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:b4b3a5725e60b4de31d09429825fcd4dfbf32df51d77d6bd7fd52f704979c381
+oid sha256:796142ce89c046553166cf4f88f0d947a04a8deee7c4be4695737c1e6bc974bc
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a561d82c3bf97236581c7ac5686699646a5fcb552718cb4ff50770807c297b96
+oid sha256:626613c76ee39915bec337d3a679c4bd774395d26f8b564edb74472cfb76269f
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ac55528709926f8dd4ad1a0da9a9ad2289c80dcd2d7b309a087574929d907d
+oid sha256:573305967544fc0b3cef699d2e87f477f38b2b054ad46dd8780aa87b41467d5f
 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": 1.450131893157959,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08576329331046312,
+  "best_metric": 1.4005824327468872,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.17152658662092624,
   "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": 91.868,
       "eval_steps_per_second": 11.6,
       "step": 25
+    },
+    {
+      "epoch": 0.08919382504288165,
+      "grad_norm": 0.20282359421253204,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.4278,
+      "step": 26
+    },
+    {
+      "epoch": 0.09262435677530018,
+      "grad_norm": 0.21370434761047363,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.4757,
+      "step": 27
+    },
+    {
+      "epoch": 0.09605488850771869,
+      "grad_norm": 0.23179413378238678,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.454,
+      "step": 28
+    },
+    {
+      "epoch": 0.09948542024013722,
+      "grad_norm": 0.20548944175243378,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4483,
+      "step": 29
+    },
+    {
+      "epoch": 0.10291595197255575,
+      "grad_norm": 0.2094879001379013,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.4118,
+      "step": 30
+    },
+    {
+      "epoch": 0.10634648370497427,
+      "grad_norm": 0.21441254019737244,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.4775,
+      "step": 31
+    },
+    {
+      "epoch": 0.1097770154373928,
+      "grad_norm": 0.20647598803043365,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3529,
+      "step": 32
+    },
+    {
+      "epoch": 0.11320754716981132,
+      "grad_norm": 0.2284150868654251,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.3661,
+      "step": 33
+    },
+    {
+      "epoch": 0.11663807890222985,
+      "grad_norm": 0.22950738668441772,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.3721,
+      "step": 34
+    },
+    {
+      "epoch": 0.12006861063464837,
+      "grad_norm": 0.24025064706802368,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3951,
+      "step": 35
+    },
+    {
+      "epoch": 0.1234991423670669,
+      "grad_norm": 0.2534557580947876,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.4142,
+      "step": 36
+    },
+    {
+      "epoch": 0.1269296740994854,
+      "grad_norm": 0.23205174505710602,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.4247,
+      "step": 37
+    },
+    {
+      "epoch": 0.13036020583190394,
+      "grad_norm": 0.23094086349010468,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4081,
+      "step": 38
+    },
+    {
+      "epoch": 0.13379073756432247,
+      "grad_norm": 0.24359112977981567,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.432,
+      "step": 39
+    },
+    {
+      "epoch": 0.137221269296741,
+      "grad_norm": 0.25243625044822693,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4048,
+      "step": 40
+    },
+    {
+      "epoch": 0.14065180102915953,
+      "grad_norm": 0.27146971225738525,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.438,
+      "step": 41
+    },
+    {
+      "epoch": 0.14408233276157806,
+      "grad_norm": 0.26898500323295593,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4197,
+      "step": 42
+    },
+    {
+      "epoch": 0.14751286449399656,
+      "grad_norm": 0.2611740231513977,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4379,
+      "step": 43
+    },
+    {
+      "epoch": 0.1509433962264151,
+      "grad_norm": 0.2807406485080719,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4284,
+      "step": 44
+    },
+    {
+      "epoch": 0.15437392795883362,
+      "grad_norm": 0.2983769178390503,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.397,
+      "step": 45
+    },
+    {
+      "epoch": 0.15780445969125215,
+      "grad_norm": 0.29316747188568115,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4727,
+      "step": 46
+    },
+    {
+      "epoch": 0.16123499142367068,
+      "grad_norm": 0.30776265263557434,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5411,
+      "step": 47
+    },
+    {
+      "epoch": 0.1646655231560892,
+      "grad_norm": 0.3639960289001465,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.4666,
+      "step": 48
+    },
+    {
+      "epoch": 0.1680960548885077,
+      "grad_norm": 0.3686543405056,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4686,
+      "step": 49
+    },
+    {
+      "epoch": 0.17152658662092624,
+      "grad_norm": 0.4303509593009949,
+      "learning_rate": 0.0,
+      "loss": 1.4826,
+      "step": 50
+    },
+    {
+      "epoch": 0.17152658662092624,
+      "eval_loss": 1.4005824327468872,
+      "eval_runtime": 5.282,
+      "eval_samples_per_second": 92.958,
+      "eval_steps_per_second": 11.738,
+      "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": 1348017609768960.0,
+  "total_flos": 2206627552296960.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null