Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ec6a1f9301e94b6cbb4289b044ef8937cb2eb024717432ef2d0f697749c971
+oid sha256:ce0d9f16242e409414b0cb3dfbbf7807b5a4a109790e50c03a92bf439d64e206
 size 116744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce42d8e98e8d96cd45f3b8ff4eaa48a2c518f9a30d976776f27dea875dd2e30
+oid sha256:60183a6c73627c6504e128c4ef32aa19e5c9b29674e0552a8260a4389980828e
 size 243310

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98011b317d46e9d480534968001bbc78adb189694ee40a080d9ad5cdf580f79
+oid sha256:2c7dbd9ba7f134a5eb17fb5066b23dec20a9133fec58fddd72ff39829cbfdd8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.368950843811035,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0327653997378768,
+  "best_metric": 10.364279747009277,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0655307994757536,
   "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": 393.712,
       "eval_steps_per_second": 98.466,
       "step": 25
+    },
+    {
+      "epoch": 0.03407601572739188,
+      "grad_norm": 0.16148076951503754,
+      "learning_rate": 5e-05,
+      "loss": 10.3677,
+      "step": 26
+    },
+    {
+      "epoch": 0.035386631716906945,
+      "grad_norm": 0.16434934735298157,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3658,
+      "step": 27
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.1641886681318283,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3659,
+      "step": 28
+    },
+    {
+      "epoch": 0.03800786369593709,
+      "grad_norm": 0.15775740146636963,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3647,
+      "step": 29
+    },
+    {
+      "epoch": 0.039318479685452164,
+      "grad_norm": 0.16612683236598969,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3673,
+      "step": 30
+    },
+    {
+      "epoch": 0.04062909567496723,
+      "grad_norm": 0.1597711741924286,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3653,
+      "step": 31
+    },
+    {
+      "epoch": 0.04193971166448231,
+      "grad_norm": 0.1618010252714157,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3666,
+      "step": 32
+    },
+    {
+      "epoch": 0.04325032765399738,
+      "grad_norm": 0.16149182617664337,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3679,
+      "step": 33
+    },
+    {
+      "epoch": 0.04456094364351245,
+      "grad_norm": 0.1728137731552124,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3639,
+      "step": 34
+    },
+    {
+      "epoch": 0.045871559633027525,
+      "grad_norm": 0.16797222197055817,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3659,
+      "step": 35
+    },
+    {
+      "epoch": 0.047182175622542594,
+      "grad_norm": 0.16320140659809113,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3627,
+      "step": 36
+    },
+    {
+      "epoch": 0.04849279161205767,
+      "grad_norm": 0.19379617273807526,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3708,
+      "step": 37
+    },
+    {
+      "epoch": 0.04980340760157274,
+      "grad_norm": 0.15521125495433807,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.373,
+      "step": 38
+    },
+    {
+      "epoch": 0.05111402359108781,
+      "grad_norm": 0.16887053847312927,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3672,
+      "step": 39
+    },
+    {
+      "epoch": 0.05242463958060288,
+      "grad_norm": 0.18718759715557098,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3681,
+      "step": 40
+    },
+    {
+      "epoch": 0.053735255570117955,
+      "grad_norm": 0.2031789869070053,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3623,
+      "step": 41
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.2114928662776947,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3669,
+      "step": 42
+    },
+    {
+      "epoch": 0.0563564875491481,
+      "grad_norm": 0.21646137535572052,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3625,
+      "step": 43
+    },
+    {
+      "epoch": 0.057667103538663174,
+      "grad_norm": 0.2333393692970276,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3634,
+      "step": 44
+    },
+    {
+      "epoch": 0.05897771952817824,
+      "grad_norm": 0.23607677221298218,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3612,
+      "step": 45
+    },
+    {
+      "epoch": 0.06028833551769332,
+      "grad_norm": 0.2799040675163269,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3644,
+      "step": 46
+    },
+    {
+      "epoch": 0.061598951507208385,
+      "grad_norm": 0.2798946797847748,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3635,
+      "step": 47
+    },
+    {
+      "epoch": 0.06290956749672345,
+      "grad_norm": 0.35055652260780334,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3718,
+      "step": 48
+    },
+    {
+      "epoch": 0.06422018348623854,
+      "grad_norm": 0.33226096630096436,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3707,
+      "step": 49
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "grad_norm": 0.4313124120235443,
+      "learning_rate": 0.0,
+      "loss": 10.379,
+      "step": 50
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "eval_loss": 10.364279747009277,
+      "eval_runtime": 24.7158,
+      "eval_samples_per_second": 104.023,
+      "eval_steps_per_second": 26.016,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 21142437888000.0,
+  "total_flos": 42284875776000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null