Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f9d0fef563a3aea68fe5a436e068cc9437ef26306896fe8f4ba667c465ca821
+oid sha256:acc3fbdaab71bafd6a9f21845b1fb8af4fb969bbc598befa650126380e3231d6
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d9fb89aa45d0ccb5265e2eb23b9c3c3d830a274a24aef5b3c58b1aafd056e7
+oid sha256:673a1e382208dbb96c16dda44cad34d37738a70587d78853894f9b51fae7bba9
 size 3174398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045c1420f6a0a004f58e4b6dee2000f73fb4c554e36404ed94a05932a5b1322d
+oid sha256:5b658fa92bb927b8ec9922d6fcb40c9f7b2f706aae9643d938fce47e2f40016d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.396878242492676,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007768272433314236,
+  "best_metric": 11.385905265808105,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0009710340541642796,
   "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": 57.02,
       "eval_steps_per_second": 28.513,
       "step": 20
+    },
+    {
+      "epoch": 0.0008156686054979948,
+      "grad_norm": 2389.484375,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 77.8951,
+      "step": 21
+    },
+    {
+      "epoch": 0.000854509967664566,
+      "grad_norm": 2134.96533203125,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 64.0943,
+      "step": 22
+    },
+    {
+      "epoch": 0.0008933513298311371,
+      "grad_norm": 1878.917724609375,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 41.0701,
+      "step": 23
+    },
+    {
+      "epoch": 0.0009321926919977084,
+      "grad_norm": 1692.27685546875,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 27.0765,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009710340541642796,
+      "grad_norm": 3104.988037109375,
+      "learning_rate": 0.0,
+      "loss": 51.3085,
+      "step": 25
+    },
+    {
+      "epoch": 0.0009710340541642796,
+      "eval_loss": 11.385905265808105,
+      "eval_runtime": 193.4288,
+      "eval_samples_per_second": 56.046,
+      "eval_steps_per_second": 28.026,
+      "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": 37378043412480.0,
+  "total_flos": 47345521655808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null