Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e74d76666e3b00feee0d526b51f54f3ac3d422967193d33b6fabad2070dd64c3
+oid sha256:566441d1ec2a535e553fafef599dfc79558d6278f2ebe74fafc6587de76dd77a
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ef13ac808be122aecf9c0207eaae9fac5c98d6627d45000eed27153c89b376
+oid sha256:94679c79f797d0ad9ee8e3fa04683f5ac3ac382e4b5be6af9c8493feaaea69bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017543859649122806,
+  "epoch": 0.03508771929824561,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.843,
       "eval_steps_per_second": 2.422,
       "step": 10
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "eval_loss": NaN,
+      "eval_runtime": 49.5916,
+      "eval_samples_per_second": 4.84,
+      "eval_steps_per_second": 2.42,
+      "step": 15
+    },
+    {
+      "epoch": 0.031578947368421054,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "eval_loss": NaN,
+      "eval_runtime": 49.6044,
+      "eval_samples_per_second": 4.838,
+      "eval_steps_per_second": 2.419,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9565295811231744.0,
+  "total_flos": 1.9392654521401344e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null