Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f765b9632202c0efb7a5d3cedf9a340b9d6f815a1474dfc1563bea017423a632
+oid sha256:81bed8336bc20b533adb47e471d0f5fd076f3d16bcc7557120e9fb5c886b2755
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f108ec767e229a767e3d8a697ef9ce2b2a773115cacb416ea44871e02516790e
+oid sha256:8861ce7e5b4b02a8488133165a43c601c061bcd41ee0e57ed3ac50ce78e47089
 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": 0.019985011241568824,
+  "epoch": 0.029977516862353237,
   "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": 31.58,
       "eval_steps_per_second": 15.79,
       "step": 20
+    },
+    {
+      "epoch": 0.020984261803647264,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.02398201348988259,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.02498126405196103,
+      "eval_loss": NaN,
+      "eval_runtime": 13.3474,
+      "eval_samples_per_second": 31.617,
+      "eval_steps_per_second": 15.808,
+      "step": 25
+    },
+    {
+      "epoch": 0.02697976517611791,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.029977516862353237,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.029977516862353237,
+      "eval_loss": NaN,
+      "eval_runtime": 13.3691,
+      "eval_samples_per_second": 31.565,
+      "eval_steps_per_second": 15.783,
+      "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": 360477150412800.0,
+  "total_flos": 540715725619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null