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:f6052060fee70b746dfbacd8af991cb069c6e2d6f47894a3b7a85456b4f5a015
+oid sha256:b225360958a382ec287517387a6abacab0f1d2394a362e9767f84473949b3e7a
 size 2931614832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1299814310ef8143db69c7e0f57933728708c9587aea349f43769e11720550c5
+oid sha256:25d9ef7e070c77b5aeefa9d8a3f85c0f430cf64b32a2830c48ac368bfb96a923
 size 628648428

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f872f30db80f4bb445041adea1f9bfc526c9ed631be5b44711cea34fecc28076
+oid sha256:376a71289f7848b2a2e275814c62ab7090b1b8276e7e80bba0894efbd9bf880b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
+oid sha256:f59a103009f3230e51c40288ef6a33247523fa398934878b1e22a81660cbade8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 0.9,
   "eval_steps": 500,
-  "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": 0.0002,
       "loss": 0.4644,
       "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.6799,
+      "step": 201
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002,
+      "loss": 0.7253,
+      "step": 202
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002,
+      "loss": 0.8481,
+      "step": 203
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002,
+      "loss": 0.662,
+      "step": 204
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002,
+      "loss": 0.6507,
+      "step": 205
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002,
+      "loss": 0.5734,
+      "step": 206
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002,
+      "loss": 0.6026,
+      "step": 207
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002,
+      "loss": 0.7017,
+      "step": 208
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002,
+      "loss": 0.6172,
+      "step": 209
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002,
+      "loss": 0.5782,
+      "step": 210
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002,
+      "loss": 0.5805,
+      "step": 211
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002,
+      "loss": 0.6031,
+      "step": 212
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002,
+      "loss": 0.5795,
+      "step": 213
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 0.6324,
+      "step": 214
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 0.5426,
+      "step": 215
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 0.5527,
+      "step": 216
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 0.6277,
+      "step": 217
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 0.5427,
+      "step": 218
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002,
+      "loss": 0.5526,
+      "step": 219
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002,
+      "loss": 0.5193,
+      "step": 220
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002,
+      "loss": 0.5112,
+      "step": 221
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 0.5111,
+      "step": 222
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 0.5119,
+      "step": 223
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002,
+      "loss": 0.5078,
+      "step": 224
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002,
+      "loss": 0.4422,
+      "step": 225
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1.1759299247996928e+16,
+  "total_flos": 1.3393660247801856e+16,
   "trial_name": null,
   "trial_params": null
 }