Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db377b13142f5a36919ac15fa0671382c2dbd507bcd6d7d6137104e399c8d281
+oid sha256:393a2644c7aa4ab801d34d0b3322301105a7470ff9f2b27807d653beb37fae92
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111095c3f7cfcd771f34c1b764e1904a53e557f22900fae8d34cde7ecc4da66b
+oid sha256:e89f71b60c382083c4d382d4216790e61b44bce26c8d1bc4247f09fd00ebdc1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05506607929515418,
+  "epoch": 0.11013215859030837,
   "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": 3.187,
       "eval_steps_per_second": 1.593,
       "step": 25
+    },
+    {
+      "epoch": 0.05726872246696035,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.05947136563876652,
+      "grad_norm": NaN,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06167400881057269,
+      "grad_norm": NaN,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.06387665198237885,
+      "grad_norm": NaN,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.06607929515418502,
+      "grad_norm": NaN,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06828193832599119,
+      "grad_norm": NaN,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.07048458149779736,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.07268722466960352,
+      "grad_norm": NaN,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.07488986784140969,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.07709251101321586,
+      "grad_norm": NaN,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.07929515418502203,
+      "grad_norm": NaN,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.08149779735682819,
+      "grad_norm": NaN,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.08370044052863436,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.08590308370044053,
+      "grad_norm": NaN,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": NaN,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09030837004405286,
+      "grad_norm": NaN,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.09251101321585903,
+      "grad_norm": NaN,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0947136563876652,
+      "grad_norm": NaN,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.09691629955947137,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.09911894273127753,
+      "grad_norm": NaN,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.1013215859030837,
+      "grad_norm": NaN,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.10352422907488987,
+      "grad_norm": NaN,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.10572687224669604,
+      "grad_norm": NaN,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.10792951541850221,
+      "grad_norm": NaN,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.11013215859030837,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.11013215859030837,
+      "eval_loss": NaN,
+      "eval_runtime": 60.2585,
+      "eval_samples_per_second": 3.186,
+      "eval_steps_per_second": 1.593,
+      "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": 3.3291147216420864e+16,
+  "total_flos": 6.625267911386726e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null