Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee611077166c26b20307fdd3c0cf39ae19b4588270e3fe1071a80a80b37edd5
+oid sha256:71d8e2c9ab6ce512e4fe5f2de9bff9c5fb04e35dd7e76c6585ba2a1f7251c9f1
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c831098936f8c9a42813e8882588a3316dea304e0af3806046395a51dd9b0eeb
+oid sha256:c4bce206b4d535dc3e5a0da947635d46d61eba86f9f2bc5d6b08b01b38370047
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004338394793926247,
+  "epoch": 0.008676789587852495,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 7.142,
       "eval_steps_per_second": 3.58,
       "step": 4
+    },
+    {
+      "epoch": 0.005422993492407809,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.006507592190889371,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.007592190889370932,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.008676789587852495,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.008676789587852495,
+      "eval_loss": NaN,
+      "eval_runtime": 80.2469,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 2.43,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1117937171693568.0,
+  "total_flos": 2235874343387136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null