Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05713d8928ad86b405c17af13543bcdfc84daeadd48cd7a31e7d37d7568c17ab
+oid sha256:63852e69edeec313501a6858c63081c50cb551b77c49304ce5ecfffcda8f84e3
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6223edaadb920eb413aba43890fa90fb2bf1afb4f0f6594525529911f2f6e2e
+oid sha256:b55ee5f68b5c66c40d0a8762bb438545614f302f13f439a6255a3478cb829128
 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": 0.005865102639296188,
+  "epoch": 0.008797653958944282,
   "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": 6.371,
       "eval_steps_per_second": 3.186,
       "step": 20
+    },
+    {
+      "epoch": 0.0061583577712609975,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.007038123167155425,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.007331378299120235,
+      "eval_loss": NaN,
+      "eval_runtime": 225.4779,
+      "eval_samples_per_second": 6.369,
+      "eval_steps_per_second": 3.184,
+      "step": 25
+    },
+    {
+      "epoch": 0.007917888563049853,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.008797653958944282,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.008797653958944282,
+      "eval_loss": NaN,
+      "eval_runtime": 225.531,
+      "eval_samples_per_second": 6.367,
+      "eval_steps_per_second": 3.184,
+      "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": 1.318462081204224e+16,
+  "total_flos": 1.977693121806336e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null