Training in progress, step 275, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2a2797b5eb8e207d71f8697295ab040c99d9447a55cb7a45765b5fcc0018149
+oid sha256:1d723d83d4eb8000019aebd0817af9932a2d1202b0ec4807093bf548ac146439
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9154468633c6d826e0b060027d9b88d350bf29d70b7280b830ee0a12499b1e
-size 42545748
+oid sha256:6eb1db2e964ec0b2c98974ec093f4bee824e1132ff949cf3e862dd0d5628c169
+size 42546196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8938b73d98fc27010dbc6b77bb6e0a5a6aa78de2bac41513e8f9a1e2730ccea
+oid sha256:560e09aa52f8a763465aa7c2436802878c12b49a525a49aed5ec676ef95f5745
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ff724ef7d9ff62658c9e4239430ba619df4bfe00095bb195d6ed43c64449e2
+oid sha256:cf9c36987bd7f761cf696e6b1b4a757a9b4bd2c54712ce685b5c522e621e6d0d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.047263446450515174,
+  "epoch": 0.05198979109556669,
   "eval_steps": 1000,
-  "global_step": 250,
+  "global_step": 275,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1507,13 +1507,163 @@
       "learning_rate": 0.00010201612903225808,
       "loss": 1.5656,
       "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010161290322580646,
+      "loss": 1.6925,
+      "step": 251
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010120967741935485,
+      "loss": 1.5055,
+      "step": 252
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010080645161290323,
+      "loss": 1.5479,
+      "step": 253
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010040322580645163,
+      "loss": 1.6352,
+      "step": 254
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 1.6747,
+      "step": 255
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.95967741935484e-05,
+      "loss": 1.7197,
+      "step": 256
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.919354838709678e-05,
+      "loss": 1.5599,
+      "step": 257
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.879032258064517e-05,
+      "loss": 1.4343,
+      "step": 258
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.838709677419355e-05,
+      "loss": 1.6037,
+      "step": 259
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.798387096774194e-05,
+      "loss": 1.6565,
+      "step": 260
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.758064516129033e-05,
+      "loss": 1.6615,
+      "step": 261
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.717741935483872e-05,
+      "loss": 1.6193,
+      "step": 262
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.677419354838711e-05,
+      "loss": 1.5369,
+      "step": 263
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.63709677419355e-05,
+      "loss": 1.7713,
+      "step": 264
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.596774193548387e-05,
+      "loss": 1.6298,
+      "step": 265
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.556451612903226e-05,
+      "loss": 1.4293,
+      "step": 266
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.516129032258065e-05,
+      "loss": 1.5491,
+      "step": 267
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.475806451612904e-05,
+      "loss": 1.6733,
+      "step": 268
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.435483870967743e-05,
+      "loss": 1.6588,
+      "step": 269
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.395161290322582e-05,
+      "loss": 1.5837,
+      "step": 270
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 1.3857,
+      "step": 271
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.314516129032259e-05,
+      "loss": 1.6731,
+      "step": 272
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.274193548387096e-05,
+      "loss": 1.5275,
+      "step": 273
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.233870967741935e-05,
+      "loss": 1.5816,
+      "step": 274
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.193548387096774e-05,
+      "loss": 1.7432,
+      "step": 275
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1.5348012927320064e+16,
+  "total_flos": 1.6916857776734208e+16,
   "trial_name": null,
   "trial_params": null
 }