Training in progress, step 117, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace8180d008b2da42bf4093c2df37186d49fa2bf86efeb748f3e6504459425d3
+oid sha256:b894b16459384adc9eae088c49c6239b3d317b6a2aad7c22d872e9a4a95a5ab5
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585668ee2d3bbb3d08e8fb23932ed517f9cd95a7a7e88fa50be7de4389439084
+oid sha256:d5ff8b11311c3c56642b3255a3d8006dc750a14cb5908fb3673f7444f527b18f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89b61481eb2980a04190d12a0165f95c9fc0a4db20ad8cc3d895835eac42f68
+oid sha256:49a9f08177ba433a82ec0fa599b737a453ff55e83dd9d31c6fddaf5bc4b0a0b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014694973330036384,
+  "epoch": 0.016531844996290932,
   "eval_steps": 13,
-  "global_step": 104,
+  "global_step": 117,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -317,6 +317,49 @@
       "eval_samples_per_second": 50.566,
       "eval_steps_per_second": 6.321,
       "step": 104
+    },
+    {
+      "epoch": 0.014836271150517503,
+      "grad_norm": NaN,
+      "learning_rate": 2.3398396174233178e-05,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.01526016461196086,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 108
+    },
+    {
+      "epoch": 0.015684058073404217,
+      "grad_norm": NaN,
+      "learning_rate": 1.7956219300748793e-05,
+      "loss": 0.0,
+      "step": 111
+    },
+    {
+      "epoch": 0.016107951534847575,
+      "grad_norm": NaN,
+      "learning_rate": 1.544686755065677e-05,
+      "loss": 0.0,
+      "step": 114
+    },
+    {
+      "epoch": 0.016531844996290932,
+      "grad_norm": NaN,
+      "learning_rate": 1.3094050125632972e-05,
+      "loss": 0.0,
+      "step": 117
+    },
+    {
+      "epoch": 0.016531844996290932,
+      "eval_loss": NaN,
+      "eval_runtime": 235.7863,
+      "eval_samples_per_second": 50.554,
+      "eval_steps_per_second": 6.319,
+      "step": 117
     }
   ],
   "logging_steps": 3,
@@ -336,7 +379,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.218473766571213e+16,
+  "total_flos": 2.4957829873926144e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null