Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc23ae79bb94432756be6a57f50fed66af80d5210e71d4fcb1b650dd001980f
+oid sha256:7556e4f5da20e2653fa5559d7e0a20c2286eb4348b09fb17899f6456a16b86a1
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b086f110558b51a500ad19497a8398f8ffe40003b916db0323fe65387e084a1
+oid sha256:6dd5be0097b9b880e0b1ae0feaff68426a1081b175d4e22a24199b9872213a6f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3a68034a6fca5f7c1565a9344e41aadbdff3752a8799ae94336c8c84c6d63d
+oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006150206978119456,
+  "epoch": 0.012300413956238912,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 18.015,
       "eval_steps_per_second": 9.008,
       "step": 13
+    },
+    {
+      "epoch": 0.009461856889414548,
+      "grad_norm": NaN,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.012300413956238912,
+      "eval_loss": NaN,
+      "eval_runtime": 49.4971,
+      "eval_samples_per_second": 17.981,
+      "eval_steps_per_second": 8.99,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3984675689201664.0,
+  "total_flos": 8092588770852864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null