Training in progress, step 11, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809d286f618987ca63e4c860bd1c08d6a87e41f8d57255781f61654d592b5ae2
+oid sha256:af0a95cc99d679504697a4c5426d479975ae7c4b85530759d2852205b07b6024
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd79a476039611daae375ced2b47e20ab6b4d45a419d0b80e16cb204e80f4c0
+oid sha256:d70d5fd50a4acb379cd33db57335c32c5a5e84f14f1afefd17ee537d5aad2775
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ff61294c07bdbde258211fd9f63ac972a29aa29214a2a7ea0304797cbca74f
+oid sha256:2ce8c58da92c180686c9bb31860b6a2ffffc161335b433ebf495991fc31705db
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:66a94a3823a4b9fc740a7a6ddf0adc605038b3d31dffac6df2de227ea7d92ecd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 5.40103006362915,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.9302325581395349,
+  "epoch": 1.069767441860465,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 11,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,13 @@
       "eval_samples_per_second": 35.577,
       "eval_steps_per_second": 21.346,
       "step": 10
+    },
+    {
+      "epoch": 1.069767441860465,
+      "grad_norm": 15934.6513671875,
+      "learning_rate": 0.0,
+      "loss": 19.8753,
+      "step": 11
     }
   ],
   "logging_steps": 1,
@@ -124,12 +131,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1899013079040.0,
+  "total_flos": 2088914386944.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null