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:ebc3b40c51a7e8a8d96055c077438f2a3ff576d051e51be50b08e4cfdc5afaf0
+oid sha256:488a08ba3b79d00f65ffe43bab0370bf4784fa27535bb2762112bef664f90e47
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dabc2cc591c0b2285d649b032eb43dfa5bbe73854447faa3f01ef25c073286b
+oid sha256:7cda8b431981e6887aa44e649294aae52b678d8a441273ec5aa78b054f110c8e
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11fbc07738c6a7ac3100d0e703a56c59dbeb3c1268b40f03594588b740eceb7a
+oid sha256:f9c1e5f978bc45c2674647f895d483327d39073912880b9e6857002e2f0148df
 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": 0.63363116979599,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.010796221322537112,
+  "best_metric": 0.5706824064254761,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.021592442645074223,
   "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": 2.717,
       "eval_steps_per_second": 1.358,
       "step": 10
+    },
+    {
+      "epoch": 0.012955465587044534,
+      "grad_norm": 3.2896554470062256,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 2.4326,
+      "step": 12
+    },
+    {
+      "epoch": 0.016194331983805668,
+      "grad_norm": 3.474226713180542,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.7939,
+      "step": 15
+    },
+    {
+      "epoch": 0.016194331983805668,
+      "eval_loss": 0.593587338924408,
+      "eval_runtime": 143.4985,
+      "eval_samples_per_second": 2.718,
+      "eval_steps_per_second": 1.359,
+      "step": 15
+    },
+    {
+      "epoch": 0.019433198380566803,
+      "grad_norm": 3.6576988697052,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 2.4422,
+      "step": 18
+    },
+    {
+      "epoch": 0.021592442645074223,
+      "eval_loss": 0.5706824064254761,
+      "eval_runtime": 143.5071,
+      "eval_samples_per_second": 2.718,
+      "eval_steps_per_second": 1.359,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4306668179423232.0,
+  "total_flos": 8789118733516800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null