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:d25b9f80edc52a786e5da1b4054f7abf096df591c4e6827e9a47b7eb9eb2b319
+oid sha256:4452a32a2b1e8b4cde5b9b5039dafadb4888b5be431d30f5eeaa8008541e3346
 size 116744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2211473839e9468512545ca703f01d05e9bc25c9cc757e993cd0b3398ee54a8c
+oid sha256:4858dab144df0c0556232111e055f4bd41432b0c6021ca08382bac51fc06c073
 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": 10.369497299194336,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0327653997378768,
+  "best_metric": 10.365045547485352,
+  "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": 393.649,
       "eval_steps_per_second": 98.45,
       "step": 25
+    },
+    {
+      "epoch": 0.03407601572739188,
+      "grad_norm": 0.14944963157176971,
+      "learning_rate": 5e-05,
+      "loss": 10.3685,
+      "step": 26
+    },
+    {
+      "epoch": 0.035386631716906945,
+      "grad_norm": 0.15662804245948792,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3667,
+      "step": 27
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.15725179016590118,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3666,
+      "step": 28
+    },
+    {
+      "epoch": 0.03800786369593709,
+      "grad_norm": 0.14667585492134094,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3658,
+      "step": 29
+    },
+    {
+      "epoch": 0.039318479685452164,
+      "grad_norm": 0.15799841284751892,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3683,
+      "step": 30
+    },
+    {
+      "epoch": 0.04062909567496723,
+      "grad_norm": 0.15322022140026093,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3657,
+      "step": 31
+    },
+    {
+      "epoch": 0.04193971166448231,
+      "grad_norm": 0.15755851566791534,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3675,
+      "step": 32
+    },
+    {
+      "epoch": 0.04325032765399738,
+      "grad_norm": 0.1500883400440216,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.369,
+      "step": 33
+    },
+    {
+      "epoch": 0.04456094364351245,
+      "grad_norm": 0.1669188141822815,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3645,
+      "step": 34
+    },
+    {
+      "epoch": 0.045871559633027525,
+      "grad_norm": 0.16092829406261444,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3667,
+      "step": 35
+    },
+    {
+      "epoch": 0.047182175622542594,
+      "grad_norm": 0.1579689085483551,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3631,
+      "step": 36
+    },
+    {
+      "epoch": 0.04849279161205767,
+      "grad_norm": 0.185369610786438,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3713,
+      "step": 37
+    },
+    {
+      "epoch": 0.04980340760157274,
+      "grad_norm": 0.15275834500789642,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3731,
+      "step": 38
+    },
+    {
+      "epoch": 0.05111402359108781,
+      "grad_norm": 0.16415461897850037,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3676,
+      "step": 39
+    },
+    {
+      "epoch": 0.05242463958060288,
+      "grad_norm": 0.18097351491451263,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3687,
+      "step": 40
+    },
+    {
+      "epoch": 0.053735255570117955,
+      "grad_norm": 0.2017277479171753,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3623,
+      "step": 41
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.2009059637784958,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3674,
+      "step": 42
+    },
+    {
+      "epoch": 0.0563564875491481,
+      "grad_norm": 0.20384857058525085,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3635,
+      "step": 43
+    },
+    {
+      "epoch": 0.057667103538663174,
+      "grad_norm": 0.22594545781612396,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3641,
+      "step": 44
+    },
+    {
+      "epoch": 0.05897771952817824,
+      "grad_norm": 0.2270260900259018,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3617,
+      "step": 45
+    },
+    {
+      "epoch": 0.06028833551769332,
+      "grad_norm": 0.27347663044929504,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3641,
+      "step": 46
+    },
+    {
+      "epoch": 0.061598951507208385,
+      "grad_norm": 0.2760813534259796,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3627,
+      "step": 47
+    },
+    {
+      "epoch": 0.06290956749672345,
+      "grad_norm": 0.3221200704574585,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3729,
+      "step": 48
+    },
+    {
+      "epoch": 0.06422018348623854,
+      "grad_norm": 0.3210524320602417,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3713,
+      "step": 49
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "grad_norm": 0.43295133113861084,
+      "learning_rate": 0.0,
+      "loss": 10.3788,
+      "step": 50
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "eval_loss": 10.365045547485352,
+      "eval_runtime": 6.5061,
+      "eval_samples_per_second": 395.167,
+      "eval_steps_per_second": 98.83,
+      "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