Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb5e501eaef8a165db1c8209e2527dcbda6f4a0cc3ca745172e436d1f4f3945
+oid sha256:2e5c0aca3f8f029ced3637269b950e2a1ebeb00c25acda6b7774cbe84356d601
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040978e36cd5bf3926be84b791671a489f526df0294f1f2b797d8e3ed336ae61
+oid sha256:e58a764dfe84e6d9907331b33b7be41bcbb70ccae99f30777fbd3a415cc5df36
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f83e4e27f402b8f2495114b56e6653c439b1bcf3a0b5d675e86b655406262ef
+oid sha256:7900fc7f27afebaf1789ef5bc97a64120f6d4d081b9218f1815b0fa8989f62ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
+oid sha256:693af3889e4633c932ce337b10348752049de987b4153b6619512b489850fe7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2233057022094727,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.06915097963887822,
+  "best_metric": 2.206617832183838,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.0768344218209758,
   "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": 15.567,
       "eval_steps_per_second": 3.892,
       "step": 450
+    },
+    {
+      "epoch": 0.07068766807529774,
+      "grad_norm": 4.114557266235352,
+      "learning_rate": 4.028783622414835e-06,
+      "loss": 4.1326,
+      "step": 460
+    },
+    {
+      "epoch": 0.07222435651171726,
+      "grad_norm": 4.679042339324951,
+      "learning_rate": 2.272649523684208e-06,
+      "loss": 4.2644,
+      "step": 470
+    },
+    {
+      "epoch": 0.07376104494813676,
+      "grad_norm": 6.639362335205078,
+      "learning_rate": 1.0121208508766823e-06,
+      "loss": 4.0476,
+      "step": 480
+    },
+    {
+      "epoch": 0.07529773338455628,
+      "grad_norm": 8.920401573181152,
+      "learning_rate": 2.533387729782834e-07,
+      "loss": 4.6659,
+      "step": 490
+    },
+    {
+      "epoch": 0.0768344218209758,
+      "grad_norm": 13.285958290100098,
+      "learning_rate": 0.0,
+      "loss": 5.0228,
+      "step": 500
+    },
+    {
+      "epoch": 0.0768344218209758,
+      "eval_loss": 2.206617832183838,
+      "eval_runtime": 175.6859,
+      "eval_samples_per_second": 15.596,
+      "eval_steps_per_second": 3.899,
+      "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": 8.854300180611072e+16,
+  "total_flos": 9.829167574233907e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null