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:dfae341eadf1b791e4244af1351e5a9cec769a2a3e8536e688eefe10f6ead0c9
+oid sha256:2ed2054520c2352e788e63cd32f717d7af86d49bf9638b1c561dde689a4aea95
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d27fc223eef69d5a82758169431a833422af0dc4171ad2ff6a117a5ad4bca7f
+oid sha256:02120d920b59bdef1221e90a8e5def0312c43246046a94ad414f9c0525eb8e96
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6249d25e9d7997d710f2ba265cd6b5631334413bb877cf032ccfb3162efee0
+oid sha256:6180b0b2bcad9d57943414b15b1883693e0ae1230bb56936fd6cf35701bac421
 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": 0.19807325303554535,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.016095284081764045,
+  "epoch": 0.02146037877568539,
   "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": 17.107,
       "eval_steps_per_second": 4.277,
       "step": 150
+    },
+    {
+      "epoch": 0.017168303020548312,
+      "grad_norm": 5.159971237182617,
+      "learning_rate": 0.00018740803823691298,
+      "loss": 0.6608,
+      "step": 160
+    },
+    {
+      "epoch": 0.018241321959332583,
+      "grad_norm": 14.589179039001465,
+      "learning_rate": 0.00018193523609311556,
+      "loss": 0.3561,
+      "step": 170
+    },
+    {
+      "epoch": 0.01931434089811685,
+      "grad_norm": 4.776534557342529,
+      "learning_rate": 0.00017610710081049675,
+      "loss": 0.2083,
+      "step": 180
+    },
+    {
+      "epoch": 0.020387359836901122,
+      "grad_norm": 29.330102920532227,
+      "learning_rate": 0.00016995202647831142,
+      "loss": 0.301,
+      "step": 190
+    },
+    {
+      "epoch": 0.02146037877568539,
+      "grad_norm": 123.9055404663086,
+      "learning_rate": 0.00016350000000000002,
+      "loss": 0.3643,
+      "step": 200
+    },
+    {
+      "epoch": 0.02146037877568539,
+      "eval_loss": 0.29956427216529846,
+      "eval_runtime": 229.3383,
+      "eval_samples_per_second": 17.11,
+      "eval_steps_per_second": 4.278,
+      "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": 2.6921134838513664e+16,
+  "total_flos": 3.5865033455960064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null