Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4706180c011789fa7ce7d894b4ab7382341f53742f948c67aae277e220bf7321
+oid sha256:b8663c5a1b351b7e358ac35fd06d575dd41d4bb2e8ae839c297516acb56ea026
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f70ff5e7d58c937960d91d55439e248668e354dcca9536a19ed0c6b84b6e4e1
+oid sha256:6d0111122582677907a3439cdc155b8f2b03ecd33b0560c3d4d969c8b991403d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032679738562091504,
+  "epoch": 0.006535947712418301,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 48.946,
       "eval_steps_per_second": 24.536,
       "step": 3
+    },
+    {
+      "epoch": 0.004357298474945534,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0054466230936819175,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.006535947712418301,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.006535947712418301,
+      "eval_loss": NaN,
+      "eval_runtime": 8.1166,
+      "eval_samples_per_second": 47.68,
+      "eval_steps_per_second": 23.902,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 25477327749120.0,
+  "total_flos": 56834038824960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null