Training in progress, step 54, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b60b8de0890f9945b9abe187160b7623af2eb90aa6d2def12bcbc4d83eba06
+oid sha256:ec4bc64a2a4d3723ce8d6d8e746b2721c3ef5ae4d728a75f020af1330d6c66b9
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f28d8fa2e8a1951654f8671d631d1d79f21c8364ce4113c741da1519130a64c
+oid sha256:d981e986fc880ede433373fb3bed25f74e9754b75202cb893fc5c6a38d25f5e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6617647058823529,
+  "epoch": 0.7941176470588235,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 6.857,
       "eval_steps_per_second": 0.894,
       "step": 45
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": NaN,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 15.3127,
+      "step": 48
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": NaN,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.8674,
+      "step": 51
+    },
+    {
+      "epoch": 0.7941176470588235,
+      "grad_norm": NaN,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 16.1705,
+      "step": 54
+    },
+    {
+      "epoch": 0.7941176470588235,
+      "eval_loss": NaN,
+      "eval_runtime": 16.7643,
+      "eval_samples_per_second": 6.86,
+      "eval_steps_per_second": 0.895,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.279699816808448e+17,
+  "total_flos": 1.5356397801701376e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null