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:a60a8938ff46a2b2325d0b1f31ffe52dfd4126bd78d4341f5a1718f59b5b11b9
+oid sha256:2bbd46aeefea3f7933ae8570a30c82f27e8d9b8c160f6941f10f8ffecb06da97
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6be1f6de41b68db7a6b5efd69cf714889a8de87ba6219644bcead6e8cd8c6e9
+oid sha256:0134ce610bf402af67097d82f1640fb8eedc5d46025d12a98c78e217f89d7de8
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ac488ce1f441ca1ae6806867cc0d824ea5a04d174d746efdffa5a728cba642
+oid sha256:b0cc465a75681ba50afdecee660968bcd8503a20558be1104c59586aa9b9c2e7
 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": 11.931650161743164,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016909744240118367,
+  "best_metric": 11.922327995300293,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0033819488480236735,
   "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": 39.233,
       "eval_steps_per_second": 19.616,
       "step": 10
+    },
+    {
+      "epoch": 0.002029169308814204,
+      "grad_norm": 0.16513514518737793,
+      "learning_rate": 0.000163742398974869,
+      "loss": 11.9352,
+      "step": 12
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 0.19673532247543335,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9258,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "eval_loss": 11.926512718200684,
+      "eval_runtime": 63.4061,
+      "eval_samples_per_second": 39.271,
+      "eval_steps_per_second": 19.635,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030437539632213063,
+      "grad_norm": 0.20807549357414246,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 11.9276,
+      "step": 18
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "eval_loss": 11.922327995300293,
+      "eval_runtime": 63.5327,
+      "eval_samples_per_second": 39.192,
+      "eval_steps_per_second": 19.596,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3110308282368.0,
+  "total_flos": 6411043602432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null