Training in progress, step 9000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be5216629ea69f9fb4c2ebc6d91de6cdb39bf7b47bfe3c2a4614c14c6392ac46
+oid sha256:06519740f41f0f97d141a51cf88e3b990f6b4f56e300f52d8f44e7672b1bc600
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:527549a60a00a7ba0dd154d42fcaf1b952119a73cc41120b662d298de646af32
+oid sha256:11c2aa02c3cd70fa400e08b77e41df284e6d1a6be911d6f2c2816beefe521972
 size 4899962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a7f3dff33da40653102d2b55173b54aa49a8e44d93fe6c8855bd0382b20f1c
+oid sha256:ed2e607c8dd8f0a3c6f93906d571c6ecc9de742cab47229951f8ad32026900fc
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930c624ce7c523ea80e34eda4c97c8070b2558cdda7cf31f871a20b9da39f272
+oid sha256:6a767c4c5b1aaa59f0fd0570fdb5104ecc494d72638ae3ce76b6ca2641c80f69
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.538701057434082,
   "best_model_checkpoint": "miner_id_24/checkpoint-8500",
-  "epoch": 2.443406395975566,
+  "epoch": 2.5871361839741285,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1341,6 +1341,84 @@
       "eval_samples_per_second": 64.56,
       "eval_steps_per_second": 16.143,
       "step": 8500
+    },
+    {
+      "epoch": 2.457779374775422,
+      "grad_norm": 0.24602361023426056,
+      "learning_rate": 1.3596438587477278e-06,
+      "loss": 11.5591,
+      "step": 8550
+    },
+    {
+      "epoch": 2.4721523535752783,
+      "grad_norm": 0.21134650707244873,
+      "learning_rate": 1.074760864438935e-06,
+      "loss": 11.5513,
+      "step": 8600
+    },
+    {
+      "epoch": 2.486525332375135,
+      "grad_norm": 0.22006399929523468,
+      "learning_rate": 8.231843471170714e-07,
+      "loss": 11.5595,
+      "step": 8650
+    },
+    {
+      "epoch": 2.500898311174991,
+      "grad_norm": 0.20436766743659973,
+      "learning_rate": 6.049926711379494e-07,
+      "loss": 11.558,
+      "step": 8700
+    },
+    {
+      "epoch": 2.515271289974847,
+      "grad_norm": 0.21755096316337585,
+      "learning_rate": 4.2025380170877514e-07,
+      "loss": 11.5426,
+      "step": 8750
+    },
+    {
+      "epoch": 2.5296442687747036,
+      "grad_norm": 0.1975020170211792,
+      "learning_rate": 2.690252837175113e-07,
+      "loss": 11.5594,
+      "step": 8800
+    },
+    {
+      "epoch": 2.5440172475745597,
+      "grad_norm": 0.23776116967201233,
+      "learning_rate": 1.5135422380793571e-07,
+      "loss": 11.5562,
+      "step": 8850
+    },
+    {
+      "epoch": 2.5583902263744163,
+      "grad_norm": 0.23030632734298706,
+      "learning_rate": 6.727727570635444e-08,
+      "loss": 11.5548,
+      "step": 8900
+    },
+    {
+      "epoch": 2.5727632051742724,
+      "grad_norm": 0.2245226800441742,
+      "learning_rate": 1.6820628804155024e-08,
+      "loss": 11.5547,
+      "step": 8950
+    },
+    {
+      "epoch": 2.5871361839741285,
+      "grad_norm": 0.2259846031665802,
+      "learning_rate": 0.0,
+      "loss": 11.5524,
+      "step": 9000
+    },
+    {
+      "epoch": 2.5871361839741285,
+      "eval_loss": 11.53870677947998,
+      "eval_runtime": 91.574,
+      "eval_samples_per_second": 63.981,
+      "eval_steps_per_second": 15.998,
+      "step": 9000
     }
   ],
   "logging_steps": 50,
@@ -1355,7 +1433,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1364,12 +1442,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9372731424768000.0,
+  "total_flos": 9924177936384000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null