Training in progress, step 24, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3d286ea812d7f47487febd90bfaaae81751895a68e09a0af013d888c1709b0
+oid sha256:99c4aa03c7dbfb68f8a1a83b79c9b04697aaef5d784b13de09f16331a9d25cef
 size 128584596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
+oid sha256:e9c762e745e6b10819fd8afb33b4a1b715c756c7b22945b0044c81ebcb593a7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
+oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.059673659673659674,
+  "epoch": 0.08951048951048951,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 4.073,
       "eval_steps_per_second": 2.036,
       "step": 16
+    },
+    {
+      "epoch": 0.06340326340326341,
+      "grad_norm": NaN,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.06713286713286713,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.07086247086247087,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.07459207459207459,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.07832167832167833,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.08205128205128205,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.08578088578088579,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.08951048951048951,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.08951048951048951,
+      "eval_loss": NaN,
+      "eval_runtime": 111.2213,
+      "eval_samples_per_second": 4.064,
+      "eval_steps_per_second": 2.032,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3417620425618227e+17,
+  "total_flos": 2.012643063842734e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null