Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a054bde49e1eaba391534cd5d6084e672a214d2bcdb35339a02e7f60b250444a
+oid sha256:cf8da7c23b1e47f3ba2493fe93f0a278b94001ecbc454bc3d1cbd1c554efc7b6
 size 2611614300

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88cdb9d1903a098ab709a4a31d88f0bc508b9856da309433ddbe56564fc7e4c6
+oid sha256:60ac0399a1858e68abc023c3dbe79181914f8d84aea2858e11c819a6ec40a38a
 size 5213028466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5980b31e2575fd555b9b5d35d9fc68ab477ebc20a6cd235cb9c30ed6d640a78
+oid sha256:9a228e0231f77a60f74c7f1659cd80088fa76c53c8543bf03a2911226aa2f93d
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0001f7c15dabc5570df0e50376618b295ab961ad32150f9a463dd24a0d337e21
+oid sha256:8de616ad8f3978afcb9d1fe171a32410caa4a828d20b3ff6b27beb33aaba188b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024993702758484677,
+  "epoch": 0.049987405516969355,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 9.875031242189454e-05,
       "loss": 89312785858.56,
       "step": 100
+    },
+    {
+      "epoch": 0.049987405516969355,
+      "grad_norm": 1.2562867403030396,
+      "learning_rate": 9.750062484378905e-05,
+      "loss": 11385077760.0,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9448797327261696e+16,
+  "total_flos": 3.889759465452339e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null