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:c4c2e887d5e5561eb9789a4bd642670857cb889c74b33b98a66c91d0ae412713
+oid sha256:c9c75f58952914e41f3fae7e70cc225100635cdf07955dbcc28d4c1ed8d9a100
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1096b198f6e998dae727de39fac5a0749ad01a76ce2485c4ec72950ee2b17429
+oid sha256:903f6dca362cc5bf772b3d657ad10beac9a1683271942864a4cfc906576366af
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af4cbe6dd62788676ba2597afaddb6a97ff06bf7b18f8e3a0ce4190a674ccd8
+oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
 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": 0.8958241939544678,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011577424023154847,
+  "best_metric": 0.6068727970123291,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.023154848046309694,
   "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": 6.801,
       "eval_steps_per_second": 3.4,
       "step": 10
+    },
+    {
+      "epoch": 0.012735166425470333,
+      "grad_norm": 1.6015220880508423,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.9102,
+      "step": 11
+    },
+    {
+      "epoch": 0.013892908827785818,
+      "grad_norm": 1.4771215915679932,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.1241,
+      "step": 12
+    },
+    {
+      "epoch": 0.015050651230101303,
+      "grad_norm": 1.1894761323928833,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.6946,
+      "step": 13
+    },
+    {
+      "epoch": 0.016208393632416787,
+      "grad_norm": 1.073376178741455,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6839,
+      "step": 14
+    },
+    {
+      "epoch": 0.017366136034732273,
+      "grad_norm": 1.1312061548233032,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.7637,
+      "step": 15
+    },
+    {
+      "epoch": 0.017366136034732273,
+      "eval_loss": 0.6495120525360107,
+      "eval_runtime": 52.2238,
+      "eval_samples_per_second": 6.97,
+      "eval_steps_per_second": 3.485,
+      "step": 15
+    },
+    {
+      "epoch": 0.018523878437047756,
+      "grad_norm": 1.0004829168319702,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.715,
+      "step": 16
+    },
+    {
+      "epoch": 0.019681620839363242,
+      "grad_norm": 1.0702334642410278,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.712,
+      "step": 17
+    },
+    {
+      "epoch": 0.020839363241678725,
+      "grad_norm": 0.9818086624145508,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.7343,
+      "step": 18
+    },
+    {
+      "epoch": 0.02199710564399421,
+      "grad_norm": 0.9808053970336914,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6963,
+      "step": 19
+    },
+    {
+      "epoch": 0.023154848046309694,
+      "grad_norm": 1.1419761180877686,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7567,
+      "step": 20
+    },
+    {
+      "epoch": 0.023154848046309694,
+      "eval_loss": 0.6068727970123291,
+      "eval_runtime": 52.5074,
+      "eval_samples_per_second": 6.932,
+      "eval_steps_per_second": 3.466,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null