Training in progress, step 10500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0baa3dd96d088bead94dbda6bab34f0c313d0c57e9151146de3df5a1e1f64865
+oid sha256:77e593f3a425792215a0ffc55ad46e682e584dd45510fd16ed87ae0d9e1aa9ec
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553bd3918a19e2ae78c3e0f7e91309a2c72baec2743a9d30370a800e7b4023ad
+oid sha256:90bdaa625228d1ffaf4ca4ad84f2df76f4a28d1be0a86cdeaaa382a0e5f37f4a
 size 2912179275

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6fd97f105f8edb4cfe7d5753c1c5716920ac3feb07414e58ddd6a461f2d28f
+oid sha256:71f0928908afa8c0698e794c9360d1cbb2fa78932a472e329e06d61e6ec5b824
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3adb6bc25384383695fdce45b404d5230771ecce083b43cbabb3d264f6d5378
+oid sha256:41ffc1bb08a6f87b20f54f9f460a367d7345cb018e76f21b6138fdfb25206ba1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.014533333333333,
+  "epoch": 4.020333333333333,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1408,6 +1408,76 @@
       "learning_rate": 2.295766776460101e-05,
       "loss": 0.09009716987609863,
       "step": 10000
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 1.9024637937545776,
+      "learning_rate": 2.2889850389631912e-05,
+      "loss": 2.2911944580078125,
+      "step": 10050
+    },
+    {
+      "epoch": 0.33666666666666667,
+      "grad_norm": 2.425832748413086,
+      "learning_rate": 2.2821809315960874e-05,
+      "loss": 2.136341400146484,
+      "step": 10100
+    },
+    {
+      "epoch": 0.3383333333333333,
+      "grad_norm": 1.8301362991333008,
+      "learning_rate": 2.2753546472737268e-05,
+      "loss": 2.104422302246094,
+      "step": 10150
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.5538557767868042,
+      "learning_rate": 2.2685063795398218e-05,
+      "loss": 2.0370709228515627,
+      "step": 10200
+    },
+    {
+      "epoch": 0.3416666666666667,
+      "grad_norm": 1.5662953853607178,
+      "learning_rate": 2.2616363225613756e-05,
+      "loss": 2.068159637451172,
+      "step": 10250
+    },
+    {
+      "epoch": 0.3433333333333333,
+      "grad_norm": 1.5763871669769287,
+      "learning_rate": 2.2547446711231746e-05,
+      "loss": 2.0447808837890626,
+      "step": 10300
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 1.388518214225769,
+      "learning_rate": 2.2479700900763443e-05,
+      "loss": 2.0605596923828124,
+      "step": 10350
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.4810057878494263,
+      "learning_rate": 2.2410362586529476e-05,
+      "loss": 2.0104673767089842,
+      "step": 10400
+    },
+    {
+      "epoch": 0.34833333333333333,
+      "grad_norm": 1.6268818378448486,
+      "learning_rate": 2.234081416837596e-05,
+      "loss": 1.985343475341797,
+      "step": 10450
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.4944297075271606,
+      "learning_rate": 2.2271057618189578e-05,
+      "loss": 1.9991339111328126,
+      "step": 10500
     }
   ],
   "logging_steps": 50,
@@ -1427,7 +1497,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.922664024295424e+17,
+  "total_flos": 9.366507127769825e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null