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:c8c542d9b13c1df8012081b423684b0ca6128a5a199cbf66bb57800f2d8840be
+oid sha256:4e51e3f469608d7041546a0fe1f9ccfd6ce80cf4f37fea575fb5a2a1fd3f6cfb
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a70fe3e6b60bd75007af523fc5c2f980cb5f3f2b9f89c83979ec747d9c5799
+oid sha256:e983642348abf8fcb0c0723d46771129bf6cb56c11d878c3d0c8263778fa8d40
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:f11fb9af2ad792f8aab0c3cf5e3137f46301e102dd75fa9c7e47ab9066811401
 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": 0.8073987364768982,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.000421474105684632,
+  "best_metric": 0.7455750703811646,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.000842948211369264,
   "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": 7.086,
       "eval_steps_per_second": 3.543,
       "step": 10
+    },
+    {
+      "epoch": 0.0005057689268215584,
+      "grad_norm": 0.5759347677230835,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.867,
+      "step": 12
+    },
+    {
+      "epoch": 0.000632211158526948,
+      "grad_norm": 0.5499302744865417,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.7854,
+      "step": 15
+    },
+    {
+      "epoch": 0.000632211158526948,
+      "eval_loss": 0.762820303440094,
+      "eval_runtime": 1410.7909,
+      "eval_samples_per_second": 7.081,
+      "eval_steps_per_second": 3.541,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007586533902323376,
+      "grad_norm": 0.4786859452724457,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7516,
+      "step": 18
+    },
+    {
+      "epoch": 0.000842948211369264,
+      "eval_loss": 0.7455750703811646,
+      "eval_runtime": 1410.8464,
+      "eval_samples_per_second": 7.081,
+      "eval_steps_per_second": 3.54,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7604344656494592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null