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:a836deec4b3bb03f50ac049c94a57064a2cedee6f57449429b8f633c913e05f9
+oid sha256:a50e67113ed05ae048e4541309bb9d786780d01028d25d23dafd4259436dd365
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef6b098145b7cc58c327557c70e52112ad6b4d4a920bc2d5fb7e65490f403b14
+oid sha256:5ea31bc314868f0081526b49b180c96af71119c2c26790b97c7cf54c85ecf9b6
 size 70584314

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f108ec767e229a767e3d8a697ef9ce2b2a773115cacb416ea44871e02516790e
+oid sha256:8861ce7e5b4b02a8488133165a43c601c061bcd41ee0e57ed3ac50ce78e47089
 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": 3.069991111755371,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0015394384898108416,
+  "best_metric": 2.9889676570892334,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0023091577347162623,
   "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": 31.164,
       "eval_steps_per_second": 15.585,
       "step": 20
+    },
+    {
+      "epoch": 0.0016164104143013835,
+      "grad_norm": 3.906784772872925,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 3.149,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018473261877730099,
+      "grad_norm": 3.5363552570343018,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.0609,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019242981122635518,
+      "eval_loss": 3.001833200454712,
+      "eval_runtime": 176.8628,
+      "eval_samples_per_second": 30.934,
+      "eval_steps_per_second": 15.47,
+      "step": 25
+    },
+    {
+      "epoch": 0.002078241961244636,
+      "grad_norm": 2.652677297592163,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.936,
+      "step": 27
+    },
+    {
+      "epoch": 0.0023091577347162623,
+      "grad_norm": 4.425987720489502,
+      "learning_rate": 0.0,
+      "loss": 2.8344,
+      "step": 30
+    },
+    {
+      "epoch": 0.0023091577347162623,
+      "eval_loss": 2.9889676570892334,
+      "eval_runtime": 175.1436,
+      "eval_samples_per_second": 31.237,
+      "eval_steps_per_second": 15.621,
+      "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": 360477150412800.0,
+  "total_flos": 540715725619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null