Training in progress, step 44000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f3f60f837bc2d6b892b2d0546640ca46d3f194d47c20345c8767c8ccaa5c07
+oid sha256:440a49b94440cacff83f386734abd67ba7ebf0590110ed4471a084cfe5123375
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6211545bbfeb1c43922e986aa4087c1ebccc0eedc2e220fb0dba4944f73f39c0
+oid sha256:fa8b9c57b8597bab044debeab7cc337cd4ec0227fbde8dd82185f8b22bf3a034
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85869ac30f3cee5a03da0dea6f3e99cba1ee27fffe68afedef7c1dce40526f4d
+oid sha256:4d5486da749b598a61d62adc9f231f7450ebff3f0e201a6edd91a104ce06d0fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6701719fda370188bcff5587df70fa5f1ce20ee16a7c8ee75ec8b4d555e1ea
+oid sha256:91c87f62d5aed9d7a6d425bf9b7734b81e555049c990c49c2d251a8a04bf9890
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9,
+  "epoch": 2.9333333333333336,
   "eval_steps": 500,
-  "global_step": 43500,
+  "global_step": 44000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3068,6 +3068,41 @@
       "learning_rate": 6.737777777777778e-07,
       "loss": 0.0521,
       "step": 43500
+    },
+    {
+      "epoch": 2.9066666666666667,
+      "grad_norm": 0.2009938806295395,
+      "learning_rate": 6.293333333333334e-07,
+      "loss": 0.0576,
+      "step": 43600
+    },
+    {
+      "epoch": 2.913333333333333,
+      "grad_norm": 0.1709711253643036,
+      "learning_rate": 5.848888888888889e-07,
+      "loss": 0.0551,
+      "step": 43700
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.21005882322788239,
+      "learning_rate": 5.404444444444444e-07,
+      "loss": 0.0525,
+      "step": 43800
+    },
+    {
+      "epoch": 2.9266666666666667,
+      "grad_norm": 0.24121809005737305,
+      "learning_rate": 4.96e-07,
+      "loss": 0.0559,
+      "step": 43900
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.31166791915893555,
+      "learning_rate": 4.5155555555555554e-07,
+      "loss": 0.051,
+      "step": 44000
     }
   ],
   "logging_steps": 100,
@@ -3087,7 +3122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0595867295744e+17,
+  "total_flos": 1.0717658873856e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null