Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:731b8699709937c46a35e59908c161b6220ab1cb6b50e3d9d3a92c7dcb746f98
+oid sha256:08736f528f12e68bcd390a6d1529103df2b65ac691d1e19d49743fb017a5f404
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d12add4e6efb39a1953b46527f289fd94e2d89b389051e75f6d57c57b58be65
+oid sha256:1983ad2c2088143205b3ef71555e886cd2867f238aae01997a6ba80147b63019
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:891e4953c95881a6340ed1ba5008218285428fb7f15eaef41f19a3733d26850a
+oid sha256:9040d72b9b9aec411920ba60747b3587396d53dd68b1139e2948795c090d9459
 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": 1.1592237949371338,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 1.1455615758895874,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02577873254564984,
   "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": 11.976,
       "eval_steps_per_second": 5.988,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 0.4648377299308777,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.2069,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 0.38540998101234436,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.2756,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 1.1481420993804932,
+      "eval_runtime": 40.8896,
+      "eval_samples_per_second": 11.983,
+      "eval_steps_per_second": 5.992,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 0.3698107600212097,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.1622,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 0.3534325659275055,
+      "learning_rate": 0.0,
+      "loss": 1.1373,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 1.1455615758895874,
+      "eval_runtime": 40.8906,
+      "eval_samples_per_second": 11.983,
+      "eval_steps_per_second": 5.992,
+      "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": 1.112830925340672e+16,
+  "total_flos": 1.6599727969665024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null