Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4525f7d00b912b73aa7b9902c4fffde400faf9ae1cc0ed2d56d636e3c38b7d30
+oid sha256:364756399496040ebdb9d89addb5cab75442b1d2fe1183fd773c6858114207a3
 size 10636096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:162b07b926a49be082a48e7e8822e4251d59fea1ccff9e30536e1249dd5b2877
+oid sha256:20d3801f30da59bd4c8e1c783f30ecbfbba2e1c208ca211f3eb9e72232822400
 size 5561210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e2a9c7fcc25d074f96ef2d450b947c50b25c45578e9c6461c0c935fd35ec9b
+oid sha256:241245b2906a181943d5a1cb917468c1f082c92d3f692e391015d2cd94a5caab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c0cbab52df187d8502a1b66e46607ea8ce4ac36a84891208388bc9974f53e8
+oid sha256:2e87d47519e32af310d5ce258e0454d331221391a1b9ee9143859120658f7a9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.45768770575523376,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.010000111112345693,
+  "epoch": 0.011111234569272993,
   "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": 29.823,
       "eval_steps_per_second": 14.912,
       "step": 450
+    },
+    {
+      "epoch": 0.010222335803731152,
+      "grad_norm": 2.616846799850464,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 1.9355,
+      "step": 460
+    },
+    {
+      "epoch": 0.010444560495116613,
+      "grad_norm": 3.487445592880249,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 1.7963,
+      "step": 470
+    },
+    {
+      "epoch": 0.010666785186502072,
+      "grad_norm": 4.147712707519531,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 2.2313,
+      "step": 480
+    },
+    {
+      "epoch": 0.010889009877887532,
+      "grad_norm": 2.158893346786499,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 1.9122,
+      "step": 490
+    },
+    {
+      "epoch": 0.011111234569272993,
+      "grad_norm": 3.25124192237854,
+      "learning_rate": 0.0,
+      "loss": 1.8567,
+      "step": 500
+    },
+    {
+      "epoch": 0.011111234569272993,
+      "eval_loss": 0.4580913186073303,
+      "eval_runtime": 635.8547,
+      "eval_samples_per_second": 29.799,
+      "eval_steps_per_second": 14.9,
+      "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": 979395957227520.0,
+  "total_flos": 1087679008604160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null