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:bf90567d6a86a24744020927870ca1ae13836cfe18d2be097fe39eb9dca83137
+oid sha256:ca7df94835e90432d3bfe642763df6c3f4e60131bb64826990bc38863a55ab71
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6657ea0323b3cc06c4e30a34f884423fd0287c056df5dc33dde09056249a1b
+oid sha256:1bedbe3b53e503bc16530eb43b7138d2876afb7e856417a70c153eb4cc531da7
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff04e7b93f7bbab46892d177b2513cb6aa76ffee390787d16e6d5345b8cb419
+oid sha256:cdf893c5bb0e76fe85a347d29151fc6a489809d8e86d61072d2615bb615078b8
 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": 0.010523177297998842,
+  "epoch": 0.014030903063998457,
   "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": 93.252,
       "eval_steps_per_second": 46.626,
       "step": 150
+    },
+    {
+      "epoch": 0.011224722451198765,
+      "grad_norm": 0.3971766233444214,
+      "learning_rate": 0.0002,
+      "loss": 11.861,
+      "step": 160
+    },
+    {
+      "epoch": 0.011926267604398688,
+      "grad_norm": 0.3338390588760376,
+      "learning_rate": 0.0002,
+      "loss": 11.8696,
+      "step": 170
+    },
+    {
+      "epoch": 0.012627812757598611,
+      "grad_norm": 0.27194201946258545,
+      "learning_rate": 0.0002,
+      "loss": 11.8622,
+      "step": 180
+    },
+    {
+      "epoch": 0.013329357910798534,
+      "grad_norm": 0.440639466047287,
+      "learning_rate": 0.0002,
+      "loss": 11.8563,
+      "step": 190
+    },
+    {
+      "epoch": 0.014030903063998457,
+      "grad_norm": 0.380655437707901,
+      "learning_rate": 0.0002,
+      "loss": 11.8561,
+      "step": 200
+    },
+    {
+      "epoch": 0.014030903063998457,
+      "eval_loss": 11.855968475341797,
+      "eval_runtime": 62.7571,
+      "eval_samples_per_second": 95.639,
+      "eval_steps_per_second": 47.819,
+      "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": 18773390131200.0,
+  "total_flos": 25031186841600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null