Training in progress, step 35500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14606a4fd2efe003cd94f2f3132f89585010c23daaa16f96514f4fcc508bfb25
+oid sha256:3861bd1608634176b86c22fab14e91d5922afbea3206f22e4f3840d5f3e25dce
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b767b8691e014dc4b9a052fdb848b8867ac7c38357c59a17bce57ff20c6a0f
+oid sha256:11a0010065f83b0c00c40c0e9534ced36be241e02735146d72a04843181a0ac6
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92676f6c9ecd30b269dc071838794534f4c77243d55ff0d335d2c17307bfeff
+oid sha256:136f96a13c6078fdd47727e710b03134e99b70b338dbfa95741c3f9cc237dd1a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.47478227841232806,
-  "global_step": 35000,
+  "epoch": 0.481564882389647,
+  "global_step": 35500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -426,11 +426,17 @@
       "learning_rate": 0.0,
       "loss": 0.0388,
       "step": 35000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0,
+      "loss": 0.0372,
+      "step": 35500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 3.657108328493875e+16,
+  "total_flos": 3.709349747962675e+16,
   "trial_name": null,
   "trial_params": null
 }

runs/Oct16_21-59-35_1b3a04926831/events.out.tfevents.1665958666.1b3a04926831.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bede8433114c707c5c372202689bab332fd7ae0f0b4a6b54423b15020ff6130e
-size 56717
+oid sha256:58bddd1d70ced0a5de185d6f5c01b273a2813af969df83c23e71d76e183117fb
+size 56877