9623430962343096,
+      "grad_norm": 3.6276679039001465,
+      "learning_rate": 8.781341178393244e-08,
+      "loss": 1.918,
+      "step": 176
+    },
+    {
+      "epoch": 2.97907949790795,
+      "grad_norm": 4.8414626121521,
+      "learning_rate": 3.9034532321408076e-08,
+      "loss": 2.19,
+      "step": 177
+    },
+    {
+      "epoch": 3.00418410041841,
+      "grad_norm": 12.374079704284668,
+      "learning_rate": 9.75958557545842e-09,
+      "loss": 3.9046,
+      "step": 178
+    },
+    {
+      "epoch": 3.02092050209205,
+      "grad_norm": 2.9037060737609863,
+      "learning_rate": 0.0,
+      "loss": 1.6255,
+      "step": 179
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1315,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.04487928725504e+17,
+  "total_flos": 1.2363281373069312e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null