Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31944740b725421e3a87d4b13ecba42d947f47dfffc236ccc46ade70e09a2380
+oid sha256:5e165ec7bd9d8ed5823f4b2db061dcc9e22f39db319c2ef23d3bae19a87b90b2
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee598828a99bfc960d72acbff1c8e3078641bdf53892013f25bc32c4bf9af5b
+oid sha256:64834cbe4761d2b55415f1e660593c6dbeb6443a8a9d74a99f5813e40df50ad2
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef335f030a326d9e70736734950affa0ae093b1ab0f3755aca7b4e9564bf45bd
+oid sha256:42293501ea1117c6db320901686b48a1c18e44514e4aaf0057955de7c3785c64
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
+oid sha256:673699a33c258fc5668f5919a0c3d2b61b77874f7dbb4fb806a02e77a15f3cef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4705545902252197,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.10582010582010581,
+  "best_metric": 1.4547858238220215,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.11757789535567313,
   "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": 12.84,
       "eval_steps_per_second": 3.212,
       "step": 450
+    },
+    {
+      "epoch": 0.10817166372721929,
+      "grad_norm": 1.2663040161132812,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 1.6161,
+      "step": 460
+    },
+    {
+      "epoch": 0.11052322163433274,
+      "grad_norm": 1.5854358673095703,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 1.4234,
+      "step": 470
+    },
+    {
+      "epoch": 0.1128747795414462,
+      "grad_norm": 1.9589043855667114,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 1.2863,
+      "step": 480
+    },
+    {
+      "epoch": 0.11522633744855967,
+      "grad_norm": 2.290048122406006,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 1.3127,
+      "step": 490
+    },
+    {
+      "epoch": 0.11757789535567313,
+      "grad_norm": 3.8831582069396973,
+      "learning_rate": 0.0,
+      "loss": 1.5305,
+      "step": 500
+    },
+    {
+      "epoch": 0.11757789535567313,
+      "eval_loss": 1.4547858238220215,
+      "eval_runtime": 138.9243,
+      "eval_samples_per_second": 12.892,
+      "eval_steps_per_second": 3.225,
+      "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": 1.119128511232082e+17,
+  "total_flos": 1.2398095975317504e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null