Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9263f00c99bf8c13ab0dfb8c8809c9669f45f49648d07d872b29d8e482f6e00c
+oid sha256:dd1d4e15d9bd9bdd00b48e2671a081eb537822a17e98e767647c5596957267ab
 size 275341720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e208ec965c072bc38e47daf1e0ab556dd5a842d3e96e5f10b0039fef05131b
+oid sha256:ee216d3d93996a4e875d2843f94dba9b7f17f45170e5766758f9b4f4302da39f
 size 140566100

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30ec500a87660d21f084656138a50e21bb889b5edc38f3003a824385a6b82c3
+oid sha256:7fbce46161e64e2088dd00a240852d83bf2555c6d29976497b4c76c12dc4cf7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c579f5f648f371ddcf6d84448bace40e1d46168d2f7b5fae9b6105a9c79d201
+oid sha256:2c9718e38efb2d48aaa61791c4fc8b4a7f9cfd08f355dda43ae7de9f2cb195d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7105076909065247,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.1953125,
+  "epoch": 0.2170138888888889,
   "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": 9.765,
       "eval_steps_per_second": 2.456,
       "step": 450
+    },
+    {
+      "epoch": 0.1996527777777778,
+      "grad_norm": 0.8355949521064758,
+      "learning_rate": 4.125629382569038e-06,
+      "loss": 0.6722,
+      "step": 460
+    },
+    {
+      "epoch": 0.20399305555555555,
+      "grad_norm": 1.7075914144515991,
+      "learning_rate": 2.327280521849694e-06,
+      "loss": 0.66,
+      "step": 470
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.7151721119880676,
+      "learning_rate": 1.0364506790227565e-06,
+      "loss": 0.6677,
+      "step": 480
+    },
+    {
+      "epoch": 0.2126736111111111,
+      "grad_norm": 0.9590463042259216,
+      "learning_rate": 2.5942864732872295e-07,
+      "loss": 0.9534,
+      "step": 490
+    },
+    {
+      "epoch": 0.2170138888888889,
+      "grad_norm": 2.80539870262146,
+      "learning_rate": 0.0,
+      "loss": 0.8418,
+      "step": 500
+    },
+    {
+      "epoch": 0.2170138888888889,
+      "eval_loss": 0.7122297286987305,
+      "eval_runtime": 49.691,
+      "eval_samples_per_second": 9.76,
+      "eval_steps_per_second": 2.455,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "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": 7.78341039168553e+16,
+  "total_flos": 8.64727392017449e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null