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:b0ba1941de85f1ba1835379675241a2bd959c308eca1295927f172ccd9df9437
+oid sha256:b084a7d38102dd939b5a2650b9bbfa67ba71795ee328acd01f7695fdea0aa9df
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e559ef431273b4e618392afa0f84b51e51bd5796f951291ec0e6ae38fe88077
+oid sha256:0a2fa349db036ad04314e37e3afdc3a6c17a5825d808c2f45689348c210d5bdc
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1784bbb4798a4d0e91168a1ceecbeba2fd38ff77ed2f52065fc7371d655bc4b6
+oid sha256:efd1174187e88b364f678316032c379fff94ada40f35ad767d555455a76366f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
+oid sha256:cc8fda128404f5cc7285a078c14dccabc8f3e7d949516ad102b12752c4b2742a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8544771671295166,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.2638522427440633,
+  "best_metric": 0.8523212671279907,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.2931691586045148,
   "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": 16.083,
       "eval_steps_per_second": 4.032,
       "step": 450
+    },
+    {
+      "epoch": 0.2697156259161536,
+      "grad_norm": 0.9589357376098633,
+      "learning_rate": 4.144998534599878e-06,
+      "loss": 1.042,
+      "step": 460
+    },
+    {
+      "epoch": 0.2755790090882439,
+      "grad_norm": 0.8186019659042358,
+      "learning_rate": 2.3382067214827915e-06,
+      "loss": 0.9008,
+      "step": 470
+    },
+    {
+      "epoch": 0.28144239226033424,
+      "grad_norm": 0.8926922082901001,
+      "learning_rate": 1.0413166446519713e-06,
+      "loss": 0.8237,
+      "step": 480
+    },
+    {
+      "epoch": 0.2873057754324245,
+      "grad_norm": 1.1307158470153809,
+      "learning_rate": 2.6064662219881083e-07,
+      "loss": 0.7824,
+      "step": 490
+    },
+    {
+      "epoch": 0.2931691586045148,
+      "grad_norm": 1.0825364589691162,
+      "learning_rate": 0.0,
+      "loss": 0.7375,
+      "step": 500
+    },
+    {
+      "epoch": 0.2931691586045148,
+      "eval_loss": 0.8523212671279907,
+      "eval_runtime": 44.7368,
+      "eval_samples_per_second": 16.049,
+      "eval_steps_per_second": 4.024,
+      "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": 7.867718010352435e+16,
+  "total_flos": 8.731657194858086e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null