Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c205648a743e8c8f6b786638db954bd7b378add5d722af4608f009a0cf0b44dc
+oid sha256:f5983c67fe0fd2352ec8abd0638dfcf09fda574085aabc876819c05463c58fc7
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00be0d44c2086161706c53a228e2af5190af7c7c631e5aecebb67b47085501ad
+oid sha256:51178576c6072f964751a7599730df4535d2d35b5f12c985cdf9f026c3be4a51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33240997229916897,
+  "epoch": 0.44321329639889195,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,43 @@
       "eval_samples_per_second": 5.674,
       "eval_steps_per_second": 2.837,
       "step": 30
+    },
+    {
+      "epoch": 0.3656509695290859,
+      "grad_norm": NaN,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.3878116343490305,
+      "eval_loss": NaN,
+      "eval_runtime": 6.6725,
+      "eval_samples_per_second": 5.695,
+      "eval_steps_per_second": 2.848,
+      "step": 35
+    },
+    {
+      "epoch": 0.3988919667590028,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.43213296398891965,
+      "grad_norm": NaN,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.44321329639889195,
+      "eval_loss": NaN,
+      "eval_runtime": 6.6829,
+      "eval_samples_per_second": 5.686,
+      "eval_steps_per_second": 2.843,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -147,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9888465609031680.0,
+  "total_flos": 1.318462081204224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null