Training in progress, step 2850, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66cf16cd354c25c44c4affc7ad3953ecc9f969c500d44e5a55a98a3083ff528c
+oid sha256:7e09c2a5dcf2e7fc1395c6f500fd04f6e9ed509fdd50cd012a60a68626bc519e
 size 39131224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4331c4dc32baee3c4394c03eab5c75389c7b5fc5069e5147279ab8c9ae82e89d
+oid sha256:489e57bb05f8b7b131b825404e7f5532f91305b731eb0b5d4894936cbda854c0
 size 78510334

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa67eb9bf7ad79dc7716ba58f0306c8677d78abe85ca7f2754cd79281aaf012
+oid sha256:e1c26ee950e9a69b9213b7e74235a077ae09cbcb03643e4b3877a05d223c05e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126ec9e64208d79536bffb656694fa4cf727027deefd223caf2c667dc5c78bc8
+oid sha256:5f76a102ac755d5bd19e6f0e55ad50e49a03a307409b32eeac7fb5a2a13752ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7818862795829773,
   "best_model_checkpoint": "miner_id_24/checkpoint-2700",
-  "epoch": 4.007419773696903,
+  "epoch": 4.230012984603969,
   "eval_steps": 150,
-  "global_step": 2700,
+  "global_step": 2850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -537,6 +537,35 @@
       "eval_samples_per_second": 40.417,
       "eval_steps_per_second": 20.209,
       "step": 2700
+    },
+    {
+      "epoch": 4.081617510665924,
+      "grad_norm": 0.18808983266353607,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 0.7197,
+      "step": 2750
+    },
+    {
+      "epoch": 4.155815247634947,
+      "grad_norm": 0.1956692934036255,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 0.7152,
+      "step": 2800
+    },
+    {
+      "epoch": 4.230012984603969,
+      "grad_norm": 0.1999446451663971,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 0.7127,
+      "step": 2850
+    },
+    {
+      "epoch": 4.230012984603969,
+      "eval_loss": 0.7822389006614685,
+      "eval_runtime": 14.2177,
+      "eval_samples_per_second": 39.95,
+      "eval_steps_per_second": 19.975,
+      "step": 2850
     }
   ],
   "logging_steps": 50,
@@ -551,7 +580,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -565,7 +594,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.07814914326528e+16,
+  "total_flos": 3.24915742900224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null