Training in progress, step 101, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe02f6b5c4e901d062dac8d896a31fa61f627176421b56928e3710bc01e35fa7
+oid sha256:6c9e66ff1ac2068f48548695b0f73a38f4d4da7e20a7ac9ef57b5483e1dea14b
 size 377538512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609a73be7bf8d0c75c7dddd565bdf0f30b026d8500fc1d60035a87fddb41c4c5
+oid sha256:4db0d976fd75dc86a24ab4b0abe6811359e26bac11049aa85fc1df83c227c3e3
 size 192144596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4709ae5ebafe5b5005746d313a28cf9df3ec7932ed22bc17bb60210b2cd443
+oid sha256:fa2edf472612a06b052ca098635a0540c75693f2b9081cf1972bc018c63da7d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a24a6c2916f1233e81ae5aa6f03102d5b2995ff1269ab70f695c9e134e003dc
+oid sha256:eda7b86cbb078beeb1e348b8f1097a0c65f3d09218fc09ba30dbc3c1792e8085
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9390347003936768,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.9950248756218906,
+  "epoch": 1.0049751243781095,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 101,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -723,6 +723,13 @@
       "eval_samples_per_second": 21.143,
       "eval_steps_per_second": 5.348,
       "step": 100
+    },
+    {
+      "epoch": 1.0049751243781095,
+      "grad_norm": 4.282508373260498,
+      "learning_rate": 0.0,
+      "loss": 1.4958,
+      "step": 101
     }
   ],
   "logging_steps": 1,
@@ -746,12 +753,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.3929253535744e+16,
+  "total_flos": 5.44348402876416e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null