Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4319a6f51a54c7413e8bf68e188a3032c16e5eb84c56040908f7a9ec1ff1d0ff
+oid sha256:9437f12960c841f1daf2e00a25774ae8bdad0eb3e4c519dded92389128edac28
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e4404bd00d9024fcfa0e5fd55f108c80822b27810a8c8b26ece36dc7bf2954
+oid sha256:c0e8cb57bb1738e114da4ba2c9fb8d1fb02970ac0d5dfc2af2947ca09e1d6eb5
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8306d67f4ae112278509d98c24005dbfe9b6cff3bd9027aebc63d98f08e35c
+oid sha256:d68d439874b3cc3c54bfb8a7b792c53676f8610cfb9b65dd7d1c08c8b1019ac4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c31f0ff329076bad6198fd634761dbf86a425d5fd3a12f8157396623a161b2f
+oid sha256:2094983ff9f11d6250b785dfe29c8c85823d0967c14aec5d510a4e0433164679
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3939879834651947,
   "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-4000",
-  "epoch": 156.86274509803923,
+  "epoch": 176.47058823529412,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -631,6 +631,84 @@
       "eval_samples_per_second": 26.993,
       "eval_steps_per_second": 3.449,
       "step": 4000
+    },
+    {
+      "epoch": 158.8235294117647,
+      "grad_norm": 0.8880926370620728,
+      "learning_rate": 6.5866666666666666e-06,
+      "loss": 0.4149,
+      "step": 4050
+    },
+    {
+      "epoch": 160.7843137254902,
+      "grad_norm": 0.8387724757194519,
+      "learning_rate": 6.5033333333333335e-06,
+      "loss": 0.4066,
+      "step": 4100
+    },
+    {
+      "epoch": 162.7450980392157,
+      "grad_norm": 0.9014448523521423,
+      "learning_rate": 6.42e-06,
+      "loss": 0.4102,
+      "step": 4150
+    },
+    {
+      "epoch": 164.7058823529412,
+      "grad_norm": 0.7693892121315002,
+      "learning_rate": 6.336666666666667e-06,
+      "loss": 0.4066,
+      "step": 4200
+    },
+    {
+      "epoch": 166.66666666666666,
+      "grad_norm": 0.9693483114242554,
+      "learning_rate": 6.253333333333333e-06,
+      "loss": 0.4084,
+      "step": 4250
+    },
+    {
+      "epoch": 168.62745098039215,
+      "grad_norm": 0.8914594054222107,
+      "learning_rate": 6.17e-06,
+      "loss": 0.4109,
+      "step": 4300
+    },
+    {
+      "epoch": 170.58823529411765,
+      "grad_norm": 11.76923942565918,
+      "learning_rate": 6.086666666666667e-06,
+      "loss": 0.4109,
+      "step": 4350
+    },
+    {
+      "epoch": 172.54901960784315,
+      "grad_norm": 0.8837347626686096,
+      "learning_rate": 6.003333333333334e-06,
+      "loss": 0.4051,
+      "step": 4400
+    },
+    {
+      "epoch": 174.50980392156862,
+      "grad_norm": 0.8585467338562012,
+      "learning_rate": 5.92e-06,
+      "loss": 0.4017,
+      "step": 4450
+    },
+    {
+      "epoch": 176.47058823529412,
+      "grad_norm": 0.967064380645752,
+      "learning_rate": 5.836666666666667e-06,
+      "loss": 0.4028,
+      "step": 4500
+    },
+    {
+      "epoch": 176.47058823529412,
+      "eval_loss": 0.395079106092453,
+      "eval_runtime": 6.3984,
+      "eval_samples_per_second": 28.132,
+      "eval_steps_per_second": 3.595,
+      "step": 4500
     }
   ],
   "logging_steps": 50,
@@ -650,7 +728,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.352128118839037e+16,
+  "total_flos": 4.896064149915233e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null