Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9a0e2e05d9eacf5c069bd04337e5de4a41461f12fee894e25c6f74e61bcfb7
+oid sha256:d8cdd28be9549af1d5bae665c6e126d72e4da1f2ba57ad65c7b14a6a4a333524
 size 37965300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f70a09efed6f9bfd0e89bcc03ed83843c149bc1a8aed4c526ce0e831f28eb8
+oid sha256:e767df46c90584f75b1e6b6257ff8fcd692290b2ffd0de4529d0298f5cd31d24
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e1ffba66ebd0baf2b920f9ae2738c8721a19b9723b342f2d169f123ca94ed3
+oid sha256:3d87a1a565de8d9454ec5b84c8c49d8c31a26f884bf198b921051cab4aead55b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7339772db12266fe7eed955eb376a3a5e6df0199ef8f977071677928845bae76
+oid sha256:7584ce9d7e86e7470dbb7669c7bdd8e57a5b4e1e70b8320491fe89e5e06fec20
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922c1f6d2c32c0a328d51fb80e9b310682ef431fd00720c628f8cd031238583e
+oid sha256:789264f785683542d0f42ae9ec4e080a45d30fc0072fb7c515425e498d63a077
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008794430194210334,
+  "epoch": 0.0131916452913155,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 43.176,
       "eval_steps_per_second": 5.406,
       "step": 6
+    },
+    {
+      "epoch": 0.010260168559912056,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.011725906925613778,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0131916452913155,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0131916452913155,
+      "eval_loss": NaN,
+      "eval_runtime": 26.6068,
+      "eval_samples_per_second": 43.222,
+      "eval_steps_per_second": 5.412,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6270090416750592.0,
+  "total_flos": 9405135625125888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null