Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289092b7402162660e501cb3bf1a85d76106a518b9f1ff0b7d37db3e33702bdc
+oid sha256:173f30dc58dab74d2bea2343bc2c34154dcb7c1f879d81a28b92b1980e87e538
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140af42b3dd3ce72edf59502c4890f5e5ea80c1962733616ffe90a60e5476d07
+oid sha256:d8499756812b26ce8f2ce9d439126e69f58899480f58682d1e03352b776e532e
 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": 0.02631578947368421,
+  "epoch": 0.05263157894736842,
   "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": 4.808,
       "eval_steps_per_second": 2.404,
       "step": 15
+    },
+    {
+      "epoch": 0.031578947368421054,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "eval_loss": NaN,
+      "eval_runtime": 49.9139,
+      "eval_samples_per_second": 4.808,
+      "eval_steps_per_second": 2.404,
+      "step": 20
+    },
+    {
+      "epoch": 0.03684210526315789,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "eval_loss": NaN,
+      "eval_runtime": 49.9239,
+      "eval_samples_per_second": 4.807,
+      "eval_steps_per_second": 2.404,
+      "step": 25
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "eval_loss": NaN,
+      "eval_runtime": 49.9657,
+      "eval_samples_per_second": 4.803,
+      "eval_steps_per_second": 2.402,
+      "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": 1.4544490891051008e+16,
+  "total_flos": 2.9088981782102016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null