Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d50eeabfb6258b47f80c4287b04eae339f2bcdd2adc92422732cfea4385d47
+oid sha256:af54bf45b4ea734175c8bd735e147b83bfa4467a6a02927fce71013f50f2e031
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925f490db36c228becd31509d72df687d2fa95aa8acf7ad4097ac7ecd0f54d30
+oid sha256:91db2977a4e8b2ac56d4d9528647fa170313a74ed3d096d47e9525e450940a2b
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b0884f157293c23ccd8333c122a369315e2deb59504578aa420ad7f9561fc9
+oid sha256:6d5d4da7add6dcbf76add6d041d8a356430f2fcdcb5e01b3a00941303e2c6c7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20da249583a46b691b28ceb0e3fd46db03f73ee684cd77a32c44cbf4d68cb68
+oid sha256:92a26e97f6adf463a9a2328a07aa990cecfc61051330c04894ef3e783375a50f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3,
+  "epoch": 1.3333333333333333,
   "eval_steps": 500,
-  "global_step": 19500,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1380,6 +1380,41 @@
       "learning_rate": 1.1336e-05,
       "loss": 0.0578,
       "step": 19500
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 0.16407087445259094,
+      "learning_rate": 1.1291555555555555e-05,
+      "loss": 0.0569,
+      "step": 19600
+    },
+    {
+      "epoch": 1.3133333333333335,
+      "grad_norm": 0.1125895082950592,
+      "learning_rate": 1.1247111111111113e-05,
+      "loss": 0.0535,
+      "step": 19700
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.24300092458724976,
+      "learning_rate": 1.1202666666666669e-05,
+      "loss": 0.0555,
+      "step": 19800
+    },
+    {
+      "epoch": 1.3266666666666667,
+      "grad_norm": 0.16412054002285004,
+      "learning_rate": 1.1158222222222224e-05,
+      "loss": 0.0569,
+      "step": 19900
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.2398436963558197,
+      "learning_rate": 1.1113777777777779e-05,
+      "loss": 0.0672,
+      "step": 20000
     }
   ],
   "logging_steps": 100,
@@ -1399,7 +1434,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.749871546368e+16,
+  "total_flos": 4.87166312448e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null