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:a6d8c24f3b3f0016788720b460d2afbfd1b0444f11138b2a44893a84b81268b9
+oid sha256:7d576dbfde67a56da0a90de4b48b49574fa166c3ec55364128f9b1552d6750d7
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef0f9c108e78a1be61ff7e75479285f83c83acd38455a17e8a76e124bc438be
+oid sha256:af0dc6be346bae7a2a17e9bf244bc663f41d20a04ddd878fb3db8b7c81b9c0b0
 size 4830970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99dcdc3bf29ab575df4a1f298a48da6e1a274fbcccd2d0db1904beb467f9c38
+oid sha256:629d4b1fb19064648f59dd97f4537b60f5240219c3807fc9d5280752502772ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.737205505371094,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.021138669673055242,
+  "best_metric": 11.737082481384277,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.02348741074783916,
   "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": 54.85,
       "eval_steps_per_second": 13.712,
       "step": 450
+    },
+    {
+      "epoch": 0.021608417888012026,
+      "grad_norm": 0.06607946008443832,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 11.8068,
+      "step": 460
+    },
+    {
+      "epoch": 0.02207816610296881,
+      "grad_norm": 0.08771055936813354,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 11.8151,
+      "step": 470
+    },
+    {
+      "epoch": 0.02254791431792559,
+      "grad_norm": 0.13412423431873322,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 11.7992,
+      "step": 480
+    },
+    {
+      "epoch": 0.023017662532882375,
+      "grad_norm": 0.1370234489440918,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 11.6781,
+      "step": 490
+    },
+    {
+      "epoch": 0.02348741074783916,
+      "grad_norm": 0.18231408298015594,
+      "learning_rate": 0.0,
+      "loss": 11.5978,
+      "step": 500
+    },
+    {
+      "epoch": 0.02348741074783916,
+      "eval_loss": 11.737082481384277,
+      "eval_runtime": 163.0236,
+      "eval_samples_per_second": 54.986,
+      "eval_steps_per_second": 13.746,
+      "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": 81119379456000.0,
+  "total_flos": 89864847360000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null