Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90dc1d9881c892828e9db1710ba7ca5fae5f23e33727fe523f3b8feeb1c59251
+oid sha256:a84deee13dd315e8fcbcb28d22e374b4e919e8d119644daac24c63ee4b326580
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e8bca7e2e4ea0ce3d7c8ca91f49b34ce31a8f4654fe65e50b8ecee5497b2c18
+oid sha256:0ab33aabb23561c4a90afb5ee894e1faaf2a53a68f4feafcc5727886b373b7cf
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d06bafe6b7413a64b1b2b7501fafe281fdadc6b8d8a7d2b8d42c504a96de904
+oid sha256:9d8414ba48354825ad20b0a3d80cc23ff1d239366d3e0da53cb9bbe2c2455ccc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1853621006011963,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0028238616307800918,
+  "best_metric": 1.7350926399230957,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0056477232615601836,
   "eval_steps": 10,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 5.568,
       "eval_steps_per_second": 5.568,
       "step": 10
+    },
+    {
+      "epoch": 0.003106247793858101,
+      "grad_norm": 0.9601467847824097,
+      "learning_rate": 0.0001999979446958366,
+      "loss": 1.9811,
+      "step": 11
+    },
+    {
+      "epoch": 0.00338863395693611,
+      "grad_norm": 1.353819489479065,
+      "learning_rate": 0.00019999177886783194,
+      "loss": 2.373,
+      "step": 12
+    },
+    {
+      "epoch": 0.0036710201200141194,
+      "grad_norm": 0.897077202796936,
+      "learning_rate": 0.00019998150276943902,
+      "loss": 1.696,
+      "step": 13
+    },
+    {
+      "epoch": 0.003953406283092128,
+      "grad_norm": 1.358173131942749,
+      "learning_rate": 0.000199967116823068,
+      "loss": 2.3396,
+      "step": 14
+    },
+    {
+      "epoch": 0.004235792446170138,
+      "grad_norm": 1.0444282293319702,
+      "learning_rate": 0.0001999486216200688,
+      "loss": 1.482,
+      "step": 15
+    },
+    {
+      "epoch": 0.004518178609248147,
+      "grad_norm": 3.5194482803344727,
+      "learning_rate": 0.00019992601792070679,
+      "loss": 1.6677,
+      "step": 16
+    },
+    {
+      "epoch": 0.004800564772326156,
+      "grad_norm": 3.523196220397949,
+      "learning_rate": 0.00019989930665413147,
+      "loss": 2.393,
+      "step": 17
+    },
+    {
+      "epoch": 0.005082950935404165,
+      "grad_norm": 0.9800947904586792,
+      "learning_rate": 0.00019986848891833845,
+      "loss": 1.6947,
+      "step": 18
+    },
+    {
+      "epoch": 0.005365337098482174,
+      "grad_norm": 1.540337324142456,
+      "learning_rate": 0.0001998335659801241,
+      "loss": 0.563,
+      "step": 19
+    },
+    {
+      "epoch": 0.0056477232615601836,
+      "grad_norm": 1.577869176864624,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 2.0525,
+      "step": 20
+    },
+    {
+      "epoch": 0.0056477232615601836,
+      "eval_loss": 1.7350926399230957,
+      "eval_runtime": 133.9613,
+      "eval_samples_per_second": 5.569,
+      "eval_steps_per_second": 5.569,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -121,7 +199,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 978803585187840.0,
+  "total_flos": 1957607170375680.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null