Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0fe35e02dbadb8de42027ba07ea418e0ffa3420ebce31759c286fa4ea9874d
+oid sha256:2898d5547b73d03484b35793bc2f4ace65f9e65804b4b177b221dc7961b5f39a
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f6c486737d8cad5b774ee54c889a55abe2b72aa44c3cbbb4abb5534e6660cc7
+oid sha256:4c4f4631f1907b7d9b42c8a81ea8818192e7021da7b567d7296942267e926d27
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab8caf8fe21de20081071c159f729edd33aed262ad01c0aed650dc7791934001
+oid sha256:d231d2c2703c34dcd70b81b0389047adad11726294543d5e57fea2202a031d67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3482195138931274,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010465450930116952,
+  "best_metric": 1.3286937475204468,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0015698176395175427,
   "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": 5.214,
       "eval_steps_per_second": 1.304,
       "step": 20
+    },
+    {
+      "epoch": 0.00109887234766228,
+      "grad_norm": 0.29628661274909973,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.0515,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012558541116140342,
+      "grad_norm": 0.3616541028022766,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.0526,
+      "step": 24
+    },
+    {
+      "epoch": 0.001308181366264619,
+      "eval_loss": 1.3322861194610596,
+      "eval_runtime": 3085.4269,
+      "eval_samples_per_second": 5.216,
+      "eval_steps_per_second": 1.304,
+      "step": 25
+    },
+    {
+      "epoch": 0.0014128358755657884,
+      "grad_norm": 0.3618899881839752,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.1563,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015698176395175427,
+      "grad_norm": 0.37173062562942505,
+      "learning_rate": 0.0,
+      "loss": 1.139,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015698176395175427,
+      "eval_loss": 1.3286937475204468,
+      "eval_runtime": 3087.5087,
+      "eval_samples_per_second": 5.212,
+      "eval_steps_per_second": 1.303,
+      "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": 2.57085482729472e+16,
+  "total_flos": 3.84041276669952e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null