Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8349d5c75006f2495c196fb2ea34033493e116e9038d1b1e1fa8721c79341e
+oid sha256:24231d9f62d9453a30d95ed5d05b38409d367a52b64901ef92783ec18aa9614a
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19808a78aa84544c5543b527b1c094c19883ff95d98e1a37e594ed4b3bbcbb8c
+oid sha256:9b2d9ea445b3bab540b249ef74f72a200d3501235ff0c235cf06f8814122b919
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014193430988990992,
+  "epoch": 0.0018196706396142299,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.0,
       "step": 35
+    },
+    {
+      "epoch": 0.001455736511691384,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.001455736511691384,
+      "eval_loss": NaN,
+      "eval_runtime": 411.0902,
+      "eval_samples_per_second": 28.145,
+      "eval_steps_per_second": 14.072,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016377035756528068,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0018196706396142299,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0018196706396142299,
+      "eval_loss": NaN,
+      "eval_runtime": 410.2429,
+      "eval_samples_per_second": 28.203,
+      "eval_steps_per_second": 14.101,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 558714477871104.0,
+  "total_flos": 716757218623488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null