Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7350d1b2818baa194908d604eef7d306d0bfda5a977b25f0ba8f3ee19c68e643
+oid sha256:b7f5f69eb370fc7cd0e87c5a48e96b6953f6920201b31709ada4329d30f011a3
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efe7f84caa469288758d729267e555e7d4959d5bd9b77991c6b054571b2b94e
+oid sha256:c0d79ef4e6c5113b42eee59ebe99aca1e4a398804d179d3775d21f338ac28624
 size 39462

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1bfd7bc146b83962f8ea49d8335d7e42b9e02cb8c55d49480bb5d6fb1f3eb70
+oid sha256:f4aefdcd16ebb09118c94fb4a5607a3f3423d69e946dd5477422923831fb7280
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c411a66287d4fb76303ae5ba8fbc6149ecf0ea6d0ba0f17e45b450c5260043f
+oid sha256:822b16bddd8bcf1ca02e61cd33e647684b752a55f3a3f365bbcb33421d66a2a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.912158012390137,
-  "best_model_checkpoint": "miner_id_24/checkpoint-2700",
-  "epoch": 4.511792945105406,
+  "best_metric": 11.912154197692871,
+  "best_model_checkpoint": "miner_id_24/checkpoint-3000",
+  "epoch": 5.01356710498852,
   "eval_steps": 300,
-  "global_step": 2700,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -150,6 +150,21 @@
       "eval_samples_per_second": 209.592,
       "eval_steps_per_second": 26.277,
       "step": 2700
+    },
+    {
+      "epoch": 5.01356710498852,
+      "grad_norm": 0.012090091593563557,
+      "learning_rate": 0.0,
+      "loss": 11.9374,
+      "step": 3000
+    },
+    {
+      "epoch": 5.01356710498852,
+      "eval_loss": 11.912154197692871,
+      "eval_runtime": 9.5524,
+      "eval_samples_per_second": 211.256,
+      "eval_steps_per_second": 26.485,
+      "step": 3000
     }
   ],
   "logging_steps": 300,
@@ -173,12 +188,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5104572825600.0,
+  "total_flos": 5671747584000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null