Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712573eeabf2cae5e7ab03a74cfeda5c9702f8ce81347fca7c65088ae9caaf4f
+oid sha256:f6052060fee70b746dfbacd8af991cb069c6e2d6f47894a3b7a85456b4f5a015
 size 2931614832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7627ecaad8de01f91bfb55d6f30496eba9ce7ff520e8900173f48b905245cd6a
+oid sha256:1299814310ef8143db69c7e0f57933728708c9587aea349f43769e11720550c5
 size 628648428

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab338548badcd1a4e62d17c7a5f50056c1797d49352e814f8ed7b335faabc83e
+oid sha256:f872f30db80f4bb445041adea1f9bfc526c9ed631be5b44711cea34fecc28076
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c17c000dd3ad474c8365253b4464489310fed0d13c745556138280174b380deb
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7,
+  "epoch": 0.8,
   "eval_steps": 500,
-  "global_step": 175,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1057,13 +1057,163 @@
       "learning_rate": 0.0002,
       "loss": 0.5009,
       "step": 175
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 176
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 0.5728,
+      "step": 177
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 0.5391,
+      "step": 178
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 0.5347,
+      "step": 179
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 0.4641,
+      "step": 180
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 0.4879,
+      "step": 181
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 0.465,
+      "step": 182
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 0.458,
+      "step": 183
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.4863,
+      "step": 184
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.4928,
+      "step": 185
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.3868,
+      "step": 186
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002,
+      "loss": 0.4672,
+      "step": 187
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002,
+      "loss": 0.421,
+      "step": 188
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 0.425,
+      "step": 189
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 0.3822,
+      "step": 190
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 0.4326,
+      "step": 191
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002,
+      "loss": 0.3932,
+      "step": 192
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002,
+      "loss": 0.3672,
+      "step": 193
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.3669,
+      "step": 194
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.3904,
+      "step": 195
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.3255,
+      "step": 196
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002,
+      "loss": 0.3567,
+      "step": 197
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002,
+      "loss": 0.3808,
+      "step": 198
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.417,
+      "step": 199
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.4644,
+      "step": 200
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1.0477514726866944e+16,
+  "total_flos": 1.1759299247996928e+16,
   "trial_name": null,
   "trial_params": null
 }