Training in progress, step 25, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ced2eae72189114c6ff0d16648f1ee12e097c453ce02d9eb193c5ad07c21c1
+oid sha256:d3298f126755d65ca6c0096a2d314ade1aa1fee47dec7f92d61aca5d4de7776f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457548b77ed5d7703d69eacdc9aca9fe710c41943f0b7a77991d95d5848083b0
+oid sha256:3ac2500e828bb117bafe9e6f5b2b3a3348096657870387839fa020a3d373b1cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e0a5fc5e4e82feb4ca34ac150b36b36710ce3de350e213fb71cf5993062420
+oid sha256:8531775f4e5c3819ae81b2ea1cfeb7e992dc0ca011334fb9ed6fb83e3392e473
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016220600162206,
+  "epoch": 0.0202757502027575,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,49 @@
       "eval_samples_per_second": 8.646,
       "eval_steps_per_second": 2.166,
       "step": 20
+    },
+    {
+      "epoch": 0.0170316301703163,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.017842660178426603,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.0186536901865369,
+      "grad_norm": NaN,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.019464720194647202,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.019464720194647202,
+      "eval_loss": NaN,
+      "eval_runtime": 60.0733,
+      "eval_samples_per_second": 8.639,
+      "eval_steps_per_second": 2.164,
+      "step": 24
+    },
+    {
+      "epoch": 0.0202757502027575,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -209,12 +252,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 9273591044505600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null