Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0788cfbd92a555b1cb0d1d5bdb25b27ae961c765f194eda1be9862c8aa1d6ad3
+oid sha256:76863f500937c8e14f03435a1d03b3d53b3ca7c06caacf3feac48ed6d3fff17e
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:438d86040c099933af83449fa21317f1571aff372d8f44bb0571b1653e566835
+oid sha256:9c35fd91b3fd036e8ae221f426058e9de5a674af5f10e3d45f0e0737bae0e8d9
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc846304558ae6b579eb3f62d9546198fad593f46ad20907d5f0712dc3f01eb3
+oid sha256:489873e7fa320f2b96afb2772784c05b78b89350364dca8a6d957e503e22fafe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.383678436279297,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.027777777777777776,
+  "best_metric": 2.3795127868652344,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.034722222222222224,
   "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": 24.968,
       "eval_steps_per_second": 12.484,
       "step": 20
+    },
+    {
+      "epoch": 0.029166666666666667,
+      "grad_norm": 10.798130989074707,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 9.1747,
+      "step": 21
+    },
+    {
+      "epoch": 0.030555555555555555,
+      "grad_norm": 11.358869552612305,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.5647,
+      "step": 22
+    },
+    {
+      "epoch": 0.03194444444444444,
+      "grad_norm": 10.732549667358398,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 10.0844,
+      "step": 23
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 8.853776931762695,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 9.0329,
+      "step": 24
+    },
+    {
+      "epoch": 0.034722222222222224,
+      "grad_norm": 10.70040225982666,
+      "learning_rate": 0.0,
+      "loss": 9.4862,
+      "step": 25
+    },
+    {
+      "epoch": 0.034722222222222224,
+      "eval_loss": 2.3795127868652344,
+      "eval_runtime": 12.317,
+      "eval_samples_per_second": 24.681,
+      "eval_steps_per_second": 12.341,
+      "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": 42459023278080.0,
+  "total_flos": 53073779097600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null