Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2384c0aaf94d8aa52dbe4a83303cac3cff37f50a40703c88d74abfc82b479907
+oid sha256:b7e95b364ca7eb163b068aa6357ce53d9733e9df1f9940bdb01060160a023232
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b9427e187c9ffc1df90f97f3d161c037369b501aa3c0979ccf45b6510bade9
+oid sha256:2c09a004248fa43b3ef994bb17793db35ce9d8adb204047401b30a63dfd3e91d
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.933917999267578,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0059228548160213225,
+  "best_metric": 11.933874130249023,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.008884282224031984,
   "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": 89.042,
       "eval_steps_per_second": 44.521,
       "step": 20
+    },
+    {
+      "epoch": 0.006218997556822388,
+      "grad_norm": 0.04174540936946869,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 11.9346,
+      "step": 21
+    },
+    {
+      "epoch": 0.0071074257792255865,
+      "grad_norm": 0.05081101134419441,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 11.9317,
+      "step": 24
+    },
+    {
+      "epoch": 0.007403568520026653,
+      "eval_loss": 11.933879852294922,
+      "eval_runtime": 16.0535,
+      "eval_samples_per_second": 88.579,
+      "eval_steps_per_second": 44.289,
+      "step": 25
+    },
+    {
+      "epoch": 0.007995854001628786,
+      "grad_norm": 0.02904302440583706,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 11.9339,
+      "step": 27
+    },
+    {
+      "epoch": 0.008884282224031984,
+      "grad_norm": 0.044318776577711105,
+      "learning_rate": 0.0,
+      "loss": 11.9343,
+      "step": 30
+    },
+    {
+      "epoch": 0.008884282224031984,
+      "eval_loss": 11.933874130249023,
+      "eval_runtime": 16.0782,
+      "eval_samples_per_second": 88.443,
+      "eval_steps_per_second": 44.221,
+      "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": 7494696960.0,
+  "total_flos": 11242045440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null