Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd874b11027d81450d3c8139a4c08c0666835afc6022318dfa6012d6ebda8ef2
+oid sha256:bcf147a3362519f407d588d38d06ad152b206e0c6dd4996a7c16963f235d52db
 size 39428606

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39570285d388458e5f194c05b0684bae7b478696486a031ebed3fa7a73607a7
+oid sha256:9919586e9469589d7ee9b6fa78fb5877d9ef507af1da76406e67152cba3215bb
 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": 0.0018759086432490737,
+  "epoch": 0.0028138629648736106,
   "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": 46.6,
       "eval_steps_per_second": 23.3,
       "step": 20
+    },
+    {
+      "epoch": 0.0019697040754115274,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0022510903718988887,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0023448858040613424,
+      "eval_loss": NaN,
+      "eval_runtime": 96.719,
+      "eval_samples_per_second": 46.423,
+      "eval_steps_per_second": 23.212,
+      "step": 25
+    },
+    {
+      "epoch": 0.0025324766683862496,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0028138629648736106,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0028138629648736106,
+      "eval_loss": NaN,
+      "eval_runtime": 96.8167,
+      "eval_samples_per_second": 46.376,
+      "eval_steps_per_second": 23.188,
+      "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": 124219418738688.0,
+  "total_flos": 188376700944384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null