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:ef67e1b23f53f1a274109b215801f62036dd76aabb1c81ad2ceaa1c0bec257bf
+oid sha256:316160f432d68f495cdcbc6255279b1fd4770c53e6b8dd3b13b4e325ddf65563
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c55f785264031c429e7c0ce688cc3aefce3c93c87d4392fb6e72d49e73b3d1
+oid sha256:a0d983d8e03d56ca4449178600628c12583caecb676e3e87bddb6fe50bd366eb
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e091a109b1d98c241cd35341a1a58393bcf5f6fb7f837866e41c8697200b8ffd
+oid sha256:cce78cffbd3f55d8970857f4be3f34a0319c1da4b496b8a8382418329d8191f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28116213683223995,
+  "epoch": 0.37488284910965325,
   "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": 10.746,
       "eval_steps_per_second": 5.397,
       "step": 150
+    },
+    {
+      "epoch": 0.29990627928772257,
+      "grad_norm": 0.5602021217346191,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 1.7472,
+      "step": 160
+    },
+    {
+      "epoch": 0.31865042174320524,
+      "grad_norm": 0.5383387804031372,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.7245,
+      "step": 170
+    },
+    {
+      "epoch": 0.3373945641986879,
+      "grad_norm": 0.47379371523857117,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.6683,
+      "step": 180
+    },
+    {
+      "epoch": 0.3561387066541706,
+      "grad_norm": 0.501379132270813,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 1.6534,
+      "step": 190
+    },
+    {
+      "epoch": 0.37488284910965325,
+      "grad_norm": 0.47937536239624023,
+      "learning_rate": 0.0,
+      "loss": 1.7251,
+      "step": 200
+    },
+    {
+      "epoch": 0.37488284910965325,
+      "eval_loss": NaN,
+      "eval_runtime": 20.9485,
+      "eval_samples_per_second": 10.741,
+      "eval_steps_per_second": 5.394,
+      "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": 9.308643967107072e+16,
+  "total_flos": 1.2395694262321152e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null