Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f598320b021e55c2d942deab4641803730db7656d5667fdd04fd834a962d24
+oid sha256:3a48ea012c5b5b05e324aae5f90f6360dec7235bce6cbc9701db49343639e059
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f1400a57f21745868d1ecb9d0d9046e847eab2b72f2b8c3f451410eb7ffc97
+oid sha256:d7e60acff6fb1190fe4d0d2f43d681324974f199e95012568f3cda9d2003319a
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43ab42ad167a0a8f6fe26ccbc5d4c69769adf433593ec5b8107571f1d92b681
+oid sha256:08f401d95ad85d59c4bce735aa7640b5f5cd8b142bf22d8bff8332204d49b363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd62d399a2450f21c7bec0f65f92f467b6df40bae3ff61b19e25062ffc80260
+oid sha256:292f236c37f22c287cc737dd1428bf82b9a9008a84eb2f517544aab166f8a97f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.13020833333333334,
+  "epoch": 0.1736111111111111,
   "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": 157.857,
       "eval_steps_per_second": 39.708,
       "step": 150
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 0.0002737689937930554,
+      "learning_rate": 0.00018654836833674362,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.14756944444444445,
+      "grad_norm": 0.0002520754642318934,
+      "learning_rate": 0.0001811006707899361,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.00039408475277014077,
+      "learning_rate": 0.0001752992700728339,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.16493055555555555,
+      "grad_norm": 0.0004714858077932149,
+      "learning_rate": 0.00016917243002657602,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.1736111111111111,
+      "grad_norm": 0.0003129263350274414,
+      "learning_rate": 0.00016275,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.1736111111111111,
+      "eval_loss": 11.5,
+      "eval_runtime": 3.0863,
+      "eval_samples_per_second": 157.147,
+      "eval_steps_per_second": 39.53,
+      "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": 3879894614016.0,
+  "total_flos": 5156569448448.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null