Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f57bed42afe3d85fe0f9b2a02732b1e5a2cf4dc02d4b017aa9df25e31d0145
+oid sha256:b3dd9cb3fd22fd5dad7431d8444b04977907ba52e1a8262371ad20823f5fcd3e
 size 1101095848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6e0ffd01fc1f0a1026245d3c96904c4eb30d927bb7dc33c94439cdb30882e7c
+oid sha256:6843a51c0c68c2c4c79fc5df4439fec55a1f2ba034101aee0bdb94c67e103b2d
 size 559894228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171ab76269805e1cf31a214b728ec291b9b9c89dafb6d52256094f67e92de308
+oid sha256:a10eb9868731c16845ce827905cc5ba03098c4ebd3e4d6108295fff20516b6b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44be7752e8f250f5c645b94c737a086e3ba6f8529fa94bf2d0ed1a0911f14f5a
+oid sha256:08c6d9b93a9a31eb6ebeb3ab3dc09ba23202435e453d5c3be3fefb3bbf21d637
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.313711553812027,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.005752085130859937,
+  "epoch": 0.007669446841146582,
   "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": 6.449,
       "eval_steps_per_second": 1.613,
       "step": 150
+    },
+    {
+      "epoch": 0.006135557472917266,
+      "grad_norm": 0.3479096293449402,
+      "learning_rate": 0.0001753726596345424,
+      "loss": 0.3809,
+      "step": 160
+    },
+    {
+      "epoch": 0.006519029814974595,
+      "grad_norm": 0.40249332785606384,
+      "learning_rate": 0.00017025132184860355,
+      "loss": 0.3108,
+      "step": 170
+    },
+    {
+      "epoch": 0.006902502157031924,
+      "grad_norm": 0.3747401237487793,
+      "learning_rate": 0.00016479747048321714,
+      "loss": 0.2576,
+      "step": 180
+    },
+    {
+      "epoch": 0.007285974499089253,
+      "grad_norm": 0.4572334289550781,
+      "learning_rate": 0.00015903767615401616,
+      "loss": 0.2175,
+      "step": 190
+    },
+    {
+      "epoch": 0.007669446841146582,
+      "grad_norm": 0.8990343809127808,
+      "learning_rate": 0.000153,
+      "loss": 0.2167,
+      "step": 200
+    },
+    {
+      "epoch": 0.007669446841146582,
+      "eval_loss": 0.3597487211227417,
+      "eval_runtime": 850.1057,
+      "eval_samples_per_second": 6.458,
+      "eval_steps_per_second": 1.615,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.435328345151898e+16,
+  "total_flos": 5.338171862050406e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null