Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105fc92449928d632683551b173fb2c96810800cb9aedde1d1fc72047ae40be0
+oid sha256:edac6347e7d560bf2208780c130958f10555b1fdf628e0aa30fdd4ea42ea5620
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7bfa4234f5daa1b62a2b70d0cd823557be8bbb76ee863bb9f1adf1331e5b012
+oid sha256:59f38879a19f46f9e6365f4d9927e46f5a51cbe42d7c5d06318db3960bf40784
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a3adb90f7cf6f36d3bb8c8b8e41a60c68d01df0d6ed1e9c00630375d80b71cc
+oid sha256:502caeaace40245c3032f6b99cb5f08051c4da7ee8bc85ffdba98ad43c08c019
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.752495527267456,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011624527753560012,
+  "best_metric": 0.684432327747345,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.023249055507120024,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 12.787,
       "eval_steps_per_second": 6.411,
       "step": 10
+    },
+    {
+      "epoch": 0.013949433304272014,
+      "grad_norm": 1.771251916885376,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 3.0502,
+      "step": 12
+    },
+    {
+      "epoch": 0.017436791630340016,
+      "grad_norm": 1.7839971780776978,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.8952,
+      "step": 15
+    },
+    {
+      "epoch": 0.017436791630340016,
+      "eval_loss": 0.7082406878471375,
+      "eval_runtime": 28.4197,
+      "eval_samples_per_second": 12.773,
+      "eval_steps_per_second": 6.404,
+      "step": 15
+    },
+    {
+      "epoch": 0.020924149956408022,
+      "grad_norm": 1.599076271057129,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8691,
+      "step": 18
+    },
+    {
+      "epoch": 0.023249055507120024,
+      "eval_loss": 0.684432327747345,
+      "eval_runtime": 28.4133,
+      "eval_samples_per_second": 12.776,
+      "eval_steps_per_second": 6.405,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3512337835229184.0,
+  "total_flos": 6942993395220480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null