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:f1fee6e026d69a438a8775d4608a7d9fec9f3895df33f1e12ebfe564ea48fc9e
+oid sha256:1bde133623b07cf2b9a3ce54a4dc3994fcdf7740c4b187e3a151c7492aaeec83
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fbb37f35a70bcf06120f7c4914ad88d8b4f3701ed199821dca293e658474c3d
+oid sha256:bcd48af96a2600e592634d6033b1eb5bf823524b103ad8c27b4fbdd12a44a809
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566a097eb69dce3be7c5da664499707e467414cc00fc4288f55a799615bedddf
+oid sha256:60192d46ff7680294c9aa94702590cf7bca760635839dbd8ff89ed30a9766708
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b20ec5a1cdcf914400996f1e5c42ff1f759ea15cb1828c8f28126518c6208c
+oid sha256:6662348f34c7614581ffe4e030fbe21fa0fcee507bdf17aa8bbd912eb05d05f2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2f6d1e29a35b1def3575b0036004742f19ad8d6d8d3940960d753fb985ef9d
+oid sha256:c3e333ed59f5eca6dfa6219a5aa28d1d2b80e515510b2519d45b03ca28915736
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f92bad9a911710d4eb57af4df3997e017b545368c8ba50469ccdccce7e9310
+oid sha256:fa04f09f11040da15badf5db4550f814da645fa94f912d0572ebae2f9eed0d88
 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": 0.5217246413230896,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6779661016949152,
+  "best_metric": 0.4297037422657013,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.3686440677966103,
   "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": 16.5,
       "eval_steps_per_second": 4.29,
       "step": 25
+    },
+    {
+      "epoch": 0.7050847457627119,
+      "grad_norm": 2.0804121494293213,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4793,
+      "step": 26
+    },
+    {
+      "epoch": 0.7322033898305085,
+      "grad_norm": 2.41282057762146,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4887,
+      "step": 27
+    },
+    {
+      "epoch": 0.7593220338983051,
+      "grad_norm": 1.6098804473876953,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4879,
+      "step": 28
+    },
+    {
+      "epoch": 0.7864406779661017,
+      "grad_norm": 1.7615506649017334,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4757,
+      "step": 29
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 1.765375018119812,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4545,
+      "step": 30
+    },
+    {
+      "epoch": 0.8406779661016949,
+      "grad_norm": 1.167455792427063,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4685,
+      "step": 31
+    },
+    {
+      "epoch": 0.8677966101694915,
+      "grad_norm": 1.3772835731506348,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.458,
+      "step": 32
+    },
+    {
+      "epoch": 0.8949152542372881,
+      "grad_norm": 1.6152493953704834,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4649,
+      "step": 33
+    },
+    {
+      "epoch": 0.9220338983050848,
+      "grad_norm": 1.2044497728347778,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4376,
+      "step": 34
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 1.3679577112197876,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4165,
+      "step": 35
+    },
+    {
+      "epoch": 0.976271186440678,
+      "grad_norm": 1.4477646350860596,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4905,
+      "step": 36
+    },
+    {
+      "epoch": 1.0161016949152541,
+      "grad_norm": 3.4008398056030273,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6072,
+      "step": 37
+    },
+    {
+      "epoch": 1.0432203389830508,
+      "grad_norm": 1.8189399242401123,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3882,
+      "step": 38
+    },
+    {
+      "epoch": 1.0703389830508474,
+      "grad_norm": 0.9250749349594116,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3339,
+      "step": 39
+    },
+    {
+      "epoch": 1.097457627118644,
+      "grad_norm": 1.2397493124008179,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4049,
+      "step": 40
+    },
+    {
+      "epoch": 1.1245762711864407,
+      "grad_norm": 1.5129092931747437,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3999,
+      "step": 41
+    },
+    {
+      "epoch": 1.1516949152542373,
+      "grad_norm": 1.52627432346344,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3978,
+      "step": 42
+    },
+    {
+      "epoch": 1.178813559322034,
+      "grad_norm": 1.3015371561050415,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.378,
+      "step": 43
+    },
+    {
+      "epoch": 1.2059322033898305,
+      "grad_norm": 1.3487688302993774,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4213,
+      "step": 44
+    },
+    {
+      "epoch": 1.2330508474576272,
+      "grad_norm": 1.26216721534729,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3905,
+      "step": 45
+    },
+    {
+      "epoch": 1.2601694915254238,
+      "grad_norm": 1.045103669166565,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3698,
+      "step": 46
+    },
+    {
+      "epoch": 1.2872881355932204,
+      "grad_norm": 1.2951055765151978,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3458,
+      "step": 47
+    },
+    {
+      "epoch": 1.314406779661017,
+      "grad_norm": 1.3998348712921143,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3566,
+      "step": 48
+    },
+    {
+      "epoch": 1.3415254237288137,
+      "grad_norm": 1.8256560564041138,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3871,
+      "step": 49
+    },
+    {
+      "epoch": 1.3686440677966103,
+      "grad_norm": 1.4336544275283813,
+      "learning_rate": 1e-05,
+      "loss": 0.3851,
+      "step": 50
+    },
+    {
+      "epoch": 1.3686440677966103,
+      "eval_loss": 0.4297037422657013,
+      "eval_runtime": 3.0435,
+      "eval_samples_per_second": 16.429,
+      "eval_steps_per_second": 4.271,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null