Training in progress, step 225, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbad3c32c72278fec001c7077781d678cb2fd778bad07da7267a2bb333cfc817
+oid sha256:4cd3afe7a5c6f92bd8e924895f18f69469f6685aa2ef2184f059a984d1d8379d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d16f5ceae6943b24109cb0f735b99bdbb139479c50060547c712e2ddbf51a91b
+oid sha256:0a7b86ad7c0e6025be5bc2c8ffed0cc7dbd120f0ca26c5fd49aa808197054cda
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3f7a56ad1a475bba2d0785209c1428117c6797270fe6f67d0179354e163bdc
+oid sha256:772d5a327fbf7113e8f59462d16a41a74a6390c940f2e126e84a4dadeb8b31f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88b2d08d068d7c188fcae65f7ab4eeb2b01722602970224771334b164e05369
+oid sha256:17943b933296baae03d840ff112ff0e3c38315c7cfbb8f89c292f61b690fac96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.037810757160412135,
+  "epoch": 0.042537101805463655,
   "eval_steps": 1000,
-  "global_step": 200,
+  "global_step": 225,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1207,13 +1207,163 @@
       "learning_rate": 0.0001221774193548387,
       "loss": 1.6444,
       "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001217741935483871,
+      "loss": 1.6056,
+      "step": 201
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00012137096774193548,
+      "loss": 1.7643,
+      "step": 202
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00012096774193548388,
+      "loss": 1.6614,
+      "step": 203
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00012056451612903226,
+      "loss": 1.4906,
+      "step": 204
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00012016129032258065,
+      "loss": 1.598,
+      "step": 205
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011975806451612903,
+      "loss": 1.6326,
+      "step": 206
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011935483870967743,
+      "loss": 1.6153,
+      "step": 207
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001189516129032258,
+      "loss": 1.6332,
+      "step": 208
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011854838709677421,
+      "loss": 1.6477,
+      "step": 209
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011814516129032258,
+      "loss": 1.6652,
+      "step": 210
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011774193548387097,
+      "loss": 1.412,
+      "step": 211
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011733870967741935,
+      "loss": 1.5335,
+      "step": 212
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011693548387096775,
+      "loss": 1.6941,
+      "step": 213
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011653225806451613,
+      "loss": 1.5277,
+      "step": 214
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011612903225806453,
+      "loss": 1.5259,
+      "step": 215
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011572580645161291,
+      "loss": 1.8913,
+      "step": 216
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011532258064516131,
+      "loss": 1.5655,
+      "step": 217
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011491935483870969,
+      "loss": 1.4732,
+      "step": 218
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011451612903225808,
+      "loss": 1.6836,
+      "step": 219
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011411290322580645,
+      "loss": 1.7453,
+      "step": 220
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011370967741935486,
+      "loss": 1.801,
+      "step": 221
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011330645161290323,
+      "loss": 1.6863,
+      "step": 222
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011290322580645163,
+      "loss": 1.7664,
+      "step": 223
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011250000000000001,
+      "loss": 1.7441,
+      "step": 224
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00011209677419354839,
+      "loss": 1.7277,
+      "step": 225
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1.2368645450366976e+16,
+  "total_flos": 1.3865689032671232e+16,
   "trial_name": null,
   "trial_params": null
 }