Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd03feddc8d5e99fbe96bb81bca6358c75f8d00360bb6631be04ada61bd70b4
+oid sha256:f704b55f57d1a0e574b4d5c5db5d5995fb72e5cc76d58c49e33098cdb4eae36b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03505b8887dba31b1537afa97bfcd565d04b7e070c4299e941dd966cc3521440
+oid sha256:e47fe8b01506d6dd3ff20c8150b882a3236e5f83f9bf52d03eab348ac3f296c9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
 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": 0.8209472894668579,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008424599831508003,
+  "best_metric": 0.7651157379150391,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.016849199663016005,
   "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": 3.137,
       "eval_steps_per_second": 1.569,
       "step": 10
+    },
+    {
+      "epoch": 0.009267059814658803,
+      "grad_norm": 4.509300708770752,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 3.1134,
+      "step": 11
+    },
+    {
+      "epoch": 0.010109519797809604,
+      "grad_norm": 4.930267333984375,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.8386,
+      "step": 12
+    },
+    {
+      "epoch": 0.010951979780960405,
+      "grad_norm": 3.4825778007507324,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.8907,
+      "step": 13
+    },
+    {
+      "epoch": 0.011794439764111205,
+      "grad_norm": 3.1873111724853516,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.047,
+      "step": 14
+    },
+    {
+      "epoch": 0.012636899747262006,
+      "grad_norm": 7.248643398284912,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.4106,
+      "step": 15
+    },
+    {
+      "epoch": 0.012636899747262006,
+      "eval_loss": 0.7930175065994263,
+      "eval_runtime": 159.3164,
+      "eval_samples_per_second": 3.138,
+      "eval_steps_per_second": 1.569,
+      "step": 15
+    },
+    {
+      "epoch": 0.013479359730412805,
+      "grad_norm": 3.6828701496124268,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.1635,
+      "step": 16
+    },
+    {
+      "epoch": 0.014321819713563605,
+      "grad_norm": 2.783341407775879,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.9676,
+      "step": 17
+    },
+    {
+      "epoch": 0.015164279696714406,
+      "grad_norm": 3.4732234477996826,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.5988,
+      "step": 18
+    },
+    {
+      "epoch": 0.016006739679865205,
+      "grad_norm": 5.506781578063965,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.662,
+      "step": 19
+    },
+    {
+      "epoch": 0.016849199663016005,
+      "grad_norm": 3.5755441188812256,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.5257,
+      "step": 20
+    },
+    {
+      "epoch": 0.016849199663016005,
+      "eval_loss": 0.7651157379150391,
+      "eval_runtime": 159.3684,
+      "eval_samples_per_second": 3.137,
+      "eval_steps_per_second": 1.569,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3505339571896320.0,
+  "total_flos": 7010679143792640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null