Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ea5efcce3795b3bb537c4b70f35568e6efa483e50139047c67cb6955533d2f
+oid sha256:4b556e9534d77181709a4a76ac898882d00e78465db94753131d52a3e29cf5a0
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc08bab24c7ece8657a1b77977ce18c3254992d75c6287565450f17cca1dab0d
+oid sha256:34cd7a12a12930cd5e1001e3938ec9486169367801d21da1f58c1a84297c8fed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.007598784194528876,
+  "epoch": 0.015197568389057751,
   "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": 5.036,
       "eval_steps_per_second": 2.523,
       "step": 10
+    },
+    {
+      "epoch": 0.008358662613981762,
+      "grad_norm": NaN,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.00911854103343465,
+      "grad_norm": NaN,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.009878419452887538,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.010638297872340425,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.011398176291793313,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.011398176291793313,
+      "eval_loss": NaN,
+      "eval_runtime": 110.7983,
+      "eval_samples_per_second": 5.009,
+      "eval_steps_per_second": 2.509,
+      "step": 15
+    },
+    {
+      "epoch": 0.0121580547112462,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.012917933130699088,
+      "grad_norm": NaN,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.013677811550151976,
+      "grad_norm": NaN,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.014437689969604863,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.015197568389057751,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.015197568389057751,
+      "eval_loss": NaN,
+      "eval_runtime": 110.2239,
+      "eval_samples_per_second": 5.035,
+      "eval_steps_per_second": 2.522,
+      "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": 3094592958234624.0,
+  "total_flos": 6229904244867072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null