Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7ff192405523d4ca14f327614a4337a95d37abe99a53a5753869b5d3d63f063
+oid sha256:023fcdac7213b51dcb6a5b3f5d247e3b7c8a207dd855c983a20a4bd3898bbf19
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2ee68b7a1edf1ee81c51eec607d22df2583032538d516731253af350bcbe87
+oid sha256:119f4e3b616e595dfdb57dc0bcb2fc565557f3c64adaa40fcecd1b7e340fd6c2
 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": 0.002430428970713331,
+  "epoch": 0.004860857941426662,
   "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": 6.549,
       "eval_steps_per_second": 3.276,
       "step": 15
+    },
+    {
+      "epoch": 0.002916514764855997,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.003240571960951108,
+      "eval_loss": NaN,
+      "eval_runtime": 396.8551,
+      "eval_samples_per_second": 6.549,
+      "eval_steps_per_second": 3.276,
+      "step": 20
+    },
+    {
+      "epoch": 0.0034026005589986633,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0038886863531413293,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.004050714951188885,
+      "eval_loss": NaN,
+      "eval_runtime": 396.7977,
+      "eval_samples_per_second": 6.55,
+      "eval_steps_per_second": 3.276,
+      "step": 25
+    },
+    {
+      "epoch": 0.004374772147283996,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.004860857941426662,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.004860857941426662,
+      "eval_loss": NaN,
+      "eval_runtime": 396.7824,
+      "eval_samples_per_second": 6.55,
+      "eval_steps_per_second": 3.276,
+      "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": 1.0464832134316032e+16,
+  "total_flos": 2.110703430480691e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null