Training in progress, step 10074, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02998f7e9d94c7f46713ace0e277bc3596448b515038d4f707450c23811962d
+oid sha256:15a7cea6ce4b9d8dac48e585a7abea04090775d79128f2909f7e9d7925c29749
 size 532568837

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:396b2e01f369a79c1a52b3ef3823ed8de1e99074cd23b445cb60415bde158199
+oid sha256:9dfeff1913f0bc2395f345ab6145fab2f726a75124923e2a8674e4e8647f93c8
 size 266276525

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9204453e030579bdd226736775f8c6095e16b9f2a366dfe9186190d57314c68
+oid sha256:9e7bf973ea7de736bb327ffc19187b92d63e286f116b6db2af5a5a588f3c2508
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6575d2c3a8439954baf4c55941916c7bf669136fc2605f9e90afd2ab3c947992
+oid sha256:6f9f3d403b37f48f67eb536bde724d16ba32882bb5029b456fb2d29d78a83c80
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7502904638484226,
+  "epoch": 0.9003485566181071,
   "eval_steps": 500,
-  "global_step": 8395,
+  "global_step": 10074,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,13 +103,37 @@
       "learning_rate": 3.8083534423689934e-05,
       "loss": 0.011,
       "step": 8000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.7338755325170554e-05,
+      "loss": 0.0094,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.659397622665118e-05,
+      "loss": 0.0101,
+      "step": 9000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.584919712813179e-05,
+      "loss": 0.0106,
+      "step": 9500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.510441802961242e-05,
+      "loss": 0.0104,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
   "max_steps": 33567,
   "num_train_epochs": 3,
   "save_steps": 1679,
-  "total_flos": 1.423517834182656e+17,
+  "total_flos": 1.7082214010191872e+17,
   "trial_name": null,
   "trial_params": null
 }