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:eff548eee739415f3208dfa57a0dd272457eece9c69f5405c975f7ac53a88f21
+oid sha256:331467b068adbe8768d0ea7a83378b90f7a846a4352adab06dbb7c5258be71e3
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15cff531bb0219244f09a79bdf4ea835b703f2dba5edc813a6f80a2985decc22
+oid sha256:88884f5eff8e8440f57be206f7f5cdf9e87f4051d3c4faa8603043401f28c549
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e07f8f4750801d099097b192e75be114651270b122bce09ba5a7730c9bf3908
+oid sha256:fdd1ebf454031a941c8766869644643e5857c05165f3942927e75947630136d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.317108392715454,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005015862665680214,
+  "best_metric": 1.1126813888549805,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0010031725331360428,
   "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": 9.949,
       "eval_steps_per_second": 4.975,
       "step": 10
+    },
+    {
+      "epoch": 0.0006019035198816257,
+      "grad_norm": 0.7829315662384033,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.318,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007523793998520321,
+      "grad_norm": 0.8488056063652039,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.1823,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007523793998520321,
+      "eval_loss": 1.142626166343689,
+      "eval_runtime": 843.7972,
+      "eval_samples_per_second": 9.949,
+      "eval_steps_per_second": 4.975,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009028552798224385,
+      "grad_norm": 0.34353208541870117,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 1.2084,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010031725331360428,
+      "eval_loss": 1.1126813888549805,
+      "eval_runtime": 844.4224,
+      "eval_samples_per_second": 9.942,
+      "eval_steps_per_second": 4.971,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1378569745858560.0,
+  "total_flos": 2791603735363584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null