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:e489a61cf79a2a014b1066e7ba5a23873d72c453c37a5d97dc70ee7e933edb99
+oid sha256:5adcf5cc8e912a0d13dfa423afe108e871c6e903d226e02a8ca3b4e58c883f0a
 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": 0.18285714285714286,
+  "epoch": 0.22857142857142856,
   "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": 0.192,
+      "grad_norm": NaN,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.192,
+      "eval_loss": NaN,
+      "eval_runtime": 4.0268,
+      "eval_samples_per_second": 23.095,
+      "eval_steps_per_second": 11.672,
+      "step": 21
+    },
+    {
+      "epoch": 0.20114285714285715,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.2102857142857143,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.21942857142857142,
+      "grad_norm": NaN,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.21942857142857142,
+      "eval_loss": NaN,
+      "eval_runtime": 4.0035,
+      "eval_samples_per_second": 23.23,
+      "eval_steps_per_second": 11.74,
+      "step": 24
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "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