Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c23145b10968122e1ff0961a7df4b46f3e6cc4cc4af56ccdc216922a817ba4
+oid sha256:2b7ad849ddfac52cd850d74209fabfdc526c979aca7ac9074f97ab41ad893f69
 size 100690184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9306dd89dbc6e7511dc84902c41e4506f8fe169bb1d3a3ab0efe26fd59aab5
+oid sha256:16025a8a40d34c0823d01219f6ecca53e2a17daf3bcfa17de7c2a24d9efc2483
 size 51345082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa70972c470389847f9cd4d826b9ecf5cd2c9257bb63bb7f6aa6e50fe764cce
+oid sha256:a9c31eda2ea2280d48d0453a1861d4936510c5f0d07d1c6b09bd267446898752
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
+oid sha256:043092824777602976966449c2a2a96527a878ad10507a3b4d0f461ea2b8d14e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.882382869720459,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.38860103626943004,
+  "best_metric": 2.8705949783325195,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.4317789291882556,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 74.746,
       "eval_steps_per_second": 18.687,
       "step": 450
+    },
+    {
+      "epoch": 0.39723661485319517,
+      "grad_norm": 48.339908599853516,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 6.0256,
+      "step": 460
+    },
+    {
+      "epoch": 0.4058721934369603,
+      "grad_norm": 83.55408477783203,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 5.9578,
+      "step": 470
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 55.561649322509766,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 5.9324,
+      "step": 480
+    },
+    {
+      "epoch": 0.4231433506044905,
+      "grad_norm": 66.6230239868164,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 5.6569,
+      "step": 490
+    },
+    {
+      "epoch": 0.4317789291882556,
+      "grad_norm": 116.90052032470703,
+      "learning_rate": 0.0,
+      "loss": 6.1575,
+      "step": 500
+    },
+    {
+      "epoch": 0.4317789291882556,
+      "eval_loss": 2.8705949783325195,
+      "eval_runtime": 6.5205,
+      "eval_samples_per_second": 74.841,
+      "eval_steps_per_second": 18.71,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4191310105804800.0,
+  "total_flos": 4657011228672000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null