Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a10910439a13d6396bb807884dfb21aaded3da52e3bbea9f064975a2b6da6a
+oid sha256:bca7d1a47f9780298c267a0ccc40ccea1ad8ff0dbd9ea06b4c648fa89d0ad993
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8ae7795446675a073d921f9debfe2f695a779b336b5bafaeaa9e3a977c1500
+oid sha256:e318465a8376e8ccf43c25e420117c92198adc960fc502750523b9e13917edba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a49108293edbb6877a3e9ba0d52e802c533bf4a33edff9df48f4e84b4fa057
+oid sha256:ca2ad0660f4430a149f84300447ae0a59e68e8b51799a2e3848afe158aff8281
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017337783364396862,
+  "epoch": 0.034675566728793725,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 6.888,
       "eval_steps_per_second": 1.723,
       "step": 25
+    },
+    {
+      "epoch": 0.018031294698972737,
+      "grad_norm": NaN,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.018724806033548612,
+      "grad_norm": NaN,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.019418317368124487,
+      "grad_norm": NaN,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.02011182870270036,
+      "grad_norm": NaN,
+      "learning_rate": 1.45e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.020805340037276233,
+      "grad_norm": NaN,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.021498851371852108,
+      "grad_norm": NaN,
+      "learning_rate": 1.55e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.022192362706427982,
+      "grad_norm": NaN,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.022885874041003857,
+      "grad_norm": NaN,
+      "learning_rate": 1.65e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.023579385375579732,
+      "grad_norm": NaN,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.024272896710155607,
+      "grad_norm": NaN,
+      "learning_rate": 1.75e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.02496640804473148,
+      "grad_norm": NaN,
+      "learning_rate": 1.8e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.025659919379307356,
+      "grad_norm": NaN,
+      "learning_rate": 1.85e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.02635343071388323,
+      "grad_norm": NaN,
+      "learning_rate": 1.9e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.027046942048459106,
+      "grad_norm": NaN,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.02774045338303498,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.028433964717610852,
+      "grad_norm": NaN,
+      "learning_rate": 2.05e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.029127476052186727,
+      "grad_norm": NaN,
+      "learning_rate": 2.1e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0298209873867626,
+      "grad_norm": NaN,
+      "learning_rate": 2.15e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.030514498721338476,
+      "grad_norm": NaN,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.03120801005591435,
+      "grad_norm": NaN,
+      "learning_rate": 2.25e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.031901521390490226,
+      "grad_norm": NaN,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0325950327250661,
+      "grad_norm": NaN,
+      "learning_rate": 2.35e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.033288544059641975,
+      "grad_norm": NaN,
+      "learning_rate": 2.4e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.03398205539421785,
+      "grad_norm": NaN,
+      "learning_rate": 2.45e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.034675566728793725,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.034675566728793725,
+      "eval_loss": NaN,
+      "eval_runtime": 703.9635,
+      "eval_samples_per_second": 6.9,
+      "eval_steps_per_second": 1.726,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.430999619600384e+17,
+  "total_flos": 2.861999239200768e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null