Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9437f12960c841f1daf2e00a25774ae8bdad0eb3e4c519dded92389128edac28
+oid sha256:b5e8f8ee6350b5bf599e72c4ed95c5ed225294745782627a48eb47afcd60198a
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e8cb57bb1738e114da4ba2c9fb8d1fb02970ac0d5dfc2af2947ca09e1d6eb5
+oid sha256:b3e98f457664f710d43650233769483b6f02ab91fe63bc5195ec194110b01ada
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d68d439874b3cc3c54bfb8a7b792c53676f8610cfb9b65dd7d1c08c8b1019ac4
+oid sha256:73ecc1efc440dd76fa6474f280ad4ef4dfdd6e209fee029d2373c73ccc111e83
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2094983ff9f11d6250b785dfe29c8c85823d0967c14aec5d510a4e0433164679
+oid sha256:1b02450bf90416881debf85ba0d776babdc9d2efe4751382ccfff0b7db595003
 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": 176.47058823529412,
+  "best_metric": 0.3931240439414978,
+  "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-5000",
+  "epoch": 196.07843137254903,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -709,6 +709,84 @@
       "eval_samples_per_second": 28.132,
       "eval_steps_per_second": 3.595,
       "step": 4500
+    },
+    {
+      "epoch": 178.4313725490196,
+      "grad_norm": 1.2672348022460938,
+      "learning_rate": 5.753333333333334e-06,
+      "loss": 0.4068,
+      "step": 4550
+    },
+    {
+      "epoch": 180.3921568627451,
+      "grad_norm": 0.8008630275726318,
+      "learning_rate": 5.67e-06,
+      "loss": 0.4112,
+      "step": 4600
+    },
+    {
+      "epoch": 182.35294117647058,
+      "grad_norm": 1.0430930852890015,
+      "learning_rate": 5.586666666666667e-06,
+      "loss": 0.4145,
+      "step": 4650
+    },
+    {
+      "epoch": 184.31372549019608,
+      "grad_norm": 0.767160952091217,
+      "learning_rate": 5.503333333333334e-06,
+      "loss": 0.3992,
+      "step": 4700
+    },
+    {
+      "epoch": 186.27450980392157,
+      "grad_norm": 1.0731803178787231,
+      "learning_rate": 5.420000000000001e-06,
+      "loss": 0.4025,
+      "step": 4750
+    },
+    {
+      "epoch": 188.23529411764707,
+      "grad_norm": 0.7984374761581421,
+      "learning_rate": 5.336666666666667e-06,
+      "loss": 0.4002,
+      "step": 4800
+    },
+    {
+      "epoch": 190.19607843137254,
+      "grad_norm": 0.8159019947052002,
+      "learning_rate": 5.2533333333333336e-06,
+      "loss": 0.4023,
+      "step": 4850
+    },
+    {
+      "epoch": 192.15686274509804,
+      "grad_norm": 1.1482937335968018,
+      "learning_rate": 5.1700000000000005e-06,
+      "loss": 0.4021,
+      "step": 4900
+    },
+    {
+      "epoch": 194.11764705882354,
+      "grad_norm": 0.9159001708030701,
+      "learning_rate": 5.086666666666667e-06,
+      "loss": 0.4058,
+      "step": 4950
+    },
+    {
+      "epoch": 196.07843137254903,
+      "grad_norm": 0.8861828446388245,
+      "learning_rate": 5.0033333333333334e-06,
+      "loss": 0.3982,
+      "step": 5000
+    },
+    {
+      "epoch": 196.07843137254903,
+      "eval_loss": 0.3931240439414978,
+      "eval_runtime": 6.4434,
+      "eval_samples_per_second": 27.936,
+      "eval_steps_per_second": 3.57,
+      "step": 5000
     }
   ],
   "logging_steps": 50,
@@ -728,7 +806,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.896064149915233e+16,
+  "total_flos": 5.440105584628308e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null