Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79919b4a95c22c196f1b579ddcbf454ffeb69a0a18c51c85129c13164353cb32
+oid sha256:d17bc0f5727a1473f78e22670530842ece53e593ada9e8b11e48118c925c6473
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1724859748fd4c8e59f4c86b5c324da9c520519d5ffa8d0347282ffee3700aa4
+oid sha256:fe72b5f69fe218049e0312cb06066fc1018538ddafafd5aff5d6ab9a4817789a
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea30508b2168921b3e75386a046978772f5cbc66bbd566c5d99dd61ea40c26f1
+oid sha256:4cf355fd48ca7fbf33eb7fc35115a0613a7bff5e1759da5fa0cb1ec53729b7e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4807919263839722,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003321983223984719,
+  "best_metric": 1.4805160760879517,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006643966447969438,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 10.702,
       "eval_steps_per_second": 5.351,
       "step": 10
+    },
+    {
+      "epoch": 0.0036541815463831907,
+      "grad_norm": 4.671273501338894e+18,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.255,
+      "step": 11
+    },
+    {
+      "epoch": 0.003986379868781663,
+      "grad_norm": 6.012352781539607e+18,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.0811,
+      "step": 12
+    },
+    {
+      "epoch": 0.004318578191180134,
+      "grad_norm": 7.595634132374258e+18,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.4829,
+      "step": 13
+    },
+    {
+      "epoch": 0.004650776513578606,
+      "grad_norm": 6.173390553078563e+18,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.318,
+      "step": 14
+    },
+    {
+      "epoch": 0.004982974835977079,
+      "grad_norm": 1.1388430278713147e+19,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.0364,
+      "step": 15
+    },
+    {
+      "epoch": 0.004982974835977079,
+      "eval_loss": 1.480578899383545,
+      "eval_runtime": 119.8944,
+      "eval_samples_per_second": 10.576,
+      "eval_steps_per_second": 5.288,
+      "step": 15
+    },
+    {
+      "epoch": 0.00531517315837555,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3942,
+      "step": 16
+    },
+    {
+      "epoch": 0.005647371480774022,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.2408,
+      "step": 17
+    },
+    {
+      "epoch": 0.005979569803172494,
+      "grad_norm": Infinity,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.5907,
+      "step": 18
+    },
+    {
+      "epoch": 0.006311768125570966,
+      "grad_norm": Infinity,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.3361,
+      "step": 19
+    },
+    {
+      "epoch": 0.006643966447969438,
+      "grad_norm": Infinity,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.2003,
+      "step": 20
+    },
+    {
+      "epoch": 0.006643966447969438,
+      "eval_loss": 1.4805160760879517,
+      "eval_runtime": 118.1865,
+      "eval_samples_per_second": 10.729,
+      "eval_steps_per_second": 5.364,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 511583956500480.0,
+  "total_flos": 1023167913000960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null