Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922da36b842124de3eb9e375f22e1b003d3718de1d1a238368b93ad59dff4975
+oid sha256:9eebd580b914ef2cfb39cd442c0ac29721862bd9546a9e1469f6ba87e5904de3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f70abbc6da3dee4d41b9020b8acca82df530748073512e535afa1a8faf1c792
+oid sha256:b3b56714d7488507b9193156497f672b57afb02518fdb35aa925ffc7a2e40375
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd21880966cccdd2052ff078d28cfc1250e11736878bcfc1efab4d384ab0abf9
+oid sha256:d6c4f649546a1ce505561ddfdb31c524a503f333d66811633631217add713d13
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bdc1680e75e7cf9661cc84482edc217f841c56aca5f9a3979c1c72a436f392
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.35070064663887024,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.001508667293601742,
+  "best_metric": 0.3503866195678711,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.0020115563914689895,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 3.508,
       "eval_steps_per_second": 1.754,
       "step": 75
+    },
+    {
+      "epoch": 0.001528782857516432,
+      "grad_norm": 0.6691503524780273,
+      "learning_rate": 2.9876321572751144e-05,
+      "loss": 0.1867,
+      "step": 76
+    },
+    {
+      "epoch": 0.0015488984214311217,
+      "grad_norm": 1.2199984788894653,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 0.2102,
+      "step": 77
+    },
+    {
+      "epoch": 0.0015690139853458116,
+      "grad_norm": 0.6254073977470398,
+      "learning_rate": 2.5317852301584643e-05,
+      "loss": 0.1688,
+      "step": 78
+    },
+    {
+      "epoch": 0.0015891295492605016,
+      "grad_norm": 0.7005298137664795,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 0.1579,
+      "step": 79
+    },
+    {
+      "epoch": 0.0016092451131751915,
+      "grad_norm": 0.359977662563324,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 0.0562,
+      "step": 80
+    },
+    {
+      "epoch": 0.0016293606770898814,
+      "grad_norm": 1.038337230682373,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.1723,
+      "step": 81
+    },
+    {
+      "epoch": 0.0016494762410045713,
+      "grad_norm": 0.537745475769043,
+      "learning_rate": 1.7199116885197995e-05,
+      "loss": 0.0839,
+      "step": 82
+    },
+    {
+      "epoch": 0.0016695918049192612,
+      "grad_norm": 0.7610992789268494,
+      "learning_rate": 1.5390474757906446e-05,
+      "loss": 0.1321,
+      "step": 83
+    },
+    {
+      "epoch": 0.0016897073688339512,
+      "grad_norm": 0.8755677342414856,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 0.158,
+      "step": 84
+    },
+    {
+      "epoch": 0.0017098229327486409,
+      "grad_norm": 1.5665292739868164,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 0.3811,
+      "step": 85
+    },
+    {
+      "epoch": 0.0017299384966633308,
+      "grad_norm": 0.665432333946228,
+      "learning_rate": 1.0527067017923654e-05,
+      "loss": 0.1981,
+      "step": 86
+    },
+    {
+      "epoch": 0.0017500540605780207,
+      "grad_norm": 0.6402338147163391,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 0.1776,
+      "step": 87
+    },
+    {
+      "epoch": 0.0017701696244927106,
+      "grad_norm": 1.7284150123596191,
+      "learning_rate": 7.771024502261526e-06,
+      "loss": 0.4189,
+      "step": 88
+    },
+    {
+      "epoch": 0.0017902851884074005,
+      "grad_norm": 0.9359285831451416,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 0.1095,
+      "step": 89
+    },
+    {
+      "epoch": 0.0018104007523220905,
+      "grad_norm": 0.8026375770568848,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 0.1492,
+      "step": 90
+    },
+    {
+      "epoch": 0.0018305163162367804,
+      "grad_norm": 2.1033782958984375,
+      "learning_rate": 4.3964218465642355e-06,
+      "loss": 0.4742,
+      "step": 91
+    },
+    {
+      "epoch": 0.0018506318801514703,
+      "grad_norm": 3.3076441287994385,
+      "learning_rate": 3.4791089722651436e-06,
+      "loss": 0.4197,
+      "step": 92
+    },
+    {
+      "epoch": 0.00187074744406616,
+      "grad_norm": 2.0006370544433594,
+      "learning_rate": 2.667340275199426e-06,
+      "loss": 0.5587,
+      "step": 93
+    },
+    {
+      "epoch": 0.00189086300798085,
+      "grad_norm": 1.3604930639266968,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 0.4432,
+      "step": 94
+    },
+    {
+      "epoch": 0.0019109785718955398,
+      "grad_norm": 1.7596443891525269,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.4846,
+      "step": 95
+    },
+    {
+      "epoch": 0.0019310941358102298,
+      "grad_norm": 2.329746723175049,
+      "learning_rate": 8.735930673024806e-07,
+      "loss": 0.6485,
+      "step": 96
+    },
+    {
+      "epoch": 0.0019512096997249197,
+      "grad_norm": 1.9191521406173706,
+      "learning_rate": 4.917097454988584e-07,
+      "loss": 0.2235,
+      "step": 97
+    },
+    {
+      "epoch": 0.0019713252636396096,
+      "grad_norm": 2.7021889686584473,
+      "learning_rate": 2.1863727812254653e-07,
+      "loss": 0.7207,
+      "step": 98
+    },
+    {
+      "epoch": 0.0019914408275542995,
+      "grad_norm": 2.9134979248046875,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 0.8107,
+      "step": 99
+    },
+    {
+      "epoch": 0.0020115563914689895,
+      "grad_norm": 1.8843333721160889,
+      "learning_rate": 0.0,
+      "loss": 0.4125,
+      "step": 100
+    },
+    {
+      "epoch": 0.0020115563914689895,
+      "eval_loss": 0.3503866195678711,
+      "eval_runtime": 5962.3258,
+      "eval_samples_per_second": 3.511,
+      "eval_steps_per_second": 1.755,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1165403617584742e+17,
+  "total_flos": 1.4874840035386982e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null