Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10397134bd3b2d9e2813433447850fb0faef5172059d40d09f7a2d1a41c55d82
+oid sha256:ec4fb2abaf31f35b38531a62b8ff0d95377345ee1d052cfa547424a6efe6e6bf
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3150461217be5cd808f399bf126b2189a2e37c274017720a5246f30099ff84f
+oid sha256:980c817b12b2bca871ea65f3057bc30f4602cf7e1b5641f3b14998858f7ce321
 size 1324282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3894c8277fae82990d5f6db6591dd659bcb0ae06b8937191372278a2e314f4b
+oid sha256:5512fa3e24a14c246e5be9e5178ea681f9edea6d0a75015662b6fd59d867a4f4
 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": 11.816428184509277,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.014500459181207405,
+  "best_metric": 11.816367149353027,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.01611162131245267,
   "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": 52.543,
       "eval_steps_per_second": 13.137,
       "step": 450
+    },
+    {
+      "epoch": 0.014822691607456459,
+      "grad_norm": 0.03759641572833061,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 11.816,
+      "step": 460
+    },
+    {
+      "epoch": 0.015144924033705511,
+      "grad_norm": 0.04052657634019852,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 11.8194,
+      "step": 470
+    },
+    {
+      "epoch": 0.015467156459954565,
+      "grad_norm": 0.04627840593457222,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 11.8205,
+      "step": 480
+    },
+    {
+      "epoch": 0.01578938888620362,
+      "grad_norm": 0.04149072989821434,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 11.8168,
+      "step": 490
+    },
+    {
+      "epoch": 0.01611162131245267,
+      "grad_norm": 0.06813540309667587,
+      "learning_rate": 0.0,
+      "loss": 11.814,
+      "step": 500
+    },
+    {
+      "epoch": 0.01611162131245267,
+      "eval_loss": 11.816367149353027,
+      "eval_runtime": 248.59,
+      "eval_samples_per_second": 52.564,
+      "eval_steps_per_second": 13.142,
+      "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": 78202036813824.0,
+  "total_flos": 86898204868608.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null