Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daaff03669a032b7c022a482789b2f3c995b01f72ad79b3cc8068b8f1e434c60
+oid sha256:96e509696c55084c5f68db216b08c236034352729f9a35d54304177b2d7c5d59
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0ce3f9ee64b0c869751a3b334d7eed8318d1c81a574dbeacadb98868be199f
+oid sha256:c5c6ad648686c9545cc7cf5739ee01d7d5df372baebe9043894c7b1ad989beb9
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a5b7fc8ba333afed8a1a8bd04eb95e00d2bd168f67ada07b2962cd70cb734ce
+oid sha256:16c92660cd9919724ef2fa3ec4b8340423c04523460cd45e086b483ace36dd17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02db3dbfb390a8f0700b2ea5550de43719bf1ee696229ad5e263b02923655626
+oid sha256:2b38320f40535085de37905499e1385aa34aad6a41a68078b15be5cc295f0a80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.30838942527771,
   "best_model_checkpoint": "miner_id_24/checkpoint-500",
-  "epoch": 0.08191685439279131,
+  "epoch": 0.09556966345825654,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,28 @@
       "eval_samples_per_second": 35.138,
       "eval_steps_per_second": 8.784,
       "step": 600
+    },
+    {
+      "epoch": 0.08874325892552393,
+      "grad_norm": 78.84331512451172,
+      "learning_rate": 0.00025,
+      "loss": 9.1057,
+      "step": 650
+    },
+    {
+      "epoch": 0.09556966345825654,
+      "grad_norm": 82.10652923583984,
+      "learning_rate": 0.00025,
+      "loss": 9.2502,
+      "step": 700
+    },
+    {
+      "epoch": 0.09556966345825654,
+      "eval_loss": 2.4388105869293213,
+      "eval_runtime": 175.7023,
+      "eval_samples_per_second": 35.105,
+      "eval_steps_per_second": 8.776,
+      "step": 700
     }
   ],
   "logging_steps": 50,
@@ -161,7 +183,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -170,12 +192,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.121758001856512e+17,
+  "total_flos": 2.475384335499264e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null