Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e218e5d11ea935b2b63120b877a689c115085c21a31c9f7510206a31fa27b8f4
+oid sha256:ecb08a1ce6d836e5f6fec92ac71c474ffc1d484b4fe0feffca20f1d651df613a
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b058e3f4efb72d1010e7edcd9a82b5cfd988e6f9f5d042e61b36316850284f75
+oid sha256:f88431b600c091712847abac58452223fc04768337c0a249239a522c8ce713ff
 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": 0.005179334455522465,
+  "epoch": 0.01035866891104493,
   "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": 8.713,
       "eval_steps_per_second": 2.181,
       "step": 10
+    },
+    {
+      "epoch": 0.005697267901074712,
+      "grad_norm": NaN,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.006215201346626958,
+      "grad_norm": NaN,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.006733134792179205,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.007251068237731451,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.007769001683283698,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.007769001683283698,
+      "eval_loss": NaN,
+      "eval_runtime": 186.8031,
+      "eval_samples_per_second": 8.704,
+      "eval_steps_per_second": 2.179,
+      "step": 15
+    },
+    {
+      "epoch": 0.008286935128835944,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.008804868574388192,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.009322802019940438,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.009840735465492684,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.01035866891104493,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.01035866891104493,
+      "eval_loss": NaN,
+      "eval_runtime": 188.6139,
+      "eval_samples_per_second": 8.621,
+      "eval_steps_per_second": 2.158,
+      "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": 6534586045562880.0,
+  "total_flos": 1.306917209112576e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null