Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa8d265400b8791cf4a64562e9e11c979135179f68220ef5ea4d9c6d3c03a42
+oid sha256:1114653a414a0e03fadfe4985f006b3d9ce4d65d3ecf2ce0c64cbc6adfd9305b
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53cf28f4d98aad829ae5bdc1a8c4046f73443537482fbc16a8e07a413da66020
+oid sha256:dd500d34df7ddcd15351a099db21a6ff93808d5a4c4b73dc7ea3a981b330c4f1
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbcf3cde1491bc0510b355c8e8cc9d1b437a18e9740ee673986de59df4b2ff6f
+oid sha256:23e913b1b09af4704f298f5d732037471d49897007ac37250e2071bb06273799
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b353b67d3c68734cb4cbcb55694f7eeeb40f54128ba041a6736d420b09008b6
+oid sha256:ea4cdeda39ba2136e592d70ee5cca1961eef743b3307c81d32a1dfebf7fdaaa7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3931240439414978,
-  "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-5000",
-  "epoch": 215.68627450980392,
+  "best_metric": 0.39249518513679504,
+  "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-6000",
+  "epoch": 235.2941176470588,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -865,6 +865,84 @@
       "eval_samples_per_second": 27.101,
       "eval_steps_per_second": 3.463,
       "step": 5500
+    },
+    {
+      "epoch": 217.64705882352942,
+      "grad_norm": 0.7886359095573425,
+      "learning_rate": 4.086666666666667e-06,
+      "loss": 0.3938,
+      "step": 5550
+    },
+    {
+      "epoch": 219.6078431372549,
+      "grad_norm": 1.1809077262878418,
+      "learning_rate": 4.003333333333334e-06,
+      "loss": 0.4033,
+      "step": 5600
+    },
+    {
+      "epoch": 221.5686274509804,
+      "grad_norm": 0.8167886137962341,
+      "learning_rate": 3.920000000000001e-06,
+      "loss": 0.4002,
+      "step": 5650
+    },
+    {
+      "epoch": 223.52941176470588,
+      "grad_norm": 1.1182901859283447,
+      "learning_rate": 3.836666666666667e-06,
+      "loss": 0.3982,
+      "step": 5700
+    },
+    {
+      "epoch": 225.49019607843138,
+      "grad_norm": 1.0442403554916382,
+      "learning_rate": 3.753333333333334e-06,
+      "loss": 0.3973,
+      "step": 5750
+    },
+    {
+      "epoch": 227.45098039215685,
+      "grad_norm": 1.0428043603897095,
+      "learning_rate": 3.6700000000000004e-06,
+      "loss": 0.4001,
+      "step": 5800
+    },
+    {
+      "epoch": 229.41176470588235,
+      "grad_norm": 0.9441725611686707,
+      "learning_rate": 3.5866666666666673e-06,
+      "loss": 0.3976,
+      "step": 5850
+    },
+    {
+      "epoch": 231.37254901960785,
+      "grad_norm": 0.8371317386627197,
+      "learning_rate": 3.5033333333333334e-06,
+      "loss": 0.3973,
+      "step": 5900
+    },
+    {
+      "epoch": 233.33333333333334,
+      "grad_norm": 0.7603981494903564,
+      "learning_rate": 3.4200000000000007e-06,
+      "loss": 0.3943,
+      "step": 5950
+    },
+    {
+      "epoch": 235.2941176470588,
+      "grad_norm": 1.1027510166168213,
+      "learning_rate": 3.3366666666666668e-06,
+      "loss": 0.4019,
+      "step": 6000
+    },
+    {
+      "epoch": 235.2941176470588,
+      "eval_loss": 0.39249518513679504,
+      "eval_runtime": 6.4221,
+      "eval_samples_per_second": 28.028,
+      "eval_steps_per_second": 3.581,
+      "step": 6000
     }
   ],
   "logging_steps": 50,
@@ -884,7 +962,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.984476827927444e+16,
+  "total_flos": 6.5283263362154376e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null