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:c22ee48800b30f99f0be7620b29e42afe310169eccd4e2a035273de3107f1644
+oid sha256:b60999f04a9dfbc92712c1af2af1d7dbf63f0b314f1800233b837bd499b29e74
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dbe20209540c3d2ec9d9bc9db1b768de98c23c92c08ad88da041409f49bea79
+oid sha256:55273e0dc5d3beeac1394cd79fcc4075c37aa0848c0981682bddfb7614dfc7a3
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49774539b104e5e6ef34aa71d329da0403c643b1e9c7c8e2e9ede9f44ac1672f
+oid sha256:d2ddf9ee0e025985957b09670e022024ded017db3b9ff654a03997bdc0428d1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
+oid sha256:c41568ec8d15c28a2145796b65c5977bed142a18699c02f8db4b41d7a5440c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0014698821154543406,
+  "epoch": 0.0019598428206057876,
   "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": 151.667,
       "eval_steps_per_second": 37.917,
       "step": 150
+    },
+    {
+      "epoch": 0.00156787425648463,
+      "grad_norm": 4.13002198911272e-05,
+      "learning_rate": 0.00018740803823691298,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.0016658663975149192,
+      "grad_norm": 7.537772762589157e-05,
+      "learning_rate": 0.00018193523609311556,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0017638585385452087,
+      "grad_norm": 7.50588224036619e-05,
+      "learning_rate": 0.00017610710081049675,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.001861850679575498,
+      "grad_norm": 0.00014107312017586082,
+      "learning_rate": 0.00016995202647831142,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "grad_norm": 0.0004938940983265638,
+      "learning_rate": 0.00016350000000000002,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "eval_loss": 11.5,
+      "eval_runtime": 282.9734,
+      "eval_samples_per_second": 151.845,
+      "eval_steps_per_second": 37.961,
+      "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": 3012154687488.0,
+  "total_flos": 4009556901888.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null