Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44041984529e3d1651d11cbed261b1dfcacb7ffef17a414df0f52a4da9bbbc0
+oid sha256:aaa6395b004f9c2d6401ff45a67d3ff77ced4e1cca08c39aaffc9d0ab4d436d0
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c76696460c5035e7be36105fcf57d1518b8088f7b053cf7bc3cee0f14a560b6f
+oid sha256:5d725da6d88da70a48d641b1e7244de8f6513972858c737cd255c634cc0c677d
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c47459c0e2dffaed00a8dda72fc27b999da170e8df9b15995d74bf1989ecab4
+oid sha256:05fba8800114836b393870e5407236cda2061438ed36a892d186b43b76973657
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c124d5873e6dde5040a6a31973ca68127e3dfe277695e3cb113af8a1a01ff662
+oid sha256:0aef1303f298e810b9c563fac5650fcaebc5d5e2a568db30104db374f503c826
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.39249518513679504,
   "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-6000",
-  "epoch": 294.11764705882354,
+  "epoch": 313.72549019607845,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1177,6 +1177,84 @@
       "eval_samples_per_second": 26.891,
       "eval_steps_per_second": 3.436,
       "step": 7500
+    },
+    {
+      "epoch": 296.078431372549,
+      "grad_norm": 0.7973820567131042,
+      "learning_rate": 7.550000000000001e-07,
+      "loss": 0.3954,
+      "step": 7550
+    },
+    {
+      "epoch": 298.03921568627453,
+      "grad_norm": 0.7256256341934204,
+      "learning_rate": 6.716666666666668e-07,
+      "loss": 0.3934,
+      "step": 7600
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 1.1149753332138062,
+      "learning_rate": 5.883333333333333e-07,
+      "loss": 0.3913,
+      "step": 7650
+    },
+    {
+      "epoch": 301.96078431372547,
+      "grad_norm": 0.6526250243186951,
+      "learning_rate": 5.05e-07,
+      "loss": 0.391,
+      "step": 7700
+    },
+    {
+      "epoch": 303.921568627451,
+      "grad_norm": 0.8052578568458557,
+      "learning_rate": 4.2166666666666667e-07,
+      "loss": 0.3889,
+      "step": 7750
+    },
+    {
+      "epoch": 305.88235294117646,
+      "grad_norm": 0.7933726906776428,
+      "learning_rate": 3.3833333333333336e-07,
+      "loss": 0.3918,
+      "step": 7800
+    },
+    {
+      "epoch": 307.84313725490193,
+      "grad_norm": 0.7680366635322571,
+      "learning_rate": 2.55e-07,
+      "loss": 0.3948,
+      "step": 7850
+    },
+    {
+      "epoch": 309.80392156862746,
+      "grad_norm": 0.8762979507446289,
+      "learning_rate": 1.7166666666666668e-07,
+      "loss": 0.3937,
+      "step": 7900
+    },
+    {
+      "epoch": 311.7647058823529,
+      "grad_norm": 0.7918867468833923,
+      "learning_rate": 8.833333333333334e-08,
+      "loss": 0.3889,
+      "step": 7950
+    },
+    {
+      "epoch": 313.72549019607845,
+      "grad_norm": 0.7141278982162476,
+      "learning_rate": 5e-09,
+      "loss": 0.3944,
+      "step": 8000
+    },
+    {
+      "epoch": 313.72549019607845,
+      "eval_loss": 0.3929772675037384,
+      "eval_runtime": 6.3752,
+      "eval_samples_per_second": 28.234,
+      "eval_steps_per_second": 3.608,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1191,12 +1269,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.159614773058426e+16,
+  "total_flos": 8.70355911863679e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null