Training in progress, step 900, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95845485e25b4e71d2c0bc5fd4f1468902c7f8a03ea37a4f2495fe5034eefc9
+oid sha256:b8776e463dfb2fb241b207dcf6f197b8bcc48d01c1573dc9e37df7cf649be1f5
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4244fea4c4b2cbbec2a91bf09236d9029134586c67149d0cb24583dee45401f
+oid sha256:167de084d9751ce323bad469c1dc3226ac11b692074ae311e213a15b0836b0ac
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae1d68d95f8f78dc7a2b9834f2969479f23c5f9f0407eda9de530dc2ff5cbfe
+oid sha256:60f4fa52f793b7ffd9d5a0e3203e96f72580141d20eac3efe05c0fac6521a8ec
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1851851851851851,
+  "epoch": 1.3333333333333333,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,13 +111,26 @@
       "eval_samples_per_second": 1.904,
       "eval_steps_per_second": 0.239,
       "step": 800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0,
+      "loss": 8.3458,
+      "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "eval_runtime": 787.2391,
+      "eval_samples_per_second": 1.905,
+      "eval_steps_per_second": 0.239,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.66592319062016e+17,
+  "total_flos": 1.87416358944768e+17,
   "trial_name": null,
   "trial_params": null
 }