Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33856acc364918614328c2a78d03cb4bc465c9f6cf183b7f21193afc32d22567
+oid sha256:822c1d335e61ca8da2a7d87051a771922c03875285a9ba53879e4d4459146519
 size 26498

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c77abaf15e25b4e9145b370c9dc48d83fd299b71887b47ead2ceb51619405f
+oid sha256:13116ae88fba26584055b52d39fa169ee22213d14d9d3568dcfbe12fcdff8955
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006512006512006512,
+  "epoch": 0.013024013024013023,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 644.78,
       "eval_steps_per_second": 322.39,
       "step": 2
+    },
+    {
+      "epoch": 0.009768009768009768,
+      "grad_norm": NaN,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.013024013024013023,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.013024013024013023,
+      "eval_loss": NaN,
+      "eval_runtime": 0.8381,
+      "eval_samples_per_second": 618.035,
+      "eval_steps_per_second": 309.018,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 845611008.0,
+  "total_flos": 1641480192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null