Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d08c29a581b7495b98db6669e8b0eb0a2e11cbf0df40c0f771ca78647e8894d4
+oid sha256:a6dcfc60a4a7dff70e0ed674bbfcb63e1c68305a3ca7e510b7f555d08ab12313
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8341503acd91b0398a249a6b1ca19c925bba5279ad8f0ee3e23b108a5e4a1a05
+oid sha256:bff2cc1b9657a0c56130366dac9c963d4763c4edec8544285fd79b684dc38c86
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e017601a85b1ad744d7bf8dc4ff27aac026cd55e1155e549fe88ac679a9134
+oid sha256:a0481072ec4a74cd78be6738d2f2c922cfd421884f9c80eeb09703ebc0c11d46
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90450db20f965e5463684029a88340d224d3fb2689f6532511f6579867f35119
+oid sha256:a6112ae98230f68d9cc2d1ade03deb74a2c93b469b04082beb1aab5cc560468b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.9804024696350098,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.006772773450728073,
+  "best_metric": 2.9288151264190674,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.009030364600970764,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 50.753,
       "eval_steps_per_second": 12.691,
       "step": 150
+    },
+    {
+      "epoch": 0.007224291680776611,
+      "grad_norm": 3.6714208126068115,
+      "learning_rate": 0.00017623232953471174,
+      "loss": 2.7889,
+      "step": 160
+    },
+    {
+      "epoch": 0.007675809910825149,
+      "grad_norm": 4.271055698394775,
+      "learning_rate": 0.00017108588715178296,
+      "loss": 2.617,
+      "step": 170
+    },
+    {
+      "epoch": 0.008127328140873687,
+      "grad_norm": 4.206169128417969,
+      "learning_rate": 0.00016560530122087996,
+      "loss": 2.8274,
+      "step": 180
+    },
+    {
+      "epoch": 0.008578846370922226,
+      "grad_norm": 4.710639476776123,
+      "learning_rate": 0.00015981727260575154,
+      "loss": 3.0149,
+      "step": 190
+    },
+    {
+      "epoch": 0.009030364600970764,
+      "grad_norm": 6.937736511230469,
+      "learning_rate": 0.00015375,
+      "loss": 3.3344,
+      "step": 200
+    },
+    {
+      "epoch": 0.009030364600970764,
+      "eval_loss": 2.9288151264190674,
+      "eval_runtime": 184.0887,
+      "eval_samples_per_second": 50.66,
+      "eval_steps_per_second": 12.668,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1356295278428160.0,
+  "total_flos": 1806891716444160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null