Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e15328a0d20d0478eb2ecbb60c135c82ad822b7575d958e34c805be6f89e88
+oid sha256:fff0dcd98b351c4abdab3e75e409aad3b0b83a5b92bd6e69af51a0c9448cf34b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e6040de33a298054920110e268d4ac498a903bcb4e8394e550f629a84e6c0a0
+oid sha256:d3c8ceefa811d7d767bb6828cc1deeb7aaac423c4a7eb63bd321ba712377d954
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71aa5568a3f7d53f629ff7ba3c6afb6d2a437d6a2ab98d74c233306348565517
+oid sha256:686f89b8aab4cd9ac1768867b010a53a3df208e679221090184e9c8bf6e32eb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1299974918365479,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05082592121982211,
+  "best_metric": 1.0221692323684692,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.06353240152477764,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 7.802,
       "eval_steps_per_second": 3.901,
       "step": 20
+    },
+    {
+      "epoch": 0.053367217280813214,
+      "grad_norm": 5.967051029205322,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.1279,
+      "step": 21
+    },
+    {
+      "epoch": 0.05590851334180432,
+      "grad_norm": 6.0283331871032715,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2087,
+      "step": 22
+    },
+    {
+      "epoch": 0.05844980940279543,
+      "grad_norm": 4.806293964385986,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.8635,
+      "step": 23
+    },
+    {
+      "epoch": 0.060991105463786534,
+      "grad_norm": 4.939551830291748,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7116,
+      "step": 24
+    },
+    {
+      "epoch": 0.06353240152477764,
+      "grad_norm": 5.187087059020996,
+      "learning_rate": 0.0,
+      "loss": 0.8951,
+      "step": 25
+    },
+    {
+      "epoch": 0.06353240152477764,
+      "eval_loss": 1.0221692323684692,
+      "eval_runtime": 21.1059,
+      "eval_samples_per_second": 7.865,
+      "eval_steps_per_second": 3.933,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3976632389861376.0,
+  "total_flos": 4993910443081728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null