Training in progress, step 6, checkpoint

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c81455e3b5fa4ac608032487865cd5d9aad1b7633e0d831b8d1e1e3f9ce6956
+oid sha256:2b9e29ca9f1840ccec759292965b44b25e81d2b6f5643637c96ef211cfb804af
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013697066544914964,
+  "epoch": 0.002739413308982993,
   "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": 7.658,
       "eval_steps_per_second": 7.658,
       "step": 3
+    },
+    {
+      "epoch": 0.0018262755393219953,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 7.7222,
+      "step": 4
+    },
+    {
+      "epoch": 0.002282844424152494,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 7.0675,
+      "step": 5
+    },
+    {
+      "epoch": 0.002739413308982993,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 7.9791,
+      "step": 6
+    },
+    {
+      "epoch": 0.002739413308982993,
+      "eval_loss": 8.7471342086792,
+      "eval_runtime": 60.3363,
+      "eval_samples_per_second": 7.657,
+      "eval_steps_per_second": 7.657,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 603178974314496.0,
+  "total_flos": 1206357948628992.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null