Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad20610cb1d096c245900d7fb010253e51111686957bbb1d29b48857d3353ef1
+oid sha256:61587868be5c392e4561e4efc4414ba3b696133a5cdad8352a0b7f9d3df444b0
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7afd599a4fd75d46898ad235d78abde80a837e4ede27d201c909ff03cec58681
+oid sha256:9cfcb9856dbdbbc2c746b77dad98ae75eed799f5ec5952a6411f672291ad80d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1348314606741573,
+  "epoch": 0.1797752808988764,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 7.148,
       "eval_steps_per_second": 1.825,
       "step": 15
+    },
+    {
+      "epoch": 0.16179775280898875,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "eval_loss": NaN,
+      "eval_runtime": 13.1494,
+      "eval_samples_per_second": 7.149,
+      "eval_steps_per_second": 1.825,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.906444164346675e+16,
+  "total_flos": 2.530968976805069e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null