Training in progress, step 25, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cea84735b20860df07e99c5d032c755433782ce57a7cebf8eb1b1f833e67ae5
+oid sha256:6af67159f323e8db33967b859c3271ea1c8b9c0ec84b6a1576ef523090de9dac
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c325a5b88aa7600e783ee566917eff9758a4ec707c33c129463258bf687aee2
+oid sha256:318d5daa1e33a35543249e590b5fd9b28d4e2137de5e81940e98782aeff96166
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:842484d97bbf42f9f92b7e7c8dcf4fda5e0b0607fec45e60ed168e6d3a7f3132
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.038314176245210725,
+  "epoch": 0.04789272030651341,
   "eval_steps": 3,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,57 @@
       "learning_rate": 1.4644660940672627e-05,
       "loss": 0.0,
       "step": 20
+    },
+    {
+      "epoch": 0.040229885057471264,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.040229885057471264,
+      "eval_loss": NaN,
+      "eval_runtime": 24.8487,
+      "eval_samples_per_second": 8.854,
+      "eval_steps_per_second": 4.427,
+      "step": 21
+    },
+    {
+      "epoch": 0.0421455938697318,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.044061302681992334,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "eval_loss": NaN,
+      "eval_runtime": 24.7154,
+      "eval_samples_per_second": 8.901,
+      "eval_steps_per_second": 4.451,
+      "step": 24
+    },
+    {
+      "epoch": 0.04789272030651341,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -217,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6572656904110080.0,
+  "total_flos": 8215821130137600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null