Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:909164143e946a79544695ae4729ed406738f0ec6408ba0da707119f7581fbf9
+oid sha256:54c4947058fd8e7ee421b0b46fc349022d4a1f3f8246ef6c3d3b6bda09b72f50
 size 838904832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b25d5b7c08a71ac14f6ba0f530f590caddf977889f0c4b04c9812dd1f4fa5fa4
+oid sha256:0a651b2e845e714d6bbbfe26616bd79e994bd844b56c8ce9664fd66902226483
 size 420633876

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c19e042a9bfc28144451bbf43f82dc0a8daf6a85a49c45d8ec4eb8089fe161b
+oid sha256:fc1f20496eb68bf92a3c0bedec6630dbaf08516bee744709362b85a6b5810eb0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59a103009f3230e51c40288ef6a33247523fa398934878b1e22a81660cbade8
+oid sha256:1d1650f5062195d8ee65b24ab00a137ab48cccbff41f41ba060d4208547a763c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 225,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1357,13 +1357,163 @@
       "learning_rate": 0.0002,
       "loss": 0.4565,
       "step": 225
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002,
+      "loss": 0.4283,
+      "step": 226
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002,
+      "loss": 0.4522,
+      "step": 227
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002,
+      "loss": 0.4712,
+      "step": 228
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002,
+      "loss": 0.5018,
+      "step": 229
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002,
+      "loss": 0.4691,
+      "step": 230
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002,
+      "loss": 0.4537,
+      "step": 231
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.4482,
+      "step": 232
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.4369,
+      "step": 233
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002,
+      "loss": 0.4772,
+      "step": 234
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002,
+      "loss": 0.4546,
+      "step": 235
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002,
+      "loss": 0.4321,
+      "step": 236
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 0.3777,
+      "step": 237
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 0.4099,
+      "step": 238
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002,
+      "loss": 0.3694,
+      "step": 239
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 240
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002,
+      "loss": 0.3989,
+      "step": 241
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002,
+      "loss": 0.4031,
+      "step": 242
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002,
+      "loss": 0.4104,
+      "step": 243
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002,
+      "loss": 0.3533,
+      "step": 244
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002,
+      "loss": 0.364,
+      "step": 245
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002,
+      "loss": 0.3696,
+      "step": 246
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002,
+      "loss": 0.3252,
+      "step": 247
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002,
+      "loss": 0.3523,
+      "step": 248
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002,
+      "loss": 0.3395,
+      "step": 249
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002,
+      "loss": 0.3503,
+      "step": 250
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2.72384291254272e+16,
+  "total_flos": 2.990177006051328e+16,
   "trial_name": null,
   "trial_params": null
 }