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:dec5ac874cce253903e0d66161ba75455199aa175e956912636e07183751e6e2
+oid sha256:104ad059cc00e3b63e9764b5c1ed911a6c11b76c53f6c1b769d8a3ba1c3802c5
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e1e14867bbeba7bce36b407598ffc68c66fe38717770a93bbfe9574424d128
+oid sha256:382d44a7fb4bd52a94753f8b9e96e0e6a1d15813b644b67eaa84916db340f447
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa24108fd4c735949f599fb69a77431790c4943e683c6b56d3c9835f7a86eea
+oid sha256:8942cd3d5cc77b5c58bef4acc2eacec5dfd05cf0e5a5a2e36147587f05803333
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814c391fe990edec2cb207518cb08bf3b78ca86479baa6f74de9b344a6811a76
+oid sha256:6b82f178f7e129eb8aabe39e93ea97fca3e7a280fc8b43f797618d17ee504312
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7692537ad54530c0311f6db7adffa4d7b7ca86b7f6a47d70ebfbfc82d6efcd80
+oid sha256:1b26aa0a7c9eba3d53a0be3fed6111b57a8cba17142ec713730d9947e1cedeee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1916d449d685ad03f87ce1f82cd9b66ecffa8568d5f1f00f763844fc9a75d1
+oid sha256:960b837b7d37199329162e1a5ea117a3c1cbc9f91e98f95122f1ce7a04e75aec
 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": 0.8477029204368591,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.032208712456719545,
+  "best_metric": 0.5923976302146912,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06441742491343909,
   "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": 12.37,
       "eval_steps_per_second": 3.216,
       "step": 25
+    },
+    {
+      "epoch": 0.03349706095498833,
+      "grad_norm": 36.677696228027344,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 24.531,
+      "step": 26
+    },
+    {
+      "epoch": 0.03478540945325711,
+      "grad_norm": 29.125059127807617,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 20.848,
+      "step": 27
+    },
+    {
+      "epoch": 0.03607375795152589,
+      "grad_norm": 25.221555709838867,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 20.9429,
+      "step": 28
+    },
+    {
+      "epoch": 0.03736210644979467,
+      "grad_norm": 24.186708450317383,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 21.7346,
+      "step": 29
+    },
+    {
+      "epoch": 0.03865045494806345,
+      "grad_norm": 24.044862747192383,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 21.4339,
+      "step": 30
+    },
+    {
+      "epoch": 0.03993880344633223,
+      "grad_norm": 24.531862258911133,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 20.8275,
+      "step": 31
+    },
+    {
+      "epoch": 0.04122715194460101,
+      "grad_norm": 24.415983200073242,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 20.4433,
+      "step": 32
+    },
+    {
+      "epoch": 0.042515500442869794,
+      "grad_norm": 20.245210647583008,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 20.7097,
+      "step": 33
+    },
+    {
+      "epoch": 0.043803848941138576,
+      "grad_norm": 20.419910430908203,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 20.0465,
+      "step": 34
+    },
+    {
+      "epoch": 0.04509219743940736,
+      "grad_norm": 21.229557037353516,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 19.755,
+      "step": 35
+    },
+    {
+      "epoch": 0.04638054593767614,
+      "grad_norm": 24.20121955871582,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 20.3669,
+      "step": 36
+    },
+    {
+      "epoch": 0.04766889443594492,
+      "grad_norm": 27.731250762939453,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 20.5599,
+      "step": 37
+    },
+    {
+      "epoch": 0.048957242934213704,
+      "grad_norm": 22.39792251586914,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 19.2265,
+      "step": 38
+    },
+    {
+      "epoch": 0.050245591432482486,
+      "grad_norm": 23.370872497558594,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 16.5371,
+      "step": 39
+    },
+    {
+      "epoch": 0.05153393993075127,
+      "grad_norm": 30.893217086791992,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 17.1265,
+      "step": 40
+    },
+    {
+      "epoch": 0.05282228842902005,
+      "grad_norm": 23.17006492614746,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 16.948,
+      "step": 41
+    },
+    {
+      "epoch": 0.05411063692728883,
+      "grad_norm": 19.363140106201172,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 18.092,
+      "step": 42
+    },
+    {
+      "epoch": 0.055398985425557615,
+      "grad_norm": 21.08965301513672,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 18.0266,
+      "step": 43
+    },
+    {
+      "epoch": 0.0566873339238264,
+      "grad_norm": 20.33384895324707,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 17.16,
+      "step": 44
+    },
+    {
+      "epoch": 0.05797568242209518,
+      "grad_norm": 22.02051544189453,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 17.0887,
+      "step": 45
+    },
+    {
+      "epoch": 0.05926403092036396,
+      "grad_norm": 24.07645606994629,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 16.9783,
+      "step": 46
+    },
+    {
+      "epoch": 0.06055237941863274,
+      "grad_norm": 25.257797241210938,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 17.5447,
+      "step": 47
+    },
+    {
+      "epoch": 0.061840727916901525,
+      "grad_norm": 32.02328872680664,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 18.0569,
+      "step": 48
+    },
+    {
+      "epoch": 0.06312907641517031,
+      "grad_norm": 27.761093139648438,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 17.8059,
+      "step": 49
+    },
+    {
+      "epoch": 0.06441742491343909,
+      "grad_norm": 36.194374084472656,
+      "learning_rate": 1e-05,
+      "loss": 17.8447,
+      "step": 50
+    },
+    {
+      "epoch": 0.06441742491343909,
+      "eval_loss": 0.5923976302146912,
+      "eval_runtime": 4.1863,
+      "eval_samples_per_second": 11.944,
+      "eval_steps_per_second": 3.105,
+      "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": 2.633661061005312e+17,
+  "total_flos": 5.268143856628531e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null