Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c768346426c737530862157676ec01eb51ee18e1c78bae35fd86a5f7c223c77
+oid sha256:f099b46e050f5f7056a0d032854feab1b2a089aa0d59f04fccec1a5fb3005fc3
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426b372258d45aa1548b54549ea9a0344015c1613a44982dcac8e240a367571e
+oid sha256:df7181d3d0df1cefbde9b4f27b9a6befb1829d14cf4804145fd0367ebbf9f1a9
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c5f8ae8f35749de87d2bd30935015b688486235dbb0f9456f760d9020e6969
+oid sha256:c1e600d3f88008e73276d99a5b1120d15a4881ba5b50d66a82ac22c9b9e451d1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f6a4bc06789ee291aef58cb4310eddbcbfcda6bb9367569ae98777fc564406
+oid sha256:7a5239f249d81d8bfa06ef3de4b500e1ac939798a7dbf67fabb6fdf26f4f0286
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33fc9c99d6c6914158d280cc7ea9921d8a41ab7b750ccff6664687352e5ce95
+oid sha256:4d3fb3c75839ecf6ed308f90b9c2940bd609f26e633ef816e3b4989d2302e7d3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2a7fd3c6d658555e61566a198ddf405855c17c7c224c221ab28f490366dfaf
+oid sha256:fdd14640f5eeb90ec4e386c79cd20d4ed3e7b6616d7a4070b600d64580c4eace
 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": 1.1935243606567383,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12876227265411236,
+  "best_metric": 1.1413780450820923,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2575245453082247,
   "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": 12.41,
       "eval_steps_per_second": 3.227,
       "step": 25
+    },
+    {
+      "epoch": 0.13391276356027684,
+      "grad_norm": 0.7202064990997314,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4946,
+      "step": 26
+    },
+    {
+      "epoch": 0.13906325446644133,
+      "grad_norm": 0.6264328956604004,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.306,
+      "step": 27
+    },
+    {
+      "epoch": 0.14421374537260584,
+      "grad_norm": 0.6478198766708374,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.3056,
+      "step": 28
+    },
+    {
+      "epoch": 0.14936423627877032,
+      "grad_norm": 0.668978750705719,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3147,
+      "step": 29
+    },
+    {
+      "epoch": 0.1545147271849348,
+      "grad_norm": 0.632352352142334,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1565,
+      "step": 30
+    },
+    {
+      "epoch": 0.15966521809109932,
+      "grad_norm": 0.6676881313323975,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.1182,
+      "step": 31
+    },
+    {
+      "epoch": 0.1648157089972638,
+      "grad_norm": 0.7223697304725647,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0622,
+      "step": 32
+    },
+    {
+      "epoch": 0.1699661999034283,
+      "grad_norm": 0.7997718453407288,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.1029,
+      "step": 33
+    },
+    {
+      "epoch": 0.1751166908095928,
+      "grad_norm": 0.8181374073028564,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0938,
+      "step": 34
+    },
+    {
+      "epoch": 0.18026718171575729,
+      "grad_norm": 0.8765294551849365,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0658,
+      "step": 35
+    },
+    {
+      "epoch": 0.18541767262192177,
+      "grad_norm": 0.9284154772758484,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.9693,
+      "step": 36
+    },
+    {
+      "epoch": 0.19056816352808628,
+      "grad_norm": 1.0015588998794556,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9085,
+      "step": 37
+    },
+    {
+      "epoch": 0.19571865443425077,
+      "grad_norm": 0.6769429445266724,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.431,
+      "step": 38
+    },
+    {
+      "epoch": 0.20086914534041525,
+      "grad_norm": 0.6472747921943665,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3343,
+      "step": 39
+    },
+    {
+      "epoch": 0.20601963624657976,
+      "grad_norm": 0.6668629050254822,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.2378,
+      "step": 40
+    },
+    {
+      "epoch": 0.21117012715274425,
+      "grad_norm": 0.6501740217208862,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2057,
+      "step": 41
+    },
+    {
+      "epoch": 0.21632061805890873,
+      "grad_norm": 0.6348807215690613,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2059,
+      "step": 42
+    },
+    {
+      "epoch": 0.22147110896507324,
+      "grad_norm": 0.6721872687339783,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1817,
+      "step": 43
+    },
+    {
+      "epoch": 0.22662159987123773,
+      "grad_norm": 0.71291184425354,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1455,
+      "step": 44
+    },
+    {
+      "epoch": 0.2317720907774022,
+      "grad_norm": 0.7063342928886414,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1157,
+      "step": 45
+    },
+    {
+      "epoch": 0.23692258168356672,
+      "grad_norm": 0.7762175798416138,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0917,
+      "step": 46
+    },
+    {
+      "epoch": 0.2420730725897312,
+      "grad_norm": 0.8917137384414673,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0488,
+      "step": 47
+    },
+    {
+      "epoch": 0.2472235634958957,
+      "grad_norm": 0.9136678576469421,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9057,
+      "step": 48
+    },
+    {
+      "epoch": 0.2523740544020602,
+      "grad_norm": 1.0555641651153564,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0153,
+      "step": 49
+    },
+    {
+      "epoch": 0.2575245453082247,
+      "grad_norm": 1.1923260688781738,
+      "learning_rate": 1e-05,
+      "loss": 0.8982,
+      "step": 50
+    },
+    {
+      "epoch": 0.2575245453082247,
+      "eval_loss": 1.1413780450820923,
+      "eval_runtime": 4.0246,
+      "eval_samples_per_second": 12.424,
+      "eval_steps_per_second": 3.23,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null