Training in progress, step 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822c1d335e61ca8da2a7d87051a771922c03875285a9ba53879e4d4459146519
+oid sha256:ae9eb09c0a92d3cec58c8aa83c51dcbb8bc5b40ee212a0c4733565b58390f2cb
 size 26498

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156ed4e76886f44f003f6e0f325875015434b8009fd9e783fb9e0ab1e65ac9e4
+oid sha256:5db50466d30b0cbab06b9299f53c692c37f60b734b9f09799979790328cd5803
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005478513953090224,
+  "epoch": 0.00684814244136278,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 131.221,
       "eval_steps_per_second": 65.61,
       "step": 4
+    },
+    {
+      "epoch": 0.00684814244136278,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1616609280.0,
+  "total_flos": 2014543872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null