Training in progress, step 29000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3614617ee76c86000db29cd744353eb118d9a3d06e5a97f4af361b3577a0b872
+oid sha256:d0d7856ac14e3c9a690e3c9dee53a7a64870218a71216a1c30e598f861133e14
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ba13f67cae6dd4ea0abf5c768c7bd8aaa350d6c17a47580822772f8d79c646
+oid sha256:ed3cf9b04c05bb73a17b1d26a6bf42f7dfd71e2f3a8b717e1cbc8e86af15e592
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:606d09e46c381a6ca79c1c2761e1f43da7a02f07449ea8dc08c4fd55302f6057
+oid sha256:13275cc6296652d5dbe96fab3538f55b506c905c768d5c0e2ff0cc00f18629a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf940af0b3fe4a79522e2cb3cee03ca9bdc7bb9e1119203316379171ea473573
+oid sha256:6cce86ca086e9ceba19d07f438b59e29c1c4e8071fe80d69909be3a44b7f8d02
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9,
+  "epoch": 1.9333333333333333,
   "eval_steps": 500,
-  "global_step": 28500,
+  "global_step": 29000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2010,6 +2010,41 @@
       "learning_rate": 7.337777777777778e-06,
       "loss": 0.0541,
       "step": 28500
+    },
+    {
+      "epoch": 1.9066666666666667,
+      "grad_norm": 0.15182781219482422,
+      "learning_rate": 7.2933333333333335e-06,
+      "loss": 0.0566,
+      "step": 28600
+    },
+    {
+      "epoch": 1.9133333333333333,
+      "grad_norm": 0.18824052810668945,
+      "learning_rate": 7.24888888888889e-06,
+      "loss": 0.0566,
+      "step": 28700
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.2716074585914612,
+      "learning_rate": 7.204444444444445e-06,
+      "loss": 0.0571,
+      "step": 28800
+    },
+    {
+      "epoch": 1.9266666666666667,
+      "grad_norm": 0.18709616363048553,
+      "learning_rate": 7.16e-06,
+      "loss": 0.0569,
+      "step": 28900
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.1409674882888794,
+      "learning_rate": 7.115555555555557e-06,
+      "loss": 0.0603,
+      "step": 29000
     }
   ],
   "logging_steps": 100,
@@ -2029,7 +2064,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.942119952384e+16,
+  "total_flos": 7.063911530496e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null