Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53590e2d62b9c7c6849c90cf431d1bc80555b8303247bbb4b042a3994b74d366
+oid sha256:023fcdac7213b51dcb6a5b3f5d247e3b7c8a207dd855c983a20a4bd3898bbf19
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d7a662bef8bba0e2f32411afdecd88cfa4323fc758e072f84f28451a63f3100
+oid sha256:6ca903450dce6b80699892361606557dab43202bf4d9fdc4da1b379157968350
 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": 0.003337644457424173,
+  "epoch": 0.005006466686136259,
   "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": 6.561,
       "eval_steps_per_second": 3.281,
       "step": 20
+    },
+    {
+      "epoch": 0.0035045266802953817,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0040051733489090075,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.004172055571780216,
+      "eval_loss": NaN,
+      "eval_runtime": 384.9239,
+      "eval_samples_per_second": 6.557,
+      "eval_steps_per_second": 3.279,
+      "step": 25
+    },
+    {
+      "epoch": 0.004505820017522633,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.005006466686136259,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.005006466686136259,
+      "eval_loss": NaN,
+      "eval_runtime": 384.5805,
+      "eval_samples_per_second": 6.563,
+      "eval_steps_per_second": 3.281,
+      "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": 1.406259802669056e+16,
+  "total_flos": 2.1006005802369024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null