Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06db194b48f2ac691ad12feee5c4ff612e4826fa66b579235c3954fcf1d1596a
+oid sha256:f606f61928fb3325a5a782fd370010762b109be88839a6f08d75dd7ff8e75535
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a713b58adf3fbd744c82d39bc2c00a43bd51b2867d65d7239c390652dd0368
+oid sha256:d7e07c6d2c31d466e48a2622e6b8c84769c83db648a31e61985afe79b1b33cb9
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adbc63955d9ff34f793ef8affb26ab37748ab990a367539d36771ebaf7e01e4e
+oid sha256:1f4026a337a16f715f23023fb1a56996a014f2603556499f5fc14e1cfa19ebee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15278838808250572,
+  "epoch": 0.20371785077667431,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 20.127,
       "eval_steps_per_second": 10.063,
       "step": 150
+    },
+    {
+      "epoch": 0.16297428062133945,
+      "grad_norm": 0.43389683961868286,
+      "learning_rate": 0.0002,
+      "loss": 0.392,
+      "step": 160
+    },
+    {
+      "epoch": 0.17316017316017315,
+      "grad_norm": 0.5267621278762817,
+      "learning_rate": 0.0002,
+      "loss": 0.4006,
+      "step": 170
+    },
+    {
+      "epoch": 0.18334606569900688,
+      "grad_norm": 0.512631356716156,
+      "learning_rate": 0.0002,
+      "loss": 0.3913,
+      "step": 180
+    },
+    {
+      "epoch": 0.19353195823784058,
+      "grad_norm": 0.5992527604103088,
+      "learning_rate": 0.0002,
+      "loss": 0.3766,
+      "step": 190
+    },
+    {
+      "epoch": 0.20371785077667431,
+      "grad_norm": 0.4778156280517578,
+      "learning_rate": 0.0002,
+      "loss": 0.38,
+      "step": 200
+    },
+    {
+      "epoch": 0.20371785077667431,
+      "eval_loss": 0.37545791268348694,
+      "eval_runtime": 20.5365,
+      "eval_samples_per_second": 20.159,
+      "eval_steps_per_second": 10.08,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.083721410032435e+16,
+  "total_flos": 4.109918218695475e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null