Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c051876b7496fda4f2caccdf5129b551534d5f88bc28af4738894764658bb314
+oid sha256:695bbbedba207764edddb65b6bd8a2d3ebdc06d036e29ba7309642d95b1cc980
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c733b0f31e3e722be51c4633bae72d5137544a40f3fb7cb94b99406a711634b
+oid sha256:3e68dfbe308897873721bb8f7c44b8d125885348449d7e2143b9178be20fcdad
 size 14244

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": 0.004796163069544364,
+  "epoch": 0.007194244604316547,
   "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": 11.237,
       "eval_steps_per_second": 5.629,
       "step": 6
+    },
+    {
+      "epoch": 0.005595523581135092,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.006394884092725819,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.007194244604316547,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.007194244604316547,
+      "eval_loss": NaN,
+      "eval_runtime": 47.0125,
+      "eval_samples_per_second": 11.21,
+      "eval_steps_per_second": 5.616,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1010386518147072.0,
+  "total_flos": 1469653117304832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null