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 sha256:0d8924557c8478635a37131418ba2bdf0bddbda7feacb690e46147484829826d
+oid sha256:df91c29695893d4818ada3e851485531193d4b0d3747848fc3423c12b94808cd
 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": 0.0007533713367318751,
+  "epoch": 0.0015067426734637502,
   "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": 4.547,
       "eval_steps_per_second": 2.274,
       "step": 15
+    },
+    {
+      "epoch": 0.0009040456040782501,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010044951156425001,
+      "eval_loss": NaN,
+      "eval_runtime": 1843.9752,
+      "eval_samples_per_second": 4.547,
+      "eval_steps_per_second": 2.273,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010547198714246251,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012053941387710002,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012556188945531252,
+      "eval_loss": NaN,
+      "eval_runtime": 1844.8536,
+      "eval_samples_per_second": 4.545,
+      "eval_steps_per_second": 2.272,
+      "step": 25
+    },
+    {
+      "epoch": 0.0013560684061173752,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015067426734637502,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015067426734637502,
+      "eval_loss": NaN,
+      "eval_runtime": 1845.4494,
+      "eval_samples_per_second": 4.543,
+      "eval_steps_per_second": 2.272,
+      "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": 6838427232239616.0,
+  "total_flos": 1.4202887328497664e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null