Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7556e4f5da20e2653fa5559d7e0a20c2286eb4348b09fb17899f6456a16b86a1
+oid sha256:ccaee9708f6919567a10a4b2c9d36dae410e47bad47fbdd7a3c8cef5912777a7
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd5be0097b9b880e0b1ae0feaff68426a1081b175d4e22a24199b9872213a6f
+oid sha256:d9f79d3e6201eee25176265d8f6eb7b6987437b565c15bc34eefce8ada3b7993
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012300413956238912,
+  "epoch": 0.01845062093435837,
   "eval_steps": 13,
-  "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": 17.981,
       "eval_steps_per_second": 8.99,
       "step": 26
+    },
+    {
+      "epoch": 0.014192785334121822,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0429,
+      "step": 30
+    },
+    {
+      "epoch": 0.01845062093435837,
+      "eval_loss": NaN,
+      "eval_runtime": 49.4911,
+      "eval_samples_per_second": 17.983,
+      "eval_steps_per_second": 8.992,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8092588770852864.0,
+  "total_flos": 1.211834359087104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null