Training in progress, step 81, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e094b6a7706bc13f3dfb399a8829ce11c6058e40322c61a240b31733545bf058
+oid sha256:88ae6b63bb2e23ca5393ba65e8024db166d018ceffb643c15b2c9af1bde132ce
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e9faf12ead7606f814b2c7b878d47944e2a6802bf5d9ed7531262bc321f20e
+oid sha256:63e29ed66e6543dff1960b19b8b4946890f74c62337f6c46d1c621b30742df02
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.414985590778098,
+  "epoch": 0.4668587896253602,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 9.477,
       "eval_steps_per_second": 1.197,
       "step": 72
+    },
+    {
+      "epoch": 0.4322766570605187,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.4495677233429395,
+      "grad_norm": NaN,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.4668587896253602,
+      "grad_norm": NaN,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.4668587896253602,
+      "eval_loss": NaN,
+      "eval_runtime": 30.8942,
+      "eval_samples_per_second": 9.484,
+      "eval_steps_per_second": 1.198,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6942643476955136e+17,
+  "total_flos": 1.9031462535757824e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null