Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102d34f3f27b40ee77ec12e016d974012f097b4b96ba45b8d940f87321cddd34
+oid sha256:119d868df08315ef6987d82547a57a18b88cd1b5b967646116fe1575cf91e1bc
 size 41119636

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:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00028650216667263544,
+  "epoch": 0.0005730043333452709,
   "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": 8.072,
       "eval_steps_per_second": 4.036,
       "step": 10
+    },
+    {
+      "epoch": 0.000315152383339899,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.00034380260000716254,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003724528166744261,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.00040110303334168964,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0004297532500089532,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004297532500089532,
+      "eval_loss": NaN,
+      "eval_runtime": 1823.5237,
+      "eval_samples_per_second": 8.06,
+      "eval_steps_per_second": 4.03,
+      "step": 15
+    },
+    {
+      "epoch": 0.00045840346667621674,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.00048705368334348026,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.0005157039000107438,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005443541166780074,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0005730043333452709,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005730043333452709,
+      "eval_loss": NaN,
+      "eval_runtime": 1883.4485,
+      "eval_samples_per_second": 7.803,
+      "eval_steps_per_second": 3.902,
+      "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": 1628733135912960.0,
+  "total_flos": 3257466271825920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null