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 sha256:295df23accd18bf63f6586c545aa39f983fe5305c20276210c3bf839c8976711
+oid sha256:e9c21d8e3e94e9283d0504cc86a9b330b1d3539f061aa7169b6a7aefd45c2421
 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": 0.01269169751454257,
+  "epoch": 0.019037546271813855,
   "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": 40.286,
       "eval_steps_per_second": 20.244,
       "step": 6
+    },
+    {
+      "epoch": 0.014806980433632998,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.016922263352723427,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.019037546271813855,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.019037546271813855,
+      "eval_loss": NaN,
+      "eval_runtime": 4.9372,
+      "eval_samples_per_second": 40.306,
+      "eval_steps_per_second": 20.254,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 597046578905088.0,
+  "total_flos": 872606538399744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null