Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8768e79529253ec6a4a9c9ac4ed31fdfdbd11d2032b8c45d8b47efa9c9d546c7
+oid sha256:135023d735474a62fef41f9fc86b17aa3dafa835f40463325b62635ce08a2f8b
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b359910b5fd17aadf25fd00b37f0d204cc86fee7b829ec01ab07ad0364a48e0c
+oid sha256:f89845f1e9c425ff77a21ebf1e6ff7f2fe52cc5d8d1eee15fffa7085d08ac1e6
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779676ad450eae2b6879d7f004a716095853f54998471414edbab1cbed9cedac
+oid sha256:9aa7e5f7f3366b7db6f25a9e3fa739116674bd641ce589a5940ff73f382fec0c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:653cba8a20af8c5396af38192396529e15aba7f27a53a1c15a4069355b1b5a35
+oid sha256:4835dfebca207db20e97bc75a0cdfb3c9040e987a06d53d84bc51055c8c81f56
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018,
+  "epoch": 0.02,
   "eval_steps": 500,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -638,6 +638,76 @@
       "learning_rate": 0.0002951963927855711,
       "loss": 71.75267333984375,
       "step": 900
+    },
+    {
+      "epoch": 0.0182,
+      "grad_norm": 7.856244087219238,
+      "learning_rate": 0.00029513627254509016,
+      "loss": 73.38182983398437,
+      "step": 910
+    },
+    {
+      "epoch": 0.0184,
+      "grad_norm": 7.895908355712891,
+      "learning_rate": 0.00029507615230460916,
+      "loss": 70.02378540039062,
+      "step": 920
+    },
+    {
+      "epoch": 0.0186,
+      "grad_norm": 9.500384330749512,
+      "learning_rate": 0.0002950160320641282,
+      "loss": 69.76512451171875,
+      "step": 930
+    },
+    {
+      "epoch": 0.0188,
+      "grad_norm": 8.77175235748291,
+      "learning_rate": 0.0002949559118236473,
+      "loss": 69.60545654296875,
+      "step": 940
+    },
+    {
+      "epoch": 0.019,
+      "grad_norm": 9.102203369140625,
+      "learning_rate": 0.0002948957915831663,
+      "loss": 71.84405517578125,
+      "step": 950
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 8.29865837097168,
+      "learning_rate": 0.00029483567134268535,
+      "loss": 67.64026489257813,
+      "step": 960
+    },
+    {
+      "epoch": 0.0194,
+      "grad_norm": 6.868947505950928,
+      "learning_rate": 0.0002947755511022044,
+      "loss": 65.34761962890624,
+      "step": 970
+    },
+    {
+      "epoch": 0.0196,
+      "grad_norm": 9.127030372619629,
+      "learning_rate": 0.00029471543086172344,
+      "loss": 69.42554321289063,
+      "step": 980
+    },
+    {
+      "epoch": 0.0198,
+      "grad_norm": 7.779689311981201,
+      "learning_rate": 0.00029465531062124244,
+      "loss": 72.64813842773438,
+      "step": 990
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 9.583319664001465,
+      "learning_rate": 0.0002945951903807615,
+      "loss": 71.14970703125,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
@@ -657,7 +727,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.071637991053056e+16,
+  "total_flos": 1.1337576305472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null