Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181b7e566f35a17be18e5cd48acf795fdb00634266732578ebb77fef6bc6ae92
+oid sha256:cfb62674ebf620d0e675ecb81fcc73d75608b817fa3036449830c52b20f404fe
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b433c868a41c2c2f6ec2792253b7a0b89b4904c0da8b55e23d78cccb5b585e1
+oid sha256:6637cce6ccc44feee3dd8a5bfba09d473486d1bf9dc3eee85a88ad1d9bf17052
 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": 0.05750431282346176,
+  "epoch": 0.11500862564692352,
   "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": 2.997,
       "eval_steps_per_second": 1.507,
       "step": 25
+    },
+    {
+      "epoch": 0.05980448533640023,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017684011108568592,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0621046578493387,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06440483036227718,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017244252047910892,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.06670500287521564,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.06900517538815411,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07130534790109258,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016525857615241687,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.07360552041403105,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.07590569292696953,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016010811472830252,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.078205865439908,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.08050603795284646,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.08280621046578493,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015189695737812152,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.08740655549166187,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001461341162978688,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.08970672800460035,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.09200690051753882,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09430707303047729,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013711972489182208,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.09660724554341575,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013402931744416433,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.09890741805635422,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.1012075905692927,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.10350776308223117,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.10580793559516964,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001213299630743747,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": NaN,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.11040828062104657,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001148263647711842,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.11270845313398505,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.11500862564692352,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.11500862564692352,
+      "eval_loss": NaN,
+      "eval_runtime": 61.0341,
+      "eval_samples_per_second": 2.998,
+      "eval_steps_per_second": 1.507,
+      "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": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null