Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45eb67cca401cd880ba8f7599fd495bc6488d8e3b0ecda6bfb7e182ef03da160
+oid sha256:1ff5cc3ae399fefc1110d323606ecb9af7962208f6abca1295850037b02b90a5
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d328e611719dc3d3552a08679fd47a4fa2dd7d9b7d30e71c1bd48bf68e1866d
+oid sha256:47ff57924e38839fb018b3d36a2f32d333b14357a38b99f41a1e46b1b217b834
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a9f0f6b06bdb03679013cabd3ff606b9358930c8ef7fe23fb3ec158757136b
+oid sha256:c633aeb3011451011a249d8429bbbecb3479c7347d3c252fed64fdf3f2447ec6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5255b828f04373e983195f2c2247c657dcb988e4a0e2cc5e37686fd38b02ea06
+oid sha256:4a030d69f2541ccf0282aac57e9119ce218940b96b68f8911a4178dcbeb4a4aa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3fee161a8750ce4baf5279a67d48eb977a122808051700aaf0bbd8b5e9f13ff
+oid sha256:e2f28f5e0c1d18008cb58e4b5cbd33191762f413e0604d766eacb114f085d3f5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3177ea4b394d20689f047a52c65a4c736ff1c10b2534d22548525087dc2bae5a
+oid sha256:69229c49401e88b3b3378c31d82dab5bb5c4af56b04c5c6fd06f1abbc7474757
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6666666666666665,
+  "epoch": 3.0,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,146 @@
       "eval_samples_per_second": 11.785,
       "eval_steps_per_second": 3.064,
       "step": 25
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 4.682634170592537e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": NaN,
+      "learning_rate": 4.3617997792374365e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 4.0470381785284936e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 3.7400287577942993e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": NaN,
+      "learning_rate": 3.4424095451291274e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 3.155768467804314e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 2.8816348799892133e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": NaN,
+      "learning_rate": 2.621471402984991e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 2.3766661215071475e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": NaN,
+      "learning_rate": 2.148525177652982e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": NaN,
+      "learning_rate": 1.938265802068357e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 1.74700981949555e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 1.5757776633528655e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": NaN,
+      "learning_rate": 1.4254829312808404e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": NaN,
+      "learning_rate": 1.2969275107035345e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 1.1907973004121738e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": NaN,
+      "learning_rate": 1.1076585509983283e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 1.0479548436620041e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": NaN,
+      "learning_rate": 1.0120047235140178e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -221,12 +361,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.9961644719629926e+17,
+  "total_flos": 5.39365555707052e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null