Training in progress, step 24, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f006b585d9775a3af8971c5ff37a0e48a648d3b62195020cb71cc09db0de7d48
+oid sha256:cac56998adf15054f52ed49436e10fd43863f3523d01e4294f5e38198d0c835b
 size 37965300

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": 0.03689292405245713,
+  "epoch": 0.05533938607868569,
   "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": 16.568,
       "eval_steps_per_second": 8.295,
       "step": 16
+    },
+    {
+      "epoch": 0.039198731805735694,
+      "grad_norm": NaN,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.041504539559014265,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.04381034731229284,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.04611615506557141,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04842196281884998,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.05072777057212855,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.053033578325407116,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.05533938607868569,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.05533938607868569,
+      "eval_loss": NaN,
+      "eval_runtime": 44.1472,
+      "eval_samples_per_second": 16.558,
+      "eval_steps_per_second": 8.29,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6720241111334912e+16,
+  "total_flos": 2.508036166700237e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null