Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9420f6e0cbe96d463b6a4014a3a4226533c94884d9c932c86cf855a82f63ab51
+oid sha256:6d88836b9df77eeafa71ebd1be49569120733ab9444d4f7b9fce08e0fa809f9c
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bae1b9e027a929ce85ac614c50c47056094e65f2096c8ce15c7d081fe833586
+oid sha256:2971cbe0f61f3a458c833915f8f877a317595f1d6fd358e7da6a072617671769
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3a68034a6fca5f7c1565a9344e41aadbdff3752a8799ae94336c8c84c6d63d
+oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028808864265927978,
+  "epoch": 0.057617728531855955,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 36.47,
       "eval_steps_per_second": 18.235,
       "step": 13
+    },
+    {
+      "epoch": 0.03102493074792244,
+      "grad_norm": NaN,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0332409972299169,
+      "grad_norm": NaN,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.03545706371191136,
+      "grad_norm": NaN,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.037673130193905814,
+      "grad_norm": NaN,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.039889196675900275,
+      "grad_norm": NaN,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": NaN,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0443213296398892,
+      "grad_norm": NaN,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04653739612188366,
+      "grad_norm": NaN,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.04875346260387812,
+      "grad_norm": NaN,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.05096952908587258,
+      "grad_norm": NaN,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.05318559556786703,
+      "grad_norm": NaN,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.055401662049861494,
+      "grad_norm": NaN,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.057617728531855955,
+      "grad_norm": NaN,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.057617728531855955,
+      "eval_loss": NaN,
+      "eval_runtime": 5.1749,
+      "eval_samples_per_second": 36.716,
+      "eval_steps_per_second": 18.358,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 843175472136192.0,
+  "total_flos": 1686350944272384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null