Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cad33dd5640c0c1a1781554ffaf748946cab9a5d2aca388fd5c4d4dd41f1bd2
+oid sha256:0d3e81090b776aed5efee86a39b2998a2278cb8f4546380cb2d9c1eb1455b22f
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6288b01f9019e9757f1daa4f6ec54d48089d6b9a51bc69bf45cc18f06eeab8
+oid sha256:7fa081e379c7b904fec4d734e680d6c3a44b1a4fbc8ebe714244b7ad46b331c7
 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": 0.00016884809018739323,
+  "epoch": 0.00033769618037478646,
   "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": 20.353,
       "eval_steps_per_second": 10.176,
       "step": 15
+    },
+    {
+      "epoch": 0.00020261770822487188,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.00022513078691652433,
+      "eval_loss": NaN,
+      "eval_runtime": 1835.4087,
+      "eval_samples_per_second": 20.38,
+      "eval_steps_per_second": 10.19,
+      "step": 20
+    },
+    {
+      "epoch": 0.00023638732626235054,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.00027015694429982916,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0002814134836456554,
+      "eval_loss": NaN,
+      "eval_runtime": 1834.8766,
+      "eval_samples_per_second": 20.386,
+      "eval_steps_per_second": 10.193,
+      "step": 25
+    },
+    {
+      "epoch": 0.00030392656233730784,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.00033769618037478646,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.00033769618037478646,
+      "eval_loss": NaN,
+      "eval_runtime": 1836.0553,
+      "eval_samples_per_second": 20.373,
+      "eval_steps_per_second": 10.187,
+      "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": 2067854618787840.0,
+  "total_flos": 4135709237575680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null