Training in progress, step 20500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af54bf45b4ea734175c8bd735e147b83bfa4467a6a02927fce71013f50f2e031
+oid sha256:c86189a77f037cbdd789ce6756a983f35d8424562557bec70f1d6f9478782956
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91db2977a4e8b2ac56d4d9528647fa170313a74ed3d096d47e9525e450940a2b
+oid sha256:5f3b9b0a558aef18a5c43688fb84bceaf30915a8e0f42a94e913404b25ec6988
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5d4da7add6dcbf76add6d041d8a356430f2fcdcb5e01b3a00941303e2c6c7d
+oid sha256:b1cb24b28fd79d1b2e08e97a1214134b31144058db4370cb477a455701ee578a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a26e97f6adf463a9a2328a07aa990cecfc61051330c04894ef3e783375a50f
+oid sha256:02d6f63efc0f911cd45ec87b983b2cf047da0e86188af05e21eda256bea09b7e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3333333333333333,
+  "epoch": 1.3666666666666667,
   "eval_steps": 500,
-  "global_step": 20000,
+  "global_step": 20500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1415,6 +1415,41 @@
       "learning_rate": 1.1113777777777779e-05,
       "loss": 0.0672,
       "step": 20000
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.19268549978733063,
+      "learning_rate": 1.1069333333333334e-05,
+      "loss": 0.0577,
+      "step": 20100
+    },
+    {
+      "epoch": 1.3466666666666667,
+      "grad_norm": 0.24096272885799408,
+      "learning_rate": 1.102488888888889e-05,
+      "loss": 0.0597,
+      "step": 20200
+    },
+    {
+      "epoch": 1.3533333333333333,
+      "grad_norm": 0.3714766204357147,
+      "learning_rate": 1.0980444444444445e-05,
+      "loss": 0.0602,
+      "step": 20300
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.15587754547595978,
+      "learning_rate": 1.0936e-05,
+      "loss": 0.056,
+      "step": 20400
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.21720756590366364,
+      "learning_rate": 1.0891555555555557e-05,
+      "loss": 0.0609,
+      "step": 20500
     }
   ],
   "logging_steps": 100,
@@ -1434,7 +1469,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.87166312448e+16,
+  "total_flos": 4.993454702592e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null