Training in progress, step 16, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3404912a82c21bf33ba87256b7b08a0c6d3a3b2bc2a5a759b6ea48582efdb1be
+oid sha256:f006b585d9775a3af8971c5ff37a0e48a648d3b62195020cb71cc09db0de7d48
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105f96f979368944b59d27d1e74fc1fa8227279f7d5146ad57761b7d32f1a2d9
+oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018446462026228565,
+  "epoch": 0.03689292405245713,
   "eval_steps": 8,
-  "global_step": 8,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,70 @@
       "eval_samples_per_second": 16.556,
       "eval_steps_per_second": 8.289,
       "step": 8
+    },
+    {
+      "epoch": 0.020752269779507133,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.023058077532785704,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.025363885286064276,
+      "grad_norm": NaN,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.027669693039342844,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.029975500792621415,
+      "grad_norm": NaN,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.03228130854589999,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.03458711629917856,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.03689292405245713,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.03689292405245713,
+      "eval_loss": NaN,
+      "eval_runtime": 44.1216,
+      "eval_samples_per_second": 16.568,
+      "eval_steps_per_second": 8.295,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -98,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8360120555667456.0,
+  "total_flos": 1.6720241111334912e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null