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:e7784e4eb06dac6f52a148a76e576cc86c5c240f836f2bc6d07038bdab5fe5d1
+oid sha256:f63f6674dbc81eda90c12df584755a34a8f71dbea1c7c9806ef576dda3407bd8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d629b537e946b00dea91a30bb52ce6b39f2d0022c0fe424b44bcec7589e0a009
+oid sha256:3ab6fa0861bf384eaa8603c0758226d0de1af191f9ee231f95e43856373a389d
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d05cdb697f1900d23354862c74efd9c24f506ab1907c586389466a97be4923a
+oid sha256:5a5d8f1e86c44aa62df10b23454963943353a0ae05bf7a1dcb46323b2414b8c0
 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": 1.4430060386657715,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0021831082003001775,
+  "best_metric": 1.3705416917800903,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.003274662300450266,
   "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": 7.172,
       "eval_steps_per_second": 1.793,
       "step": 20
+    },
+    {
+      "epoch": 0.002292263610315186,
+      "grad_norm": 8.80397891998291,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 5.7287,
+      "step": 21
+    },
+    {
+      "epoch": 0.0026197298403602127,
+      "grad_norm": 9.108375549316406,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 5.637,
+      "step": 24
+    },
+    {
+      "epoch": 0.0027288852503752218,
+      "eval_loss": 1.3819360733032227,
+      "eval_runtime": 1076.1061,
+      "eval_samples_per_second": 7.169,
+      "eval_steps_per_second": 1.793,
+      "step": 25
+    },
+    {
+      "epoch": 0.0029471960704052394,
+      "grad_norm": 9.284589767456055,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 5.4122,
+      "step": 27
+    },
+    {
+      "epoch": 0.003274662300450266,
+      "grad_norm": 9.895240783691406,
+      "learning_rate": 0.0,
+      "loss": 5.2954,
+      "step": 30
+    },
+    {
+      "epoch": 0.003274662300450266,
+      "eval_loss": 1.3705416917800903,
+      "eval_runtime": 1075.5476,
+      "eval_samples_per_second": 7.173,
+      "eval_steps_per_second": 1.794,
+      "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": 1.406258997362688e+16,
+  "total_flos": 2.109388496044032e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null