Training in progress, step 175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2453c2e3294848e5fdfc24e048c1067e321df75f1c3196c442f2aba8b9f0279
+oid sha256:82c29a240327704fc6308528a79479382296de6cfed508d0b0162ecf997b2e81
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e077b08c719bb7b427e236996fb0c792fd3d4c0ef0d2c88800c48772d9d3dac7
+oid sha256:d0c943c3d72ba71df99f13267a644cecf346914768f99cdf1633a736691ffbbc
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1edea7e57130e0f2957bce0ab868e371c690b8d0bc7a6dcec629366489ad56d6
+oid sha256:a917d4671a090e9d6e24eb6118f2b87fee978309a5cb80de0030b8ff15757299
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12ad3f73c37b908f7e6d73930423bb8448afc36fc1f9dcd87868ce173eebb611
+oid sha256:de22cc9e265638e0274e21fc41c39f9e04260749bf4242dc266a4f3abba5955d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028358067870309103,
+  "epoch": 0.03308441251536062,
   "eval_steps": 1000,
-  "global_step": 150,
+  "global_step": 175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -907,13 +907,163 @@
       "learning_rate": 0.00014233870967741936,
       "loss": 1.4998,
       "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014193548387096775,
+      "loss": 1.6332,
+      "step": 151
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014153225806451614,
+      "loss": 1.7242,
+      "step": 152
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014112903225806453,
+      "loss": 1.9499,
+      "step": 153
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014072580645161292,
+      "loss": 1.6425,
+      "step": 154
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001403225806451613,
+      "loss": 1.7308,
+      "step": 155
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013991935483870967,
+      "loss": 1.8306,
+      "step": 156
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001395161290322581,
+      "loss": 1.6522,
+      "step": 157
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013911290322580645,
+      "loss": 1.432,
+      "step": 158
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013870967741935487,
+      "loss": 1.3832,
+      "step": 159
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013830645161290323,
+      "loss": 1.4807,
+      "step": 160
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013790322580645162,
+      "loss": 1.4447,
+      "step": 161
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001375,
+      "loss": 1.6328,
+      "step": 162
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013709677419354837,
+      "loss": 1.5871,
+      "step": 163
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001366935483870968,
+      "loss": 1.5617,
+      "step": 164
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013629032258064515,
+      "loss": 1.5104,
+      "step": 165
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013588709677419357,
+      "loss": 1.7455,
+      "step": 166
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013548387096774193,
+      "loss": 1.5425,
+      "step": 167
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013508064516129032,
+      "loss": 1.5297,
+      "step": 168
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001346774193548387,
+      "loss": 1.6117,
+      "step": 169
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001342741935483871,
+      "loss": 1.4543,
+      "step": 170
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001338709677419355,
+      "loss": 1.6787,
+      "step": 171
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013346774193548388,
+      "loss": 1.4363,
+      "step": 172
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013306451612903227,
+      "loss": 1.7276,
+      "step": 173
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013266129032258066,
+      "loss": 1.6509,
+      "step": 174
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013225806451612905,
+      "loss": 1.7243,
+      "step": 175
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 9333394508070912.0,
+  "total_flos": 1.0874511573762048e+16,
   "trial_name": null,
   "trial_params": null
 }