Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac56998adf15054f52ed49436e10fd43863f3523d01e4294f5e38198d0c835b
+oid sha256:630f059df20c05409be296472b48bae96adbf73d4ea327c19cab1bebfb79a0ce
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c762e745e6b10819fd8afb33b4a1b715c756c7b22945b0044c81ebcb593a7d
+oid sha256:8cbc589a06e2970f3d1e1f484146819e64848b461fbefd953e917f429a552096
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05533938607868569,
+  "epoch": 0.06917423259835712,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 16.558,
       "eval_steps_per_second": 8.29,
       "step": 24
+    },
+    {
+      "epoch": 0.05764519383196426,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.05995100158524283,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0622568093385214,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06456261709179997,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.06686842484507854,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.06917423259835712,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.508036166700237e+16,
+  "total_flos": 3.135045208375296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null