Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e58130a103d5fc8bd96c57ac864ce3f85a9a1a2861e3b39643089656fba37fc2
+oid sha256:6783aeab96cbe103d14e8895a0698b346f4f14ebc56b55be6bd8f04ee272df2c
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5aa6cbd7bd95c69f7b0a8226cbe0c4a8668f11b4343ce70e651374c855ffeca
+oid sha256:6532c8b672a79cd29de867fb127236fb5ca92bd0ac70d24dabb0569edeb4b2ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4ae3842d5f151f968dca77e1398d806e7ccbbb71022d80233230f6c7d83bcb
+oid sha256:9567f2f3182e832808fd621212e0dd5e8f1a88bd24ddda3ea0d289496073738c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1422475106685633,
+  "epoch": 0.2844950213371266,
   "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": 10.007,
       "eval_steps_per_second": 5.003,
       "step": 25
+    },
+    {
+      "epoch": 0.14793741109530584,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017684011108568592,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.15362731152204837,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.1593172119487909,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017244252047910892,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.16500711237553342,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.17069701280227595,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.1763869132290185,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016525857615241687,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.18207681365576103,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.18776671408250356,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016010811472830252,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.1934566145092461,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.19914651493598862,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.20483641536273114,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015189695737812152,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001461341162978688,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.22190611664295876,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.22759601706970128,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.2332859174964438,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013711972489182208,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.23897581792318634,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013402931744416433,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.24466571834992887,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.2503556187766714,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.25604551920341395,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.26173541963015645,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001213299630743747,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.267425320056899,
+      "grad_norm": NaN,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.27311522048364156,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001148263647711842,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.27880512091038406,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.2844950213371266,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.2844950213371266,
+      "eval_loss": NaN,
+      "eval_runtime": 7.4049,
+      "eval_samples_per_second": 9.993,
+      "eval_steps_per_second": 4.997,
+      "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": 5146843860172800.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null