Training in progress, step 25000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8610811ed8a6c984f4ba4b596c8751754075c4b67ff76dde17830518a3dc70c
+oid sha256:2722deb908bbd38cad63df1b375c8bc60131ac97ddabdd2a426347fcf48e820f
 size 247936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1246567fd3f4ffce8889dfeaaa417b9a38d0b1451fbc5538d933227789f00573
+oid sha256:c72d159ee70d30faa309a73617d398e3da6ca167a9a8501c9f9531c8d2cf69dc
 size 505710

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd56e03e329a84d977e27c3cc026bd2fe383599ee8cf5d3483a74ea75d70c14
+oid sha256:3a80d4cc4819899941c071570b896bf1cb8ec400c67c039c357c0305cd5c807a
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6317aa227efad5a57077f580d6e7e28ede451da340a32cf943be0794ebf18fdf
+oid sha256:268e1fb37ccb350acffe2bb52518a4cdafc95c104475a4cba4a1b9055de4d479
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.91716480255127,
-  "best_model_checkpoint": "miner_id_24/checkpoint-24000",
-  "epoch": 5.53125440948215,
+  "best_metric": 10.917153358459473,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25000",
+  "epoch": 5.644137152532807,
   "eval_steps": 500,
-  "global_step": 24500,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3837,6 +3837,84 @@
       "eval_samples_per_second": 242.405,
       "eval_steps_per_second": 60.601,
       "step": 24500
+    },
+    {
+      "epoch": 5.542542683787216,
+      "grad_norm": 0.9217231273651123,
+      "learning_rate": 1.6274242827592223e-07,
+      "loss": 87.4725,
+      "step": 24550
+    },
+    {
+      "epoch": 5.5538309580922816,
+      "grad_norm": 0.9970532655715942,
+      "learning_rate": 1.285938599891674e-07,
+      "loss": 87.4674,
+      "step": 24600
+    },
+    {
+      "epoch": 5.565119232397347,
+      "grad_norm": 1.004233717918396,
+      "learning_rate": 9.845957200581679e-08,
+      "loss": 87.4541,
+      "step": 24650
+    },
+    {
+      "epoch": 5.576407506702413,
+      "grad_norm": 1.119969367980957,
+      "learning_rate": 7.234076355052144e-08,
+      "loss": 87.4745,
+      "step": 24700
+    },
+    {
+      "epoch": 5.587695781007478,
+      "grad_norm": 1.3986485004425049,
+      "learning_rate": 5.023847404788151e-08,
+      "loss": 87.4549,
+      "step": 24750
+    },
+    {
+      "epoch": 5.598984055312544,
+      "grad_norm": 0.8913583755493164,
+      "learning_rate": 3.215358308097971e-08,
+      "loss": 87.4608,
+      "step": 24800
+    },
+    {
+      "epoch": 5.61027232961761,
+      "grad_norm": 0.788675844669342,
+      "learning_rate": 1.808681035648563e-08,
+      "loss": 87.451,
+      "step": 24850
+    },
+    {
+      "epoch": 5.621560603922675,
+      "grad_norm": 1.1363633871078491,
+      "learning_rate": 8.038715675938613e-09,
+      "loss": 87.4567,
+      "step": 24900
+    },
+    {
+      "epoch": 5.632848878227741,
+      "grad_norm": 0.9056441783905029,
+      "learning_rate": 2.009698913489455e-09,
+      "loss": 87.468,
+      "step": 24950
+    },
+    {
+      "epoch": 5.644137152532807,
+      "grad_norm": 0.7180477976799011,
+      "learning_rate": 0.0,
+      "loss": 87.4639,
+      "step": 25000
+    },
+    {
+      "epoch": 5.644137152532807,
+      "eval_loss": 10.917153358459473,
+      "eval_runtime": 30.6995,
+      "eval_samples_per_second": 243.001,
+      "eval_steps_per_second": 60.75,
+      "step": 25000
     }
   ],
   "logging_steps": 50,
@@ -3851,7 +3929,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -3860,12 +3938,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 442332162293760.0,
+  "total_flos": 451360362332160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null