Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd736e39e28b1a6481ced19ff1d42ebf42f6e2dd6e7bf4c563abe20214b1f681
+oid sha256:867ef9872d5e9dd5240a6face491f04334c48917489c2db701de72710116b58b
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0047711346354554944,
+  "epoch": 0.009542269270910989,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 100.405,
       "eval_steps_per_second": 50.203,
       "step": 2
+    },
+    {
+      "epoch": 0.007156701953183241,
+      "grad_norm": NaN,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.009542269270910989,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.009542269270910989,
+      "eval_loss": NaN,
+      "eval_runtime": 7.092,
+      "eval_samples_per_second": 99.548,
+      "eval_steps_per_second": 49.774,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 259438606811136.0,
+  "total_flos": 518877213622272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null