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:af124cc5726213e226091e2bfb2ec2a4dd1d8d868e5836e0038f80d1499ed49c
+oid sha256:0591d762a1970547c88cfe8f117f5f9cb3bc92540026ae1e31b65a0712446356
 size 503407240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a555aca5604e0406fbd2ce07fadc2cbbc9a140d6a9efad4fb1b2f0a7049f0658
+oid sha256:be29e5e6f12cf92ce4393c3895566331da8f41c0aef29285e349aa49f1425a1a
 size 1007201074

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754a48e654b04b4ec3cdc44221461b9a55c4909310327156e93de2a1f512fca5
+oid sha256:8e729895f87e1e3324e23be26349da9aff62a87999b361f3bb9506937ff799c8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aab62fbbaab025b2388655ea4620b6148e2795469c2007fea9a9789279baf9a
+oid sha256:54fcf4a5a29b927232617868e34a6e37fd525112ff848a1490398db0a218392c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa8161aae8491fc749581df6b5472cbc0e2045766314d0ac27b883cf9c741e2
+oid sha256:1bbbcf5f4ca7cb55ec87500ba9dbd99a62b4a1001cf95834478d107bfa5a2809
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63f467e52b0009d561f10b214129bb282edd105d0aa77678c7f6ef5ea614a510
+oid sha256:bac51af9ea173bb988176498727e08ab5c0df9194e5e6bd16e5f5e1d1b1623ba
 size 15024

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": 1.6913299560546875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016559032952475575,
+  "best_metric": 1.6356873512268066,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03311806590495115,
   "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": 23.347,
       "eval_steps_per_second": 2.92,
       "step": 25
+    },
+    {
+      "epoch": 0.0172213942705746,
+      "grad_norm": 23.54070472717285,
+      "learning_rate": 5e-05,
+      "loss": 22.5009,
+      "step": 26
+    },
+    {
+      "epoch": 0.01788375558867362,
+      "grad_norm": 20.027286529541016,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 23.1153,
+      "step": 27
+    },
+    {
+      "epoch": 0.018546116906772644,
+      "grad_norm": 18.963481903076172,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 23.7903,
+      "step": 28
+    },
+    {
+      "epoch": 0.019208478224871667,
+      "grad_norm": 26.33202362060547,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 27.938,
+      "step": 29
+    },
+    {
+      "epoch": 0.01987083954297069,
+      "grad_norm": 21.261442184448242,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 25.7281,
+      "step": 30
+    },
+    {
+      "epoch": 0.020533200861069714,
+      "grad_norm": 20.291833877563477,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 24.2849,
+      "step": 31
+    },
+    {
+      "epoch": 0.021195562179168737,
+      "grad_norm": 22.858013153076172,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 25.7152,
+      "step": 32
+    },
+    {
+      "epoch": 0.02185792349726776,
+      "grad_norm": 23.46312713623047,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 26.8651,
+      "step": 33
+    },
+    {
+      "epoch": 0.022520284815366783,
+      "grad_norm": 23.533655166625977,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 26.9475,
+      "step": 34
+    },
+    {
+      "epoch": 0.023182646133465806,
+      "grad_norm": 23.187999725341797,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 25.6272,
+      "step": 35
+    },
+    {
+      "epoch": 0.02384500745156483,
+      "grad_norm": 26.695240020751953,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 28.5214,
+      "step": 36
+    },
+    {
+      "epoch": 0.02450736876966385,
+      "grad_norm": 27.083887100219727,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 31.241,
+      "step": 37
+    },
+    {
+      "epoch": 0.025169730087762875,
+      "grad_norm": 33.784095764160156,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 27.0767,
+      "step": 38
+    },
+    {
+      "epoch": 0.025832091405861898,
+      "grad_norm": 17.89984130859375,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 23.7762,
+      "step": 39
+    },
+    {
+      "epoch": 0.02649445272396092,
+      "grad_norm": 25.040252685546875,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 26.2669,
+      "step": 40
+    },
+    {
+      "epoch": 0.027156814042059944,
+      "grad_norm": 17.308666229248047,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 22.8648,
+      "step": 41
+    },
+    {
+      "epoch": 0.027819175360158967,
+      "grad_norm": 17.806684494018555,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 25.445,
+      "step": 42
+    },
+    {
+      "epoch": 0.02848153667825799,
+      "grad_norm": 18.2435359954834,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 25.0637,
+      "step": 43
+    },
+    {
+      "epoch": 0.029143897996357013,
+      "grad_norm": 22.409690856933594,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 28.0825,
+      "step": 44
+    },
+    {
+      "epoch": 0.029806259314456036,
+      "grad_norm": 18.422311782836914,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 26.1024,
+      "step": 45
+    },
+    {
+      "epoch": 0.03046862063255506,
+      "grad_norm": 21.495967864990234,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 25.523,
+      "step": 46
+    },
+    {
+      "epoch": 0.031130981950654082,
+      "grad_norm": 22.34445571899414,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 25.1083,
+      "step": 47
+    },
+    {
+      "epoch": 0.031793343268753105,
+      "grad_norm": 24.14988136291504,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 26.1674,
+      "step": 48
+    },
+    {
+      "epoch": 0.03245570458685213,
+      "grad_norm": 24.39285659790039,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 27.8474,
+      "step": 49
+    },
+    {
+      "epoch": 0.03311806590495115,
+      "grad_norm": 28.339920043945312,
+      "learning_rate": 0.0,
+      "loss": 28.8547,
+      "step": 50
+    },
+    {
+      "epoch": 0.03311806590495115,
+      "eval_loss": 1.6356873512268066,
+      "eval_runtime": 431.7917,
+      "eval_samples_per_second": 23.555,
+      "eval_steps_per_second": 2.946,
+      "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": 4.217745394630656e+17,
+  "total_flos": 8.435490789261312e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null