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:fb5930c0ff12445c315221d516130cf23a03b64fa03a3304c282c062187cd7fc
+oid sha256:51ebbe267f65d74e251d940d9c6544d168c19d19c49748d3667b4b2b7c710cef
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee4f8c108c8004c0aec93f2fd0fb435971721008686c5300c7e3974878a0aab1
+oid sha256:63bd2c5e647bf8ab3e535bad8e9b980dd95e955ac68605c58aa850280251ebfa
 size 167923706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286cbddbe58e94b390d9c43f9eeef9abf68010ab845f692c08c30a9935964055
+oid sha256:6ca669e357aa0e15c87e40a1da0e0ab9476977a64e76ef375c8f5d113bdeafa4
 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": 2.988180637359619,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005377789728421619,
+  "best_metric": 2.5447235107421875,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.010755579456843238,
   "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": 17.694,
       "eval_steps_per_second": 8.858,
       "step": 10
+    },
+    {
+      "epoch": 0.006453347674105943,
+      "grad_norm": 7.595180511474609,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 12.3926,
+      "step": 12
+    },
+    {
+      "epoch": 0.008066684592632429,
+      "grad_norm": 7.204962253570557,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.3131,
+      "step": 15
+    },
+    {
+      "epoch": 0.008066684592632429,
+      "eval_loss": 2.7008702754974365,
+      "eval_runtime": 44.416,
+      "eval_samples_per_second": 17.629,
+      "eval_steps_per_second": 8.826,
+      "step": 15
+    },
+    {
+      "epoch": 0.009680021511158914,
+      "grad_norm": 5.720189094543457,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.1332,
+      "step": 18
+    },
+    {
+      "epoch": 0.010755579456843238,
+      "eval_loss": 2.5447235107421875,
+      "eval_runtime": 44.2569,
+      "eval_samples_per_second": 17.692,
+      "eval_steps_per_second": 8.857,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1311052608307200.0,
+  "total_flos": 2622105216614400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null