Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a20e42f228d66e5e1ef7c3e904241d4700bc42d3030daabf20110d4831164cc
+oid sha256:1f3e52a3921808d5243bd4d25361e27378db547355114798e0235ae3400ef7c6
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164d7dba7f6b9395ebc5a65e61d17ed965b12d2b08457c968db171c783941dd6
+oid sha256:ab91eda6ebbeb02aa43de9cb2cd36c7612a67042d5ff166ceb903cbedc10d733
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ae6c8690fc2b9075a0d9e7e3c9080d75caabd06574e8aea03a47e50558bfdb
+oid sha256:b285ff34c41ba5b47224bf99dae8708da44b1c1be9b970458bce2c659e2a2618
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5acc220b5b66a73edf2201cc54804c21b8b8b9b157464db880ec776871bc4888
+oid sha256:de51ca36bae33a9b0122f0ff5809466d963ab37e4394fb1ba8f9a32d233033d9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6860c9562c4b1609da724402bef7b3c23152ac0431943f4947d6a845d2a68f
+oid sha256:a6663492c9039f45094b3386ded9fd0897df06575714517ce170045078dc92f1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.035754189944134075,
+  "epoch": 0.07150837988826815,
   "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": 15.357,
       "eval_steps_per_second": 3.993,
       "step": 25
+    },
+    {
+      "epoch": 0.03718435754189944,
+      "grad_norm": NaN,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.038614525139664804,
+      "grad_norm": NaN,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.040044692737430165,
+      "grad_norm": NaN,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.04147486033519553,
+      "grad_norm": NaN,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.042905027932960894,
+      "grad_norm": NaN,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.044335195530726255,
+      "grad_norm": NaN,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.04576536312849162,
+      "grad_norm": NaN,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.047195530726256985,
+      "grad_norm": NaN,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.048625698324022346,
+      "grad_norm": NaN,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.05005586592178771,
+      "grad_norm": NaN,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.051486033519553075,
+      "grad_norm": NaN,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.052916201117318436,
+      "grad_norm": NaN,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.0543463687150838,
+      "grad_norm": NaN,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.055776536312849165,
+      "grad_norm": NaN,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.057206703910614526,
+      "grad_norm": NaN,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.05863687150837989,
+      "grad_norm": NaN,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.06006703910614525,
+      "grad_norm": NaN,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.061497206703910616,
+      "grad_norm": NaN,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.06292737430167598,
+      "grad_norm": NaN,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.06435754189944135,
+      "grad_norm": NaN,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0657877094972067,
+      "grad_norm": NaN,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.06721787709497207,
+      "grad_norm": NaN,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.06864804469273743,
+      "grad_norm": NaN,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.07007821229050279,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.07150837988826815,
+      "grad_norm": NaN,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.07150837988826815,
+      "eval_loss": NaN,
+      "eval_runtime": 3.2433,
+      "eval_samples_per_second": 15.416,
+      "eval_steps_per_second": 4.008,
+      "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": 2.987771858905989e+17,
+  "total_flos": 5.9736786926882e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null