Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af2633bdc91cc64cb4373e5aa9748befbf2cbba825529c137463e1a9f36d921
+oid sha256:d2c0277f54c09c949fa6a8943edf7edac098878a0d43666f5fcb22403b14c145
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc0411c095970571aa2b3a3607d73b2764c47d98e33fc5177fb0e3b7189f8117
+oid sha256:0e5ea83ac97396889fe2821e60cc59e33e316d14ac1826fe80fb9efcd4c6f98b
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ecf824154209c6975f8d26bc363df3e9a4fbe420a38decd4f828630be720d0
+oid sha256:a414c666e8625c7f4e23102be45d01b76de4812ff286110f0f9a0e1c67f33573
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad1b29a2638e1b447334a358eec29a8b7ed7b3b45a0cb1bd7d41f21fb38e93d2
+oid sha256:3b37e9ef30e383e795affd2915d5979e774d36e929b105a379fff9b722cf9675
 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": 235.2941176470588,
+  "epoch": 274.5098039215686,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,84 @@
       "eval_samples_per_second": 28.143,
       "eval_steps_per_second": 3.596,
       "step": 3000
+    },
+    {
+      "epoch": 239.2156862745098,
+      "grad_norm": 0.7012345790863037,
+      "learning_rate": 4.755e-06,
+      "loss": 0.4103,
+      "step": 3050
+    },
+    {
+      "epoch": 243.13725490196077,
+      "grad_norm": 0.7060217261314392,
+      "learning_rate": 4.505e-06,
+      "loss": 0.4114,
+      "step": 3100
+    },
+    {
+      "epoch": 247.05882352941177,
+      "grad_norm": 0.8892201781272888,
+      "learning_rate": 4.255e-06,
+      "loss": 0.4093,
+      "step": 3150
+    },
+    {
+      "epoch": 250.98039215686273,
+      "grad_norm": 0.6098002791404724,
+      "learning_rate": 4.005000000000001e-06,
+      "loss": 0.411,
+      "step": 3200
+    },
+    {
+      "epoch": 254.90196078431373,
+      "grad_norm": 0.7227322459220886,
+      "learning_rate": 3.7550000000000005e-06,
+      "loss": 0.4108,
+      "step": 3250
+    },
+    {
+      "epoch": 258.8235294117647,
+      "grad_norm": 0.8260012865066528,
+      "learning_rate": 3.505e-06,
+      "loss": 0.412,
+      "step": 3300
+    },
+    {
+      "epoch": 262.7450980392157,
+      "grad_norm": 0.6897534132003784,
+      "learning_rate": 3.255e-06,
+      "loss": 0.4112,
+      "step": 3350
+    },
+    {
+      "epoch": 266.6666666666667,
+      "grad_norm": 1.0072269439697266,
+      "learning_rate": 3.005e-06,
+      "loss": 0.413,
+      "step": 3400
+    },
+    {
+      "epoch": 270.5882352941176,
+      "grad_norm": 0.6094086170196533,
+      "learning_rate": 2.7550000000000003e-06,
+      "loss": 0.4104,
+      "step": 3450
+    },
+    {
+      "epoch": 274.5098039215686,
+      "grad_norm": 0.6129186749458313,
+      "learning_rate": 2.505e-06,
+      "loss": 0.4129,
+      "step": 3500
+    },
+    {
+      "epoch": 274.5098039215686,
+      "eval_loss": 0.39622604846954346,
+      "eval_runtime": 6.4203,
+      "eval_samples_per_second": 28.036,
+      "eval_steps_per_second": 3.582,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -494,7 +572,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.5283263362154376e+16,
+  "total_flos": 7.616303628785914e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null