Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16faa2f0e020ee34ef0aa4e8c4370d6469571f45d9b61d0b313b4b3b10a52b85
+oid sha256:ac77a258b2357271877b7d0ca044bc5dea771eec1e94f91fa4763384d79cf11e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf9acfa7a494a322e8af18a537bb7e42cba478e17a05556b452f627b00dbdd1
+oid sha256:ca578c2e043134e5b097f417e24adf234bde8fa1bfb9519a82b8f49defabefec
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae592f5b56869a5199b46dcaab343cbe5455d328d9aa29d6d21e369bab3be64
+oid sha256:383ccac3871241b40ceddec4c7db3538bc0aabad27e924e98591062a69f3ff98
 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": 0.002468069352748812,
+  "epoch": 0.0032907591369984164,
   "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": 15.688,
       "eval_steps_per_second": 7.844,
       "step": 150
+    },
+    {
+      "epoch": 0.002632607309598733,
+      "grad_norm": 2.4761176109313965,
+      "learning_rate": 0.0002,
+      "loss": 2.9751,
+      "step": 160
+    },
+    {
+      "epoch": 0.002797145266448654,
+      "grad_norm": 2.7750675678253174,
+      "learning_rate": 0.0002,
+      "loss": 2.6672,
+      "step": 170
+    },
+    {
+      "epoch": 0.0029616832232985746,
+      "grad_norm": 2.303779363632202,
+      "learning_rate": 0.0002,
+      "loss": 2.5169,
+      "step": 180
+    },
+    {
+      "epoch": 0.0031262211801484957,
+      "grad_norm": 2.367227792739868,
+      "learning_rate": 0.0002,
+      "loss": 2.6783,
+      "step": 190
+    },
+    {
+      "epoch": 0.0032907591369984164,
+      "grad_norm": 1.861033320426941,
+      "learning_rate": 0.0002,
+      "loss": 2.8931,
+      "step": 200
+    },
+    {
+      "epoch": 0.0032907591369984164,
+      "eval_loss": 0.6726848483085632,
+      "eval_runtime": 1629.8478,
+      "eval_samples_per_second": 15.701,
+      "eval_steps_per_second": 7.85,
+      "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": 6.087027522011136e+16,
+  "total_flos": 8.105482682105856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null