Training in progress, step 32400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0ba60c26c51cf355e00f36b738194907999ee45ca4f8785c8e31a7623c98e9b
+oid sha256:7d064f2332ced8d589411b314d74aa64dbff4eaac037d31068824e3f0f523bb4
 size 355967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c91ffc2b10c397203e4c7dead597b4287d25e577c0e6df9529c30b50b8aa2a
+oid sha256:2ab97c4aa3f15e2600cfe333e231ff19c0e23e67658b81c4a2261ae5c1af8966
 size 712029114

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10bb518808924f8ec5f4cbecfd83ac3913ab2f1042a575afcab54bd6c4cbfb73
+oid sha256:cae11df3d2278a8ff4a04dff28369bcaea0cb0b7c145bd92f25a776466f1de16
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70f42d06afa8cde3bcd311e92f70e0210525048300805011ba7af6d0c326c99
+oid sha256:7303cf337b0f3230e3aa10fc27672d49524c56a76ad0cc51d0583606599733d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9945653010638462,
+  "epoch": 0.9976444506027435,
   "eval_steps": 500,
-  "global_step": 32300,
+  "global_step": 32400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22617,6 +22617,76 @@
       "learning_rate": 4.355681129189493e-09,
       "loss": 0.3696,
       "step": 32300
+    },
+    {
+      "epoch": 0.9948732160177359,
+      "grad_norm": 17.661426544189453,
+      "learning_rate": 3.909265612511703e-09,
+      "loss": 0.4423,
+      "step": 32310
+    },
+    {
+      "epoch": 0.9951811309716256,
+      "grad_norm": 25.57279396057129,
+      "learning_rate": 3.486978218514292e-09,
+      "loss": 0.3579,
+      "step": 32320
+    },
+    {
+      "epoch": 0.9954890459255153,
+      "grad_norm": 14.529350280761719,
+      "learning_rate": 3.0888193548239687e-09,
+      "loss": 0.3905,
+      "step": 32330
+    },
+    {
+      "epoch": 0.9957969608794051,
+      "grad_norm": 13.980672836303711,
+      "learning_rate": 2.714789405772189e-09,
+      "loss": 0.2954,
+      "step": 32340
+    },
+    {
+      "epoch": 0.9961048758332949,
+      "grad_norm": 15.562602043151855,
+      "learning_rate": 2.364888732403481e-09,
+      "loss": 0.2862,
+      "step": 32350
+    },
+    {
+      "epoch": 0.9964127907871846,
+      "grad_norm": 13.155916213989258,
+      "learning_rate": 2.039117672464341e-09,
+      "loss": 0.4238,
+      "step": 32360
+    },
+    {
+      "epoch": 0.9967207057410743,
+      "grad_norm": 10.378691673278809,
+      "learning_rate": 1.7374765404143401e-09,
+      "loss": 0.4403,
+      "step": 32370
+    },
+    {
+      "epoch": 0.997028620694964,
+      "grad_norm": 11.533722877502441,
+      "learning_rate": 1.4599656274261186e-09,
+      "loss": 0.4543,
+      "step": 32380
+    },
+    {
+      "epoch": 0.9973365356488538,
+      "grad_norm": 15.00934886932373,
+      "learning_rate": 1.2065852013659618e-09,
+      "loss": 0.5758,
+      "step": 32390
+    },
+    {
+      "epoch": 0.9976444506027435,
+      "grad_norm": 19.549671173095703,
+      "learning_rate": 9.773355068215528e-10,
+      "loss": 0.6151,
+      "step": 32400
     }
   ],
   "logging_steps": 10,
@@ -22636,7 +22706,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1605715542016e+18,
+  "total_flos": 2.1672606302208e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null