Training in progress, step 792, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de05afcc546a2ee34140cbd4c32264a9ae4e90701579048d280b564f7b4fae2d
+oid sha256:b4dbee798d44dbcabb914ec35238d10388310cb47d10a041107ee960504806ab
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7120ad04c657280076e854a3a45c0cd0c9d81eb27b78e6be287df6e01cdaa069
+oid sha256:6f8d0477825cd9026da09ca1c4553d0e044616640851cd4193c564cc41fb807c
 size 71078228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07dd64b81a4a8ba6cd05967d431431caeff586cc6936097e54c47ce11512713b
+oid sha256:33fb007f8d857f9b183129c19566dda94989de04ecbd84ee572519e630f2f12a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031d9d4a3b196c7a36a2854f0921f12cf44faf0e25ee086b85b6802cdb926b70
+oid sha256:d4ecdcea16334b7d49ab05a4dbe60d78446124eb14a01af7ac3ef45a43be808c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7934648990631104,
   "best_model_checkpoint": "miner_id_24/checkpoint-750",
-  "epoch": 0.946969696969697,
+  "epoch": 1.0,
   "eval_steps": 150,
-  "global_step": 750,
+  "global_step": 792,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -580,6 +580,34 @@
       "eval_samples_per_second": 75.269,
       "eval_steps_per_second": 18.846,
       "step": 750
+    },
+    {
+      "epoch": 0.9595959595959596,
+      "grad_norm": 0.2528385818004608,
+      "learning_rate": 4.582130475683011e-07,
+      "loss": 0.7733,
+      "step": 760
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.3325110673904419,
+      "learning_rate": 2.167520804698009e-07,
+      "loss": 0.8165,
+      "step": 770
+    },
+    {
+      "epoch": 0.9848484848484849,
+      "grad_norm": 0.3532811105251312,
+      "learning_rate": 6.452098811035035e-08,
+      "loss": 0.8199,
+      "step": 780
+    },
+    {
+      "epoch": 0.9974747474747475,
+      "grad_norm": 0.4770316779613495,
+      "learning_rate": 1.7926245497179583e-09,
+      "loss": 0.7625,
+      "step": 790
     }
   ],
   "logging_steps": 10,
@@ -603,12 +631,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.575829827584e+16,
+  "total_flos": 2.719432340471808e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null