Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c306e0d8eb863fa7f156ce9765ad9b28406303063fca7a89889f37fa3b5b9d
+oid sha256:e68c51301c02c840e3c302a65dfacace0873cc189483592c399c7ce06fbef21e
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad7b7027b7c61af8157df28c281203cb6a7ab3fac972e42de97b99c42d2d637
+oid sha256:a0c4f815295245ecb104073a48d72ad98b33b2eadab4974e759c8a4176308c69
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90efee331ac9bcdb2e4f63bae83396c78dd900015159ffa010420c7d94807b3b
+oid sha256:8112a5d1696724c83834696c803611df85e1ad912751daf9433f721aedfe910b
 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": 1.9547957181930542,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00457482701435352,
+  "best_metric": 1.9018210172653198,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0057185337679419,
   "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": 5.807,
       "eval_steps_per_second": 2.905,
       "step": 20
+    },
+    {
+      "epoch": 0.004803568365071196,
+      "grad_norm": 10.91247844696045,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 6.3325,
+      "step": 21
+    },
+    {
+      "epoch": 0.005032309715788871,
+      "grad_norm": 10.488737106323242,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 8.6445,
+      "step": 22
+    },
+    {
+      "epoch": 0.005261051066506548,
+      "grad_norm": 9.67850399017334,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 6.8417,
+      "step": 23
+    },
+    {
+      "epoch": 0.005489792417224223,
+      "grad_norm": 9.22018814086914,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 5.6596,
+      "step": 24
+    },
+    {
+      "epoch": 0.0057185337679419,
+      "grad_norm": 10.53501033782959,
+      "learning_rate": 0.0,
+      "loss": 7.4384,
+      "step": 25
+    },
+    {
+      "epoch": 0.0057185337679419,
+      "eval_loss": 1.9018210172653198,
+      "eval_runtime": 317.3453,
+      "eval_samples_per_second": 5.801,
+      "eval_steps_per_second": 2.902,
+      "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": 6794734731264000.0,
+  "total_flos": 8493418414080000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null