Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3125c5cdd907859825b85e2b44f1a2c45eced9608219b8491212276b64dd40b6
+oid sha256:5af2633bdc91cc64cb4373e5aa9748befbf2cbba825529c137463e1a9f36d921
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e743907e3ef9df701cfdaa04f41653cedb1fb402064f70e353c7669c6b3222
+oid sha256:fc0411c095970571aa2b3a3607d73b2764c47d98e33fc5177fb0e3b7189f8117
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6562043b413fa7e5997eaf05f34bba7850c0b7649af0796d00c8d62fb292ee1d
+oid sha256:d9ecf824154209c6975f8d26bc363df3e9a4fbe420a38decd4f828630be720d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d180e6bb7b7c41ee65a41a5e646849b13af9646efdef1095f15a2a7e5f3cda1
+oid sha256:ad1b29a2638e1b447334a358eec29a8b7ed7b3b45a0cb1bd7d41f21fb38e93d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.39692553877830505,
-  "best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-2500",
-  "epoch": 196.07843137254903,
+  "best_metric": 0.39595454931259155,
+  "best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-3000",
+  "epoch": 235.2941176470588,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,84 @@
       "eval_samples_per_second": 27.956,
       "eval_steps_per_second": 3.572,
       "step": 2500
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.7426376342773438,
+      "learning_rate": 7.255000000000001e-06,
+      "loss": 0.4157,
+      "step": 2550
+    },
+    {
+      "epoch": 203.92156862745097,
+      "grad_norm": 1.1800576448440552,
+      "learning_rate": 7.005000000000001e-06,
+      "loss": 0.419,
+      "step": 2600
+    },
+    {
+      "epoch": 207.84313725490196,
+      "grad_norm": 0.7355245351791382,
+      "learning_rate": 6.7550000000000005e-06,
+      "loss": 0.4174,
+      "step": 2650
+    },
+    {
+      "epoch": 211.76470588235293,
+      "grad_norm": 0.5805600881576538,
+      "learning_rate": 6.505e-06,
+      "loss": 0.4146,
+      "step": 2700
+    },
+    {
+      "epoch": 215.68627450980392,
+      "grad_norm": 0.9223101139068604,
+      "learning_rate": 6.255e-06,
+      "loss": 0.4178,
+      "step": 2750
+    },
+    {
+      "epoch": 219.6078431372549,
+      "grad_norm": 0.8155106902122498,
+      "learning_rate": 6.005000000000001e-06,
+      "loss": 0.4151,
+      "step": 2800
+    },
+    {
+      "epoch": 223.52941176470588,
+      "grad_norm": 0.6420881748199463,
+      "learning_rate": 5.755000000000001e-06,
+      "loss": 0.4156,
+      "step": 2850
+    },
+    {
+      "epoch": 227.45098039215685,
+      "grad_norm": 0.7704824209213257,
+      "learning_rate": 5.505000000000001e-06,
+      "loss": 0.4157,
+      "step": 2900
+    },
+    {
+      "epoch": 231.37254901960785,
+      "grad_norm": 0.6147534251213074,
+      "learning_rate": 5.2550000000000005e-06,
+      "loss": 0.4177,
+      "step": 2950
+    },
+    {
+      "epoch": 235.2941176470588,
+      "grad_norm": 0.758510172367096,
+      "learning_rate": 5.0049999999999995e-06,
+      "loss": 0.4149,
+      "step": 3000
+    },
+    {
+      "epoch": 235.2941176470588,
+      "eval_loss": 0.39595454931259155,
+      "eval_runtime": 6.3959,
+      "eval_samples_per_second": 28.143,
+      "eval_steps_per_second": 3.596,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -416,7 +494,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.440105584628308e+16,
+  "total_flos": 6.5283263362154376e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null