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:d04ba57f40efaa964bb90dbb9efdbba165ba85e6697fc334b04934a278882eb1
+oid sha256:ededd094979e25ecb7073ae9e1e359a92db63e6488982a9f2ee88e1273aa8028
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9528e4be11b180b1128fbcf04a588059c3acac966ba361e941596b9657e6c5b4
+oid sha256:b7fe6973e89cc5a3ce978d53f1c02689fa084e21dddd73e302f02ab59cb9c67a
 size 91850618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa72dcf060bd99b02d38a4c5f934fc408181cf8a0d3001969e6ded9bdd88ac9a
+oid sha256:aa0849c112fc2fa45d2f5157459229169b43efdef071e50277fdab1d21374497
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f69d9f90a0d5ce8ac61f1f875459a761943b0c4252d8391ecd4046776d8753
+oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8036990165710449,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.09679370840895342,
+  "best_metric": 0.7930504679679871,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.1088929219600726,
   "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": 33.498,
       "eval_steps_per_second": 8.374,
       "step": 400
+    },
+    {
+      "epoch": 0.09921355111917725,
+      "grad_norm": 0.8406041860580444,
+      "learning_rate": 1.9480266573755372e-05,
+      "loss": 0.7104,
+      "step": 410
+    },
+    {
+      "epoch": 0.10163339382940109,
+      "grad_norm": 1.3040482997894287,
+      "learning_rate": 1.5499094192044554e-05,
+      "loss": 0.7257,
+      "step": 420
+    },
+    {
+      "epoch": 0.10405323653962492,
+      "grad_norm": 1.192878246307373,
+      "learning_rate": 1.1939345528389446e-05,
+      "loss": 0.8004,
+      "step": 430
+    },
+    {
+      "epoch": 0.10647307924984876,
+      "grad_norm": 2.158026695251465,
+      "learning_rate": 8.818363320454701e-06,
+      "loss": 0.8862,
+      "step": 440
+    },
+    {
+      "epoch": 0.1088929219600726,
+      "grad_norm": 1.5391501188278198,
+      "learning_rate": 6.1513526798373514e-06,
+      "loss": 0.6706,
+      "step": 450
+    },
+    {
+      "epoch": 0.1088929219600726,
+      "eval_loss": 0.7930504679679871,
+      "eval_runtime": 51.8728,
+      "eval_samples_per_second": 33.544,
+      "eval_steps_per_second": 8.386,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.88932260102144e+16,
+  "total_flos": 2.1270519349248e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null