Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fcc3074e882c5d2b7dc5efbf7399ba565df48ee8e6685b48a6c7082bf87b9d6
+oid sha256:e8b657f4ec441bd871c27768750238d8148ecd1b4a38d24ddb29dee4a3ab7ece
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a165402674e71a8ea66c1ee2e18ded7b2c0509bfa56388e573f361c26c94c2
+oid sha256:2a82de3b26dc4c542da2704296ab87a178e6a1806a18cc98842b4406b802c067
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:83eb5cdc8dd621b9d3b7cf06b9b893f32eef10d148e5187947364f07998add5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.252562999725342,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.027903732124171608,
+  "best_metric": 2.2362687587738037,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.04185559818625741,
   "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": 7.606,
       "eval_steps_per_second": 3.803,
       "step": 20
+    },
+    {
+      "epoch": 0.029298918730380187,
+      "grad_norm": 0.49606454372406006,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.2712,
+      "step": 21
+    },
+    {
+      "epoch": 0.03348447854900593,
+      "grad_norm": 0.5008409023284912,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.2295,
+      "step": 24
+    },
+    {
+      "epoch": 0.03487966515521451,
+      "eval_loss": 2.2383034229278564,
+      "eval_runtime": 39.6708,
+      "eval_samples_per_second": 7.613,
+      "eval_steps_per_second": 3.806,
+      "step": 25
+    },
+    {
+      "epoch": 0.03767003836763167,
+      "grad_norm": 0.48829907178878784,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.1718,
+      "step": 27
+    },
+    {
+      "epoch": 0.04185559818625741,
+      "grad_norm": 0.47491899132728577,
+      "learning_rate": 0.0,
+      "loss": 2.2365,
+      "step": 30
+    },
+    {
+      "epoch": 0.04185559818625741,
+      "eval_loss": 2.2362687587738037,
+      "eval_runtime": 39.6779,
+      "eval_samples_per_second": 7.611,
+      "eval_steps_per_second": 3.806,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null