Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba8406c53f83c09c1ffeabb8ce1224cbfb422c48a8d00576b75192664a252c36
+oid sha256:81de9b280c9780cf3feaf944ed951aca1ee11fa1f451d8fe3983a73cd5acf1ff
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a0eee39df69ccbd8f983b1f8a785ab0e689171b4e4bf4b721400c5924aa6fe6
+oid sha256:af4dab1bd40e26061d7373627d7696e6ebcd35c8a058d709a83490dc1881eb7c
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31b319d83cac2dd433a790a8abad45ac5c816140a98898786a198f16bd883cd
+oid sha256:74d64db17f5541ae52946e5b4e988b9c8496b896a7fd08f53e3196d74b6433cb
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf04c7f94b59cd606c42cf0fc828e78ab899584bb7bbb628645ada4c3c807cf
+oid sha256:be625e9e3b7c2d0674d4d1ce1044104bf1d523b3db3eb682bb066436988eb458
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006,
+  "epoch": 0.008,
   "eval_steps": 500,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,76 @@
       "learning_rate": 0.00029880360721442885,
       "loss": 10.386916351318359,
       "step": 300
+    },
+    {
+      "epoch": 0.0062,
+      "grad_norm": 2.5315372943878174,
+      "learning_rate": 0.00029874348697394784,
+      "loss": 8.981736755371093,
+      "step": 310
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 1.1698753833770752,
+      "learning_rate": 0.0002986833667334669,
+      "loss": 8.788543701171875,
+      "step": 320
+    },
+    {
+      "epoch": 0.0066,
+      "grad_norm": 1.353128433227539,
+      "learning_rate": 0.00029862324649298594,
+      "loss": 9.83536148071289,
+      "step": 330
+    },
+    {
+      "epoch": 0.0068,
+      "grad_norm": 1.1758288145065308,
+      "learning_rate": 0.000298563126252505,
+      "loss": 11.545357513427735,
+      "step": 340
+    },
+    {
+      "epoch": 0.007,
+      "grad_norm": 1.2862794399261475,
+      "learning_rate": 0.00029850300601202403,
+      "loss": 9.087370300292969,
+      "step": 350
+    },
+    {
+      "epoch": 0.0072,
+      "grad_norm": 1.449062466621399,
+      "learning_rate": 0.0002984428857715431,
+      "loss": 11.168739318847656,
+      "step": 360
+    },
+    {
+      "epoch": 0.0074,
+      "grad_norm": 0.5698562264442444,
+      "learning_rate": 0.00029838276553106213,
+      "loss": 7.454578399658203,
+      "step": 370
+    },
+    {
+      "epoch": 0.0076,
+      "grad_norm": 0.9205979108810425,
+      "learning_rate": 0.0002983226452905811,
+      "loss": 11.321672058105468,
+      "step": 380
+    },
+    {
+      "epoch": 0.0078,
+      "grad_norm": 0.8094843626022339,
+      "learning_rate": 0.00029826252505010017,
+      "loss": 9.661857604980469,
+      "step": 390
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.9517568945884705,
+      "learning_rate": 0.0002982024048096192,
+      "loss": 7.4337646484375,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -237,7 +307,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5668312449024000.0,
+  "total_flos": 7557749932032000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null