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:f092c07f30adcd259408e5377c36b846f668d40465957575405dcf96f565b103
+oid sha256:c0e64d2f1caec5f7e8f381b516b77a4aa0ea0aac659884cb968e6d57c8509bcf
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f0f598aaf0467c9f189a6097e0d44c86533c378c3a15845e403e2c40cc21bb6
+oid sha256:1cb330219404c60ecd1d3e53afe91971b924107a25ad8463e751e77489b25665
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9e1f475b9c0c42fb7ecf58643600e84c955b5b51d416fb24ed33fb1444cbc0a
+oid sha256:b028a07eb9b8df202ab053169b8ccc289be0a99adacfd2f2461d86813bbc7e0a
 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": 1.0942537784576416,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016909744240118367,
+  "best_metric": 0.18960347771644592,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0033819488480236735,
   "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": 9.068,
       "eval_steps_per_second": 4.534,
       "step": 10
+    },
+    {
+      "epoch": 0.0018600718664130206,
+      "grad_norm": 9.713255882263184,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.885,
+      "step": 11
+    },
+    {
+      "epoch": 0.002029169308814204,
+      "grad_norm": 9.36893081665039,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.6507,
+      "step": 12
+    },
+    {
+      "epoch": 0.002198266751215388,
+      "grad_norm": 10.034486770629883,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.3335,
+      "step": 13
+    },
+    {
+      "epoch": 0.0023673641936165714,
+      "grad_norm": 6.692185878753662,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.1796,
+      "step": 14
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 2.2280964851379395,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2752,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "eval_loss": 0.23506276309490204,
+      "eval_runtime": 274.8892,
+      "eval_samples_per_second": 9.058,
+      "eval_steps_per_second": 4.529,
+      "step": 15
+    },
+    {
+      "epoch": 0.002705559078418939,
+      "grad_norm": 7.754329681396484,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.3235,
+      "step": 16
+    },
+    {
+      "epoch": 0.0028746565208201224,
+      "grad_norm": 4.014993190765381,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.1894,
+      "step": 17
+    },
+    {
+      "epoch": 0.0030437539632213063,
+      "grad_norm": 2.463385820388794,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.2001,
+      "step": 18
+    },
+    {
+      "epoch": 0.00321285140562249,
+      "grad_norm": 1.8779284954071045,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0398,
+      "step": 19
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "grad_norm": 0.5477899312973022,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0106,
+      "step": 20
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "eval_loss": 0.18960347771644592,
+      "eval_runtime": 273.3332,
+      "eval_samples_per_second": 9.11,
+      "eval_steps_per_second": 4.555,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 104619842469888.0,
+  "total_flos": 202561822654464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null