Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bbd46aeefea3f7933ae8570a30c82f27e8d9b8c160f6941f10f8ffecb06da97
+oid sha256:9b4eec6e2f48592988c9cb17399b0fb13d0f4beba3afae362a2884dd2f1bd2dd
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0134ce610bf402af67097d82f1640fb8eedc5d46025d12a98c78e217f89d7de8
+oid sha256:7f810d5aaa5785233eaf18d3fa3b2a8f96d1ccb652df04f4570064f7ff5fc2b2
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0cc465a75681ba50afdecee660968bcd8503a20558be1104c59586aa9b9c2e7
+oid sha256:d1af2d1ad71d0a525efd297d63ece1800652033d73e1aabfc1096f4a3269303a
 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": 11.922327995300293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0033819488480236735,
+  "best_metric": 11.919669151306152,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0050729232720355105,
   "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": 39.192,
       "eval_steps_per_second": 19.596,
       "step": 20
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 0.2239098697900772,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9274,
+      "step": 21
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 0.2766207754611969,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9269,
+      "step": 24
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "eval_loss": 11.920109748840332,
+      "eval_runtime": 63.4878,
+      "eval_samples_per_second": 39.22,
+      "eval_steps_per_second": 19.61,
+      "step": 25
+    },
+    {
+      "epoch": 0.004565630944831959,
+      "grad_norm": 0.28358063101768494,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9232,
+      "step": 27
+    },
+    {
+      "epoch": 0.0050729232720355105,
+      "grad_norm": 0.2541441321372986,
+      "learning_rate": 0.0,
+      "loss": 11.9231,
+      "step": 30
+    },
+    {
+      "epoch": 0.0050729232720355105,
+      "eval_loss": 11.919669151306152,
+      "eval_runtime": 63.5352,
+      "eval_samples_per_second": 39.191,
+      "eval_steps_per_second": 19.595,
+      "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": 6411043602432.0,
+  "total_flos": 9648303243264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null