Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e6ee9cf840d964a3a716fa4bfe81efe0f7eeb38ced0d027ff47c7e5eba1c12
+oid sha256:476340c8df28d1720ea3531efe340c2f8fa950f0c2c8bc475fab18f3781e869e
 size 445688440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7b4cff5342d3e1e07850fc6cca44a325c0a77b28f8131ec24186c35190fbc3
+oid sha256:d4efbb013fc7815ef4bcc70277820f77bf11c5e247938917767ae7ce5a645530
 size 226680596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494c7c864cfcb6e573fe802b7ae8e689ce9953d75764cc3750be60bfbd50aa2b
+oid sha256:d86506acd053e219015bb2d3d4899f53acfe910adb33e6960825dde67f7210f0
 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": 0.15544041450777202,
+  "epoch": 0.20725388601036268,
   "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": 9.562,
       "eval_steps_per_second": 4.781,
       "step": 150
+    },
+    {
+      "epoch": 0.16580310880829016,
+      "grad_norm": 0.5783207416534424,
+      "learning_rate": 0.0002,
+      "loss": 1.2162,
+      "step": 160
+    },
+    {
+      "epoch": 0.17616580310880828,
+      "grad_norm": 0.5993497967720032,
+      "learning_rate": 0.0002,
+      "loss": 1.2693,
+      "step": 170
+    },
+    {
+      "epoch": 0.18652849740932642,
+      "grad_norm": 0.8267126679420471,
+      "learning_rate": 0.0002,
+      "loss": 1.2687,
+      "step": 180
+    },
+    {
+      "epoch": 0.19689119170984457,
+      "grad_norm": 0.9705228805541992,
+      "learning_rate": 0.0002,
+      "loss": 1.2394,
+      "step": 190
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 0.5224875807762146,
+      "learning_rate": 0.0002,
+      "loss": 1.1163,
+      "step": 200
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "eval_loss": 0.6216335892677307,
+      "eval_runtime": 21.3659,
+      "eval_samples_per_second": 9.548,
+      "eval_steps_per_second": 4.774,
+      "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": 4.89614558625792e+16,
+  "total_flos": 6.55382838509568e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null