Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488a08ba3b79d00f65ffe43bab0370bf4784fa27535bb2762112bef664f90e47
+oid sha256:a23c657c290c4f55e396550fdc8c40ef9d26dc8de07bbbb00d9b97ee847e2ee8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cda8b431981e6887aa44e649294aae52b678d8a441273ec5aa78b054f110c8e
+oid sha256:10e95cd64f0864cc003cadfa27f8f800eadc4f02d6fa0969c1267b503e840be7
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c1e5f978bc45c2674647f895d483327d39073912880b9e6857002e2f0148df
+oid sha256:799139bb7f3b3a97c4812eb7c2ca47d60e3b82bcad4edb627fbf950f4f1aec09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5706824064254761,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.021592442645074223,
+  "best_metric": 0.5623267292976379,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.032388663967611336,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 2.718,
       "eval_steps_per_second": 1.359,
       "step": 20
+    },
+    {
+      "epoch": 0.022672064777327937,
+      "grad_norm": 3.4338033199310303,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.5011,
+      "step": 21
+    },
+    {
+      "epoch": 0.025910931174089068,
+      "grad_norm": 3.8558363914489746,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.52,
+      "step": 24
+    },
+    {
+      "epoch": 0.02699055330634278,
+      "eval_loss": 0.5635903477668762,
+      "eval_runtime": 143.4824,
+      "eval_samples_per_second": 2.718,
+      "eval_steps_per_second": 1.359,
+      "step": 25
+    },
+    {
+      "epoch": 0.029149797570850202,
+      "grad_norm": 4.289108753204346,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 2.0916,
+      "step": 27
+    },
+    {
+      "epoch": 0.032388663967611336,
+      "grad_norm": 2.4321413040161133,
+      "learning_rate": 0.0,
+      "loss": 1.8959,
+      "step": 30
+    },
+    {
+      "epoch": 0.032388663967611336,
+      "eval_loss": 0.5623267292976379,
+      "eval_runtime": 143.4714,
+      "eval_samples_per_second": 2.718,
+      "eval_steps_per_second": 1.359,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8789118733516800.0,
+  "total_flos": 1.2920004538269696e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null