Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b0338daac15cfc77c983eea6a6122874f95852031cec6efb33fb6843974f909
+oid sha256:e017ff86b8a295f11193c500291f5991ea24bf880a065787121b3fb732878a01
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff7218517ca4458c3d29b7230cefb18dfe8c171f0a8309d5494771317c7b329
+oid sha256:8013718d7b486d4bea38838926eb12f405577f302b56db31ac78355ece57c039
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c94fe50942676a4b800b8807f5b832311548d8f2c40eff1078995f3e3f0ab5
+oid sha256:331fb2b7f8ecd022b2d839d7c7167894d42e426406c8fde67ed9a8d4c78176de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e5e69cb9645219d028edd3b028ebf30583f1263680ed0ab467551ed740d562
+oid sha256:805137337f587aa7655dd5f599cea8ff7a9813cfb0f1bcf2d0b7dd019723b5ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4666666666666667,
+  "epoch": 0.5,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,6 +497,41 @@
       "learning_rate": 1.6890222222222224e-05,
       "loss": 0.067,
       "step": 7000
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 0.21629302203655243,
+      "learning_rate": 1.684577777777778e-05,
+      "loss": 0.0684,
+      "step": 7100
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.45061948895454407,
+      "learning_rate": 1.6801333333333335e-05,
+      "loss": 0.0713,
+      "step": 7200
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 0.19869284331798553,
+      "learning_rate": 1.675688888888889e-05,
+      "loss": 0.0608,
+      "step": 7300
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 0.23369118571281433,
+      "learning_rate": 1.6712444444444445e-05,
+      "loss": 0.0675,
+      "step": 7400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.16967739164829254,
+      "learning_rate": 1.6668e-05,
+      "loss": 0.0604,
+      "step": 7500
     }
   ],
   "logging_steps": 100,
@@ -516,7 +551,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.705082093568e+16,
+  "total_flos": 1.82687367168e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null