Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c91878e6e9deccb36f6df1e2f46c343a38ccd08c1675b0b841183395ea71c5
+oid sha256:3612c0f49652fbe70e4ac6ee1e436d5cfed65aab190a46010715c71aa4cca057
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d75164aa5c8f5011af213234b7c74d7891060a324bd63c20af0530d8878013a
+oid sha256:a447a11f47c1d09286fa2ca0f22ef6df750b1d6ef2bafcde5e5b58a329d5f6c7
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290b2bff3358a286d1f8988d5ee9b579a34bf2cccd5d50326744d8869317f714
+oid sha256:c559b74517a6c45c5becc7755879be99f44dea75b257ca726ae26b9886b86530
 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": 2.507934093475342,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07640878701050621,
+  "best_metric": 2.4877736568450928,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.11461318051575932,
   "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": 4.002,
       "eval_steps_per_second": 1.014,
       "step": 20
+    },
+    {
+      "epoch": 0.08022922636103152,
+      "grad_norm": 0.3289887607097626,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.5418,
+      "step": 21
+    },
+    {
+      "epoch": 0.09169054441260745,
+      "grad_norm": 0.3244362771511078,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.4964,
+      "step": 24
+    },
+    {
+      "epoch": 0.09551098376313276,
+      "eval_loss": 2.4908852577209473,
+      "eval_runtime": 55.1682,
+      "eval_samples_per_second": 4.006,
+      "eval_steps_per_second": 1.015,
+      "step": 25
+    },
+    {
+      "epoch": 0.10315186246418338,
+      "grad_norm": 0.28559231758117676,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.4793,
+      "step": 27
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "grad_norm": 0.29243090748786926,
+      "learning_rate": 0.0,
+      "loss": 2.4764,
+      "step": 30
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "eval_loss": 2.4877736568450928,
+      "eval_runtime": 55.2145,
+      "eval_samples_per_second": 4.003,
+      "eval_steps_per_second": 1.014,
+      "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": 2.967549134241792e+16,
+  "total_flos": 4.451323701362688e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null