Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8267c824573f5f1ab1d946189fa51b02cdb91a186a993c4ba441179d91a56b6
+oid sha256:e8208ca5db1ef52c6488e2cde0e7f75eacfab3533bb1b63ec7bc609933629aae
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d539fe4d67d4d8fda2e72f75d140391a0aaf6f7ce2131b7b9f8701adbd03b4
+oid sha256:4329764fc299dd85a84b7a55661e86fcab9bb1b815145a2c18430ce0fa85af0f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8bc8abd4c9f82dfc46828b9bd127304694d7b33110834b4b23e29a7f6b47fd
+oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0056409533211112676,
+  "epoch": 0.011281906642222535,
   "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": 15.858,
       "eval_steps_per_second": 7.94,
       "step": 10
+    },
+    {
+      "epoch": 0.006205048653222395,
+      "grad_norm": NaN,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.006769143985333521,
+      "grad_norm": NaN,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.007333239317444648,
+      "grad_norm": NaN,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.007897334649555774,
+      "grad_norm": NaN,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.008461429981666902,
+      "grad_norm": NaN,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.008461429981666902,
+      "eval_loss": NaN,
+      "eval_runtime": 47.2272,
+      "eval_samples_per_second": 15.817,
+      "eval_steps_per_second": 7.919,
+      "step": 15
+    },
+    {
+      "epoch": 0.009025525313778029,
+      "grad_norm": NaN,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.009589620645889155,
+      "grad_norm": NaN,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.010153715978000282,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.01071781131011141,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.011281906642222535,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.011281906642222535,
+      "eval_loss": NaN,
+      "eval_runtime": 47.1345,
+      "eval_samples_per_second": 15.848,
+      "eval_steps_per_second": 7.935,
+      "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": 1628734142545920.0,
+  "total_flos": 3257468285091840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null