Training in progress, step 150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c2ecd92e57b2e66ca22969473f53cb6e090828806462e132c671e6e2d3f419
+oid sha256:a53818166c997a5f044919047269de5637df30c7f3e35e43de5a49620a745bac
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b8912999820c91e1c8c8c8687a2636c8a6f4f493c6ac56b50cf98a74706856
+oid sha256:28dd6e6307fa015e692b6b556932fde5666659c25197be0bf989d11c190341f1
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddb8fcdae8dea7e10388731f63246ec0494e51d6d509273113166b14d83f0e3
+oid sha256:6371144a111a3072f591f746239d824c555a871e29310d8421824db33cb69d80
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24238ca2ad5e52c7a2d983c253be8a0ab25f258c2785c7ba56c4bfa08fb89d84
+oid sha256:2bc12850c9ff9801525024d9966df4799da11201038cba4971a720ddadfcd7ec
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
+oid sha256:bb0e11d33e42a9adcc5c976e37e059307e91eb6ae74c969ff1b3eb2f755782d6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.6923076923076925,
+  "epoch": 11.538461538461538,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 284.164,
       "eval_steps_per_second": 4.544,
       "step": 100
+    },
+    {
+      "epoch": 8.461538461538462,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00019043571606975777,
+      "loss": 9.942,
+      "step": 110
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 9.8887,
+      "step": 120
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00018519194088383273,
+      "loss": 9.836,
+      "step": 130
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.0001821777815225245,
+      "loss": 9.7845,
+      "step": 140
+    },
+    {
+      "epoch": 11.538461538461538,
+      "grad_norm": 0.361328125,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 9.7359,
+      "step": 150
+    },
+    {
+      "epoch": 11.538461538461538,
+      "eval_loss": 9.719038963317871,
+      "eval_runtime": 5.2736,
+      "eval_samples_per_second": 284.626,
+      "eval_steps_per_second": 4.551,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 40915854950400.0,
+  "total_flos": 61373782425600.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null