Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd9548b41ac9e4994d34cade4810b448960c7ee2ae3ad7ae88177bb442797a2
+oid sha256:b4a3cc88a45ea77f9a3a2f7839a34390b557d06fd5988d769c1ed0d68a773056
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e163d0c3a3947479f5ea69fa37b72bf329673a13b0c0f24c95f163c340628fa4
+oid sha256:bbddeeab063797026d9bf027c02b4670983aba04a2c1ea8299c1b214ec9f4e1b
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d003b050fa29d84b2d6ac06520f8c0077ef2a5a35e872410f9db8150de3af7
+oid sha256:7feca88993b380bc76cbcc0f6b1bcaf966f32b474ccc94cc6efc2479432e9285
 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": 1.7760616540908813,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00032997855139415937,
+  "best_metric": 1.6954796314239502,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0006599571027883187,
   "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": 5.207,
       "eval_steps_per_second": 1.302,
       "step": 10
+    },
+    {
+      "epoch": 0.00039597426167299127,
+      "grad_norm": 1.2617883682250977,
+      "learning_rate": 0.000163742398974869,
+      "loss": 6.3922,
+      "step": 12
+    },
+    {
+      "epoch": 0.000494967827091239,
+      "grad_norm": 1.170369029045105,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.6538,
+      "step": 15
+    },
+    {
+      "epoch": 0.000494967827091239,
+      "eval_loss": 1.716353178024292,
+      "eval_runtime": 4910.0447,
+      "eval_samples_per_second": 5.198,
+      "eval_steps_per_second": 1.299,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005939613925094869,
+      "grad_norm": 1.3879562616348267,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 6.4795,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006599571027883187,
+      "eval_loss": 1.6954796314239502,
+      "eval_runtime": 4905.6933,
+      "eval_samples_per_second": 5.202,
+      "eval_steps_per_second": 1.301,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.68216426971136e+16,
+  "total_flos": 2.95172220911616e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null