Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2725cc1640d41a1112c4d72bfdac1a14573405b0098ebcdf5bb972cfa02833be
+oid sha256:17c5cc9bfc28787437355cf137099b22df7e1ec7ecf7b4827a87e02714dd256b
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e10e7e084e9d9c969a8d9c919cc8f1ecdc23be93922140c6c36dc329b7d816c
+oid sha256:6d2d6bc08ef3abdbd8d1e9ebf2fe9eda911a26db8affa656809086ee10975bba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0a9ae08a837d696210720a364c40061c9c8b036f36570a99f11fe3b8d70f51
+oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011403508771929825,
+  "epoch": 0.02280701754385965,
   "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": 33.151,
       "eval_steps_per_second": 16.575,
       "step": 13
+    },
+    {
+      "epoch": 0.017543859649122806,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02280701754385965,
+      "eval_loss": NaN,
+      "eval_runtime": 7.2505,
+      "eval_samples_per_second": 33.101,
+      "eval_steps_per_second": 16.551,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1149285584338944.0,
+  "total_flos": 2298571168677888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null