Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fe48b843498c9061579eaf1a2418c20182cd07daab5a950c94123e7dbac742
+oid sha256:20df34dac73b628b16739c6d12b4b7866c4554f74d1ec9a26ce321acf17d5ba3
 size 231448

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e887c93d6120a870ce552f0339935e777d30596e3cf781e13484a5767887be
+oid sha256:1dc0a836b4f95a28d7aeddf98b0ebe1f77e8f8dd83a5aa3c8627b7d7f0a58f47
 size 254640

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728bbce56524490ca8e12b2261182985aa03855ed753181a61ba38b5058cfbfc
+oid sha256:b5f7844d61c9f1bfcaa55dd5aeb5ef517e4ef0eb4e548e5c0fe2c2cbb577c4b9
 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": 10.29311752319336,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.16737957969127767,
+  "epoch": 0.1859773107680863,
   "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": 390.227,
       "eval_steps_per_second": 97.557,
       "step": 450
+    },
+    {
+      "epoch": 0.1710991259066394,
+      "grad_norm": 0.24755986034870148,
+      "learning_rate": 4.144998534599878e-06,
+      "loss": 10.3142,
+      "step": 460
+    },
+    {
+      "epoch": 0.1748186721220011,
+      "grad_norm": 0.2610633969306946,
+      "learning_rate": 2.3382067214827915e-06,
+      "loss": 10.3032,
+      "step": 470
+    },
+    {
+      "epoch": 0.17853821833736283,
+      "grad_norm": 0.2485753893852234,
+      "learning_rate": 1.0413166446519713e-06,
+      "loss": 10.2918,
+      "step": 480
+    },
+    {
+      "epoch": 0.18225776455272458,
+      "grad_norm": 0.30265066027641296,
+      "learning_rate": 2.6064662219881083e-07,
+      "loss": 10.2869,
+      "step": 490
+    },
+    {
+      "epoch": 0.1859773107680863,
+      "grad_norm": 0.3461194634437561,
+      "learning_rate": 0.0,
+      "loss": 10.2771,
+      "step": 500
+    },
+    {
+      "epoch": 0.1859773107680863,
+      "eval_loss": 10.293418884277344,
+      "eval_runtime": 2.8988,
+      "eval_samples_per_second": 390.504,
+      "eval_steps_per_second": 97.626,
+      "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": 12209710694400.0,
+  "total_flos": 13566345216000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null