Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7482227c716352e999a6e037a36f830b17c952620a93034c255657b64fde42e3
+oid sha256:6cf04fb89d8ab3e3f8dbe70117278b7eb9197385d8313cabcc8300268cf28a2f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5911a3ee49d56137b5d9154fe0a37a2429605d0e93b042196bfb6e409bc727ee
+oid sha256:a421a299ad6a3eae913817fb92227d46b3871f84045ac02a9c0ccd6f0ee6ce58
 size 42546196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c53b7c8db298fbfcd4a33138e917716be734ff8c10e00c87f58a2eea9bb85d55
+oid sha256:d38fd17de7c489936706f3143d8f4e16cd16a35673d1c10a9410665266a51b56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f849364dfa23e889fd91f98c245f66c5c55af948e62488dea2ea09edd802d5d7
+oid sha256:d523f99908891a364ebfcdaaec71fd2a09caeab25c8c6a44dbc4b9707d82c8ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07089516967577275,
+  "epoch": 0.07562151432082427,
   "eval_steps": 1000,
-  "global_step": 375,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2257,13 +2257,163 @@
       "learning_rate": 5.161290322580645e-05,
       "loss": 1.6664,
       "step": 375
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.120967741935484e-05,
+      "loss": 1.6375,
+      "step": 376
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.080645161290323e-05,
+      "loss": 1.5933,
+      "step": 377
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.040322580645161e-05,
+      "loss": 1.6126,
+      "step": 378
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5e-05,
+      "loss": 1.645,
+      "step": 379
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.959677419354839e-05,
+      "loss": 1.5649,
+      "step": 380
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9193548387096775e-05,
+      "loss": 1.5601,
+      "step": 381
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.8790322580645164e-05,
+      "loss": 1.6028,
+      "step": 382
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.8387096774193554e-05,
+      "loss": 1.675,
+      "step": 383
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.7983870967741937e-05,
+      "loss": 1.5058,
+      "step": 384
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.7580645161290326e-05,
+      "loss": 1.7313,
+      "step": 385
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.7177419354838716e-05,
+      "loss": 1.609,
+      "step": 386
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.67741935483871e-05,
+      "loss": 1.5993,
+      "step": 387
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.637096774193548e-05,
+      "loss": 1.7103,
+      "step": 388
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.596774193548387e-05,
+      "loss": 1.6556,
+      "step": 389
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.556451612903226e-05,
+      "loss": 1.6981,
+      "step": 390
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.516129032258064e-05,
+      "loss": 1.6413,
+      "step": 391
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.475806451612903e-05,
+      "loss": 1.5337,
+      "step": 392
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.435483870967742e-05,
+      "loss": 1.7622,
+      "step": 393
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.395161290322581e-05,
+      "loss": 1.6373,
+      "step": 394
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.3548387096774194e-05,
+      "loss": 1.7476,
+      "step": 395
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.3145161290322584e-05,
+      "loss": 1.7093,
+      "step": 396
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.2741935483870973e-05,
+      "loss": 1.225,
+      "step": 397
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.2338709677419356e-05,
+      "loss": 1.8272,
+      "step": 398
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.1935483870967746e-05,
+      "loss": 1.6983,
+      "step": 399
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.1532258064516135e-05,
+      "loss": 1.5777,
+      "step": 400
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2.3185476387618816e+16,
+  "total_flos": 2.4726679032889344e+16,
   "trial_name": null,
   "trial_params": null
 }