Training in progress, step 25, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5b001a2fc939ecf43fb0d86edcd5bf104abdef1bc3131e002054358dce29e25
+oid sha256:3853886b34bfb1c2a56973fa6b7fc2878f1b41758161d70accbd245923cbb25a
 size 69844690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450126e07c0c8b1791f3f3aa2cf6e5120163749c0d302c76afbdee1feab14888
+oid sha256:9ae04b47a1332a71e382f9669f981c300c61f43247f44f70c555d2b15d571c02
 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": 0.008598452278589854,
+  "epoch": 0.010748065348237317,
   "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": 0.009028374892519347,
+      "grad_norm": NaN,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.009028374892519347,
+      "eval_loss": NaN,
+      "eval_runtime": 35.6565,
+      "eval_samples_per_second": 27.485,
+      "eval_steps_per_second": 13.742,
+      "step": 21
+    },
+    {
+      "epoch": 0.010318142734307825,
+      "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": 345645817528320.0,
+  "total_flos": 425104626155520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null