Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90bf04dbe31b2d551bbe57b603947a5207be18bb9226a542f1660038ffd8193c
+oid sha256:75deba98266a7adac71bdd92e4160ead07109a9b0b726a16393c043bbf722d72
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d688b156b589c979c23949a2ff69197271f90d7872867c28fcde38eabb61344a
+oid sha256:eacf690c1b7ddeb1054ce350ebf0970ff9007b807aab56a4065d073c5441ae7e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03601440576230492,
+  "epoch": 0.07202881152460984,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 12.071,
       "eval_steps_per_second": 6.036,
       "step": 15
+    },
+    {
+      "epoch": 0.04321728691476591,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.04801920768307323,
+      "eval_loss": NaN,
+      "eval_runtime": 14.5775,
+      "eval_samples_per_second": 12.073,
+      "eval_steps_per_second": 6.037,
+      "step": 20
+    },
+    {
+      "epoch": 0.05042016806722689,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.057623049219687875,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.060024009603841535,
+      "eval_loss": NaN,
+      "eval_runtime": 14.565,
+      "eval_samples_per_second": 12.084,
+      "eval_steps_per_second": 6.042,
+      "step": 25
+    },
+    {
+      "epoch": 0.06482593037214886,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.07202881152460984,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07202881152460984,
+      "eval_loss": NaN,
+      "eval_runtime": 14.586,
+      "eval_samples_per_second": 12.066,
+      "eval_steps_per_second": 6.033,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5520916167524352.0,
+  "total_flos": 1.1129465925009408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null