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:fe0975286c87ae082c5a2d7a6705783a7769454340306837b0d7722335f933d0
+oid sha256:38326df96ef01835036266b87f1c709db83e9fdc5a2e3a436f895f096d3416ad
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386aad142fcce91ce7daa4979e44f120867e9fe18716bc92ef53f9d4a63b52f0
+oid sha256:74195b20692420df8f97d001953937acade0d38e353ff03f1ddb7e1171aaea61
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
+oid sha256:41e83f307180ac8f488ffa5d12e6485869ba276842bbc2776b54d5f280df42a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.214880466461182,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.044370493621741544,
+  "best_metric": 4.194016933441162,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.05546311702717693,
   "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": 7.838,
       "eval_steps_per_second": 3.919,
       "step": 20
+    },
+    {
+      "epoch": 0.04658901830282862,
+      "grad_norm": 3.743157386779785,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 3.9504,
+      "step": 21
+    },
+    {
+      "epoch": 0.048807542983915694,
+      "grad_norm": 3.625865936279297,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 3.887,
+      "step": 22
+    },
+    {
+      "epoch": 0.051026067665002776,
+      "grad_norm": 2.858363628387451,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 3.9769,
+      "step": 23
+    },
+    {
+      "epoch": 0.05324459234608985,
+      "grad_norm": 2.82611346244812,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 3.5076,
+      "step": 24
+    },
+    {
+      "epoch": 0.05546311702717693,
+      "grad_norm": 4.127472877502441,
+      "learning_rate": 0.0,
+      "loss": 3.9647,
+      "step": 25
+    },
+    {
+      "epoch": 0.05546311702717693,
+      "eval_loss": 4.194016933441162,
+      "eval_runtime": 25.2248,
+      "eval_samples_per_second": 7.532,
+      "eval_steps_per_second": 3.766,
+      "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": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null