Training in progress, step 35000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70be4ea2eb3b605b7bbf19f657f7030b3328a2472cfce6fd98277ee878f3d42d
+oid sha256:54c3b650aacadef454b8db2ad2f4748bd2cc9caa9988d9586a8661ac87876f39
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea42d9a3f547f1d5475d09c5cf077e380e3710c708660172e4c053a5a76213e
+oid sha256:3300d0ac109580f5456c1f0fcf9e3276c33da9efc5df83c8e4bc2c715849e9ac
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd91d8604c3c73ee737187beb59c853ab84bc04334806ba928b483da59e07022
+oid sha256:c640612ca6874adba07e3028442a5de517f2bd82ce8dc7d5cdd1701c4e1b1ee5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b582570b847f10b59692f51f82170b4e892f7a8342116f22c17cd2ce4cb0c5e
+oid sha256:1ec6550e2fb94624e4937a6e7d695ee415ac08cd206a873e9804651b6a923373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3,
+  "epoch": 2.3333333333333335,
   "eval_steps": 500,
-  "global_step": 34500,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2438,6 +2438,41 @@
       "learning_rate": 4.672444444444445e-06,
       "loss": 0.0484,
       "step": 34500
+    },
+    {
+      "epoch": 2.3066666666666666,
+      "grad_norm": 0.112776979804039,
+      "learning_rate": 4.628e-06,
+      "loss": 0.0534,
+      "step": 34600
+    },
+    {
+      "epoch": 2.3133333333333335,
+      "grad_norm": 0.3088347315788269,
+      "learning_rate": 4.5835555555555565e-06,
+      "loss": 0.0565,
+      "step": 34700
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.18766255676746368,
+      "learning_rate": 4.539111111111112e-06,
+      "loss": 0.0548,
+      "step": 34800
+    },
+    {
+      "epoch": 2.3266666666666667,
+      "grad_norm": 0.24050170183181763,
+      "learning_rate": 4.494666666666667e-06,
+      "loss": 0.0602,
+      "step": 34900
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.15460790693759918,
+      "learning_rate": 4.450222222222222e-06,
+      "loss": 0.0558,
+      "step": 35000
     }
   ],
   "logging_steps": 100,
@@ -2457,7 +2492,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.403618889728e+16,
+  "total_flos": 8.52541046784e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null