Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72140ecee1516e32981c6152ddd63e6e00a4478dcd6b17db301e9a3630af4d2a
+oid sha256:f3055b5f0c2a0912d299ebb7bdc789dcad1520815664faf6fe02e0e22d12411a
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d00d9712372897ac397c2114c0667f9bb0cacd2f0b0d9d4114cc132c73dae203
+oid sha256:434e78670576a9475ee93be2c4ee52b6f412d6cea81fa763e62e6ebf98e8cb60
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac6f5627679c7148a96e5bbed63ddcd0db478b3e5ef1430929a158ea76838ea
+oid sha256:b02c3519ab0200ccf932a8cf6d7b0ec6cb9fd27b9a3f125427bc98b6d3706c85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.006787714237230613,
+  "epoch": 0.013575428474461226,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 15.326,
       "eval_steps_per_second": 3.841,
       "step": 10
+    },
+    {
+      "epoch": 0.007466485660953674,
+      "grad_norm": NaN,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.008145257084676736,
+      "grad_norm": NaN,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.008824028508399796,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.009502799932122857,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.010181571355845919,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.010181571355845919,
+      "eval_loss": NaN,
+      "eval_runtime": 81.0103,
+      "eval_samples_per_second": 15.319,
+      "eval_steps_per_second": 3.839,
+      "step": 15
+    },
+    {
+      "epoch": 0.01086034277956898,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.01153911420329204,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.012217885627015103,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.012896657050738164,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.013575428474461226,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.013575428474461226,
+      "eval_loss": NaN,
+      "eval_runtime": 81.9636,
+      "eval_samples_per_second": 15.141,
+      "eval_steps_per_second": 3.794,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -115,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -124,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1881382456393728.0,
+  "total_flos": 3842823740719104.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null