Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13315843d9be9cc0e80a2aacd6c3cf38e5c5c11cbc1228cb5409c470ea7f7f62
+oid sha256:4144ff24cdcece7cf42e2aca457804c9b3ceb343277b30828a4b0a06fe09dd10
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9054fb8e5237b1c2ed26213330757f9a87bbfbf6236b67cece84cea126b1333
+oid sha256:c676c5213c5ac6cf5faee4bbf0b6f86a3055701b2744972196fcddd20e681137
 size 13005370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:973cb9c31f34267369ffd901bd9098fd8f4cb03b37083277b617aa82784f0094
+oid sha256:ab30765be6f3fc06f48afc18afbac7a60f85012715b51fd034866fd7d34a3e1b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baec16f1d3203641053b140012c961fd8b8e1dac231c353313afb13a49c1d1fe
+oid sha256:d9d4e004ca157e9e2e51f06820328f72b00d1e93f5fe5770010a13d46b658813
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.743666648864746,
   "best_model_checkpoint": "miner_id_24/checkpoint-1350",
-  "epoch": 0.026067563262114176,
+  "epoch": 0.028963959180126862,
   "eval_steps": 150,
-  "global_step": 1350,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1032,6 +1032,119 @@
       "eval_samples_per_second": 130.924,
       "eval_steps_per_second": 32.731,
       "step": 1350
+    },
+    {
+      "epoch": 0.02626065632331502,
+      "grad_norm": 6.833707809448242,
+      "learning_rate": 0.0001,
+      "loss": 10.0071,
+      "step": 1360
+    },
+    {
+      "epoch": 0.026453749384515866,
+      "grad_norm": 8.814143180847168,
+      "learning_rate": 0.0001,
+      "loss": 9.8842,
+      "step": 1370
+    },
+    {
+      "epoch": 0.026646842445716714,
+      "grad_norm": 10.0423583984375,
+      "learning_rate": 0.0001,
+      "loss": 10.6022,
+      "step": 1380
+    },
+    {
+      "epoch": 0.02683993550691756,
+      "grad_norm": 11.296242713928223,
+      "learning_rate": 0.0001,
+      "loss": 11.2607,
+      "step": 1390
+    },
+    {
+      "epoch": 0.027033028568118404,
+      "grad_norm": 21.390296936035156,
+      "learning_rate": 0.0001,
+      "loss": 12.9834,
+      "step": 1400
+    },
+    {
+      "epoch": 0.027226121629319252,
+      "grad_norm": 8.968457221984863,
+      "learning_rate": 0.0001,
+      "loss": 10.0666,
+      "step": 1410
+    },
+    {
+      "epoch": 0.027419214690520097,
+      "grad_norm": 11.966334342956543,
+      "learning_rate": 0.0001,
+      "loss": 10.0537,
+      "step": 1420
+    },
+    {
+      "epoch": 0.02761230775172094,
+      "grad_norm": 13.229506492614746,
+      "learning_rate": 0.0001,
+      "loss": 10.3221,
+      "step": 1430
+    },
+    {
+      "epoch": 0.027805400812921786,
+      "grad_norm": 20.169370651245117,
+      "learning_rate": 0.0001,
+      "loss": 11.0951,
+      "step": 1440
+    },
+    {
+      "epoch": 0.027998493874122635,
+      "grad_norm": 43.70033264160156,
+      "learning_rate": 0.0001,
+      "loss": 13.0941,
+      "step": 1450
+    },
+    {
+      "epoch": 0.02819158693532348,
+      "grad_norm": 9.215312957763672,
+      "learning_rate": 0.0001,
+      "loss": 10.0646,
+      "step": 1460
+    },
+    {
+      "epoch": 0.028384679996524324,
+      "grad_norm": 20.890764236450195,
+      "learning_rate": 0.0001,
+      "loss": 9.7248,
+      "step": 1470
+    },
+    {
+      "epoch": 0.02857777305772517,
+      "grad_norm": 12.14108943939209,
+      "learning_rate": 0.0001,
+      "loss": 10.3096,
+      "step": 1480
+    },
+    {
+      "epoch": 0.028770866118926017,
+      "grad_norm": 15.33022689819336,
+      "learning_rate": 0.0001,
+      "loss": 11.5878,
+      "step": 1490
+    },
+    {
+      "epoch": 0.028963959180126862,
+      "grad_norm": 29.498929977416992,
+      "learning_rate": 0.0001,
+      "loss": 13.2048,
+      "step": 1500
+    },
+    {
+      "epoch": 0.028963959180126862,
+      "eval_loss": 2.7453110218048096,
+      "eval_runtime": 336.37,
+      "eval_samples_per_second": 129.655,
+      "eval_steps_per_second": 32.414,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
@@ -1046,7 +1159,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1055,12 +1168,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.785147236856627e+16,
+  "total_flos": 3.0944605381853184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null