Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b95b38a9c4063b89dd41cf9e0b9fcf7e42355a0ee82ee7a6647b738e951d9bcc
+oid sha256:1f35714587ac1df395e60d7cc5e7528459c0bd0a9fb3b87890bf58aecac04c99
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baac4123888cbf0fc54a7d5bf8906049757ce8e78329ca573940fd9625647887
+oid sha256:43b0deb5b7c3c84f6dd5341a2dfc455a7d3484e5a5e8cabd1ec98720c5fc6d34
 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": 0.1388888888888889,
+  "epoch": 0.2777777777777778,
   "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": 7.153,
       "eval_steps_per_second": 3.576,
       "step": 15
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "eval_loss": NaN,
+      "eval_runtime": 6.4061,
+      "eval_samples_per_second": 7.181,
+      "eval_steps_per_second": 3.59,
+      "step": 20
+    },
+    {
+      "epoch": 0.19444444444444445,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "eval_loss": NaN,
+      "eval_runtime": 6.4209,
+      "eval_samples_per_second": 7.164,
+      "eval_steps_per_second": 3.582,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "eval_loss": NaN,
+      "eval_runtime": 6.4337,
+      "eval_samples_per_second": 7.15,
+      "eval_steps_per_second": 3.575,
+      "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": 1.03381900197888e+16,
+  "total_flos": 2.06763800395776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null