Training in progress, step 248, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3de8853dbe2df5638c27ff1621f209da764c1624bc146a20a297ed8c140d9e5
+oid sha256:48cc61ae89dc20d20a2f61b56530d0dfc15b94dff733d379e910add4706a746b
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd250dd0c51b0bf4b5b06e9038d9fb650be5aa6077a05e6f89da33d3357bf6a
+oid sha256:8bfac6d96e386be973df286efb49727d4712b8a2affa6674fbd8118964caff37
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7fa2f55da67fa56c860c55e8ad4ef077509a8e155e81e262d65f7788726fe16
+oid sha256:f31d368d9c82e2695ce87ea588903256d358935050307016666eb97a385c31fa
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa38f4f3b4ff3d4226570f78923bf03378db3e1bb0314ca8627f519a2ab0c60
+oid sha256:8aedaee037e46b024710b8fe7dc1bb43c3cd0b1c992477d115770486fcbf7d8f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.139243245124817,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.8080808080808081,
+  "epoch": 1.002020202020202,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 248,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,34 @@
       "eval_samples_per_second": 14.495,
       "eval_steps_per_second": 3.727,
       "step": 200
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.5558744072914124,
+      "learning_rate": 1.7720503566301816e-05,
+      "loss": 1.1532,
+      "step": 210
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.6250934600830078,
+      "learning_rate": 9.755882902194584e-06,
+      "loss": 1.1075,
+      "step": 220
+    },
+    {
+      "epoch": 0.9292929292929293,
+      "grad_norm": 0.6512425541877747,
+      "learning_rate": 4.070956151743026e-06,
+      "loss": 0.9673,
+      "step": 230
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 1.4905589818954468,
+      "learning_rate": 8.085413105050683e-07,
+      "loss": 1.0013,
+      "step": 240
     }
   ],
   "logging_steps": 10,
@@ -210,12 +238,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.123477187493888e+16,
+  "total_flos": 5.123242669375488e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null