Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d8128d3ee97dfc5815897000fb196918d75596b92d9fce4fe4affefcac8f66
+oid sha256:7c257b247e8c08acbfcd7291433a1faa2e705e5481f1c0044ca79d1fad933d43
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea9bf44004c33643f7f74aafd292aa4cca7aefd935a3682b55c0f70f2a3db8ae
+oid sha256:b1ae6309517a2108e6bd10ea1fd8da0edc71a65cb14916086f3915020657220a
 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": 0.14457831325301204,
+  "epoch": 0.21686746987951808,
   "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": 19.046,
       "eval_steps_per_second": 9.523,
       "step": 6
+    },
+    {
+      "epoch": 0.1686746987951807,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 1.142,
+      "step": 9
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "eval_loss": NaN,
+      "eval_runtime": 0.9436,
+      "eval_samples_per_second": 19.076,
+      "eval_steps_per_second": 9.538,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2091163255308288.0,
+  "total_flos": 3049613080657920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null