Training in progress, step 34500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4ab360c914af5780dbdab371c96384f68fadc50929f69d6d527fb768d4c4fc
+oid sha256:70be4ea2eb3b605b7bbf19f657f7030b3328a2472cfce6fd98277ee878f3d42d
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe48f4318badae6c7301c7e1af6b474ccbe7f71331abdb7cdd8a9a8ea72715a
+oid sha256:0ea42d9a3f547f1d5475d09c5cf077e380e3710c708660172e4c053a5a76213e
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d089c8bc4767a68a0971e6301211196ccb288fdbf802f4d0800d2c395bd6e0
+oid sha256:fd91d8604c3c73ee737187beb59c853ab84bc04334806ba928b483da59e07022
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5881a400174694043dc48b7e6a0f928fe1bcddfe30dc261df5a9e4e69d0e718
+oid sha256:7b582570b847f10b59692f51f82170b4e892f7a8342116f22c17cd2ce4cb0c5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2666666666666666,
+  "epoch": 2.3,
   "eval_steps": 500,
-  "global_step": 34000,
+  "global_step": 34500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2403,6 +2403,41 @@
       "learning_rate": 4.8942222222222225e-06,
       "loss": 0.0533,
       "step": 34000
+    },
+    {
+      "epoch": 2.2733333333333334,
+      "grad_norm": 0.2103540301322937,
+      "learning_rate": 4.8497777777777786e-06,
+      "loss": 0.0544,
+      "step": 34100
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.3394009470939636,
+      "learning_rate": 4.805333333333334e-06,
+      "loss": 0.0512,
+      "step": 34200
+    },
+    {
+      "epoch": 2.2866666666666666,
+      "grad_norm": 0.18866145610809326,
+      "learning_rate": 4.760888888888889e-06,
+      "loss": 0.0505,
+      "step": 34300
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 0.21299579739570618,
+      "learning_rate": 4.716888888888889e-06,
+      "loss": 0.0466,
+      "step": 34400
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.12839581072330475,
+      "learning_rate": 4.672444444444445e-06,
+      "loss": 0.0484,
+      "step": 34500
     }
   ],
   "logging_steps": 100,
@@ -2422,7 +2457,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.281827311616e+16,
+  "total_flos": 8.403618889728e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null