Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0ab9d950d70ece30bb6f23c7d6a25eba3ccd89ff2abe1c2eec36251e90b6ab
+oid sha256:6fb5e501eaef8a165db1c8209e2527dcbda6f4a0cc3ca745172e436d1f4f3945
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd38a4effccc714e7a9f2ddc7d689828e4fd4bd8b1b558a54130529bbef4c38
+oid sha256:040978e36cd5bf3926be84b791671a489f526df0294f1f2b797d8e3ed336ae61
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743823328bb3612f590ee4af3270c58a4c350ab4447d07101b5feccb05f46b1a
+oid sha256:7f83e4e27f402b8f2495114b56e6653c439b1bcf3a0b5d675e86b655406262ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a53e373878af8696de39d4b7adb8634138f0e346e89bffc05bcb76c7b6de169
+oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.400266170501709,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.06146753745678064,
+  "best_metric": 2.2233057022094727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.06915097963887822,
   "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": 15.581,
       "eval_steps_per_second": 3.895,
       "step": 400
+    },
+    {
+      "epoch": 0.06300422589320015,
+      "grad_norm": 3.9970903396606445,
+      "learning_rate": 1.9862232585005475e-05,
+      "loss": 4.2686,
+      "step": 410
+    },
+    {
+      "epoch": 0.06454091432961967,
+      "grad_norm": 6.5729546546936035,
+      "learning_rate": 1.58029979997317e-05,
+      "loss": 4.3436,
+      "step": 420
+    },
+    {
+      "epoch": 0.06607760276603919,
+      "grad_norm": 7.991576194763184,
+      "learning_rate": 1.2173450342671593e-05,
+      "loss": 3.9325,
+      "step": 430
+    },
+    {
+      "epoch": 0.0676142912024587,
+      "grad_norm": 11.29770278930664,
+      "learning_rate": 8.991272405169498e-06,
+      "loss": 4.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.06915097963887822,
+      "grad_norm": 15.63181209564209,
+      "learning_rate": 6.271967438265535e-06,
+      "loss": 5.0258,
+      "step": 450
+    },
+    {
+      "epoch": 0.06915097963887822,
+      "eval_loss": 2.2233057022094727,
+      "eval_runtime": 176.0184,
+      "eval_samples_per_second": 15.567,
+      "eval_steps_per_second": 3.892,
+      "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": 7.870489049432064e+16,
+  "total_flos": 8.854300180611072e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null