Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ee0d4ddda541a203e2a4fd39995d9fc3b8c7c02ee3fa88c7cea9ee18e86fca
+oid sha256:d06cadcd155bc0cb6ae3615ddd047171f489a08edc1ed534306f6e8960228f29
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae738b61a2f3456b18554cc58eb513dd3c1277f3fead5b35885070bc7c71e22
+oid sha256:da369eeaf0617594a767b219e389ef3ef03913a634076d5aed0a19c0b910238b
 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": 0.0036383481899217754,
+  "epoch": 0.007276696379843551,
   "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": 15.335,
       "eval_steps_per_second": 3.835,
       "step": 10
+    },
+    {
+      "epoch": 0.004002183008913953,
+      "grad_norm": NaN,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.004366017827906131,
+      "grad_norm": NaN,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.004729852646898308,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.005093687465890485,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.005457522284882663,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.005457522284882663,
+      "eval_loss": NaN,
+      "eval_runtime": 151.8582,
+      "eval_samples_per_second": 15.244,
+      "eval_steps_per_second": 3.813,
+      "step": 15
+    },
+    {
+      "epoch": 0.005821357103874841,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.0061851919228670185,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.006549026741859196,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.006912861560851373,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.007276696379843551,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.007276696379843551,
+      "eval_loss": NaN,
+      "eval_runtime": 153.6267,
+      "eval_samples_per_second": 15.069,
+      "eval_steps_per_second": 3.769,
+      "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": 1803914789781504.0,
+  "total_flos": 3492686082342912.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null