Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f8ed3236c52996a01c25847ddcc1aa015645c3e401b336cf7425a733c6684b
+oid sha256:c370464e9d057c7449588f5be792a14bda7df4ff91833130a8de1e25f9a49d69
 size 69844690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a427adcb42a5e21efe60aeff1fc331ce48c7ff904cf00d837fab2409ae1ed3f
+oid sha256:702327b551c4e20ef5af863061e25c1972735379504477c4bd2355e08bc4820d
 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": 0.0016820150540347335,
+  "epoch": 0.0025230225810521003,
   "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": 0.00013090169943749476,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.0017661158067364703,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020184180648416803,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020184180648416803,
+      "eval_loss": NaN,
+      "eval_runtime": 114.533,
+      "eval_samples_per_second": 43.717,
+      "eval_steps_per_second": 21.863,
+      "step": 24
+    },
+    {
+      "epoch": 0.0022707203229468905,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0025230225810521003,
+      "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": 317835234508800.0,
+  "total_flos": 476752851763200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null