Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5494dcef6fe239ea4005761fb16b58f8d0398779d1934e1eb8e3adb379bcd7
+oid sha256:6ddbbddeb9462bf83abd8da3f8ba0d688137983e323bfec72ac032138fe99db2
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23ab09e8a597cf8477d88f74a87b4dc6953b369bea295c0110e0821e6a59965
+oid sha256:ec9e283f65a2cb23389dcbcdd95cd733794729b0e7301caf7e71a723ab9e6cd8
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff9c6f706b9b8ffad8fb8c3dd50fffa678f40c5309c4d9217170f7459106f71
+oid sha256:f8212e6863b171d3909e83eb807c43ba07592c46f3ce45a63f6dd980d02a0028
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.8688809871673584,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.2234359483614697,
+  "epoch": 0.24826216484607747,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 48.065,
       "eval_steps_per_second": 12.016,
       "step": 450
+    },
+    {
+      "epoch": 0.22840119165839126,
+      "grad_norm": 0.6016173958778381,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 2.7879,
+      "step": 460
+    },
+    {
+      "epoch": 0.2333664349553128,
+      "grad_norm": 0.7445509433746338,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 2.8099,
+      "step": 470
+    },
+    {
+      "epoch": 0.23833167825223436,
+      "grad_norm": 0.8929831385612488,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 2.9323,
+      "step": 480
+    },
+    {
+      "epoch": 0.24329692154915591,
+      "grad_norm": 1.2002997398376465,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 2.8912,
+      "step": 490
+    },
+    {
+      "epoch": 0.24826216484607747,
+      "grad_norm": 4.329601287841797,
+      "learning_rate": 0.0,
+      "loss": 3.0803,
+      "step": 500
+    },
+    {
+      "epoch": 0.24826216484607747,
+      "eval_loss": 2.869129180908203,
+      "eval_runtime": 17.604,
+      "eval_samples_per_second": 48.171,
+      "eval_steps_per_second": 12.043,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4487940522639360.0,
+  "total_flos": 4979090640076800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null