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:a2966e874df549b243591b51f3ae63b96b31dd0e4553cf713ba2e0a25032c9a1
+oid sha256:608628c4b1324acd6f65e65ac4270f053dbadda9222c461102fca697bcb62ddf
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ece55141ec0c856ac8352ce6c062e01f24f93c72ad1fbcd23722ab440c69e5
+oid sha256:b5873c605751528b445a447467a054e13662cdda852762411a81c137ffad619c
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7f40b4328f1741b2e5c7591aa1f8f52be0a3bc528723543b8ca83b001d217c
+oid sha256:e48ad1d830527d0b0c533d7e418f0cafe4bbe125fa44172d315b74b44ccac83d
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b638125345eee66261d2423c36c01b02453186ef536e9a5b8085fc8faa3a2a46
+oid sha256:5ca13c3530cb36506b3692f740061cffec6ee384ba8c3a08d5aff4eb57c1361e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6028205156326294,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.02853428870359215,
+  "best_metric": 0.6025488376617432,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.0317047652262135,
   "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": 23.605,
       "eval_steps_per_second": 5.904,
       "step": 450
+    },
+    {
+      "epoch": 0.02916838400811642,
+      "grad_norm": 0.16671153903007507,
+      "learning_rate": 3.970676166322313e-06,
+      "loss": 0.5375,
+      "step": 460
+    },
+    {
+      "epoch": 0.02980247931264069,
+      "grad_norm": 0.17899635434150696,
+      "learning_rate": 2.239870924784917e-06,
+      "loss": 0.5783,
+      "step": 470
+    },
+    {
+      "epoch": 0.03043657461716496,
+      "grad_norm": 0.1619870811700821,
+      "learning_rate": 9.97522953989038e-07,
+      "loss": 0.5893,
+      "step": 480
+    },
+    {
+      "epoch": 0.03107066992168923,
+      "grad_norm": 0.17906083166599274,
+      "learning_rate": 2.4968484836801973e-07,
+      "loss": 0.6017,
+      "step": 490
+    },
+    {
+      "epoch": 0.0317047652262135,
+      "grad_norm": 0.2084181010723114,
+      "learning_rate": 0.0,
+      "loss": 0.7595,
+      "step": 500
+    },
+    {
+      "epoch": 0.0317047652262135,
+      "eval_loss": 0.6025488376617432,
+      "eval_runtime": 281.8077,
+      "eval_samples_per_second": 23.566,
+      "eval_steps_per_second": 5.894,
+      "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": 3.5766281378463744e+16,
+  "total_flos": 3.974920806806323e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null