Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cd78b0763b2a5b758b08c2ffa586ad039bd1a5e002dd7ac6fc9c151b8e88fb
+oid sha256:8a91b248d59b64b7203b803f0815cf9238d56e52af285549b65724f6f94b4e6c
 size 239452242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cba71b8400e9751a7ec40a5c65b542bac6c7fcb18bf7d203e4972b12b069895
+oid sha256:da99da3d55cb9ee5e64b8186fba394cd386afb82ae8605be7fc40772a11a824d
 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": 0.02302158273381295,
+  "epoch": 0.034532374100719423,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.024172661870503598,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.02762589928057554,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.02762589928057554,
+      "eval_loss": NaN,
+      "eval_runtime": 27.993,
+      "eval_samples_per_second": 13.075,
+      "eval_steps_per_second": 6.537,
+      "step": 24
+    },
+    {
+      "epoch": 0.03107913669064748,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.034532374100719423,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3688821581414400.0,
+  "total_flos": 5579342641889280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null