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:a7c411d16fd17f20040dd85ec0377f3e886a556b40af6ff41dc036d7e2dbabc9
+oid sha256:1d226f74c2beb108b41edc3b643899de05b6d1e1e6835d7f016d6d30b618d341
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:896bad84f75ce1f04620ba90d068d2d6c6f85f2594c21dc7074a9f8744afe77c
+oid sha256:23dc6662743bba85623e49213df28a6506fbdf74cadaa0c2709fa44a98d26dbd
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa13545c8ca8dc6508204472c2d6eaeb3b165f99b0f8f8e1a14c2c8d7b4fb324
+oid sha256:9ec83ba458b88cc3045117b1d709de1495acbf0825f2c78f2246151ee210f3d8
 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": 11.029707908630371,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007474539848640568,
+  "best_metric": 11.024052619934082,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00934317481080071,
   "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": 154.651,
       "eval_steps_per_second": 77.394,
       "step": 20
+    },
+    {
+      "epoch": 0.007848266841072597,
+      "grad_norm": 2.3549764156341553,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 44.1263,
+      "step": 21
+    },
+    {
+      "epoch": 0.008221993833504625,
+      "grad_norm": 2.45450496673584,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 44.045,
+      "step": 22
+    },
+    {
+      "epoch": 0.008595720825936654,
+      "grad_norm": 2.3912954330444336,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 44.1419,
+      "step": 23
+    },
+    {
+      "epoch": 0.008969447818368682,
+      "grad_norm": 2.5055766105651855,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 44.0682,
+      "step": 24
+    },
+    {
+      "epoch": 0.00934317481080071,
+      "grad_norm": 2.4970130920410156,
+      "learning_rate": 0.0,
+      "loss": 44.0782,
+      "step": 25
+    },
+    {
+      "epoch": 0.00934317481080071,
+      "eval_loss": 11.024052619934082,
+      "eval_runtime": 7.133,
+      "eval_samples_per_second": 157.997,
+      "eval_steps_per_second": 79.069,
+      "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": 221830447104.0,
+  "total_flos": 279699259392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null