Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967f972196c65bba4175494ae6cbdab47a0e6423bedce7fdc5e5d7e813a1c768
+oid sha256:9cc75082c70e3374dee2e9501e882c2843ae15dd6858888d284f7aa4fe3d71b1
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc921be75d08ee70cf0531df83ec47ba279925100d60be9816f8e0e8b1828a0c
+oid sha256:029cc6ef760bc80ae426e7ad1676e41e96ba9942926ca3046625387a309491d9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b3fe0e6f9fe9fe286aa82b317c9cf8caf44aadc683dd39a9a8050e8a6b47b5
+oid sha256:315aa11a236cce47edd479297a8424b02f34592203ba9ca57d01846a5cb106c0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f41dd1d40df7c06672b0b8167c2acfdbe12ba3ba9b7d20e39d7e1c6cfec8ee11
+oid sha256:6a03709708d053864803de356052cc74bfa70a73a58b017f97b47c5214e8349f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d062e9758330030b95b1f24ffd221a6b95b7a3cdb9d9e36b9c14a6019b2e93
+oid sha256:83aaa8f6c4c54abc85d230d33269035166ca93bd70954ecc682ffc724fcff39b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8f887dea281aeb8b377e1d457e92d779e03bdeb444157dcb6bebc2102b6b8e
+oid sha256:74b96f38471b652cb3f8b3240c6bde11e0750255d932514273ee65240eb02d6c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.034928848641656,
+  "epoch": 2.069857697283312,
   "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": 16.053,
       "eval_steps_per_second": 4.174,
       "step": 25
+    },
+    {
+      "epoch": 1.076326002587322,
+      "grad_norm": NaN,
+      "learning_rate": 7.692277797823585e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.1177231565329884,
+      "grad_norm": NaN,
+      "learning_rate": 7.516300527944104e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.1591203104786545,
+      "grad_norm": NaN,
+      "learning_rate": 7.336376255095591e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.2005174644243208,
+      "grad_norm": NaN,
+      "learning_rate": 7.152857189491406e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.2419146183699872,
+      "grad_norm": NaN,
+      "learning_rate": 6.96610257832053e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.2833117723156533,
+      "grad_norm": NaN,
+      "learning_rate": 6.776478002504335e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.3247089262613194,
+      "grad_norm": NaN,
+      "learning_rate": 6.584354661054765e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.3661060802069858,
+      "grad_norm": NaN,
+      "learning_rate": 6.390108644434829e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.407503234152652,
+      "grad_norm": NaN,
+      "learning_rate": 6.19412019834386e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.4489003880983182,
+      "grad_norm": NaN,
+      "learning_rate": 5.9967729793687156e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.4902975420439843,
+      "grad_norm": NaN,
+      "learning_rate": 5.798453303957968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.5316946959896507,
+      "grad_norm": NaN,
+      "learning_rate": 5.599549392189342e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.573091849935317,
+      "grad_norm": NaN,
+      "learning_rate": 5.40045060781066e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.6144890038809832,
+      "grad_norm": NaN,
+      "learning_rate": 5.201546696042033e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.6558861578266493,
+      "grad_norm": NaN,
+      "learning_rate": 5.003227020631287e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.6972833117723156,
+      "grad_norm": NaN,
+      "learning_rate": 4.805879801656139e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.738680465717982,
+      "grad_norm": NaN,
+      "learning_rate": 4.6098913555651725e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.780077619663648,
+      "grad_norm": NaN,
+      "learning_rate": 4.4156453389452354e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.8214747736093142,
+      "grad_norm": NaN,
+      "learning_rate": 4.223521997495665e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.8628719275549805,
+      "grad_norm": NaN,
+      "learning_rate": 4.0338974216794725e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.9042690815006469,
+      "grad_norm": NaN,
+      "learning_rate": 3.847142810508596e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 1.9456662354463132,
+      "grad_norm": NaN,
+      "learning_rate": 3.6636237449044076e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 1.9870633893919794,
+      "grad_norm": NaN,
+      "learning_rate": 3.483699472055897e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.0284605433376455,
+      "grad_norm": NaN,
+      "learning_rate": 3.307722202176417e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.069857697283312,
+      "grad_norm": NaN,
+      "learning_rate": 3.136036419035656e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.069857697283312,
+      "eval_loss": NaN,
+      "eval_runtime": 3.1151,
+      "eval_samples_per_second": 16.051,
+      "eval_steps_per_second": 4.173,
+      "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": 2.829062208749568e+17,
+  "total_flos": 5.658124417499136e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null