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:cdfc2deb421a21be2faac472d368d77349ac4d20f69ffb7d5dabd469532e1463
+oid sha256:e6b281a001d697e83e03126cb45e7934d40bd435f43ba97ec17741bdc7df8ea7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec87d64ad1ce194032a2287dabd39930976d9ea52d1585d837c8e402d99e3e99
+oid sha256:9d4944cb9d7184381d6fb83cb7a9b948ecb857a9d20ae71c8714e3625decc0d3
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12fb0f5353eed23dbb574f1ef3314d3ab686bb99930e87b6e6313be6f73994f1
+oid sha256:0eaa896fd95a61ed8c30eed7dbb62c65a8ca1fd80550d35ac9127e458a83ffe1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8704153299331665,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016256197675363732,
+  "best_metric": 0.8091033101081848,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0032512395350727465,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 7.081,
       "eval_steps_per_second": 3.542,
       "step": 10
+    },
+    {
+      "epoch": 0.0017881817442900105,
+      "grad_norm": 1.6804190874099731,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 3.5526,
+      "step": 11
+    },
+    {
+      "epoch": 0.001950743721043648,
+      "grad_norm": 1.655336618423462,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.6632,
+      "step": 12
+    },
+    {
+      "epoch": 0.002113305697797285,
+      "grad_norm": 2.5160911083221436,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.5932,
+      "step": 13
+    },
+    {
+      "epoch": 0.0022758676745509225,
+      "grad_norm": 2.3304178714752197,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.391,
+      "step": 14
+    },
+    {
+      "epoch": 0.00243842965130456,
+      "grad_norm": 2.385143518447876,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.0551,
+      "step": 15
+    },
+    {
+      "epoch": 0.00243842965130456,
+      "eval_loss": 0.8331114649772644,
+      "eval_runtime": 365.1739,
+      "eval_samples_per_second": 7.095,
+      "eval_steps_per_second": 3.549,
+      "step": 15
+    },
+    {
+      "epoch": 0.002600991628058197,
+      "grad_norm": 2.6784660816192627,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.2755,
+      "step": 16
+    },
+    {
+      "epoch": 0.0027635536048118345,
+      "grad_norm": 1.6437331438064575,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.9725,
+      "step": 17
+    },
+    {
+      "epoch": 0.002926115581565472,
+      "grad_norm": 1.9800294637680054,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.463,
+      "step": 18
+    },
+    {
+      "epoch": 0.003088677558319109,
+      "grad_norm": 1.9015357494354248,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.1569,
+      "step": 19
+    },
+    {
+      "epoch": 0.0032512395350727465,
+      "grad_norm": 2.7715961933135986,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.6,
+      "step": 20
+    },
+    {
+      "epoch": 0.0032512395350727465,
+      "eval_loss": 0.8091033101081848,
+      "eval_runtime": 368.0357,
+      "eval_samples_per_second": 7.04,
+      "eval_steps_per_second": 3.521,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1710169792708608.0,
+  "total_flos": 3338902928621568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null