Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6b51cc3bc62b8190fc18b578d89b8a61b859ba3b6b1b7b9ac63fe594b8124b
+oid sha256:169e89b9cbb961dfd9f07b43711bba3573a2bf03f61255023fc0e62008c8708f
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f438f2604fdceaa16d93ca245522dd9a43f19b74b0e189fcf464959a4a8d46
+oid sha256:30384a35942eb32b0b6b7c8078c8d783147ff874a45074c7d124f6998f5e97ac
 size 13005370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6558da346ac45529467675e437cb6dae4b9aaab0fcbe184bbb74c2ab6cbd9d
+oid sha256:4d3a73943c34a73bf5f52472f78c27f6da00349623f69eea36c35a9ed670e41e
 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": 2.546696424484253,
   "best_model_checkpoint": "miner_id_24/checkpoint-1350",
-  "epoch": 2.33160621761658,
+  "epoch": 2.5906735751295336,
   "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": 139.461,
       "eval_steps_per_second": 34.865,
       "step": 1350
+    },
+    {
+      "epoch": 2.3488773747841103,
+      "grad_norm": 146.88360595703125,
+      "learning_rate": 0.0001,
+      "loss": 10.1538,
+      "step": 1360
+    },
+    {
+      "epoch": 2.366148531951641,
+      "grad_norm": 186.4013671875,
+      "learning_rate": 0.0001,
+      "loss": 10.0984,
+      "step": 1370
+    },
+    {
+      "epoch": 2.383419689119171,
+      "grad_norm": 78.0069351196289,
+      "learning_rate": 0.0001,
+      "loss": 10.1345,
+      "step": 1380
+    },
+    {
+      "epoch": 2.400690846286701,
+      "grad_norm": 61.604061126708984,
+      "learning_rate": 0.0001,
+      "loss": 10.3753,
+      "step": 1390
+    },
+    {
+      "epoch": 2.4179620034542313,
+      "grad_norm": 76.18042755126953,
+      "learning_rate": 0.0001,
+      "loss": 10.3891,
+      "step": 1400
+    },
+    {
+      "epoch": 2.4352331606217614,
+      "grad_norm": 108.20265197753906,
+      "learning_rate": 0.0001,
+      "loss": 10.0772,
+      "step": 1410
+    },
+    {
+      "epoch": 2.452504317789292,
+      "grad_norm": 76.92615509033203,
+      "learning_rate": 0.0001,
+      "loss": 9.8017,
+      "step": 1420
+    },
+    {
+      "epoch": 2.469775474956822,
+      "grad_norm": 138.38558959960938,
+      "learning_rate": 0.0001,
+      "loss": 9.6187,
+      "step": 1430
+    },
+    {
+      "epoch": 2.4870466321243523,
+      "grad_norm": 171.43023681640625,
+      "learning_rate": 0.0001,
+      "loss": 9.9722,
+      "step": 1440
+    },
+    {
+      "epoch": 2.5043177892918824,
+      "grad_norm": 136.78587341308594,
+      "learning_rate": 0.0001,
+      "loss": 11.1977,
+      "step": 1450
+    },
+    {
+      "epoch": 2.5215889464594126,
+      "grad_norm": 144.79205322265625,
+      "learning_rate": 0.0001,
+      "loss": 10.4862,
+      "step": 1460
+    },
+    {
+      "epoch": 2.538860103626943,
+      "grad_norm": 127.37538146972656,
+      "learning_rate": 0.0001,
+      "loss": 10.8806,
+      "step": 1470
+    },
+    {
+      "epoch": 2.5561312607944733,
+      "grad_norm": 122.02765655517578,
+      "learning_rate": 0.0001,
+      "loss": 10.4921,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5734024179620034,
+      "grad_norm": 653.7969970703125,
+      "learning_rate": 0.0001,
+      "loss": 10.2225,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5906735751295336,
+      "grad_norm": 125.18404388427734,
+      "learning_rate": 0.0001,
+      "loss": 10.6133,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5906735751295336,
+      "eval_loss": 2.5841307640075684,
+      "eval_runtime": 3.5077,
+      "eval_samples_per_second": 139.122,
+      "eval_steps_per_second": 34.78,
+      "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": 2.389102308832051e+16,
+  "total_flos": 2.654607288513331e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null