Training in progress, step 22, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b949dfb5355b24f1b8d268ed1be96fa7b43730be769c40dcd0c411ac727d0e5
+oid sha256:5ee123a1de6e87be9d9eba040e1bf9807aafdc4d9ee5c6f316acd432591a0587
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5c7cfa093439ab704de326580465b59681fe3e26a34e4ac402b78ce6215c69
+oid sha256:e52ede2c3f13ff888dbda5a069373f926e245e9caab199c53ea8a28c06a59154
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
+oid sha256:5431d395b8637afe35530f89086e8b21131e1472dc26d45a18eeeaf048503824
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a4d5a6254db6f62a1af88344fd48b32c05cdf78870a0f236ce09b217eefbf3
+oid sha256:673e63a495b7a57d30a536ff33ff871d542fcc70b7b123e80bf5435762100a07
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3455663323402405,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.9302325581395349,
+  "epoch": 1.0232558139534884,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 22,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,20 @@
       "eval_samples_per_second": 13.944,
       "eval_steps_per_second": 7.747,
       "step": 20
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 11.221933364868164,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.7855,
+      "step": 21
+    },
+    {
+      "epoch": 1.0232558139534884,
+      "grad_norm": 15.579513549804688,
+      "learning_rate": 0.0,
+      "loss": 1.2954,
+      "step": 22
     }
   ],
   "logging_steps": 1,
@@ -210,12 +224,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 597144738201600.0,
+  "total_flos": 653127057408000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null