Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f74548e5a78bf6cf5abd1142a3d3f59959cf100a96d04c044c6ed5f08d299f
+oid sha256:80c6d7ad096547f84cf33043753b89323bf518e796812286d91745ff696c6d48
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b8ca7e671ccc87c1d407749d7a201f71c0c0c4b4c30b2b28565a76a6f97114
+oid sha256:9fc4a9797364eb871e7d488879ae8a975cfe75ff77e28d53be9c3ec4730aac1e
 size 588700500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f8738976c873c6ba5baff112bc02356e3685386bd797f76d4b2c4969703c33
+oid sha256:912f61cab3ca37aaf1de8089bce634938ef8fab87fda54825cf8494660342bf7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89df26d2648b7bbd96c19b1cc0947215f3b7f788b7b6e7a6d1179c8d03cbffea
+oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.625133752822876,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.1136848088674151,
+  "best_metric": 1.584151268005371,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.12789540997584198,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 9.026,
       "eval_steps_per_second": 2.266,
       "step": 400
+    },
+    {
+      "epoch": 0.11652692908910046,
+      "grad_norm": 1.849120855331421,
+      "learning_rate": 1.9671249579380422e-05,
+      "loss": 1.5864,
+      "step": 410
+    },
+    {
+      "epoch": 0.11936904931078585,
+      "grad_norm": 1.457759976387024,
+      "learning_rate": 1.5651046095888127e-05,
+      "loss": 1.543,
+      "step": 420
+    },
+    {
+      "epoch": 0.12221116953247123,
+      "grad_norm": 2.084972858428955,
+      "learning_rate": 1.205639793553052e-05,
+      "loss": 1.5948,
+      "step": 430
+    },
+    {
+      "epoch": 0.1250532897541566,
+      "grad_norm": 2.2695581912994385,
+      "learning_rate": 8.904817862812098e-06,
+      "loss": 1.8299,
+      "step": 440
+    },
+    {
+      "epoch": 0.12789540997584198,
+      "grad_norm": 2.3242664337158203,
+      "learning_rate": 6.211660059051443e-06,
+      "loss": 1.9295,
+      "step": 450
+    },
+    {
+      "epoch": 0.12789540997584198,
+      "eval_loss": 1.584151268005371,
+      "eval_runtime": 81.6227,
+      "eval_samples_per_second": 9.078,
+      "eval_steps_per_second": 2.279,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -373,7 +416,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.932068558700544e+16,
+  "total_flos": 7.83983944138752e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null