Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b3506f4d8f60ee79343b7e4058edde035f2877849a8d7b1623a3e5077ee983f
+oid sha256:17472985c127ebe0535c6412136fe9f0f9ccaf502d7d11a7d1312c1e68ff5617
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d09bb9e2cb0b45bc76aece119117146e4dbe1a22aa759f2e871fa80a27d9fa0
+oid sha256:2a1a18dcdb02458fcefc7f97700baec01bf909b7afbfdcbd8cbe340c3299b8fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021079300734735244,
+  "epoch": 0.03161895110210286,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 14.653,
       "eval_steps_per_second": 1.832,
       "step": 20
+    },
+    {
+      "epoch": 0.024322270078540664,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.024322270078540664,
+      "eval_loss": NaN,
+      "eval_runtime": 566.1102,
+      "eval_samples_per_second": 14.679,
+      "eval_steps_per_second": 1.835,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.605454882052506e+16,
+  "total_flos": 1.1417367655061914e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null