Training in progress, step 25500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d1a3176dab0c716b2cb9e2228acd9a8189902ef7d0de3f1a8887cac5395af2b
+oid sha256:cb834eab847e8e28dec407e59bb0d8e4fb19cd54d9f3d073943c433681e78580
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117b69449b80d22018e7a1446e9587a0c72614a77188fa42a8403de5c5a99beb
+oid sha256:6a58bfbea0ba319ef812042f985398f0d1c4c4574768319cbb4404df7554a97c
 size 424342

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4860adba5ee7478bb07b9927ff6a669b0d3afd76a7de26d7eed63b2c70717d92
+oid sha256:b275d981db52339dd3e5b625c97d2fc32266d9e8bfbf53825cc6f3a487e5c1c4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c47f6988562d95347ca3617a47b67af7109f8b9dc1ff18e8837397b25c7fb155
+oid sha256:1a7a8143394efd02a858ec1c71378ac1441217f91088ab489b87b43340e54b14
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.737992286682129,
   "best_model_checkpoint": "miner_id_24/checkpoint-24000",
-  "epoch": 9.080167052521675,
+  "epoch": 9.261745880430341,
   "eval_steps": 500,
-  "global_step": 25000,
+  "global_step": 25500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3915,6 +3915,84 @@
       "eval_samples_per_second": 490.552,
       "eval_steps_per_second": 122.691,
       "step": 25000
+    },
+    {
+      "epoch": 9.098324935312542,
+      "grad_norm": 0.32145312428474426,
+      "learning_rate": 4.3060546058765975e-06,
+      "loss": 6.7494,
+      "step": 25050
+    },
+    {
+      "epoch": 9.116482818103409,
+      "grad_norm": 0.32838886976242065,
+      "learning_rate": 4.1356977178935615e-06,
+      "loss": 6.7581,
+      "step": 25100
+    },
+    {
+      "epoch": 9.134640700894275,
+      "grad_norm": 0.2937028408050537,
+      "learning_rate": 3.9687126288057616e-06,
+      "loss": 6.7556,
+      "step": 25150
+    },
+    {
+      "epoch": 9.152798583685142,
+      "grad_norm": 0.3333373963832855,
+      "learning_rate": 3.8051048122335777e-06,
+      "loss": 6.7596,
+      "step": 25200
+    },
+    {
+      "epoch": 9.170956466476008,
+      "grad_norm": 0.29934102296829224,
+      "learning_rate": 3.644879631093374e-06,
+      "loss": 6.7524,
+      "step": 25250
+    },
+    {
+      "epoch": 9.189114349266875,
+      "grad_norm": 0.3680090606212616,
+      "learning_rate": 3.488042337421889e-06,
+      "loss": 6.7547,
+      "step": 25300
+    },
+    {
+      "epoch": 9.207272232057742,
+      "grad_norm": 0.3357902467250824,
+      "learning_rate": 3.3345980722038647e-06,
+      "loss": 6.7557,
+      "step": 25350
+    },
+    {
+      "epoch": 9.225430114848608,
+      "grad_norm": 0.31992048025131226,
+      "learning_rate": 3.184551865203717e-06,
+      "loss": 6.7545,
+      "step": 25400
+    },
+    {
+      "epoch": 9.243587997639475,
+      "grad_norm": 0.2933006286621094,
+      "learning_rate": 3.0379086348005164e-06,
+      "loss": 6.7502,
+      "step": 25450
+    },
+    {
+      "epoch": 9.261745880430341,
+      "grad_norm": 0.32160452008247375,
+      "learning_rate": 2.8946731878269183e-06,
+      "loss": 6.7559,
+      "step": 25500
+    },
+    {
+      "epoch": 9.261745880430341,
+      "eval_loss": 6.738137722015381,
+      "eval_runtime": 9.4312,
+      "eval_samples_per_second": 491.773,
+      "eval_steps_per_second": 122.996,
+      "step": 25500
     }
   ],
   "logging_steps": 50,
@@ -3929,7 +4007,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -3938,12 +4016,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 480564019200000.0,
+  "total_flos": 490175299584000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null