Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df3835ebb8a410086e40775839dcd215ef004799cfb91fcd99f06ed300090ac
+oid sha256:9f6eebfa927dd597f5b2467576d1b4e5a74f50d01f39872c16db123c54f82a8c
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4781021424dfe21d5e3b5512b453bc796c4f3a8a727e03932fd2a9a0231c980
+oid sha256:b3e73b5e3c013bcae7afbd24e1fe85edb611862c66c9afeb07e64296806e4d87
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024891101431238332,
+  "epoch": 0.049782202862476664,
   "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": 39.75,
       "eval_steps_per_second": 19.875,
       "step": 10
+    },
+    {
+      "epoch": 0.029869321717486,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.037336652146857496,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.037336652146857496,
+      "eval_loss": NaN,
+      "eval_runtime": 4.3264,
+      "eval_samples_per_second": 39.294,
+      "eval_steps_per_second": 19.647,
+      "step": 15
+    },
+    {
+      "epoch": 0.044803982576229,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.049782202862476664,
+      "eval_loss": NaN,
+      "eval_runtime": 4.2831,
+      "eval_samples_per_second": 39.691,
+      "eval_steps_per_second": 19.845,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 767623314800640.0,
+  "total_flos": 1535246629601280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null