Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d80efb87d11f17ebb283d9dda9995dc999263fba8711a9d0a320ca84e036d5
+oid sha256:030e04975418fe55b404d7241a036d4257ac5726c762218f5798ebac37c32020
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7098ed589633ebe6e61bc1384f918a181b738c3931be5979b3d1e878db0b017
+oid sha256:2d52b895066c90a8c7fbb61525a9fa9c48a248642fdcb30b8cb88370065530de
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e781d4de74a376f62b3dab9fbfdd6f349e5485013db3f9a7a8b5c0c58f822a02
+oid sha256:0fad39b025ad7572ac326f66594baa0eba5d1e56eeb4f32dc71e0081f85e4952
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdcafde4de54854e715c6bd59aa06fddefbf193f4a0d1cabc2a35c45a0b6a364
+oid sha256:10d7a7b8211623c446bfd0b68e92f5c6721c1093d48d9724a2ba3a1760a1b52a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.08751458576429405,
+  "epoch": 0.11668611435239207,
   "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": 182.046,
       "eval_steps_per_second": 45.638,
       "step": 150
+    },
+    {
+      "epoch": 0.09334889148191365,
+      "grad_norm": 0.00015543992049060762,
+      "learning_rate": 0.00018225001883589702,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.09918319719953325,
+      "grad_norm": 0.00040469339000992477,
+      "learning_rate": 0.00017692784427403898,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.10501750291715285,
+      "grad_norm": 0.0006950330571271479,
+      "learning_rate": 0.00017126011638451976,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.11085180863477247,
+      "grad_norm": 0.0004899466875940561,
+      "learning_rate": 0.00016527444776789915,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.11668611435239207,
+      "grad_norm": 0.0006722796242684126,
+      "learning_rate": 0.00015900000000000002,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.11668611435239207,
+      "eval_loss": 11.5,
+      "eval_runtime": 3.9865,
+      "eval_samples_per_second": 181.113,
+      "eval_steps_per_second": 45.404,
+      "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": 3002180665344.0,
+  "total_flos": 3999582879744.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null