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:c2b5fc3e774d94663589f5061e0677df23a82dc4fceb12dbcd57e454f92c27b5
+oid sha256:a7c411d16fd17f20040dd85ec0377f3e886a556b40af6ff41dc036d7e2dbabc9
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa543cd5b183ef6c46a435a00a168bee8ea9c35e61670a805580a8cc0c38b877
+oid sha256:896bad84f75ce1f04620ba90d068d2d6c6f85f2594c21dc7074a9f8744afe77c
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:aa13545c8ca8dc6508204472c2d6eaeb3b165f99b0f8f8e1a14c2c8d7b4fb324
 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": 11.091446876525879,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003737269924320284,
+  "best_metric": 11.029707908630371,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.007474539848640568,
   "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": 158.35,
       "eval_steps_per_second": 79.245,
       "step": 10
+    },
+    {
+      "epoch": 0.0041109969167523125,
+      "grad_norm": 2.0944066047668457,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 44.3654,
+      "step": 11
+    },
+    {
+      "epoch": 0.004484723909184341,
+      "grad_norm": 2.1180760860443115,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 44.4339,
+      "step": 12
+    },
+    {
+      "epoch": 0.0048584509016163695,
+      "grad_norm": 2.2716116905212402,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 44.2943,
+      "step": 13
+    },
+    {
+      "epoch": 0.005232177894048398,
+      "grad_norm": 2.27824330329895,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 44.2583,
+      "step": 14
+    },
+    {
+      "epoch": 0.005605904886480426,
+      "grad_norm": 2.1385979652404785,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 44.249,
+      "step": 15
+    },
+    {
+      "epoch": 0.005605904886480426,
+      "eval_loss": 11.055086135864258,
+      "eval_runtime": 7.0721,
+      "eval_samples_per_second": 159.358,
+      "eval_steps_per_second": 79.75,
+      "step": 15
+    },
+    {
+      "epoch": 0.005979631878912454,
+      "grad_norm": 2.326420545578003,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 44.1148,
+      "step": 16
+    },
+    {
+      "epoch": 0.006353358871344483,
+      "grad_norm": 2.224518060684204,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 44.2163,
+      "step": 17
+    },
+    {
+      "epoch": 0.006727085863776511,
+      "grad_norm": 2.348910331726074,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 44.1174,
+      "step": 18
+    },
+    {
+      "epoch": 0.00710081285620854,
+      "grad_norm": 2.201992988586426,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 44.064,
+      "step": 19
+    },
+    {
+      "epoch": 0.007474539848640568,
+      "grad_norm": 2.425978660583496,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 44.2236,
+      "step": 20
+    },
+    {
+      "epoch": 0.007474539848640568,
+      "eval_loss": 11.029707908630371,
+      "eval_runtime": 7.2874,
+      "eval_samples_per_second": 154.651,
+      "eval_steps_per_second": 77.394,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 115737624576.0,
+  "total_flos": 221830447104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null