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:da46f375ade2c8b97bf5e51e18840b5bd07b0af966e7c43b70034cd0f73a1c44
+oid sha256:8ce356f5f5ac23c1f8801a047e1a3b0f62dbeee903da3f4a986498237bcd0dd6
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2262018327f91b121d0333691cc8c74a5f26a77207b2219a19cff7ee228edd8
+oid sha256:0c02b5b86712c906f4e11b61ee10186c4c9422a494316f34e836fc75f5e3d3aa
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc058781cdbb2911c0a08aca3723ec2615b2ee617650513f58264c641fbb821
+oid sha256:aac016cd33d97d492e9a407a37dde267d3258c34e30e14d6c375b0dd17c5d563
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7274938821792603,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012175818823815902,
+  "best_metric": 0.7136901617050171,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024351637647631805,
   "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": 66.39,
       "eval_steps_per_second": 8.311,
       "step": 25
+    },
+    {
+      "epoch": 0.012662851576768538,
+      "grad_norm": 0.6272983551025391,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.8071,
+      "step": 26
+    },
+    {
+      "epoch": 0.013149884329721175,
+      "grad_norm": 0.6493189930915833,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.7136,
+      "step": 27
+    },
+    {
+      "epoch": 0.01363691708267381,
+      "grad_norm": 0.6973922848701477,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.7716,
+      "step": 28
+    },
+    {
+      "epoch": 0.014123949835626447,
+      "grad_norm": 0.6309564709663391,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.7482,
+      "step": 29
+    },
+    {
+      "epoch": 0.014610982588579081,
+      "grad_norm": 0.6153619885444641,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.6542,
+      "step": 30
+    },
+    {
+      "epoch": 0.015098015341531717,
+      "grad_norm": 0.7095900177955627,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.6749,
+      "step": 31
+    },
+    {
+      "epoch": 0.015585048094484353,
+      "grad_norm": 0.635250449180603,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6969,
+      "step": 32
+    },
+    {
+      "epoch": 0.01607208084743699,
+      "grad_norm": 0.682678759098053,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.7622,
+      "step": 33
+    },
+    {
+      "epoch": 0.016559113600389627,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.7362,
+      "step": 34
+    },
+    {
+      "epoch": 0.017046146353342263,
+      "grad_norm": 0.7890238761901855,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8235,
+      "step": 35
+    },
+    {
+      "epoch": 0.0175331791062949,
+      "grad_norm": 0.6336987018585205,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.6591,
+      "step": 36
+    },
+    {
+      "epoch": 0.018020211859247535,
+      "grad_norm": 0.7005982398986816,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.6779,
+      "step": 37
+    },
+    {
+      "epoch": 0.01850724461220017,
+      "grad_norm": 0.7151241898536682,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.7475,
+      "step": 38
+    },
+    {
+      "epoch": 0.018994277365152808,
+      "grad_norm": 0.7008761167526245,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6476,
+      "step": 39
+    },
+    {
+      "epoch": 0.019481310118105444,
+      "grad_norm": 0.6506037712097168,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7245,
+      "step": 40
+    },
+    {
+      "epoch": 0.01996834287105808,
+      "grad_norm": 0.6690606474876404,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6692,
+      "step": 41
+    },
+    {
+      "epoch": 0.020455375624010716,
+      "grad_norm": 0.7103585600852966,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.686,
+      "step": 42
+    },
+    {
+      "epoch": 0.020942408376963352,
+      "grad_norm": 0.764558732509613,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6856,
+      "step": 43
+    },
+    {
+      "epoch": 0.021429441129915988,
+      "grad_norm": 0.7136645317077637,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.6547,
+      "step": 44
+    },
+    {
+      "epoch": 0.021916473882868624,
+      "grad_norm": 0.7253732085227966,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7102,
+      "step": 45
+    },
+    {
+      "epoch": 0.02240350663582126,
+      "grad_norm": 0.75505131483078,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.6675,
+      "step": 46
+    },
+    {
+      "epoch": 0.022890539388773896,
+      "grad_norm": 0.7235407829284668,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6469,
+      "step": 47
+    },
+    {
+      "epoch": 0.023377572141726533,
+      "grad_norm": 0.7759289741516113,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6449,
+      "step": 48
+    },
+    {
+      "epoch": 0.02386460489467917,
+      "grad_norm": 0.872998833656311,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7025,
+      "step": 49
+    },
+    {
+      "epoch": 0.024351637647631805,
+      "grad_norm": 0.9340502619743347,
+      "learning_rate": 0.0,
+      "loss": 0.576,
+      "step": 50
+    },
+    {
+      "epoch": 0.024351637647631805,
+      "eval_loss": 0.7136901617050171,
+      "eval_runtime": 52.1457,
+      "eval_samples_per_second": 66.333,
+      "eval_steps_per_second": 8.304,
+      "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": 1932120607948800.0,
+  "total_flos": 3603404933824512.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null