Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a837ec43b7c7eaf40047c65bf722e41623c4adbe2e66c16fa9533ca26d5b5f1
+oid sha256:6402b149e6f4f7b22d3b9341c3682ea0f61ba0c78cb59afafbceef3a2a813742
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da71c9e234d01266a725468ae39cdabb1fbb4272cbb48849e3f7cf69941b1189
+oid sha256:21b7bf310f8ff4d2653648aa45dc8c385615e2d8212d4941f7ed2865b44c4627
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ca8b28803c0ee9d1119ecfa452224868ef01b4e46dd3411ff9764b93ac6d56
+oid sha256:76b9d255948392eb9829789b5157f95c01b00af53ec98b469a5a2b89b3e94e7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662c9e898ac39a71b423a2785b52925d7ca06517ad79ef8a45be543246b1a1b6
+oid sha256:ae20548bf37ed9ce24a89f932598e5e41d81b46882f80f29333348ce3845be91
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.006002761270184284,
+  "epoch": 0.008003681693579047,
   "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": 150.668,
       "eval_steps_per_second": 37.674,
       "step": 150
+    },
+    {
+      "epoch": 0.006402945354863237,
+      "grad_norm": 4.887337127001956e-05,
+      "learning_rate": 0.00017881133923521971,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.00680312943954219,
+      "grad_norm": 6.486769416369498e-05,
+      "learning_rate": 0.00017358958306132124,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.007203313524221142,
+      "grad_norm": 0.00011283026833552867,
+      "learning_rate": 0.00016802879343386844,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.007603497608900094,
+      "grad_norm": 6.451643275795504e-05,
+      "learning_rate": 0.00016215606196095766,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.008003681693579047,
+      "grad_norm": 0.0002875132777262479,
+      "learning_rate": 0.000156,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.008003681693579047,
+      "eval_loss": 11.5,
+      "eval_runtime": 69.9694,
+      "eval_samples_per_second": 150.38,
+      "eval_steps_per_second": 37.602,
+      "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": 3052050776064.0,
+  "total_flos": 4059427012608.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null