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:ef8e33c2e8e8a12577f5317b8d3ba1a3fc5b493bafcf2f991c95bb813de09966
+oid sha256:391a0643a69cb890a0166d29f58893739e47e3bf31b07995d44787fe2f4f7562
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7145692b66ffbc88f26fcd36d9a178bcb566c1ba1f622682f95068bde7decacd
+oid sha256:6d85079468b080fa5af9ff4b965fa003f031da62cdb7d7667f0ebfcc3f8b94bd
 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": 0.7276486754417419,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012175818823815902,
+  "best_metric": 0.7137496471405029,
+  "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": 66.365,
       "eval_steps_per_second": 8.308,
       "step": 25
+    },
+    {
+      "epoch": 0.012662851576768538,
+      "grad_norm": 0.6263149976730347,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.8059,
+      "step": 26
+    },
+    {
+      "epoch": 0.013149884329721175,
+      "grad_norm": 0.649336576461792,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.714,
+      "step": 27
+    },
+    {
+      "epoch": 0.01363691708267381,
+      "grad_norm": 0.6983732581138611,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.7714,
+      "step": 28
+    },
+    {
+      "epoch": 0.014123949835626447,
+      "grad_norm": 0.6310800909996033,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.7492,
+      "step": 29
+    },
+    {
+      "epoch": 0.014610982588579081,
+      "grad_norm": 0.6215700507164001,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.6541,
+      "step": 30
+    },
+    {
+      "epoch": 0.015098015341531717,
+      "grad_norm": 0.7055749893188477,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.6742,
+      "step": 31
+    },
+    {
+      "epoch": 0.015585048094484353,
+      "grad_norm": 0.634620189666748,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6968,
+      "step": 32
+    },
+    {
+      "epoch": 0.01607208084743699,
+      "grad_norm": 0.6823827028274536,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.7632,
+      "step": 33
+    },
+    {
+      "epoch": 0.016559113600389627,
+      "grad_norm": 0.6950632929801941,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.7368,
+      "step": 34
+    },
+    {
+      "epoch": 0.017046146353342263,
+      "grad_norm": 0.7879264950752258,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8233,
+      "step": 35
+    },
+    {
+      "epoch": 0.0175331791062949,
+      "grad_norm": 0.6341107487678528,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.6603,
+      "step": 36
+    },
+    {
+      "epoch": 0.018020211859247535,
+      "grad_norm": 0.6985974311828613,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.6774,
+      "step": 37
+    },
+    {
+      "epoch": 0.01850724461220017,
+      "grad_norm": 0.7165974378585815,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.7472,
+      "step": 38
+    },
+    {
+      "epoch": 0.018994277365152808,
+      "grad_norm": 0.7006275057792664,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6472,
+      "step": 39
+    },
+    {
+      "epoch": 0.019481310118105444,
+      "grad_norm": 0.6504078507423401,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7263,
+      "step": 40
+    },
+    {
+      "epoch": 0.01996834287105808,
+      "grad_norm": 0.6661069989204407,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6685,
+      "step": 41
+    },
+    {
+      "epoch": 0.020455375624010716,
+      "grad_norm": 0.7080692648887634,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6859,
+      "step": 42
+    },
+    {
+      "epoch": 0.020942408376963352,
+      "grad_norm": 0.7681254744529724,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6853,
+      "step": 43
+    },
+    {
+      "epoch": 0.021429441129915988,
+      "grad_norm": 0.7165603637695312,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.6546,
+      "step": 44
+    },
+    {
+      "epoch": 0.021916473882868624,
+      "grad_norm": 0.7238483428955078,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7094,
+      "step": 45
+    },
+    {
+      "epoch": 0.02240350663582126,
+      "grad_norm": 0.7569670677185059,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.669,
+      "step": 46
+    },
+    {
+      "epoch": 0.022890539388773896,
+      "grad_norm": 0.7207056879997253,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6464,
+      "step": 47
+    },
+    {
+      "epoch": 0.023377572141726533,
+      "grad_norm": 0.7816201448440552,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6456,
+      "step": 48
+    },
+    {
+      "epoch": 0.02386460489467917,
+      "grad_norm": 0.8748300671577454,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7031,
+      "step": 49
+    },
+    {
+      "epoch": 0.024351637647631805,
+      "grad_norm": 0.933390200138092,
+      "learning_rate": 0.0,
+      "loss": 0.5756,
+      "step": 50
+    },
+    {
+      "epoch": 0.024351637647631805,
+      "eval_loss": 0.7137496471405029,
+      "eval_runtime": 52.1712,
+      "eval_samples_per_second": 66.301,
+      "eval_steps_per_second": 8.3,
+      "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