Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b04785217b0f517f8eaeb7b72a483a0f50e137df4af284a5627f4b68467874
+oid sha256:e2351bae8dfb5757471fcee73e661d3915ca04b3e0367f9acd6dea072f74450c
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab290f667cc5fa584ad2b9c98c3f202fdf688c17909738e57524a0a9af4b584
+oid sha256:0b7e567a2ce01c7d5955c2793128baf7946f50ef388850ee8f17c1c29a60eb8f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e62c7fed0c45750f6095e7b5d78669d15ea8467b5a67546793338d939ca97802
+oid sha256:023f2c8bc6c41f887c9afb7c05f5dd2bf86e1f9402a692db8c982f0078e55953
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b49f9f10e639c15431a346c42a0d6d6b909f2da74fddf60c36d0a32d490ea2c
+oid sha256:a0ed5d7c3db643b7438559770ea0e0eca9d26488baef8faf89ef91541d604cf6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f91b8bdc47cf9e8d4b8fead012238416618ba113fe10b0a19de7b006a1b9990d
+oid sha256:f12211d30ed81d99fd9e0851abdbae5212e21943caaceadd4ffa9815e946462a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.398406374501992,
+  "epoch": 0.796812749003984,
   "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": 12.701,
       "eval_steps_per_second": 3.302,
       "step": 25
+    },
+    {
+      "epoch": 0.41434262948207173,
+      "grad_norm": NaN,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.4302788844621514,
+      "grad_norm": NaN,
+      "learning_rate": 7.75e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.44621513944223107,
+      "grad_norm": NaN,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.46215139442231074,
+      "grad_norm": NaN,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.47808764940239046,
+      "grad_norm": NaN,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.4940239043824701,
+      "grad_norm": NaN,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.5099601593625498,
+      "grad_norm": NaN,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.5258964143426295,
+      "grad_norm": NaN,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.5418326693227091,
+      "grad_norm": NaN,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.5577689243027888,
+      "grad_norm": NaN,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.5737051792828686,
+      "grad_norm": NaN,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.5896414342629482,
+      "grad_norm": NaN,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.6055776892430279,
+      "grad_norm": NaN,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.6215139442231076,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.6374501992031872,
+      "grad_norm": NaN,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.6533864541832669,
+      "grad_norm": NaN,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.6693227091633466,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.6852589641434262,
+      "grad_norm": NaN,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.701195219123506,
+      "grad_norm": NaN,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.7171314741035857,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.7330677290836654,
+      "grad_norm": NaN,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.749003984063745,
+      "grad_norm": NaN,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.7649402390438247,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.7808764940239044,
+      "grad_norm": NaN,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.796812749003984,
+      "grad_norm": NaN,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.796812749003984,
+      "eval_loss": NaN,
+      "eval_runtime": 3.8692,
+      "eval_samples_per_second": 12.923,
+      "eval_steps_per_second": 3.36,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null