Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d72746b4fe3d63ea060b6a18299dacdb237b7d8880ac33bfda32fa70c685a91
+oid sha256:1948a1fe7b6ffe217f930dbc7092629d97c04adec70f098fa16b6dae1e3a4e28
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242634cab847cc5dab3990c64cf828700a36da1948c883a019f7def2966a0b96
+oid sha256:749d38555ba580de274f55590478354e7ab395d15fb5892b188f9fd66d130b7f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c33e14a11ceb8c821f48f34266bdf8f3280085a2fa7d0e2c8dd64abee7439d2
+oid sha256:f760f9a1410cf17fff48f1f37b58e9c594f8c3f120c35016c9434be2131aa74a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8928427696228027,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.03568242640499554,
+  "best_metric": 1.5477936267852783,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07136485280999108,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 9.775,
       "eval_steps_per_second": 2.444,
       "step": 10
+    },
+    {
+      "epoch": 0.042818911685994644,
+      "grad_norm": 11.166938781738281,
+      "learning_rate": 0.000163742398974869,
+      "loss": 5.2163,
+      "step": 12
+    },
+    {
+      "epoch": 0.05352363960749331,
+      "grad_norm": 11.668803215026855,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.4989,
+      "step": 15
+    },
+    {
+      "epoch": 0.05352363960749331,
+      "eval_loss": 1.7072616815567017,
+      "eval_runtime": 24.2567,
+      "eval_samples_per_second": 9.729,
+      "eval_steps_per_second": 2.432,
+      "step": 15
+    },
+    {
+      "epoch": 0.06422836752899197,
+      "grad_norm": 13.31494140625,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 5.7607,
+      "step": 18
+    },
+    {
+      "epoch": 0.07136485280999108,
+      "eval_loss": 1.5477936267852783,
+      "eval_runtime": 24.2406,
+      "eval_samples_per_second": 9.736,
+      "eval_steps_per_second": 2.434,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6534582019031040.0,
+  "total_flos": 1.306916403806208e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null