Training in progress, step 75500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c522b64bf739d00b582ffd0a643c3efac07a2c50ad5c8217960816597aa1b7
+oid sha256:5ed82d5257b4cdeaec1d231fbec337de862f44e90266f53728fcbf29b890f8e6
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea6b08f3a21ebd27e904f6c480a2e53e645065339857b33fb47d39a33ab84a4
+oid sha256:69cdecd3770cd3ae9c846d7dadb18be339bd32aceb2caffae5672232803f7c66
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a111aa87150022a7015d18e06b4152718ab7403244bfc3590d03281fc35af0e
+oid sha256:f3671ea294e107cc370136abc27be7287dc3b56ef92ccc5f8f9601f526a27ee5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d655df9252eb0df8fffa1d13ade85fbe45fc35430c05ca667845bcc4d9ed179
+oid sha256:a453de14621fc10a1234ab9d975e3259dfd9038a626ba405b531f0f548996565
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.48,
+  "epoch": 0.4832,
   "eval_steps": 500,
-  "global_step": 75000,
+  "global_step": 75500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1057,6 +1057,13 @@
       "learning_rate": 3.8004320000000006e-05,
       "loss": 0.3153,
       "step": 75000
+    },
+    {
+      "epoch": 0.4832,
+      "grad_norm": 0.6181166768074036,
+      "learning_rate": 3.792432e-05,
+      "loss": 0.3113,
+      "step": 75500
     }
   ],
   "logging_steps": 500,
@@ -1076,7 +1083,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.65374734336e+17,
+  "total_flos": 3.6781056589824e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null