Training in progress, step 1700, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad3d06f0f980d4edd0f8032b0d5b2084cb4ed65a2b41d878824284e87b4394a
+oid sha256:b967e2784a474c2b26a772d6672c7c1550fbc2adbfc9acc49598b5c489a5d89f
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997a463cccc37ed909b6ca16f4417c673f1e6a3e05dc425808a13eea5f9dd965
+oid sha256:caa26cd40f8bd339159d1064efac06feb5cc588c22df170f65fdc862f4bca0ad
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feeaa9dcb687f34c537c5701e819b6bcadabf7b8c8429475390fcaf3b1c3a91e
+oid sha256:119acaabeb3e83e43ca8b3d26532ead56181d0051d00810e5cb205761dea60f2
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3703703703703702,
+  "epoch": 2.5185185185185186,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -215,13 +215,26 @@
       "eval_samples_per_second": 1.903,
       "eval_steps_per_second": 0.238,
       "step": 1600
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.0,
+      "loss": 8.7091,
+      "step": 1700
+    },
+    {
+      "epoch": 2.52,
+      "eval_runtime": 788.7408,
+      "eval_samples_per_second": 1.902,
+      "eval_steps_per_second": 0.238,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.33184638124032e+17,
+  "total_flos": 3.54008678006784e+17,
   "trial_name": null,
   "trial_params": null
 }