Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3803ac9811f210adc8c443ecf668677ef2ec861a2a9c8cd89cb51310e1249291
+oid sha256:1b32214d468ab6732fb01c5e5b492ecf3af95915bf12b368b8b456d19cbb17ce
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e399d114690be1d175fe6945d474f3bfbe5820d96aedfb7ada6fcbf87107043
+oid sha256:4541276bcbd02d62f18ec90f370144a040bd157b6aa82cd978f17a7ee58b51e8
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b946586db19ccaeb4dd74f24997efcbe279b5d36509bac7a986bd0df1de5f433
+oid sha256:3e73b09dfedcc20fe98c028842939a948923b18ad251d24eb8236e87e8f64ea6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.800294280052185,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005047573379097999,
+  "best_metric": 1.7412056922912598,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0010095146758195997,
   "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": 5.939,
       "eval_steps_per_second": 2.969,
       "step": 10
+    },
+    {
+      "epoch": 0.0006057088054917598,
+      "grad_norm": 0.31189802289009094,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.7429,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007571360068646998,
+      "grad_norm": 0.49632543325424194,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.7142,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007571360068646998,
+      "eval_loss": 1.7793023586273193,
+      "eval_runtime": 1404.032,
+      "eval_samples_per_second": 5.941,
+      "eval_steps_per_second": 2.971,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009085632082376397,
+      "grad_norm": 0.2652880847454071,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.773,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010095146758195997,
+      "eval_loss": 1.7412056922912598,
+      "eval_runtime": 1403.7973,
+      "eval_samples_per_second": 5.942,
+      "eval_steps_per_second": 2.971,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4492525138083840.0,
+  "total_flos": 9475143927595008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null