Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0a44dd525d72fa0a552ed385e6959f8939d7a3f99103d7693a0282bb2a27e6
+oid sha256:5b25f23b7b0daf100324011f79da89e62581f8b29999ad8cb9b32fc1783e4022
 size 295765866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50f388098c6562fca4757115dfb689e1ba33131d7e3e2d3f996e9d37b582574
+oid sha256:a8ed8c92c2a9957b058e7ee144c540261f14244e30499caf458459ac628e91e9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
+oid sha256:0f6003820aa1d9b0e6aa1d70309948568223b16abb8759408bc4ed8976518161
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01412928293889085,
+  "epoch": 0.021193924408336277,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 16.49,
       "eval_steps_per_second": 8.245,
       "step": 50
+    },
+    {
+      "epoch": 0.014411868597668668,
+      "grad_norm": NaN,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.014694454256446485,
+      "grad_norm": NaN,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.014977039915224302,
+      "grad_norm": NaN,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.015259625574002119,
+      "grad_norm": NaN,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.015542211232779936,
+      "grad_norm": NaN,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.015824796891557753,
+      "grad_norm": NaN,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.016107382550335572,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.016389968209113388,
+      "grad_norm": NaN,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.016672553867891203,
+      "grad_norm": NaN,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.016955139526669022,
+      "grad_norm": NaN,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.017237725185446837,
+      "grad_norm": NaN,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.017520310844224656,
+      "grad_norm": NaN,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.01780289650300247,
+      "grad_norm": NaN,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.01808548216178029,
+      "grad_norm": NaN,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.018368067820558106,
+      "grad_norm": NaN,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.018650653479335925,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.01893323913811374,
+      "grad_norm": NaN,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.01921582479689156,
+      "grad_norm": NaN,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.019498410455669375,
+      "grad_norm": NaN,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.019780996114447193,
+      "grad_norm": NaN,
+      "learning_rate": 5.925998220016659e-07,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.02006358177322501,
+      "grad_norm": NaN,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.020346167432002824,
+      "grad_norm": NaN,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.020628753090780643,
+      "grad_norm": NaN,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.02091133874955846,
+      "grad_norm": NaN,
+      "learning_rate": 2.3794460453555047e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.021193924408336277,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.021193924408336277,
+      "eval_loss": NaN,
+      "eval_runtime": 90.4859,
+      "eval_samples_per_second": 16.467,
+      "eval_steps_per_second": 8.233,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9072280030150656.0,
+  "total_flos": 1.4667956399112192e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null