Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d709ad70ac8921428b7c016f37de68efeab1ccd68256b6902f7165a6c8c1462
+oid sha256:796588ff1457c7f230a59133d2cec8acb94640dca79fdb10053513cd2f252d20
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8410569afd53db6e7fa6ce5469fa1429bd8d62a7267c875201c596b93a177e31
+oid sha256:23e52e2dc66113667fc1513701beee3c4d2b46d02c6a33af68deae80070a8a40
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:816a671d1d7dd31880cb1867f27862b875fe457f15aed06003a04757362b440b
+oid sha256:c80118428b62ac09661baf0182d9941c981d8a11c7947c3428be1a68a27e33eb
 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": 2.2733120918273926,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04073319755600815,
+  "best_metric": 2.2300872802734375,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.06109979633401222,
   "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": 30.341,
       "eval_steps_per_second": 7.622,
       "step": 20
+    },
+    {
+      "epoch": 0.04276985743380855,
+      "grad_norm": 3.9431509971618652,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 9.1226,
+      "step": 21
+    },
+    {
+      "epoch": 0.048879837067209775,
+      "grad_norm": 3.7178170680999756,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.6709,
+      "step": 24
+    },
+    {
+      "epoch": 0.05091649694501019,
+      "eval_loss": 2.2334296703338623,
+      "eval_runtime": 13.6481,
+      "eval_samples_per_second": 30.334,
+      "eval_steps_per_second": 7.62,
+      "step": 25
+    },
+    {
+      "epoch": 0.054989816700611,
+      "grad_norm": 3.574514627456665,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 8.4494,
+      "step": 27
+    },
+    {
+      "epoch": 0.06109979633401222,
+      "grad_norm": 3.8659167289733887,
+      "learning_rate": 0.0,
+      "loss": 8.9901,
+      "step": 30
+    },
+    {
+      "epoch": 0.06109979633401222,
+      "eval_loss": 2.2300872802734375,
+      "eval_runtime": 13.6637,
+      "eval_samples_per_second": 30.299,
+      "eval_steps_per_second": 7.611,
+      "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": 606741976842240.0,
+  "total_flos": 910112965263360.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null