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:aafb4ffa32d17808558d092f1076cda5ef1ba263c66b2441f02aba06f7e2c610
+oid sha256:b6299922706f7fd7a71ae5ca7ba2d6b506407d83816347b71c3256aa98c0076a
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3baa080af1fa1245d7afb484e60cfc1025e9d7972c82d3bb904688d2f2a8c856
+oid sha256:b318838d7b999477c33ffad2d5552e0f0bf7b8181dd4274397dff39e2a854bea
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd77b785e4be80fea18db71bb7d9c0eb2f14d8c71031560cdc4284450cc3ea0f
+oid sha256:f81683f5f07629802bed0101e4d9d6cd92ce644012e6f5677c194f522ee017e6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9136d8fa47823e6c60d44e015fb07b308502698a38e23974288968c39d1759a1
+oid sha256:31a634d1130a174c0cdb657a555add6d0fc3c0704baa2d3e87fabf1c1e09ec11
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f39d10f2a0b60a147f7ebdba84f618bf8c6c93406aae1558c1da99f5ae43681
+oid sha256:506b07fb24bd1f5cd4efea761af49e8f32802b10a39b0689859491def79414c6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32f4e69ca8a8447637d820b7d77618ff80182ac8086e4a169ed9eccfef4a5e3
+oid sha256:ffbf15a2540e3edbb45715fd3fa6f5c040a8a7097c4e5b2b029ebf3aa1878c0e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.703987121582031,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010428888019814887,
+  "best_metric": 10.567898750305176,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.020857776039629773,
   "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": 597.656,
       "eval_steps_per_second": 155.391,
       "step": 25
+    },
+    {
+      "epoch": 0.010846043540607482,
+      "grad_norm": 15.183359146118164,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 172.194,
+      "step": 26
+    },
+    {
+      "epoch": 0.011263199061400078,
+      "grad_norm": 17.194549560546875,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 170.835,
+      "step": 27
+    },
+    {
+      "epoch": 0.011680354582192673,
+      "grad_norm": 16.776403427124023,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 170.8668,
+      "step": 28
+    },
+    {
+      "epoch": 0.012097510102985268,
+      "grad_norm": 17.39474105834961,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 170.3105,
+      "step": 29
+    },
+    {
+      "epoch": 0.012514665623777864,
+      "grad_norm": 17.14206886291504,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 170.1634,
+      "step": 30
+    },
+    {
+      "epoch": 0.01293182114457046,
+      "grad_norm": 16.973140716552734,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 170.1308,
+      "step": 31
+    },
+    {
+      "epoch": 0.013348976665363055,
+      "grad_norm": 16.690622329711914,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 170.1685,
+      "step": 32
+    },
+    {
+      "epoch": 0.01376613218615565,
+      "grad_norm": 17.22452163696289,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 169.8173,
+      "step": 33
+    },
+    {
+      "epoch": 0.014183287706948247,
+      "grad_norm": 16.15555191040039,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 170.0619,
+      "step": 34
+    },
+    {
+      "epoch": 0.014600443227740843,
+      "grad_norm": 15.78242015838623,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 170.3394,
+      "step": 35
+    },
+    {
+      "epoch": 0.015017598748533438,
+      "grad_norm": 16.192392349243164,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 169.9828,
+      "step": 36
+    },
+    {
+      "epoch": 0.015434754269326034,
+      "grad_norm": 16.889453887939453,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 170.1619,
+      "step": 37
+    },
+    {
+      "epoch": 0.015851909790118628,
+      "grad_norm": 14.697663307189941,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 171.5415,
+      "step": 38
+    },
+    {
+      "epoch": 0.016269065310911223,
+      "grad_norm": 14.812946319580078,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 170.041,
+      "step": 39
+    },
+    {
+      "epoch": 0.01668622083170382,
+      "grad_norm": 15.579548835754395,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 169.3603,
+      "step": 40
+    },
+    {
+      "epoch": 0.017103376352496414,
+      "grad_norm": 15.448450088500977,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 169.2855,
+      "step": 41
+    },
+    {
+      "epoch": 0.01752053187328901,
+      "grad_norm": 15.2275390625,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 169.3168,
+      "step": 42
+    },
+    {
+      "epoch": 0.017937687394081605,
+      "grad_norm": 15.755297660827637,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 168.8581,
+      "step": 43
+    },
+    {
+      "epoch": 0.0183548429148742,
+      "grad_norm": 15.333876609802246,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 169.1523,
+      "step": 44
+    },
+    {
+      "epoch": 0.018771998435666796,
+      "grad_norm": 15.545121192932129,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 169.1059,
+      "step": 45
+    },
+    {
+      "epoch": 0.01918915395645939,
+      "grad_norm": 15.434908866882324,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 169.0822,
+      "step": 46
+    },
+    {
+      "epoch": 0.019606309477251987,
+      "grad_norm": 14.696342468261719,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 169.5559,
+      "step": 47
+    },
+    {
+      "epoch": 0.020023464998044582,
+      "grad_norm": 15.240139961242676,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 169.6834,
+      "step": 48
+    },
+    {
+      "epoch": 0.020440620518837178,
+      "grad_norm": 16.353404998779297,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 169.1321,
+      "step": 49
+    },
+    {
+      "epoch": 0.020857776039629773,
+      "grad_norm": 18.517147064208984,
+      "learning_rate": 1e-05,
+      "loss": 170.0445,
+      "step": 50
+    },
+    {
+      "epoch": 0.020857776039629773,
+      "eval_loss": 10.567898750305176,
+      "eval_runtime": 0.0956,
+      "eval_samples_per_second": 523.206,
+      "eval_steps_per_second": 136.034,
+      "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": 19055561932800.0,
+  "total_flos": 38111123865600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null