Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a605582c38a0c725a08493abc72794cb54c84e8bfb09f90dab88345dc4f2c30
+oid sha256:744079be02a6ed5b23e89ab092526590b7c221d6fdc5ea17bcab9d8dbf8905c5
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:785ad6e5b59a84a0e4b7ad719a169ffabf6724dcf1230a8d0996043f3f7e8b46
+oid sha256:e0664b28c9003e3cadce7e5f7b4c31346602c8dbb36ddd912f45e94b1da9d371
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009488341200749579,
+  "epoch": 0.0014232511801124368,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 29.116,
       "eval_steps_per_second": 14.558,
       "step": 20
+    },
+    {
+      "epoch": 0.0009962758260787057,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011386009440899495,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011860426500936974,
+      "eval_loss": NaN,
+      "eval_runtime": 304.8279,
+      "eval_samples_per_second": 29.118,
+      "eval_steps_per_second": 14.559,
+      "step": 25
+    },
+    {
+      "epoch": 0.001280926062101193,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014232511801124368,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0014232511801124368,
+      "eval_loss": NaN,
+      "eval_runtime": 304.7394,
+      "eval_samples_per_second": 29.127,
+      "eval_steps_per_second": 14.563,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1621191265615872.0,
+  "total_flos": 2421779544932352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null