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:d8797afc38c093cbbed5ce36062dc7f470d5fc9a31709c394900518ebdaeda04
+oid sha256:0fc5da87d358477318dd608756e76cf90a6cee22db7705b3db4b46baa3cd1a49
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e39b50c9bb4932e57d872e42ff662f73cc0c625d174a9836ad30ba8db143040
+oid sha256:7f668756e8eaf5cee5ea768edde05923af121c5728e9a8ca194dcc9e34ea175e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75457ff9047a61e3f41ba81a128623afe5b1ae5c7463bc37a9196ea84fd005fc
+oid sha256:f0b3186018a30c5ffc18c3acbe2fb9c6db6cc6718a81ff4342bee08442c4ca2c
 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": 0.003199488081906895,
+  "epoch": 0.004265984109209193,
   "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": 15.869,
       "eval_steps_per_second": 7.935,
       "step": 150
+    },
+    {
+      "epoch": 0.0034127872873673548,
+      "grad_norm": 1.1245367527008057,
+      "learning_rate": 0.0002,
+      "loss": 1.082,
+      "step": 160
+    },
+    {
+      "epoch": 0.0036260864928278143,
+      "grad_norm": 1.2070635557174683,
+      "learning_rate": 0.0002,
+      "loss": 1.0912,
+      "step": 170
+    },
+    {
+      "epoch": 0.003839385698288274,
+      "grad_norm": 0.9941854476928711,
+      "learning_rate": 0.0002,
+      "loss": 1.0162,
+      "step": 180
+    },
+    {
+      "epoch": 0.004052684903748734,
+      "grad_norm": 1.1030969619750977,
+      "learning_rate": 0.0002,
+      "loss": 1.0922,
+      "step": 190
+    },
+    {
+      "epoch": 0.004265984109209193,
+      "grad_norm": 1.0685251951217651,
+      "learning_rate": 0.0002,
+      "loss": 1.0855,
+      "step": 200
+    },
+    {
+      "epoch": 0.004265984109209193,
+      "eval_loss": 0.27673590183258057,
+      "eval_runtime": 1243.0657,
+      "eval_samples_per_second": 15.88,
+      "eval_steps_per_second": 7.94,
+      "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": 5.5408925343744e+16,
+  "total_flos": 7.3218937061376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null