Training in progress, step 72, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693ff4204f2c381359f37672e2e08211d45de79c7eea5ecc791a3a399031be52
+oid sha256:e094b6a7706bc13f3dfb399a8829ce11c6058e40322c61a240b31733545bf058
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a57addfbff74916a19f69367dbaba8fb11c41a22dbd8d8d5643cf9660a77e109
+oid sha256:17e9faf12ead7606f814b2c7b878d47944e2a6802bf5d9ed7531262bc321f20e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3631123919308357,
+  "epoch": 0.414985590778098,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 9.495,
       "eval_steps_per_second": 1.199,
       "step": 63
+    },
+    {
+      "epoch": 0.3804034582132565,
+      "grad_norm": NaN,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.3976945244956772,
+      "grad_norm": NaN,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.414985590778098,
+      "grad_norm": NaN,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.414985590778098,
+      "eval_loss": NaN,
+      "eval_runtime": 30.9168,
+      "eval_samples_per_second": 9.477,
+      "eval_steps_per_second": 1.197,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4737778914885632e+17,
+  "total_flos": 1.6942643476955136e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null