Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c89dee5c61de548deb2db9578a5e9259f82205d27f5092c0c977764811ffc8
+oid sha256:ff2a459108e64ed3970015219b3e1378b689b3e5fc33d989bcad9ac7d00ee51f
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fd4be02a7f819d53bbbdb9c67de510c9d5436d838bbc82b774645086399d2e
+oid sha256:9358f79c9c7686ebf0ddfcc4ef1e503a6c9e3038299d12a05cca7e7996ade2a4
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:860bb6cff318023972659630d90ada0acae20b5bf938265a139f0d30c6e4fbd4
+oid sha256:9c57262aecf7f7853da1512d85d0d1c60a9cc74188ca121ca1c041a5b55b9b23
 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": 0.6912946701049805,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00023734646650447992,
+  "best_metric": 0.6668534874916077,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00047469293300895983,
   "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": 6.866,
       "eval_steps_per_second": 3.433,
       "step": 10
+    },
+    {
+      "epoch": 0.0002610811131549279,
+      "grad_norm": 0.6327543258666992,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.4734,
+      "step": 11
+    },
+    {
+      "epoch": 0.0002848157598053759,
+      "grad_norm": 0.6682198643684387,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.6091,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003085504064558239,
+      "grad_norm": 0.7342543005943298,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.6427,
+      "step": 13
+    },
+    {
+      "epoch": 0.00033228505310627186,
+      "grad_norm": 0.8865476846694946,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6535,
+      "step": 14
+    },
+    {
+      "epoch": 0.00035601969975671986,
+      "grad_norm": 0.7189099192619324,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.7433,
+      "step": 15
+    },
+    {
+      "epoch": 0.00035601969975671986,
+      "eval_loss": 0.6719456911087036,
+      "eval_runtime": 2596.0954,
+      "eval_samples_per_second": 6.833,
+      "eval_steps_per_second": 3.417,
+      "step": 15
+    },
+    {
+      "epoch": 0.00037975434640716787,
+      "grad_norm": 0.6812601685523987,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5215,
+      "step": 16
+    },
+    {
+      "epoch": 0.00040348899305761587,
+      "grad_norm": 0.6531539559364319,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6499,
+      "step": 17
+    },
+    {
+      "epoch": 0.0004272236397080638,
+      "grad_norm": 0.5508365631103516,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4736,
+      "step": 18
+    },
+    {
+      "epoch": 0.00045095828635851183,
+      "grad_norm": 0.8346902132034302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.7911,
+      "step": 19
+    },
+    {
+      "epoch": 0.00047469293300895983,
+      "grad_norm": 0.6113680005073547,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6001,
+      "step": 20
+    },
+    {
+      "epoch": 0.00047469293300895983,
+      "eval_loss": 0.6668534874916077,
+      "eval_runtime": 2597.8558,
+      "eval_samples_per_second": 6.829,
+      "eval_steps_per_second": 3.414,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 662628963188736.0,
+  "total_flos": 1312755493109760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null