Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afbaded7c3b9d8deb58e1f271e3c148e83f51e7a591daf1afee24dccb9be2f06
+oid sha256:e8b846a61e4b386e9400f5e427f9b4cac1a2d7eb669e773ae40cdd4e79945554
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78732252ebe2540999734269ea891831ad9be44083715d58b955246a72cafe50
+oid sha256:a4a693c0f44bd2d1b1d3d4899488ddb189d8a0eee850161e63b9277898c66c5b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b4287ebfe98e0880d76bdc1c85fe046c51ea6b8d5f8218b8f20fdba1e35cd4
+oid sha256:f44913944fb41975038262bc89808a2dc2c413d683e3dd0b4bea6332e025c0de
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f777d43c055cc2a82938ff166bcc04769915a94eaa31334e31adddc927010ee4
+oid sha256:d43d53e77c733cc5a943e234759b75b696a301c17ca1a34219c98c37ef5f5388
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27dd506d96c0443ce2ea182dd87a487e95bc5e9d6efa1741aa2d2fc1327764e
+oid sha256:aa980c1b00e6cab5fdcb37e23c48d344112ebe9c7fb6d5b02007d9f7b44287be
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98e2cafbee7e2dc6cc416b874fabce58bb4b9c5f16190e7bc77e29a2e8c950b
+oid sha256:7e838fed774f5bd6ed040d95e4aaf450503260b4fb9c07a02d9590ab9b72086d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3050570962479608,
+  "epoch": 2.6101141924959217,
   "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": 57.417,
       "eval_steps_per_second": 14.928,
       "step": 25
+    },
+    {
+      "epoch": 1.3572593800978794,
+      "grad_norm": NaN,
+      "learning_rate": 6.501344202803414e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.4094616639477977,
+      "grad_norm": NaN,
+      "learning_rate": 6.253778004871315e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.461663947797716,
+      "grad_norm": NaN,
+      "learning_rate": 6.003840142464886e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.5138662316476346,
+      "grad_norm": NaN,
+      "learning_rate": 5.752317012567363e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.566068515497553,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.6182707993474714,
+      "grad_norm": NaN,
+      "learning_rate": 5.247682987432637e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.6704730831973897,
+      "grad_norm": NaN,
+      "learning_rate": 4.9961598575351155e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.7226753670473083,
+      "grad_norm": NaN,
+      "learning_rate": 4.7462219951286867e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.7748776508972268,
+      "grad_norm": NaN,
+      "learning_rate": 4.498655797196586e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.8270799347471451,
+      "grad_norm": NaN,
+      "learning_rate": 4.2542401985881784e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.8792822185970635,
+      "grad_norm": NaN,
+      "learning_rate": 4.01374422120175e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.931484502446982,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.9836867862969005,
+      "grad_norm": NaN,
+      "learning_rate": 3.547523173970989e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.035889070146819,
+      "grad_norm": NaN,
+      "learning_rate": 3.323265008026421e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.088091353996737,
+      "grad_norm": NaN,
+      "learning_rate": 3.105855655680986e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.1402936378466557,
+      "grad_norm": NaN,
+      "learning_rate": 2.8959791671908742e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.1924959216965743,
+      "grad_norm": NaN,
+      "learning_rate": 2.6942958916356998e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.244698205546493,
+      "grad_norm": NaN,
+      "learning_rate": 2.501440399215983e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.2969004893964113,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.3491027732463294,
+      "grad_norm": NaN,
+      "learning_rate": 2.144610258025755e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.401305057096248,
+      "grad_norm": NaN,
+      "learning_rate": 1.981758328893866e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.4535073409461665,
+      "grad_norm": NaN,
+      "learning_rate": 1.8299760896833295e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.5057096247960846,
+      "grad_norm": NaN,
+      "learning_rate": 1.6897411034727218e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.557911908646003,
+      "grad_norm": NaN,
+      "learning_rate": 1.5614946014106085e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.6101141924959217,
+      "grad_norm": NaN,
+      "learning_rate": 1.4456400944391146e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.6101141924959217,
+      "eval_loss": NaN,
+      "eval_runtime": 0.8708,
+      "eval_samples_per_second": 57.416,
+      "eval_steps_per_second": 14.928,
+      "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": 6.401917324361728e+16,
+  "total_flos": 1.2616760234606592e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null