Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8c1a2784a829fdfc331007b32dc37b75afe9dd675c03b38d12181ec60c2d23
+oid sha256:78fc44db87fd38938ab8a804c005d347f325a22c345096f4a29a8e5661dbad04
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1ffd10f91c1079e85776d7c80be5465de96f1703427f19a144ea1cc7cfecde
+oid sha256:e8dc1b9518659e007860727d6967069e94e53a70b51df9b27a219a9e32f30e0e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b48415b9e78e4312042b4166d9a934f38bc95cb5a78170f8942c97c344aa9c1
+oid sha256:f74ca324355024b1bc3cdaf5e61e07df907426038a98bb548eac48bb9e6efbb5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0520634651184082,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0003249786732745664,
+  "best_metric": 0.839118242263794,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0006499573465491328,
   "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": 5.526,
       "eval_steps_per_second": 2.763,
       "step": 10
+    },
+    {
+      "epoch": 0.0003899744079294796,
+      "grad_norm": 12.171273231506348,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 3.9456,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004874680099118495,
+      "grad_norm": 10.046751022338867,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.8244,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004874680099118495,
+      "eval_loss": 0.897432267665863,
+      "eval_runtime": 2348.5492,
+      "eval_samples_per_second": 5.517,
+      "eval_steps_per_second": 2.759,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005849616118942195,
+      "grad_norm": 7.874410629272461,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.3084,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006499573465491328,
+      "eval_loss": 0.839118242263794,
+      "eval_runtime": 2346.33,
+      "eval_samples_per_second": 5.522,
+      "eval_steps_per_second": 2.761,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4570341741428736.0,
+  "total_flos": 8525445171511296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null