Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed6d29f8d2060912f433828fc190ca18537d5a7e3a8a456a8acc322a77611723
+oid sha256:01651328fbd1cec34faf721f02d0783f890a386f6a4f4f0d9f1e32ea00d2498a
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1967de11d6cc2b44f3311b43c86d1e3884ed72c2ada05856ff25e2754521498
+oid sha256:4faafbdcaf0abdde162abd5f883c04b88de9781efc6a4c6d4ebf0a02e9037be5
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634345ffff44f3e8e4423663d863ed75446c8280bff442ff1db1b9329c552ae6
+oid sha256:08f56d340e48aa67a72f5d6a5b30a5fa3291792bfab38a0cbd3c7b1d8ac44dc8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f384cbad86102ecd09ddbafda859f0542a096bde905a5fcc9ea29d2111b680c
+oid sha256:24272170972086a4eef89ebfd01fe5a5524476a110f5005cbc4510bcd255be84
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 2.429969625379683,
+  "epoch": 3.239959500506244,
   "eval_steps": 300,
-  "global_step": 900,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 720.85,
       "eval_steps_per_second": 45.071,
       "step": 900
+    },
+    {
+      "epoch": 3.239959500506244,
+      "grad_norm": 0.001791034359484911,
+      "learning_rate": 0.00039912357463265427,
+      "loss": 92.0,
+      "step": 1200
+    },
+    {
+      "epoch": 3.239959500506244,
+      "eval_loss": 11.5,
+      "eval_runtime": 3.5767,
+      "eval_samples_per_second": 697.574,
+      "eval_steps_per_second": 43.616,
+      "step": 1200
     }
   ],
   "logging_steps": 300,
@@ -74,7 +89,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -83,12 +98,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 286874507722752.0,
+  "total_flos": 382496853270528.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null