Training in progress, step 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:294fde63636bc3a4eb39062dbc54100433381cbd9cd582167811199794e0fd7f
+oid sha256:9e2a4f099838ddff60be323f47f3f7d3a06b88723fa69d07f78a5c961a89057c
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d0ab2b507d487fe3cdf107a26d6222d2fd30b493db39cc1012490685af18ce
+oid sha256:4771900747b28279cebe93ffeda409618f5cbc1563ec4f7b60b34a354f4a4061
 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": 0.8421052631578947,
+  "epoch": 1.1052631578947367,
   "eval_steps": 1,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,6 +39,21 @@
       "eval_samples_per_second": 7.519,
       "eval_steps_per_second": 3.759,
       "step": 4
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "eval_loss": NaN,
+      "eval_runtime": 0.2623,
+      "eval_samples_per_second": 7.625,
+      "eval_steps_per_second": 3.813,
+      "step": 5
     }
   ],
   "logging_steps": 5,
@@ -53,12 +68,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 367413279326208.0,
+  "total_flos": 459266599157760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null