Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aff9f85c78bb1313f336acceb889e423988a7f7072a130b0058ca32fe3d8b7e
+oid sha256:033a56672257d2be9832c051692dceff2c6d86f9f750ee15caf028d3fc5c8e46
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327f8ff05f44a5c27b46e17d2f7c8d50f0601064dfc227bf796e76279cbbd110
+oid sha256:bceccf0f4e7a110d3c1a475939ca486c219f9b25efa001b83a99effe160cb078
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec215d0987b1599ddea0e5ceb4db8ca5f9c0d15cd4e11b1960d198226c2ce7f9
+oid sha256:d07d049760a64bae661bec26d42023972279de934b92a5245705ca10929c862f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffa785c34328f04c63665117ecc37ec357550e2261e2b06954d6932effb26455
+oid sha256:119dcdd5e62603ae96a3f194bba585af70ccf458e1bfcca04489c86625cf5102
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253aba309d4a808b07a88b5a50d70a7aec3382e480ffe9b5bf2dd59edcf1920d
+oid sha256:0df9bf94b7676e5f66f77bb275750b3b7ab89a563abffde5ac332e98cf80df8e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22dfeb079f604599def1042937a6a9bcc4b5d9f374df0bd33600df6a6a702f06
+oid sha256:a01e50e322fec9d738d53421bb50e8bc3b5daabb4124dc74f2e4f5da50ecccdf
 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": 1.452702283859253,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.47961630695443647,
+  "best_metric": 1.4119333028793335,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.9592326139088729,
   "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": 16.283,
       "eval_steps_per_second": 4.234,
       "step": 25
+    },
+    {
+      "epoch": 0.4988009592326139,
+      "grad_norm": 0.3837337791919708,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4694,
+      "step": 26
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 0.31981226801872253,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.4007,
+      "step": 27
+    },
+    {
+      "epoch": 0.5371702637889688,
+      "grad_norm": 0.29301542043685913,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.425,
+      "step": 28
+    },
+    {
+      "epoch": 0.5563549160671463,
+      "grad_norm": 0.27098387479782104,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3783,
+      "step": 29
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.2766132652759552,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3708,
+      "step": 30
+    },
+    {
+      "epoch": 0.5947242206235012,
+      "grad_norm": 0.2871565520763397,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.3912,
+      "step": 31
+    },
+    {
+      "epoch": 0.6139088729016786,
+      "grad_norm": 0.2908610701560974,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3315,
+      "step": 32
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 0.332882285118103,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.2766,
+      "step": 33
+    },
+    {
+      "epoch": 0.6522781774580336,
+      "grad_norm": 0.2988963723182678,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.3176,
+      "step": 34
+    },
+    {
+      "epoch": 0.6714628297362111,
+      "grad_norm": 0.32519230246543884,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.3037,
+      "step": 35
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 0.33219724893569946,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.3243,
+      "step": 36
+    },
+    {
+      "epoch": 0.709832134292566,
+      "grad_norm": 0.36349430680274963,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.3258,
+      "step": 37
+    },
+    {
+      "epoch": 0.7290167865707434,
+      "grad_norm": 0.3923780918121338,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4683,
+      "step": 38
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 0.45209190249443054,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4447,
+      "step": 39
+    },
+    {
+      "epoch": 0.7673860911270983,
+      "grad_norm": 0.44667184352874756,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.3867,
+      "step": 40
+    },
+    {
+      "epoch": 0.7865707434052758,
+      "grad_norm": 0.4654199182987213,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3885,
+      "step": 41
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 0.4635009169578552,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3306,
+      "step": 42
+    },
+    {
+      "epoch": 0.8249400479616307,
+      "grad_norm": 0.3623160719871521,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.3448,
+      "step": 43
+    },
+    {
+      "epoch": 0.8441247002398081,
+      "grad_norm": 0.2907363176345825,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2858,
+      "step": 44
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.2541451156139374,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.3097,
+      "step": 45
+    },
+    {
+      "epoch": 0.882494004796163,
+      "grad_norm": 0.25829795002937317,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.3359,
+      "step": 46
+    },
+    {
+      "epoch": 0.9016786570743405,
+      "grad_norm": 0.27368149161338806,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.2904,
+      "step": 47
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 0.3009626567363739,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.3405,
+      "step": 48
+    },
+    {
+      "epoch": 0.9400479616306955,
+      "grad_norm": 0.34668755531311035,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.3204,
+      "step": 49
+    },
+    {
+      "epoch": 0.9592326139088729,
+      "grad_norm": 0.4955449104309082,
+      "learning_rate": 1e-05,
+      "loss": 1.3941,
+      "step": 50
+    },
+    {
+      "epoch": 0.9592326139088729,
+      "eval_loss": 1.4119333028793335,
+      "eval_runtime": 2.9994,
+      "eval_samples_per_second": 16.67,
+      "eval_steps_per_second": 4.334,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null