Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd29145048a23423cca0adb5cb859568f45db566f2fdb1acea5e2a6204028e1
+oid sha256:5cace0424f44d559e65413108fbc06c6211e5f9b6e46c33b5347672e6645a4a9
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4396f0394a4800cb178cfbf85f3ef0d8c0b4cde4d09fd37b2f8b7e2195c9a357
+oid sha256:3c9789c97dd861879e578686c7dc37e2f7bb9fca9d1ef83399f4361d1720185b
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4242d8e3ed159b6b934672d9dfcc288eb33fd1754b4942b790e04d10a5d26127
+oid sha256:ed99a13c6fad0f3bfc2711f3a09d74be1371eea7a3664944c1e31b4d134a94ad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc7a3e9090e82f461aeffa59c922124ae9d0ffbf2acc78b8dd1a9c862ccf3c5
+oid sha256:3813de28a115e58309f0fdbd484c8709fa2daf3049d6fb53def40c5e363e1085
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1018b3a65d7eb6017f9d9418ede9aa41f420f1d93946b326bae1a329cbf620d9
+oid sha256:e028239fed62af78822eed5d9893175e8d7ae96b7f1c6861f0d0314db33159b2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd25f69324e96e814f1b8252caf18014e94eb1aee93d8c063c296c2a646a2bf3
+oid sha256:31353de36fb8e94dc0a01f50a320de6e0d50070de2f10bd47fdfa2e740bd3356
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
+oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5912128686904907,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06212144742972511,
+  "best_metric": 1.4801632165908813,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12424289485945023,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 99.599,
       "eval_steps_per_second": 25.896,
       "step": 25
+    },
+    {
+      "epoch": 0.06460630532691412,
+      "grad_norm": 0.4997400939464569,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 1.1591,
+      "step": 26
+    },
+    {
+      "epoch": 0.06709116322410312,
+      "grad_norm": 0.6131523847579956,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 1.2452,
+      "step": 27
+    },
+    {
+      "epoch": 0.06957602112129213,
+      "grad_norm": 0.5031818747520447,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 1.2703,
+      "step": 28
+    },
+    {
+      "epoch": 0.07206087901848113,
+      "grad_norm": 0.5141401886940002,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 1.3225,
+      "step": 29
+    },
+    {
+      "epoch": 0.07454573691567014,
+      "grad_norm": 0.4961668848991394,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 1.3459,
+      "step": 30
+    },
+    {
+      "epoch": 0.07703059481285914,
+      "grad_norm": 0.4645865857601166,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 1.3681,
+      "step": 31
+    },
+    {
+      "epoch": 0.07951545271004815,
+      "grad_norm": 0.4720369577407837,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 1.4398,
+      "step": 32
+    },
+    {
+      "epoch": 0.08200031060723714,
+      "grad_norm": 0.5064677596092224,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 1.4973,
+      "step": 33
+    },
+    {
+      "epoch": 0.08448516850442615,
+      "grad_norm": 0.7844948172569275,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 1.6429,
+      "step": 34
+    },
+    {
+      "epoch": 0.08697002640161516,
+      "grad_norm": 1.0937235355377197,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 1.655,
+      "step": 35
+    },
+    {
+      "epoch": 0.08945488429880416,
+      "grad_norm": 1.5023084878921509,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 1.9494,
+      "step": 36
+    },
+    {
+      "epoch": 0.09193974219599317,
+      "grad_norm": 1.9704169034957886,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 2.0052,
+      "step": 37
+    },
+    {
+      "epoch": 0.09442460009318217,
+      "grad_norm": 0.3317461609840393,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 1.1168,
+      "step": 38
+    },
+    {
+      "epoch": 0.09690945799037118,
+      "grad_norm": 0.3098306357860565,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 1.2064,
+      "step": 39
+    },
+    {
+      "epoch": 0.09939431588756018,
+      "grad_norm": 0.2434069812297821,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 1.2017,
+      "step": 40
+    },
+    {
+      "epoch": 0.10187917378474919,
+      "grad_norm": 0.2517208158969879,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 1.2654,
+      "step": 41
+    },
+    {
+      "epoch": 0.10436403168193818,
+      "grad_norm": 0.2552037537097931,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 1.3208,
+      "step": 42
+    },
+    {
+      "epoch": 0.1068488895791272,
+      "grad_norm": 0.2989708483219147,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 1.3169,
+      "step": 43
+    },
+    {
+      "epoch": 0.1093337474763162,
+      "grad_norm": 0.38415053486824036,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 1.3684,
+      "step": 44
+    },
+    {
+      "epoch": 0.1118186053735052,
+      "grad_norm": 0.40901339054107666,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 1.464,
+      "step": 45
+    },
+    {
+      "epoch": 0.11430346327069421,
+      "grad_norm": 0.5247498750686646,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 1.5311,
+      "step": 46
+    },
+    {
+      "epoch": 0.11678832116788321,
+      "grad_norm": 0.756410539150238,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 1.6284,
+      "step": 47
+    },
+    {
+      "epoch": 0.11927317906507222,
+      "grad_norm": 0.9791819453239441,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 1.6159,
+      "step": 48
+    },
+    {
+      "epoch": 0.12175803696226122,
+      "grad_norm": 1.455810546875,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 1.939,
+      "step": 49
+    },
+    {
+      "epoch": 0.12424289485945023,
+      "grad_norm": 2.2369606494903564,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 2.421,
+      "step": 50
+    },
+    {
+      "epoch": 0.12424289485945023,
+      "eval_loss": 1.4801632165908813,
+      "eval_runtime": 0.5016,
+      "eval_samples_per_second": 99.69,
+      "eval_steps_per_second": 25.919,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null