Training in progress, step 25, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b3a5dd23a8ba5febeaefbfdd7893eb2946c384ba9fc0ad0b8ca5b13934f9a5
+oid sha256:5ac773f5d65faa92a2f6980f7b33dd39dca4a8f514716e18e3e86af0ab16c6c1
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827a869844b9d198e193184921a140e6132a0ebb431279ef0ceeb6c89a553ae3
+oid sha256:bd179c0c4ca1de8d0bfba8a39b9e9c9c9671a6547c4af4c41f48f0409182650b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004958933829226716,
+  "epoch": 0.0006198667286533395,
   "eval_steps": 3,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,57 @@
       "learning_rate": 5.000000000000002e-05,
       "loss": 0.0,
       "step": 20
+    },
+    {
+      "epoch": 0.0005206880520688052,
+      "grad_norm": NaN,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005206880520688052,
+      "eval_loss": NaN,
+      "eval_runtime": 1451.8773,
+      "eval_samples_per_second": 23.393,
+      "eval_steps_per_second": 11.697,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005454827212149388,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.0005702773903610724,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.000595072059507206,
+      "grad_norm": NaN,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.000595072059507206,
+      "eval_loss": NaN,
+      "eval_runtime": 1449.6919,
+      "eval_samples_per_second": 23.428,
+      "eval_steps_per_second": 11.714,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006198667286533395,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -217,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5225075347292160.0,
+  "total_flos": 6531344184115200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null