Training in progress, step 1100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:135023d735474a62fef41f9fc86b17aa3dafa835f40463325b62635ce08a2f8b
+oid sha256:0b0e9b3f4ea4bfa18d8649a6588e6f31e5c42ffd86b85f74f3759d40af7fe5ec
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f89845f1e9c425ff77a21ebf1e6ff7f2fe52cc5d8d1eee15fffa7085d08ac1e6
+oid sha256:4f83cff620522aa496468277a3bc22911f9c6f4bbc5118c2de2593b7cadedc59
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aa7e5f7f3366b7db6f25a9e3fa739116674bd641ce589a5940ff73f382fec0c
+oid sha256:35f81b1683bb9d9f30a4338a9869629a080b447f19358d02a2b979f0e40cf033
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4835dfebca207db20e97bc75a0cdfb3c9040e987a06d53d84bc51055c8c81f56
+oid sha256:ff8a23e76bdb5af3bd48e8027611be72cb7ebf75d37e5954461baee2e16e1294
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02,
+  "epoch": 0.022,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -708,6 +708,76 @@
       "learning_rate": 0.0002945951903807615,
       "loss": 71.14970703125,
       "step": 1000
+    },
+    {
+      "epoch": 0.0202,
+      "grad_norm": 9.4298677444458,
+      "learning_rate": 0.00029453507014028053,
+      "loss": 68.8579345703125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.0204,
+      "grad_norm": 11.69355583190918,
+      "learning_rate": 0.0002944749498997996,
+      "loss": 66.29926147460938,
+      "step": 1020
+    },
+    {
+      "epoch": 0.0206,
+      "grad_norm": 9.638633728027344,
+      "learning_rate": 0.00029441482965931857,
+      "loss": 69.4812744140625,
+      "step": 1030
+    },
+    {
+      "epoch": 0.0208,
+      "grad_norm": 7.3949384689331055,
+      "learning_rate": 0.0002943547094188377,
+      "loss": 69.908984375,
+      "step": 1040
+    },
+    {
+      "epoch": 0.021,
+      "grad_norm": 9.138998031616211,
+      "learning_rate": 0.0002942945891783567,
+      "loss": 68.20003662109374,
+      "step": 1050
+    },
+    {
+      "epoch": 0.0212,
+      "grad_norm": 9.650430679321289,
+      "learning_rate": 0.0002942344689378757,
+      "loss": 64.76406860351562,
+      "step": 1060
+    },
+    {
+      "epoch": 0.0214,
+      "grad_norm": 8.263360977172852,
+      "learning_rate": 0.00029417434869739476,
+      "loss": 73.39156494140624,
+      "step": 1070
+    },
+    {
+      "epoch": 0.0216,
+      "grad_norm": 8.509857177734375,
+      "learning_rate": 0.0002941142284569138,
+      "loss": 65.55498657226562,
+      "step": 1080
+    },
+    {
+      "epoch": 0.0218,
+      "grad_norm": 10.162703514099121,
+      "learning_rate": 0.00029405410821643286,
+      "loss": 71.94191284179688,
+      "step": 1090
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 10.938014030456543,
+      "learning_rate": 0.00029399398797595185,
+      "loss": 68.12153930664063,
+      "step": 1100
     }
   ],
   "logging_steps": 10,
@@ -727,7 +797,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1337576305472e+16,
+  "total_flos": 1.19190649908096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null