Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c0277f54c09c949fa6a8943edf7edac098878a0d43666f5fcb22403b14c145
+oid sha256:c8d3c8dd94f84edaa86e5bd551b7162baf24e06c95af4e529bb9d4594c6a6db5
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e5ea83ac97396889fe2821e60cc59e33e316d14ac1826fe80fb9efcd4c6f98b
+oid sha256:2048e83e96cb7813259491a8808e1d0ab1e6d1d06aed4036ff05048952b8dc6c
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a414c666e8625c7f4e23102be45d01b76de4812ff286110f0f9a0e1c67f33573
+oid sha256:3bf859859237e604ff95efafec03b923cfd86a352aded0ea1471a828fd47b6ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b37e9ef30e383e795affd2915d5979e774d36e929b105a379fff9b722cf9675
+oid sha256:b861104f137d1fe8ca8f0827472a7b8a3a6723f1ff99340210bc3ae74cc04899
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.39595454931259155,
-  "best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-3000",
-  "epoch": 274.5098039215686,
+  "best_metric": 0.39425286650657654,
+  "best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-4000",
+  "epoch": 313.72549019607845,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,84 @@
       "eval_samples_per_second": 28.036,
       "eval_steps_per_second": 3.582,
       "step": 3500
+    },
+    {
+      "epoch": 278.4313725490196,
+      "grad_norm": 0.6087095737457275,
+      "learning_rate": 2.2550000000000004e-06,
+      "loss": 0.4122,
+      "step": 3550
+    },
+    {
+      "epoch": 282.3529411764706,
+      "grad_norm": 0.5597049593925476,
+      "learning_rate": 2.0050000000000003e-06,
+      "loss": 0.4111,
+      "step": 3600
+    },
+    {
+      "epoch": 286.27450980392155,
+      "grad_norm": 0.5411703586578369,
+      "learning_rate": 1.7550000000000001e-06,
+      "loss": 0.4069,
+      "step": 3650
+    },
+    {
+      "epoch": 290.19607843137254,
+      "grad_norm": 0.6042822599411011,
+      "learning_rate": 1.505e-06,
+      "loss": 0.4079,
+      "step": 3700
+    },
+    {
+      "epoch": 294.11764705882354,
+      "grad_norm": 0.6852837204933167,
+      "learning_rate": 1.255e-06,
+      "loss": 0.4068,
+      "step": 3750
+    },
+    {
+      "epoch": 298.03921568627453,
+      "grad_norm": 0.6229822039604187,
+      "learning_rate": 1.0050000000000001e-06,
+      "loss": 0.4112,
+      "step": 3800
+    },
+    {
+      "epoch": 301.96078431372547,
+      "grad_norm": 0.6330438256263733,
+      "learning_rate": 7.550000000000001e-07,
+      "loss": 0.4053,
+      "step": 3850
+    },
+    {
+      "epoch": 305.88235294117646,
+      "grad_norm": 0.5041052103042603,
+      "learning_rate": 5.05e-07,
+      "loss": 0.405,
+      "step": 3900
+    },
+    {
+      "epoch": 309.80392156862746,
+      "grad_norm": 0.6818642020225525,
+      "learning_rate": 2.55e-07,
+      "loss": 0.4095,
+      "step": 3950
+    },
+    {
+      "epoch": 313.72549019607845,
+      "grad_norm": 0.4621037542819977,
+      "learning_rate": 5e-09,
+      "loss": 0.4108,
+      "step": 4000
+    },
+    {
+      "epoch": 313.72549019607845,
+      "eval_loss": 0.39425286650657654,
+      "eval_runtime": 6.437,
+      "eval_samples_per_second": 27.963,
+      "eval_steps_per_second": 3.573,
+      "step": 4000
     }
   ],
   "logging_steps": 50,
@@ -567,12 +645,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.616303628785914e+16,
+  "total_flos": 8.70355911863679e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null