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:d65b7fb54ea7389ee0a244c0e3f33262bef0c1391ec305517d5176a921a7f993
+oid sha256:9e235caf1fc39690d2653f8d542d2461306f2064d976c9a8c78a83a5152887be
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad52547d4520e12cd09a39227a667c02654c20bfc4489c12f829a082aa5ef75
+oid sha256:a4a6a893c39c365b1881cb949f8c6e9b95be639774db878aef5e1b42503fdc2d
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd7995a90728beba6b3a5ba4effd49bb270260c6aefb26dc9bacc9796fec4ee
+oid sha256:508553257e217165a214c0be92b028528283e5b951b31a736b90480478135cb2
 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": 0.34874510765075684,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.001508667293601742,
+  "best_metric": 0.34765490889549255,
+  "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": 2.856,
       "eval_steps_per_second": 1.428,
       "step": 75
+    },
+    {
+      "epoch": 0.001528782857516432,
+      "grad_norm": 0.7186751365661621,
+      "learning_rate": 2.9876321572751144e-05,
+      "loss": 0.1929,
+      "step": 76
+    },
+    {
+      "epoch": 0.0015488984214311217,
+      "grad_norm": 0.8120232224464417,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 0.1906,
+      "step": 77
+    },
+    {
+      "epoch": 0.0015690139853458116,
+      "grad_norm": 0.5622069835662842,
+      "learning_rate": 2.5317852301584643e-05,
+      "loss": 0.158,
+      "step": 78
+    },
+    {
+      "epoch": 0.0015891295492605016,
+      "grad_norm": 0.6373627185821533,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 0.158,
+      "step": 79
+    },
+    {
+      "epoch": 0.0016092451131751915,
+      "grad_norm": 0.3394858241081238,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 0.0549,
+      "step": 80
+    },
+    {
+      "epoch": 0.0016293606770898814,
+      "grad_norm": 0.9142265915870667,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.1498,
+      "step": 81
+    },
+    {
+      "epoch": 0.0016494762410045713,
+      "grad_norm": 0.5488215088844299,
+      "learning_rate": 1.7199116885197995e-05,
+      "loss": 0.086,
+      "step": 82
+    },
+    {
+      "epoch": 0.0016695918049192612,
+      "grad_norm": 0.6231745481491089,
+      "learning_rate": 1.5390474757906446e-05,
+      "loss": 0.1239,
+      "step": 83
+    },
+    {
+      "epoch": 0.0016897073688339512,
+      "grad_norm": 0.7093625664710999,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 0.1512,
+      "step": 84
+    },
+    {
+      "epoch": 0.0017098229327486409,
+      "grad_norm": 1.516791820526123,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 0.3605,
+      "step": 85
+    },
+    {
+      "epoch": 0.0017299384966633308,
+      "grad_norm": 0.8480135202407837,
+      "learning_rate": 1.0527067017923654e-05,
+      "loss": 0.2031,
+      "step": 86
+    },
+    {
+      "epoch": 0.0017500540605780207,
+      "grad_norm": 0.6130940318107605,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 0.1745,
+      "step": 87
+    },
+    {
+      "epoch": 0.0017701696244927106,
+      "grad_norm": 1.8014602661132812,
+      "learning_rate": 7.771024502261526e-06,
+      "loss": 0.4315,
+      "step": 88
+    },
+    {
+      "epoch": 0.0017902851884074005,
+      "grad_norm": 0.6862621307373047,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 0.1008,
+      "step": 89
+    },
+    {
+      "epoch": 0.0018104007523220905,
+      "grad_norm": 0.6760240197181702,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 0.1387,
+      "step": 90
+    },
+    {
+      "epoch": 0.0018305163162367804,
+      "grad_norm": 2.04972767829895,
+      "learning_rate": 4.3964218465642355e-06,
+      "loss": 0.4774,
+      "step": 91
+    },
+    {
+      "epoch": 0.0018506318801514703,
+      "grad_norm": 3.159485101699829,
+      "learning_rate": 3.4791089722651436e-06,
+      "loss": 0.4218,
+      "step": 92
+    },
+    {
+      "epoch": 0.00187074744406616,
+      "grad_norm": 2.143138885498047,
+      "learning_rate": 2.667340275199426e-06,
+      "loss": 0.556,
+      "step": 93
+    },
+    {
+      "epoch": 0.00189086300798085,
+      "grad_norm": 1.6069244146347046,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 0.4657,
+      "step": 94
+    },
+    {
+      "epoch": 0.0019109785718955398,
+      "grad_norm": 1.5652406215667725,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.4702,
+      "step": 95
+    },
+    {
+      "epoch": 0.0019310941358102298,
+      "grad_norm": 2.650838613510132,
+      "learning_rate": 8.735930673024806e-07,
+      "loss": 0.6213,
+      "step": 96
+    },
+    {
+      "epoch": 0.0019512096997249197,
+      "grad_norm": 0.9253861904144287,
+      "learning_rate": 4.917097454988584e-07,
+      "loss": 0.2009,
+      "step": 97
+    },
+    {
+      "epoch": 0.0019713252636396096,
+      "grad_norm": 2.9420182704925537,
+      "learning_rate": 2.1863727812254653e-07,
+      "loss": 0.6738,
+      "step": 98
+    },
+    {
+      "epoch": 0.0019914408275542995,
+      "grad_norm": 3.0107245445251465,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 0.8191,
+      "step": 99
+    },
+    {
+      "epoch": 0.0020115563914689895,
+      "grad_norm": 1.9796432256698608,
+      "learning_rate": 0.0,
+      "loss": 0.4038,
+      "step": 100
+    },
+    {
+      "epoch": 0.0020115563914689895,
+      "eval_loss": 0.34765490889549255,
+      "eval_runtime": 7329.2018,
+      "eval_samples_per_second": 2.856,
+      "eval_steps_per_second": 1.428,
+      "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