Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514193f21d1830a4bb640d13c364bbd769b37f0d21fc77be55be484c59b8e335
+oid sha256:420fe78db57063c9080722202117ec8b0a5dc881966294f9d65d3bcddf6a4245
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42eff9b448d2ee30b5da865ed9aadbc076df043318189cb027d8b623bc5a5b1
+oid sha256:b31dccee3f6e9d1edbef43b90a155f8afdf9ea0e688a001d9cffc285373735bd
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4c4d3e2a63413186fdc624383f0085bcb1896dfa4dd2647931a2a1e5d987b6
+oid sha256:2ad636d5cf633a906fc3f3ccc5e2d0efef31060640b5f5a43055356e4a3ba83f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9463703036308289,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0011246063877642825,
+  "best_metric": 0.9306618571281433,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0016869095816464238,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.018,
       "eval_steps_per_second": 2.509,
       "step": 20
+    },
+    {
+      "epoch": 0.0011808367071524967,
+      "grad_norm": 0.5461187958717346,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.8704,
+      "step": 21
+    },
+    {
+      "epoch": 0.001349527665317139,
+      "grad_norm": 0.5976988077163696,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.9366,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014057579847053532,
+      "eval_loss": 0.9341148734092712,
+      "eval_runtime": 1490.8156,
+      "eval_samples_per_second": 5.023,
+      "eval_steps_per_second": 2.511,
+      "step": 25
+    },
+    {
+      "epoch": 0.0015182186234817814,
+      "grad_norm": 0.6252656579017639,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.8787,
+      "step": 27
+    },
+    {
+      "epoch": 0.0016869095816464238,
+      "grad_norm": 0.6815670728683472,
+      "learning_rate": 0.0,
+      "loss": 0.9762,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016869095816464238,
+      "eval_loss": 0.9306618571281433,
+      "eval_runtime": 1490.8162,
+      "eval_samples_per_second": 5.023,
+      "eval_steps_per_second": 2.511,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8236125420257280.0,
+  "total_flos": 1.235418813038592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null