Training in progress, step 260, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8055d2764c12216b0e46e9e6bf1bdb2ed21e379d85c4c630698a9f4b56f3abe
+oid sha256:13f77a6e08b348f3bfb900b881b3c0efd47cddd13ccec836d46baf6594b6f3e2
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:002030670da2c6c1d5f6f14b7e7d0cf24108da51304d9ecb3a09892895958096
+oid sha256:f80b6d762e8051ccdd6210ef7b74a7ba43674bb3e1e3e7699e248b774548282e
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac82c9e97acc88aa1fa4930480a8fc2c4136df9608e7f4941250ac47b8c3ac9
+oid sha256:c5c9c2ffce3220f0a3b45e92be8237cbba5afc5034da73b9518a294a18be9087
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ac16ada9aeee5f77175e25a04261752f50812666958fe6ce8c2d82948a891d
+oid sha256:2f2f956373db75de51d3c7ddd6d4c86d4b3f8ed55480d2a899fce0776e14a980
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108ec0968af236f6199c1f716a40487225162213cb414b717c6f1aeb82bcbc29
+oid sha256:d3a36d0f4565e0cd31cd0465a8062a29bd158a6ba54be5d6acec2d94425b0892
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.46153846153846,
+  "epoch": 20.0,
   "eval_steps": 40,
-  "global_step": 240,
+  "global_step": 260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 284.702,
       "eval_steps_per_second": 4.552,
       "step": 240
+    },
+    {
+      "epoch": 19.23076923076923,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00013506375551927547,
+      "loss": 9.3407,
+      "step": 250
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.400390625,
+      "learning_rate": 0.00012985148110016947,
+      "loss": 9.3153,
+      "step": 260
     }
   ],
   "logging_steps": 10,
@@ -250,7 +264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 98198051880960.0,
+  "total_flos": 106381222871040.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null