Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06855456633e9c177d29f38e4e5bfb2575cf426c5849718ece5f77f165f1992a
+oid sha256:dd3fa6236d2749a55242b29421edecb8708766c82311a1e5b1a8ea58b6a63dfb
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05dcaf9f45791df35f64094e645134aefbc736edd01083f4eb874f5d1577a5e1
+oid sha256:709c80b55da27c6e2165d9a6723f9fae8b15783a7f0ea0f8dc21f3a6131d3ecc
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91fa1f8fbb2774bfd631e60ad45cf4647755811e667a8166358d41b8bd9080be
+oid sha256:b5b5a60182ae7ef6ea9dd6e724396b690857d3dc74402c4bc82c2cf6a613b27e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8962831e3d86904d22fc01bcdd178ce3999ff5b8e01b41b9acbc9d41563ee062
+oid sha256:5b62300afa38d4c24732ed51fb2444b35bf8eab6864db1ca5317ccbadd974a49
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20d81d03c937b7bebd71fda38487b74c6be7a2188e43efac1022339b9ad40c7
+oid sha256:4634a9e693d4cf36f6ed8a98c544b75c6f5973d7ca8808e0e514e2e15f8d62b5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:484bb73b000c174cd6ba6bb2cec03f47ec5ceaf47c4a0e2344af0689ea52c253
+oid sha256:dcc538beed0ce114727a1c726c122d079e172dc84fc4de27342fbf6477ec0110
 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": 0.42468079924583435,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.042923060414207535,
+  "best_metric": 0.40812382102012634,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08584612082841507,
   "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": 57.773,
       "eval_steps_per_second": 15.021,
       "step": 25
+    },
+    {
+      "epoch": 0.04463998283077583,
+      "grad_norm": 0.21563903987407684,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.332,
+      "step": 26
+    },
+    {
+      "epoch": 0.046356905247344135,
+      "grad_norm": 0.24940654635429382,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4055,
+      "step": 27
+    },
+    {
+      "epoch": 0.04807382766391244,
+      "grad_norm": 0.25732117891311646,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4137,
+      "step": 28
+    },
+    {
+      "epoch": 0.049790750080480735,
+      "grad_norm": 0.2807253897190094,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4411,
+      "step": 29
+    },
+    {
+      "epoch": 0.05150767249704904,
+      "grad_norm": 0.2723471224308014,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4307,
+      "step": 30
+    },
+    {
+      "epoch": 0.05322459491361734,
+      "grad_norm": 0.27555128931999207,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4244,
+      "step": 31
+    },
+    {
+      "epoch": 0.054941517330185645,
+      "grad_norm": 0.28199151158332825,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.4497,
+      "step": 32
+    },
+    {
+      "epoch": 0.05665843974675394,
+      "grad_norm": 0.2908327579498291,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4427,
+      "step": 33
+    },
+    {
+      "epoch": 0.058375362163322245,
+      "grad_norm": 0.3176117241382599,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4469,
+      "step": 34
+    },
+    {
+      "epoch": 0.06009228457989055,
+      "grad_norm": 0.31177636981010437,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4536,
+      "step": 35
+    },
+    {
+      "epoch": 0.061809206996458844,
+      "grad_norm": 0.3403571844100952,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4703,
+      "step": 36
+    },
+    {
+      "epoch": 0.06352612941302715,
+      "grad_norm": 0.3851555585861206,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4157,
+      "step": 37
+    },
+    {
+      "epoch": 0.06524305182959544,
+      "grad_norm": 0.21249587833881378,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3325,
+      "step": 38
+    },
+    {
+      "epoch": 0.06695997424616375,
+      "grad_norm": 0.2026110589504242,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3721,
+      "step": 39
+    },
+    {
+      "epoch": 0.06867689666273205,
+      "grad_norm": 0.22161202132701874,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4041,
+      "step": 40
+    },
+    {
+      "epoch": 0.07039381907930035,
+      "grad_norm": 0.22970175743103027,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3862,
+      "step": 41
+    },
+    {
+      "epoch": 0.07211074149586866,
+      "grad_norm": 0.24665836989879608,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4327,
+      "step": 42
+    },
+    {
+      "epoch": 0.07382766391243696,
+      "grad_norm": 0.2487974464893341,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4008,
+      "step": 43
+    },
+    {
+      "epoch": 0.07554458632900526,
+      "grad_norm": 0.2714938819408417,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4436,
+      "step": 44
+    },
+    {
+      "epoch": 0.07726150874557355,
+      "grad_norm": 0.27039292454719543,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4286,
+      "step": 45
+    },
+    {
+      "epoch": 0.07897843116214186,
+      "grad_norm": 0.280936598777771,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4681,
+      "step": 46
+    },
+    {
+      "epoch": 0.08069535357871016,
+      "grad_norm": 0.2817816138267517,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4288,
+      "step": 47
+    },
+    {
+      "epoch": 0.08241227599527846,
+      "grad_norm": 0.3105645775794983,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4546,
+      "step": 48
+    },
+    {
+      "epoch": 0.08412919841184677,
+      "grad_norm": 0.34473907947540283,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4575,
+      "step": 49
+    },
+    {
+      "epoch": 0.08584612082841507,
+      "grad_norm": 0.4184184968471527,
+      "learning_rate": 1e-05,
+      "loss": 0.4269,
+      "step": 50
+    },
+    {
+      "epoch": 0.08584612082841507,
+      "eval_loss": 0.40812382102012634,
+      "eval_runtime": 0.8579,
+      "eval_samples_per_second": 58.279,
+      "eval_steps_per_second": 15.153,
+      "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": 7.952285976808653e+16,
+  "total_flos": 1.5899604877626573e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null