Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8776e463dfb2fb241b207dcf6f197b8bcc48d01c1573dc9e37df7cf649be1f5
+oid sha256:a91c94a3317d424396cebab93b82a8c58b613fe4abf0d6fcffd5315b8502bb89
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:167de084d9751ce323bad469c1dc3226ac11b692074ae311e213a15b0836b0ac
+oid sha256:b1f4e39da86dc5867b7d3c7f30f9588fe7974d19848a0aea34e0df4cde8b3932
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f4fa52f793b7ffd9d5a0e3203e96f72580141d20eac3efe05c0fac6521a8ec
+oid sha256:8ed2d4b131d874aa658f97c179cbc7aae45ebbdf63422dc95963b45fededa2b1
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3333333333333333,
+  "epoch": 1.4814814814814814,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -124,13 +124,26 @@
       "eval_samples_per_second": 1.905,
       "eval_steps_per_second": 0.239,
       "step": 900
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0,
+      "loss": 8.5777,
+      "step": 1000
+    },
+    {
+      "epoch": 1.48,
+      "eval_runtime": 787.2473,
+      "eval_samples_per_second": 1.905,
+      "eval_steps_per_second": 0.239,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.87416358944768e+17,
+  "total_flos": 2.0824039882752e+17,
   "trial_name": null,
   "trial_params": null
 }