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:f09b951587d74364ff59622d394c4ed26a7a91ecfd719f22341ccbdd9b271d50
+oid sha256:190a969c48542a552b857c7e82b1d72c71165d6372f10a2e8a2942dca7f68ef7
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:796e7e8bf11ec23e2356381ee5e8a98cde4c78c789dbf2df57248716eeb6f54f
+oid sha256:47acf31ea9c85228b89a6eaa1440d547a9a4848f3233d486b785eafbd19c25fc
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a1359d1b4ebdff24847faf107f09b16b17e59b2ba40f0dcd5e055640303f20
+oid sha256:d6c3f05aca969942ca223e25095607485dfd24792c9f1ce26c5047473ba603ee
 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": 1.332247018814087,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01173192550227306,
+  "best_metric": 1.3153902292251587,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.01759788825340959,
   "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": 11.337,
       "eval_steps_per_second": 2.834,
       "step": 20
+    },
+    {
+      "epoch": 0.012318521777386713,
+      "grad_norm": 0.4295673966407776,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.1232,
+      "step": 21
+    },
+    {
+      "epoch": 0.014078310602727673,
+      "grad_norm": 0.4502706229686737,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.1681,
+      "step": 24
+    },
+    {
+      "epoch": 0.014664906877841326,
+      "eval_loss": 1.318825125694275,
+      "eval_runtime": 126.6397,
+      "eval_samples_per_second": 11.339,
+      "eval_steps_per_second": 2.835,
+      "step": 25
+    },
+    {
+      "epoch": 0.01583809942806863,
+      "grad_norm": 0.43909117579460144,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.1311,
+      "step": 27
+    },
+    {
+      "epoch": 0.01759788825340959,
+      "grad_norm": 0.5408356189727783,
+      "learning_rate": 0.0,
+      "loss": 1.2378,
+      "step": 30
+    },
+    {
+      "epoch": 0.01759788825340959,
+      "eval_loss": 1.3153902292251587,
+      "eval_runtime": 126.6814,
+      "eval_samples_per_second": 11.336,
+      "eval_steps_per_second": 2.834,
+      "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": 1.6678153976020992e+16,
+  "total_flos": 2.491427939627827e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null