Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9083026baf394fb415584f9450a9815f04c4f920e1a3d7e0792f399cb0c8f14
+oid sha256:7e7df361fa5657a8da4a5771da472699fdcc53d00002aaf78cdbb2775a1c8933
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17497878d08faf25fe38885077e3aa1828a302dbf1462506caa61bc0949aa9e
+oid sha256:c571a56e86ec8c5e7e19d268195b65724654cac92b20bb980f95f1d2d75baef4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005780346820809248,
+  "epoch": 0.011560693641618497,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 13.576,
       "eval_steps_per_second": 6.825,
       "step": 10
+    },
+    {
+      "epoch": 0.006936416184971098,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.008670520231213872,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.008670520231213872,
+      "eval_loss": NaN,
+      "eval_runtime": 13.5426,
+      "eval_samples_per_second": 13.513,
+      "eval_steps_per_second": 6.793,
+      "step": 15
+    },
+    {
+      "epoch": 0.010404624277456647,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.011560693641618497,
+      "eval_loss": NaN,
+      "eval_runtime": 13.5725,
+      "eval_samples_per_second": 13.483,
+      "eval_steps_per_second": 6.778,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -66,12 +103,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 873798366658560.0,
+  "total_flos": 1747596733317120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null