Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b184ddf78308c9a0062bdd4ac2aea71dbb59614141f7e670c55eb12205bfd32
+oid sha256:ff9db6e23c92fdcbf6127ff35c7f1fd6ef4cf0f8084ba798e623b35b94f01bd4
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a792fe7db85f3b298cce69bb327e8b154601ef7fc807d1fa65f61417691df8ad
+oid sha256:f7215daaf4083333c881aec3f934a4eca6017b8e9b07ea9f78670a882171a4b4
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b8943e674f8bbdced045cb2530ea33584297335f08ea6bc4a911f482fdfb11
+oid sha256:4e31a0db1fe901aae8d342a723e96edfbdf00ec59df64e785ff59a6a197f3a04
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96aa36799c943a9bfefa20f32f650908880b1404c454cf725bf5d9ee2c75343e
+oid sha256:126a95bf1277ff34f610ecef71ab3da4221c5fdf57145767d775e04c91223794
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.35316547751426697,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.13129102844638948,
+  "epoch": 0.175054704595186,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 9.991,
       "eval_steps_per_second": 2.513,
       "step": 150
+    },
+    {
+      "epoch": 0.1400437636761488,
+      "grad_norm": 0.5799025893211365,
+      "learning_rate": 0.0001813903489357277,
+      "loss": 0.9458,
+      "step": 160
+    },
+    {
+      "epoch": 0.1487964989059081,
+      "grad_norm": 0.33210673928260803,
+      "learning_rate": 0.00017609327897085954,
+      "loss": 0.4653,
+      "step": 170
+    },
+    {
+      "epoch": 0.1575492341356674,
+      "grad_norm": 0.07417658716440201,
+      "learning_rate": 0.00017045228564685694,
+      "loss": 0.101,
+      "step": 180
+    },
+    {
+      "epoch": 0.16630196936542668,
+      "grad_norm": 0.005981265101581812,
+      "learning_rate": 0.0001644948513161638,
+      "loss": 0.0118,
+      "step": 190
+    },
+    {
+      "epoch": 0.175054704595186,
+      "grad_norm": 0.0026285904459655285,
+      "learning_rate": 0.00015825,
+      "loss": 0.001,
+      "step": 200
+    },
+    {
+      "epoch": 0.175054704595186,
+      "eval_loss": 0.3552694618701935,
+      "eval_runtime": 47.8669,
+      "eval_samples_per_second": 10.049,
+      "eval_steps_per_second": 2.528,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.905515964432384e+16,
+  "total_flos": 6.540687952576512e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null