Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683c86a71a8db3ca736d366c0eb5f1f2510e0b86b78a982f534376d3009dc217
+oid sha256:e0fa1d781903c4bf9001717ee7a464b871ba8191ebc80845700b88bd69f19af0
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ee02b89ee6ab5c1649a775e2437198f935cfddcbee31e906fe8a064e56f821
+oid sha256:9f868e27cf7f8421768a16e1b3c8f24ada4db89b0b78ec44e07bc59e6729fbff
 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": 0.017765144785930005,
+  "epoch": 0.03553028957186001,
   "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": 8.211,
       "eval_steps_per_second": 4.112,
       "step": 25
+    },
+    {
+      "epoch": 0.018475750577367205,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017684011108568592,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.019186356368804405,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.019896962160241605,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017244252047910892,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.020607567951678805,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.021318173743116006,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.022028779534553206,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016525857615241687,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.022739385325990406,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.023449991117427606,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016010811472830252,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.024160596908864806,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.024871202700302006,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.02558180849173921,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015189695737812152,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.02629241428317641,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.02700302007461361,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001461341162978688,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.02771362586605081,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.02842423165748801,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.02913483744892521,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013711972489182208,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.02984544324036241,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013402931744416433,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.03055604903179961,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.03126665482323681,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.03197726061467401,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.03268786640611121,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001213299630743747,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.03339847219754841,
+      "grad_norm": NaN,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.03410907798898561,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001148263647711842,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.034819683780422814,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.03553028957186001,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.03553028957186001,
+      "eval_loss": NaN,
+      "eval_runtime": 72.2238,
+      "eval_samples_per_second": 8.211,
+      "eval_steps_per_second": 4.112,
+      "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": 6531344184115200.0,
+  "total_flos": 1.30626883682304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null