Training in progress, step 281, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bba339afb518bb15b3d24e1c59d7b3bec8973539aa3405a08db0e52b625354b
+oid sha256:cdf00d6dd7caac15706a4a1d036edd4e59fe1192a2152ad858b5ab6462c6897f
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32f911427f983f02594c91a9852162a992411f05ead99f227aca08a385170a57
-size 4830714
+oid sha256:095bae509f0837518164ab17286c941a920989662cc7057e2a68726490a05d6c
+size 4830970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bed73607212a21666b42426bd9405bc868787315c885bdb087571abd8f2975d
+oid sha256:c9fb162e83473553c40e277b8beb76ab3813acb3d515a1d8c41bf2774583d1dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9131e9c04f2eb989207883bbb5ce8261af20398f9d579cc1d8520ba699074e6a
+oid sha256:b4cf55505cbb0f0b73a90824f74af6134ad2bc2b4c72ae46dfd5c479ee916c04
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.86061954498291,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.8912655971479501,
+  "epoch": 1.0017825311942958,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 281,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,27 @@
       "eval_samples_per_second": 77.412,
       "eval_steps_per_second": 19.516,
       "step": 250
+    },
+    {
+      "epoch": 0.9269162210338681,
+      "grad_norm": 0.20626193284988403,
+      "learning_rate": 4.172223717706782e-06,
+      "loss": 11.8871,
+      "step": 260
+    },
+    {
+      "epoch": 0.9625668449197861,
+      "grad_norm": 0.25518620014190674,
+      "learning_rate": 1.150424898811762e-06,
+      "loss": 11.8631,
+      "step": 270
+    },
+    {
+      "epoch": 0.9982174688057041,
+      "grad_norm": 0.5435452461242676,
+      "learning_rate": 9.52524863441373e-09,
+      "loss": 11.8305,
+      "step": 280
     }
   ],
   "logging_steps": 10,
@@ -253,12 +274,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 34430976000000.0,
+  "total_flos": 38665986048000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null