Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cbe9f0f7ff1c28e5f1a2bede71af35fa34b0b651dfd1175c540745074896792
+oid sha256:8307bb90500a3dd28f1e24679e25e83080fd00864148a04c35807a58eeb3e5ce
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9003941ed9416c0d017c8acfd26c7467e4baccb2328fa6a82fe02dcb12c3381
+oid sha256:1c6535b718b2af36ddb8783c712db36b12c20dd206a66cddeaaf1fbf34fc2481
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8cb3edd1e8f6eb1ec1a0c608cf4768dbd71f659ad06583c14db36cedce31801
+oid sha256:362f3d76bee51dd39bf301fc77818e5a0d2c6aae514d92d0812773060c2b2811
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11bec62294e31259bc6fdb36fdb57ca57f460e558fe49499ee8328c64c6daad8
+oid sha256:10f6b7ed88e6fc3c0b1895faa9671f3f60aff7bb8559c6855b4907735946cce5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42f3df0e9df3524680fae05c5f5e263cc39b34801c05dcb213d504b7d50d5b2
+oid sha256:b7394a521f8fef745603ee895dbd1e6b8bc3a5ff8d2213120e6a8f8340e79ffc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7aaffba6771ee03507e31137d46572fad74a844e2499c5321a67bb0c1552e8
+oid sha256:caf5ec184b1cde633d4720e23f6c1df0b944d9be30c04941e4321451988fa73a
 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": 10.368451118469238,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1398112548060119,
+  "best_metric": 10.361746788024902,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2796225096120238,
   "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": 447.013,
       "eval_steps_per_second": 116.223,
       "step": 25
+    },
+    {
+      "epoch": 0.14540370499825236,
+      "grad_norm": 0.19245736300945282,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3696,
+      "step": 26
+    },
+    {
+      "epoch": 0.15099615519049284,
+      "grad_norm": 0.18666407465934753,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3691,
+      "step": 27
+    },
+    {
+      "epoch": 0.1565886053827333,
+      "grad_norm": 0.18163171410560608,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3689,
+      "step": 28
+    },
+    {
+      "epoch": 0.16218105557497378,
+      "grad_norm": 0.17533497512340546,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3671,
+      "step": 29
+    },
+    {
+      "epoch": 0.16777350576721425,
+      "grad_norm": 0.1728811413049698,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3676,
+      "step": 30
+    },
+    {
+      "epoch": 0.17336595595945473,
+      "grad_norm": 0.16648425161838531,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3689,
+      "step": 31
+    },
+    {
+      "epoch": 0.1789584061516952,
+      "grad_norm": 0.16129642724990845,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3691,
+      "step": 32
+    },
+    {
+      "epoch": 0.1845508563439357,
+      "grad_norm": 0.16618475317955017,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3692,
+      "step": 33
+    },
+    {
+      "epoch": 0.19014330653617617,
+      "grad_norm": 0.1671101450920105,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3682,
+      "step": 34
+    },
+    {
+      "epoch": 0.19573575672841664,
+      "grad_norm": 0.1676071584224701,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3671,
+      "step": 35
+    },
+    {
+      "epoch": 0.20132820692065712,
+      "grad_norm": 0.16497556865215302,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3637,
+      "step": 36
+    },
+    {
+      "epoch": 0.2069206571128976,
+      "grad_norm": 0.16900619864463806,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3615,
+      "step": 37
+    },
+    {
+      "epoch": 0.21251310730513806,
+      "grad_norm": 0.22142191231250763,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3646,
+      "step": 38
+    },
+    {
+      "epoch": 0.21810555749737853,
+      "grad_norm": 0.21971495449543,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3646,
+      "step": 39
+    },
+    {
+      "epoch": 0.223698007689619,
+      "grad_norm": 0.21041202545166016,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3645,
+      "step": 40
+    },
+    {
+      "epoch": 0.22929045788185948,
+      "grad_norm": 0.2077437788248062,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3635,
+      "step": 41
+    },
+    {
+      "epoch": 0.23488290807409998,
+      "grad_norm": 0.19469435513019562,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3635,
+      "step": 42
+    },
+    {
+      "epoch": 0.24047535826634045,
+      "grad_norm": 0.19135217368602753,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3646,
+      "step": 43
+    },
+    {
+      "epoch": 0.24606780845858092,
+      "grad_norm": 0.1929345279932022,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3648,
+      "step": 44
+    },
+    {
+      "epoch": 0.25166025865082137,
+      "grad_norm": 0.18326839804649353,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3651,
+      "step": 45
+    },
+    {
+      "epoch": 0.25725270884306184,
+      "grad_norm": 0.18715374171733856,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3651,
+      "step": 46
+    },
+    {
+      "epoch": 0.26284515903530237,
+      "grad_norm": 0.1834271103143692,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3643,
+      "step": 47
+    },
+    {
+      "epoch": 0.26843760922754284,
+      "grad_norm": 0.17882713675498962,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3625,
+      "step": 48
+    },
+    {
+      "epoch": 0.2740300594197833,
+      "grad_norm": 0.1836736798286438,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3601,
+      "step": 49
+    },
+    {
+      "epoch": 0.2796225096120238,
+      "grad_norm": 0.19659334421157837,
+      "learning_rate": 1e-05,
+      "loss": 10.3583,
+      "step": 50
+    },
+    {
+      "epoch": 0.2796225096120238,
+      "eval_loss": 10.361746788024902,
+      "eval_runtime": 0.1143,
+      "eval_samples_per_second": 437.425,
+      "eval_steps_per_second": 113.731,
+      "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": 21504314966016.0,
+  "total_flos": 43075455025152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null