Training in progress, step 25, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2da722d9084155b5ca3d2384fd39c2e33a2db3e5e940d85709d5965779ebef
+oid sha256:712e613b8dd4ae5e463adc6fa7b0ed2264a22e552dcf867116cf906cd7c896d2
 size 39428606

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b65d03791e80ce93066570d1199da2b53cca2067a4bed561b909589e913003ac
+oid sha256:f96ef2eda26ac3d8cf70d31015e930f7377ff79bc2bec59fe1c2859ca1b2c3c3
 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": 0.0035956672209986966,
+  "epoch": 0.004494584026248371,
   "eval_steps": 7,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,28 @@
       "learning_rate": 8.954715367323468e-05,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.0037754505820486316,
+      "grad_norm": NaN,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0037754505820486316,
+      "eval_loss": NaN,
+      "eval_runtime": 86.718,
+      "eval_samples_per_second": 27.007,
+      "eval_steps_per_second": 13.504,
+      "step": 21
+    },
+    {
+      "epoch": 0.004314800665198436,
+      "grad_norm": NaN,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -87,12 +109,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 158345632677888.0,
+  "total_flos": 197932040847360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null