Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64c1477820028eee2fb6c486cd3c9eb6ce52f7549de7d5ee2c60990c19561ae3
+oid sha256:ec214429a23b35f18fdbde9af438e4c79485249ac92996fbb96ffecd89268c27
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a188b82151c1be9c35f36107e79816269c20f50b151a89998d64756d2f421376
+oid sha256:afbaa3dc102bcf13f36ac1126b7d424ae1c8620f84997209b5bdffb7b1410ca5
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e72bc71221041d2c0dd01366b7431c2115c334f9e64bb75ddbeaa419992a7b6
+oid sha256:136a69080e8188f033afddc0bfb7ed1e128fe06f6d676a2c11027049c8d698e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.926045417785645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.06436041834271923,
+  "best_metric": 11.924607276916504,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.09654062751407884,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 45.381,
       "eval_steps_per_second": 11.432,
       "step": 20
+    },
+    {
+      "epoch": 0.06757843925985518,
+      "grad_norm": 0.11477506160736084,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9279,
+      "step": 21
+    },
+    {
+      "epoch": 0.07723250201126307,
+      "grad_norm": 0.14436446130275726,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.924,
+      "step": 24
+    },
+    {
+      "epoch": 0.08045052292839903,
+      "eval_loss": 11.924811363220215,
+      "eval_runtime": 6.2262,
+      "eval_samples_per_second": 42.08,
+      "eval_steps_per_second": 10.6,
+      "step": 25
+    },
+    {
+      "epoch": 0.08688656476267095,
+      "grad_norm": 0.18682144582271576,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9231,
+      "step": 27
+    },
+    {
+      "epoch": 0.09654062751407884,
+      "grad_norm": 0.14765076339244843,
+      "learning_rate": 0.0,
+      "loss": 11.9238,
+      "step": 30
+    },
+    {
+      "epoch": 0.09654062751407884,
+      "eval_loss": 11.924607276916504,
+      "eval_runtime": 6.1002,
+      "eval_samples_per_second": 42.949,
+      "eval_steps_per_second": 10.819,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 20312217354240.0,
+  "total_flos": 30468326031360.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null