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:b8369151b1e9c729988696d48a5a7bb8a10bad12a6c247528def7586aecc0980
+oid sha256:1535c5dd89688cf7601881334b4b9b6bc068faeb0798fc721fbcb5f9cbd8b105
 size 377538512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0639e85056c7ed4de65de6324ab5d534010ebf95c4d019fe4f650f829fc2c2c1
+oid sha256:aad8df05b33d0481ef93f8d9fa88f10f9f925b059936b8c68aaf3d0a55e3b560
 size 192144980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97697fa90535d3219bbcbf79c89a308e303f420579ec879dbce7a99639a9f4fc
+oid sha256:9908b7b8160baf149c855c74bd731bfc14aa7304d7063c230160c029238f4683
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
+oid sha256:cc8fda128404f5cc7285a078c14dccabc8f3e7d949516ad102b12752c4b2742a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6434217095375061,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.01896613491243968,
+  "best_metric": 0.6423805356025696,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.021073483236044084,
   "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": 17.471,
       "eval_steps_per_second": 4.369,
       "step": 450
+    },
+    {
+      "epoch": 0.019387604577160558,
+      "grad_norm": 3.8856089115142822,
+      "learning_rate": 4.144998534599878e-06,
+      "loss": 0.6378,
+      "step": 460
+    },
+    {
+      "epoch": 0.01980907424188144,
+      "grad_norm": 4.656737327575684,
+      "learning_rate": 2.3382067214827915e-06,
+      "loss": 0.5873,
+      "step": 470
+    },
+    {
+      "epoch": 0.02023054390660232,
+      "grad_norm": 2.6959891319274902,
+      "learning_rate": 1.0413166446519713e-06,
+      "loss": 0.7526,
+      "step": 480
+    },
+    {
+      "epoch": 0.020652013571323204,
+      "grad_norm": 3.2412455081939697,
+      "learning_rate": 2.6064662219881083e-07,
+      "loss": 0.629,
+      "step": 490
+    },
+    {
+      "epoch": 0.021073483236044084,
+      "grad_norm": 2.849865436553955,
+      "learning_rate": 0.0,
+      "loss": 0.737,
+      "step": 500
+    },
+    {
+      "epoch": 0.021073483236044084,
+      "eval_loss": 0.6423805356025696,
+      "eval_runtime": 572.6595,
+      "eval_samples_per_second": 17.445,
+      "eval_steps_per_second": 4.362,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "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": 5.136761399279616e+16,
+  "total_flos": 5.69627740471296e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null