Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c996069ccaafb7cc010c8a683f9e90998a7147a1194b4b9f4bc6722acfb99be
+oid sha256:ddb48df08a4b408fea103f1839695dc7dc626930536eeebed400f7af5637d141
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa91133351808aacad3e45f05aebdf1a2981ac4aa08431c95904a973b1b12d5
+oid sha256:b90cec581bf01b7b4ecfb930623a750a1d6c081eb2553ed745e3e8de8e41bc7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002178708570494839,
+  "epoch": 0.0032680628557422587,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 16.289,
       "eval_steps_per_second": 8.144,
       "step": 20
+    },
+    {
+      "epoch": 0.0022876439990195813,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0026144502845938072,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.002723385713118549,
+      "eval_loss": NaN,
+      "eval_runtime": 237.3766,
+      "eval_samples_per_second": 16.286,
+      "eval_steps_per_second": 8.143,
+      "step": 25
+    },
+    {
+      "epoch": 0.0029412565701680327,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0032680628557422587,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0032680628557422587,
+      "eval_loss": NaN,
+      "eval_runtime": 237.4031,
+      "eval_samples_per_second": 16.285,
+      "eval_steps_per_second": 8.142,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7220940609945600.0,
+  "total_flos": 1.08314109149184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null