Training in progress, step 231, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d590de7f58f586a410e01a95b72b3c7847a432ae56a447c23b7d77357247709d
+oid sha256:bac351958e2569279be43111b6ec93ed75ea4c4ce0c86981a6281862443fdbd0
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c6436fa2ab683d908c820e2392344b4dacb64100e19bf529f2252848e8b70b
+oid sha256:3e6da587b736c858b7388c9239cab838037aeb60d8f04f3b48ae493b728f8dbe
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e70bc91a0683ac5fcfb898099615306e491eb4ab424ab7a6e6d834c1c8ccb01
+oid sha256:9992d4e99774b4f1dd5d32495e662afe6f1ecc69be1da8787d02a4423c74dd29
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68bcbc5d331080b541bdffea9f92896fc830fbbca1b10945d8446fdc72f5b07e
+oid sha256:8a191c66b886a4619c1aa1c661a14c6f0d546e7477ec4a37bfd489177e600d5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5005075931549072,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.8676789587852495,
+  "epoch": 1.002169197396963,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 231,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,27 @@
       "eval_samples_per_second": 40.762,
       "eval_steps_per_second": 10.398,
       "step": 200
+    },
+    {
+      "epoch": 0.911062906724512,
+      "grad_norm": 0.4956224858760834,
+      "learning_rate": 6.7666678704352e-06,
+      "loss": 1.4672,
+      "step": 210
+    },
+    {
+      "epoch": 0.9544468546637744,
+      "grad_norm": 0.6833217144012451,
+      "learning_rate": 1.8716107547278716e-06,
+      "loss": 1.419,
+      "step": 220
+    },
+    {
+      "epoch": 0.9978308026030369,
+      "grad_norm": 1.7939646244049072,
+      "learning_rate": 1.5514540650944263e-08,
+      "loss": 1.592,
+      "step": 230
     }
   ],
   "logging_steps": 10,
@@ -210,12 +231,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1876062724423680.0,
+  "total_flos": 2171209892167680.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null