Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2486faa614fefac339054a626954e901ed19edcd5c4630e13d6f17fcc4e122
+oid sha256:3a53e67f900d6f4e2bbd3b35b2f81421df59c5d763fcedb22c671941b2b5c9e5
 size 536906096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a202cd852528ab00873ca3f1d4f8e386a8264d607612cae77ab5ffeccc6872
+oid sha256:8755246a4ea026b83dd138f2d34b63b1e024ea178cbd41ff82d4f069a99c1642
 size 269267284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e3bd96c9227f8005659a008a5de4b22b3d54ac87368e34f44e67994ab38530
+oid sha256:fb19b4241f3fa973ce278cd7e299bf5c1382f2c8baefb52b4a8b59ee6a38edb4
 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": 0.395,
       "step": 175
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 0.41,
+      "step": 176
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 0.4239,
+      "step": 177
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 0.3911,
+      "step": 178
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 0.3239,
+      "step": 179
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 0.3694,
+      "step": 180
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 0.3924,
+      "step": 181
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 0.3373,
+      "step": 182
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 0.3966,
+      "step": 183
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.3735,
+      "step": 184
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.392,
+      "step": 185
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.3747,
+      "step": 186
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002,
+      "loss": 0.4057,
+      "step": 187
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002,
+      "loss": 0.3088,
+      "step": 188
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 0.3273,
+      "step": 189
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 0.4217,
+      "step": 190
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 0.3751,
+      "step": 191
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002,
+      "loss": 0.3798,
+      "step": 192
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002,
+      "loss": 0.3812,
+      "step": 193
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.317,
+      "step": 194
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.3209,
+      "step": 195
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.3249,
+      "step": 196
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002,
+      "loss": 0.2607,
+      "step": 197
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002,
+      "loss": 0.2947,
+      "step": 198
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.285,
+      "step": 199
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.3175,
+      "step": 200
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1.382556660645888e+16,
+  "total_flos": 1.553804770000896e+16,
   "trial_name": null,
   "trial_params": null
 }