Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd16865f9cd765dc6095ba0da10f8f0471206cffe4f6fdf3e6f5fe160b11832
-size 2024
+oid sha256:c797d444df6d175c431d7c6439766226ced8a1d607cd53d64c1e297f7408bfaa
+size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b9e29ca9f1840ccec759292965b44b25e81d2b6f5643637c96ef211cfb804af
+oid sha256:975e2fef0ce023c45a0d7bbabf76a79358b37a1de8f82a4354020f8b97bfa2fa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
+oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002739413308982993,
+  "epoch": 0.004109119963474489,
   "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": 7.657,
       "eval_steps_per_second": 7.657,
       "step": 6
+    },
+    {
+      "epoch": 0.0031959821938134917,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 8.8075,
+      "step": 7
+    },
+    {
+      "epoch": 0.0036525510786439906,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 9.0902,
+      "step": 8
+    },
+    {
+      "epoch": 0.004109119963474489,
+      "grad_norm": 34.917747497558594,
+      "learning_rate": 2e-05,
+      "loss": 6.32,
+      "step": 9
+    },
+    {
+      "epoch": 0.004109119963474489,
+      "eval_loss": 8.7471342086792,
+      "eval_runtime": 59.8996,
+      "eval_samples_per_second": 7.713,
+      "eval_steps_per_second": 7.713,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1206357948628992.0,
+  "total_flos": 1809536922943488.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null