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:c14efe289e9d6b68e1d5f6f2d468758e34e5fccad14fe98d0aa59c891e015f7a
+oid sha256:695b28b1c144c13da4abcc5eaca3a9212e89fab9b9e1efd0f79f83e7c88310a9
 size 435773944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ad0dc15dff5be446ba97f3ab39de0804ea19c6708fac1efe95d00110eddd93
+oid sha256:415612b7b397ce1b2a3efb303fc1ad86a479c212f2aa988e6e34a69c580f856a
 size 222034900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2c1d5a97dae61d9453fafd03f4c7d8eea28e16ba48efd0c4f825b9e78ee9a7
+oid sha256:67c68a2e62a022f32398cbfbfd50c0f81cb2155d53706fbea70b77a3ecd283b8
 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": 0.25252525252525254,
+  "epoch": 0.3367003367003367,
   "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": 24.545,
       "eval_steps_per_second": 12.371,
       "step": 150
+    },
+    {
+      "epoch": 0.26936026936026936,
+      "grad_norm": 6.440443485189462e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.28619528619528617,
+      "grad_norm": 5.90744548389921e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 6.136083356977906e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.31986531986531985,
+      "grad_norm": 5.108250661578495e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.3367003367003367,
+      "grad_norm": 5.8488562899583485e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.3367003367003367,
+      "eval_loss": 1.2466983889680705e-07,
+      "eval_runtime": 5.0445,
+      "eval_samples_per_second": 24.78,
+      "eval_steps_per_second": 12.489,
+      "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": 1.59919424667648e+16,
+  "total_flos": 2.13225899556864e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null