Training in progress, step 225, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75eca5dddc386a889c6eadd70a8f95b34b18eeca352934088d95cb81557f417c
+oid sha256:674226647c0af0371804ab2d68e3d707974b6551b87819cd9b51eaf76d96623d
 size 1822093912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf94306fbcd9fbb459530b7f3721ba13ee9ded04cbefa8a326a59a76016d9ba
+oid sha256:ed5cf37ce34fe8faf97f2f26392f8fe21ffa3a7dfbb31c731986c8abfcd99633
 size 651839518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6f0f8239ffefed30e603cf30841bbf0c2fcff79585c1498fc94f8f96b5ea45
+oid sha256:421f99707ecd0d99d7fb40197f028ceb02c2ffdc30698df74ad0b16e6900f2cf
 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": 1.6,
+  "epoch": 1.8,
   "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": 0.4379,
       "step": 200
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0002,
+      "loss": 0.412,
+      "step": 201
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0002,
+      "loss": 0.4059,
+      "step": 202
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0002,
+      "loss": 0.4189,
+      "step": 203
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0002,
+      "loss": 0.4127,
+      "step": 204
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002,
+      "loss": 0.4131,
+      "step": 205
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0002,
+      "loss": 0.3867,
+      "step": 206
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0002,
+      "loss": 0.3402,
+      "step": 207
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 208
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0002,
+      "loss": 0.3904,
+      "step": 209
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 0.3413,
+      "step": 210
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002,
+      "loss": 0.3568,
+      "step": 211
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002,
+      "loss": 0.3333,
+      "step": 212
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002,
+      "loss": 0.3481,
+      "step": 213
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.0002,
+      "loss": 0.3571,
+      "step": 214
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0002,
+      "loss": 0.31,
+      "step": 215
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 0.3437,
+      "step": 216
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0002,
+      "loss": 0.3051,
+      "step": 217
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0002,
+      "loss": 0.3035,
+      "step": 218
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 0.5871,
+      "step": 219
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0002,
+      "loss": 0.5218,
+      "step": 220
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0002,
+      "loss": 0.5163,
+      "step": 221
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0002,
+      "loss": 0.5002,
+      "step": 222
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0002,
+      "loss": 0.4768,
+      "step": 223
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0002,
+      "loss": 0.5197,
+      "step": 224
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.0002,
+      "loss": 0.4529,
+      "step": 225
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 2,
   "save_steps": 25,
-  "total_flos": 2.592463382721331e+16,
+  "total_flos": 2.907887080911667e+16,
   "trial_name": null,
   "trial_params": null
 }