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:e4de0075cc9eee808e24fedb4d483a7123502417322e537ba5c534c5331dec9a
+oid sha256:7bee362bf798bed2b12e520a225f03d51e4e0582318c485804b1781430f13c27
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd9ebd38dd4d1498e9d16ffee93b91ef29d2633bffc83bd9325d3a0048a1c9b
+oid sha256:045068e607bf93eddc6856ee19b086f83bd7b8684624b2d042aaa2e9524f369e
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ab72f23bd8fe5041f7f2dc5f0bc1b45c4d1c803eb0aaf73f1fe5ef6de41a81
+oid sha256:e40a6a8406c510ee7dd11da3a3bbc6824fc8ed8f6e21ef91e4ef8c2812b68e2c
 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": 0.030796078632654107,
+  "epoch": 0.04106143817687215,
   "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": 23.796,
       "eval_steps_per_second": 11.904,
       "step": 150
+    },
+    {
+      "epoch": 0.032849150541497715,
+      "grad_norm": 0.4601839482784271,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.2784,
+      "step": 160
+    },
+    {
+      "epoch": 0.03490222245034132,
+      "grad_norm": 0.397343248128891,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.2513,
+      "step": 170
+    },
+    {
+      "epoch": 0.03695529435918493,
+      "grad_norm": 0.4850408434867859,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.2755,
+      "step": 180
+    },
+    {
+      "epoch": 0.03900836626802854,
+      "grad_norm": 0.45969998836517334,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.2717,
+      "step": 190
+    },
+    {
+      "epoch": 0.04106143817687215,
+      "grad_norm": 0.47403478622436523,
+      "learning_rate": 0.0,
+      "loss": 0.2972,
+      "step": 200
+    },
+    {
+      "epoch": 0.04106143817687215,
+      "eval_loss": 0.284105122089386,
+      "eval_runtime": 86.1463,
+      "eval_samples_per_second": 23.808,
+      "eval_steps_per_second": 11.91,
+      "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": 3.384772789272576e+16,
+  "total_flos": 4.51479053795328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null